research paper on computer aided drug design

Computer-Aided Drug Design: An Update

Affiliations.

• 1 Department of Pharmaceutical Sciences, Computer-Aided Drug Design Center, School of Pharmacy, University of Maryland, Baltimore, MD, USA. [email protected].
• 2 Institute for Bioscience and Biotechnology Research (IBBR), Rockville, MD, USA. [email protected].
• 3 Center for Biomolecular Therapeutics (CBT), School of Medicine, University of Maryland, Baltimore, MD, USA. [email protected].
• 4 Institute for Bioscience and Biotechnology Research (IBBR), Rockville, MD, USA.
• 5 Center for Biomolecular Therapeutics (CBT), School of Medicine, University of Maryland, Baltimore, MD, USA.
• 6 Department of Pharmaceutical Sciences, Computer-Aided Drug Design Center, School of Pharmacy, University of Maryland, Baltimore, MD, USA. [email protected].
• 7 Institute for Bioscience and Biotechnology Research (IBBR), Rockville, MD, USA. [email protected].
• 8 Center for Biomolecular Therapeutics (CBT), School of Medicine, University of Maryland, Baltimore, MD, USA. [email protected].
• PMID: 36445582
• PMCID: PMC9838881
• DOI: 10.1007/978-1-0716-2855-3_7

Computer-aided drug design (CADD) approaches are playing an increasingly important role in understanding the fundamentals of ligand-receptor interactions and helping medicinal chemists design therapeutics. About 5 years ago, we presented a chapter devoted to an overview of CADD methods and covered typical CADD protocols including structure-based drug design (SBDD) and ligand-based drug design (LBDD) approaches that were frequently used in the antibiotic drug design process. Advances in computational hardware and algorithms and emerging CADD methods are enhancing the accuracy and ability of CADD in drug design and development. In this chapter, an update to our previous chapter is provided with a focus on new CADD approaches from our laboratory and other peers that can be employed to facilitate the development of antibiotic therapeutics.

Keywords: Binding site prediction; Biologics; Computer-aided drug design; Drude polarizable force field; Machine learning; Membrane permeation; Molecular dynamics; Protein-protein interaction; SILCS; Site identification by ligand competitive saturation.

© 2023. The Author(s), under exclusive license to Springer Science+Business Media, LLC, part of Springer Nature.

Publication types

• Research Support, Non-U.S. Gov't
• Research Support, N.I.H., Extramural
• Algorithms*
• Anti-Bacterial Agents / pharmacology
• Drug Design*
• Laboratories
• Anti-Bacterial Agents

Grants and funding

• R01 GM129327/GM/NIGMS NIH HHS/United States
• R35 GM131710/GM/NIGMS NIH HHS/United States
• R56 AI152397/AI/NIAID NIH HHS/United States

Computer Aided Drug Design

• Abdulilah Ece

Biruni University, Turkey

Articles (13 in this collection)

Prospective virtual screening combined with bio-molecular simulation enabled identification of new inhibitors for the kras drug target, authors (first, second and last of 8).

• Hind A Alkhatabi
• Abdul Wadood
• Content type: Research
• Open Access
• Published: 25 March 2024
• Article: 57

An immunoinformatics and structural vaccinology approach to design a novel and potent multi-epitope base vaccine targeting Zika virus

• Mohammed Ageeli Hakami
• Published: 13 February 2024
• Article: 31

Novel quinazolines bearing 1,3,4-thiadiazole-aryl urea derivative as anticancer agents: design, synthesis, molecular docking, DFT and bioactivity evaluations

Authors (first, second and last of 5).

• Sara Masoudinia
• Marjaneh Samadizadeh
• Alireza Foroumadi
• Published: 12 February 2024
• Article: 30

Lead generation of UPPS inhibitors targeting MRSA: Using 3D-QSAR pharmacophore modeling, virtual screening, molecular docking, and molecular dynamic simulations

Authors (first, second and last of 4).

• Basma M. Qandeel
• Samar Mowafy
• Nahla A. Farag
• Published: 20 January 2024
• Article: 14

Discovery of dual rho-associated protein kinase 1 (ROCK1)/apoptosis signal–regulating kinase 1 (ASK1) inhibitors as a novel approach for non-alcoholic steatohepatitis (NASH) treatment

• Yara A. Zaky
• Mai W. Rashad
• Ahmed M. El Kerdawy
• Published: 03 January 2024

Solubility of mesalazine in pseudo-binary mixtures of choline chloride/ethylene glycol deep eutectic solvent and water at 293.15 K to 313.15 K

Authors (first, second and last of 6).

• Elina Armani
• Parisa Jafari
• Abolghasem Jouyban
• Published: 28 November 2023
• Article: 171

Logic-based modeling and drug repurposing for the prediction of novel therapeutic targets and combination regimens against E2F1-driven melanoma progression

• Nivedita Singh
• Faiz M Khan
• Shailendra K. Gupta
• Published: 22 November 2023
• Article: 161

Theoretical study of interaction between temozolomide anticancer drug and hydroxyethyl carboxymethyl cellulose nanocarriers for targeted drug delivery by DFT quantum mechanical calculation

• Masoumeh Shahi
• Fatemeh Azarakhshi
• Published: 14 September 2023
• Article: 114

Synthesis, DFT and molecular docking of novel ( Z )-4-bromo- N -(4-butyl-3 (quinolin-3-yl)thiazol-2(3 H )-ylidene)benzamide as elastase inhibitor

Authors (first, second and last of 11).

• Muhammad Naeem Mustafa
• Pervaiz Ali Channar
• Tuncer Hökelek
• Published: 07 August 2023
• Article: 95

In-silico activity prediction and docking studies of some flavonol derivatives as anti-prostate cancer agents based on Monte Carlo optimization

• Faezeh Tajiani
• Shahin Ahmadi
• Ali Almasirad
• Published: 26 July 2023
• Article: 87

A study of the interaction space of two lactate dehydrogenase isoforms (LDHA and LDHB) and some of their inhibitors using proteochemometrics modeling

• Sedigheh Damavandi
• Fereshteh Shiri
• Hamid Beyzaei
• Published: 06 July 2023
• Article: 70

Synthesis, antimicrobial and antioxidant activity of triazole, pyrazole containing thiazole derivatives and molecular docking studies on COVID-19

• Raghavender Matta
• Jalapathi Pochampally
• Anjini Gayatri Akkiraju
• Published: 17 June 2023
• Article: 61

Computer-aided drug design

• Content type: Editorial
• Published: 24 March 2023
• Article: 26

Participating journals

BMC Chemistry

• Find a journal
• Publish with us
• Track your research

• Reference Manager
• Simple TEXT file

People also looked at

Editorial article, editorial: hot trends in computer-aided drug design techniques.

• 1 Postgraduate Program in Natural and Synthetic Bioactive Products, Federal University of Paraíba, João Pessoa, Brazil
• 2 University Hospital, Federal University of Paraíba, João Pessoa, Brazil
• 3 Department of Chemical & Biological Engineering, Moscow, United States
• 4 Department of Pharmacology and Physiology in Université de Sherbrooke, QC, Sherbrooke, Canada

Editorial on the Research Topic: Hot trends in computer-aided drug design techniques

The drug discovery process is complex, and designing an effective and commercially viable drug requires interdisciplinary work. For this reason, the Computer Aided Drug Design (CADD) Centre works in collaboration with structure biologists, biophysicists, and computational scientists to find new therapeutic agents. The design and development of any medicine takes many years: it begins when scientists learn about a biological target (e.g., a receptor, enzyme, protein, gene) that is involved in a biological process thought to be dysfunctional in patients with a disease, followed by the determination of a specific target receptor and often by the determination of an active compound from the mass of compounds. The target could prevent an altered biological process without being dysfunctional itself ( de Araujo et al., 2020 ; de Sousa et al., 2021 ; de Araujo et al., 2022 ).

In this collection, we—researchers of in silico methods—focused on the publication of papers that take computer-assisted approaches such as:

- Structure-based drug design

- Virtual screening

- Combining docking and molecular dynamics simulations

- Pharmacophore modeling

- Statistical methods (quantum chemistry calculation and 3D quantitative structure–activity relationships (QSAR) methods)

- Ligand-binding pocket prediction

- Pharmacokinetics/pharmacodynamics (PK/PD) prediction

- Physical property prediction

- Homology modeling to identify novel bioactive compounds.

We are glad about our work, because this issue has amassed 10,000 views and five high-quality manuscript submissions.

The review by Oliveira et al. , entitled Biological Membrane-Penetrating Peptides: Computational Prediction and Applications , discussed some classes of peptides that are able to naturally cross the biological membranes, such as the cell membrane and blood–brain barrier (BBB). Cell-penetrating peptides (CPPs) and blood–brain barrier-penetrating peptides (B3PPs) have been explored by the biotechnological and pharmaceutical industries to develop new therapeutic molecules and carrier systems. The computational prediction of peptides’ penetration into biological membranes has emerged as an interesting strategy due to their high throughput and low-cost screening of large chemical libraries.

Kumar et al. reported their findings in the research paper entitled 3D-QSAR-Based Pharmacophore Modeling, Virtual Screening, and Molecular Dynamics Simulations for the Identification of Spleen Tyrosine Kinase Inhibitors. The primary goal of this research was to identify potential inhibitors with higher affinity, higher selectivity based on key molecular interactions, and better drug-like properties than the available inhibitor, fostamatinib. In this study, a 3D-QSAR model was built for SYK based on known inhibitor IC 50 values. The best pharmacophore model was then used as a 3D query to screen a drug-like database to retrieve hits with novel chemical scaffolds. The obtained compounds were subjected to binding affinity prediction using the molecular docking approach, and the results were subsequently validated using molecular dynamics (MD) simulations.

In silico investigation and potential therapeutic approaches of natural products for COVID-19: Computer-aided drug design perspective is the review by Rahman et al. Through a computational approach, the study contributed to the development of effective treatment methods by examining the mechanisms related to the binding and subsequent inhibition of the SARS-CoV-2 ribonucleic acid (RNA)-dependent RNA polymerase (RdRp). The in silico method was also employed to determine the most effective drug on the mentioned compound, and their aquatic, non-aquatic, and pharmacokinetic data were analyzed.

Drug development is a lengthy and risky work that requires significant money, resources, and labor. Breast and lung cancer contribute to the death of millions of people throughout the world each year, according to the report by the World Health Organization, and has been a public threat worldwide, although the global medical sector is developed and updated day by day. However, no proper treatment has been found until now. Therefore, research has been conducted to find a new bioactive molecule to treat breast and lung cancer—such as natural myricetin and its derivatives—by using the latest and most authentic computer-aided drug design approaches. Drug-likeness, ADME, and toxicity prediction were fulfilled in the investigation of Akash et al. titled Development of new bioactive molecules to treat breast and lung cancer with natural myricetin and its derivatives: A computational and SAR approach. It was noted that all the derivatives were highly soluble in a water medium, whereas they were totally free from AMES toxicity, hepatotoxicity, and skin sensitization, excluding only two ligands. Thus, the authors proposed that the natural myricetin derivatives could be a better inhibitor for treating breast and lung cancer.

Lianhua Qingwen granules (LHQW) can reduce tissue damage caused by inflammatory reactions and relieve patients’ clinical symptoms. Cao et al. employed bioinformatics to screen active ingredients in LHQW and intersection gene targets. PPI, GO, and KEGG were used to analyze the relationship between the intersection gene targets. Molecular dynamics simulations validated the binding stability of the active ingredients and target proteins. The binding free energy, radius of gyration, and solvent accessible surface area were analyzed by a supercomputer platform. This study was reported in their research article titled Molecular docking and molecular dynamics study Lianhua Qingwen granules (LHQW) treats COVID-19 by inhibiting inflammatory response and regulating cell survival.

We, the guest editors, would like to express our gratitude to the many authors who contributed to this Research Topic, reporting investigations in various aspects of Hot Trends in Computer-Aided Drug Design Techniques.

Author contributions

All authors listed have made a substantial, direct, and intellectual contribution to the work and approved it for publication.

Acknowledgments

CAPES & CNPq

Conflict of interest

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Publisher’s note

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.

de Araujo, R. S. A., da Silva, E. F., de Aquino, T. M., Scotti, M. T., Ishiki, H. M., Scotti, L., et al. (2020). Computer-aided drug design applied to secondary metabolites as anticancer agents. Curr. Topics Medicinal Chem. 20 (19), 1677–1703. doi: 10.2174/1568026620666200607191838

CrossRef Full Text | Google Scholar

de Araujo, R. S. A., Mendonca, F. J. B., Scotti, M. T., Scotti, L. (2021). “4 Protein modeling”. In Silico Chemistry and Biology: current and Future Prospects edited by Girish Kumar Gupta and Mohammad Hassan Baig, Berlin, Boston: De Gruyter. pp. 85–100. doi: 10.1515/9783110493955-004

de Sousa, N. F., Scotti, L., Rodrigues, G. C. S., de Moura, E. P., Barros, R., Sessions, Z. L., et al. (2021). Recent studies on neglected drug design. Curr. Topics Medicinal Chem. 21 (21), 1943–1974. doi: 10.2174/1568026621666210920155939

Keywords: CADD, in silico , computer-aided drug design, drug research, molecular properties

Citation: Scotti L, Patel JS, Hassanzadeh M and Scotti MT (2023) Editorial: Hot trends in computer-aided drug design techniques. Front. Cell. Infect. Microbiol. 13:1149994. doi: 10.3389/fcimb.2023.1149994

Received: 23 January 2023; Accepted: 04 April 2023; Published: 17 April 2023.

Edited and Reviewed by:

Copyright © 2023 Scotti, Patel, Hassanzadeh and Scotti. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

*Correspondence: Luciana Scotti, [email protected]

This article is part of the Research Topic

Hot Trends in Computer-Aided Drug Design Techniques

• Search for: Toggle Search

NVIDIA BioNeMo Expands Computer-Aided Drug Discovery With New Foundation Models

Pharma and biology researchers developing the next generation of therapeutics can now take advantage of NVIDIA BioNeMo ’s expanded generative AI toolkit, along with new ways to access its models.

The latest BioNeMo foundation models can analyze DNA sequences, predict how proteins will change shape in response to a drug molecule, and determine a cell’s function based on its RNA.

Models for accelerating protein structure prediction, generative chemistry and molecular docking prediction are now available as microservices through NVIDIA NIM , a collection of models for inference announced today at NVIDIA GTC — and available through the NVIDIA AI Enterprise platform.

BioNeMo models will soon be accessible on AWS HealthOmics , a purpose-built service that helps healthcare and life sciences organizations store, query and analyze biological data, including DNA and RNA.

With these capabilities, drug discovery teams can easily integrate generative AI into their workflows to better understand and design drug molecules virtually — and reduce the need for time- and resource-heavy physical experiments.

BioNeMo Expands to Foundation Models for Genomics, Protein Design

Among the new foundation models available in BioNeMo is its first genomics model, DNABERT . Trained on DNA sequences, the model can be used to predict the function of specific regions of the genome, analyze the effects of gene mutations and variants, and more.

A second model coming soon to BioNeMo, scBERT, is trained on data from single-cell RNA sequencing, enabling users to apply it to downstream tasks such as predicting the effects of gene knockouts — where a specific gene is removed or deactivated — or identifying cell types such as neurons, blood cells or muscle cells.

EquiDock , a third, joins a collection of BioNeMo models that can predict the 3D structure of how two proteins interact, which is critical to understanding if a drug molecule will be effective.

At Your Service: New Microservices Enable AI Insights

The NIM catalog of containerized AI microservices features more than two dozen healthcare models . Among them are DiffDock, which predicts the 3D structure of potential drug candidates and their protein candidates, and ESMFold, which can predict protein structure based on a single amino acid sequence.

Another NIM, MolMIM, generates drug candidates optimized for properties defined by the user — and is even able to design molecules that are optimized to bind to a specific protein target.

Developers can access production-grade NIM microservices through NVIDIA AI Enterprise using NVIDIA-Certified Systems on premises as well as leading cloud marketplaces, including Amazon Web Services (AWS), Google Cloud, Microsoft Azure and Oracle Cloud Infrastructure.

100+ Companies Integrate BioNeMo-Powered AI Into Drug Discovery Workflows

NVIDIA BioNeMo is being used by more than 100 companies worldwide, including:

• Astellas Pharma : The Tokyo-based company is using BioNeMo to accelerate molecular simulations and large language models for drug discovery applications. The company will use the Tokyo-1 AI supercomputer to further advance its work.
• Cadence : A leading developer of computation software, San Jose, Calif.-based Cadence is integrating BioNeMo microservices with its Orion platform to accelerate molecular simulation.
• Iambic : Based in San Diego, the drug discovery company has adopted BioNeMo and will contribute its NeuralPLexer model as a BioNeMo cloud API, or application programming interface, for noncommercial use, helping researchers predict how a protein’s 3D structure changes in response to a drug molecule.
• Insilico Medicine : A premier member of the NVIDIA Inception program for startups, New York City-based Insilico has integrated BioNeMo in its AI-accelerated drug discovery workflow, developing a pipeline of over 30 therapeutic assets — including six in clinical stages.
• Recursion : The Salt Lake City-based drug discovery company is a hosting partner offering its Phenom-Beta AI model through BioNeMo. The transformer model extracts insights from cellular microscopy images to help researchers better understand cell function.
• Terray Therapeutics : The biotech company, based in Southern California,  is using BioNeMo to help develop a multi-target structural binding model — and is training generative AI models for small molecule design on NVIDIA DGX Cloud.

Discover the latest in AI and healthcare at GTC, a global AI conference running in San Jose, Calif., and online through Thursday, March 21. Tune in to a special address on generative AI in healthcare delivered by Kimberly Powell, vice president of healthcare at NVIDIA, on Tuesday at 8 a.m. PT.

Watch the GTC keynote address by NVIDIA founder and CEO Jensen Huang below:

NVIDIA websites use cookies to deliver and improve the website experience. See our cookie policy for further details on how we use cookies and how to change your cookie settings.

Share on Mastodon

• Contact Contact icon Contact
• Training Training icon Training

• Portuguese, Brazil
• Chinese, Simplified

Check the spelling in your query or search for a new term.

Site search accepts advanced operators to help refine your query. Learn more.

CAS Announces 2024 Selections for Prestigious CAS Future Leaders™ Program

The unique program provides early-career scientists with leadership training and connections to peers from around the world

Columbus, Ohio, March 25, 2024 : CAS, a division of the American Chemical Society specializing in scientific knowledge management, is proud to announce the 2024 CAS Future Leaders . These exceptional early-career scientists were selected from a large pool of global candidates who applied for a spot in the program known as one of the best leadership learning experiences in the world of science.

The 2024 selectees are a diverse group, hailing from 13 countries, working at 33 graduate or post-doctoral programs, and specializing in scientific disciplines that span computer-aided drug design, atmospheric/environmental chemistry, sustainable polymers, and cancer diagnostics.

“CAS Future Leaders offers early-career scientists the opportunity to participate in leadership and storytelling seminars, learn from industry thought leaders how to present their ideas in an impactful manner, engage in scientific discourse, and develop connections with peer scientists from around the world,” said Peter Carlton, CAS Future Leaders program director.

Participants in the program, which will take place in August, will also get a behind-the-scenes look into how CAS connects the world’s science. They will present their research at ACS Fall 2024 in Denver, Colorado, and receive a three-year ACS membership as well.

The 2024 CAS Future Leaders :

• Aziz Abu-Saleh , University of Windsor, Canada
• Noah Bartfield , Yale University, United States
• Michelle Brann , Harvard & Smithsonian Center for Astrophysics, United States
• Rosemary L. Calabro , U . S . Army DEVCOM Armaments Center and United States Military Academy, United States
• Xiangkun (Elvis) Cao , Massachusetts Institute of Technology, United States
• Áine Coogan , Trinity College Dublin, Ireland
• Chiara Deriu , Politecnico di Torino, Italy
• Madison Elaine Edwards , Texas A&M University, United States
• Olga Eremina , University of Southern California, United States
• Inès Forrest , Scripps Research Institute, United States
• Patrick W. Fritz , University of Fribourg, Switzerland
• Nabojit Kar , Indiana University Bloomington , United States
• Stavros Kariofillis , Columbia University, United States
• Joshua Kofsky , Queen's University, Canada
• Eric Kohn , University of Wisconsin-Madison, United States
• Danielle Maxwell , University of Michigan, United States
• Keita Mori , Tokyo University of Agriculture and Technology, Japan
• Aditya Nandy , University of Chicago, United States
• Akachukwu Obi , Massachusetts Institute of Technology, United States
• Ernest Opoku , Auburn University, United States
• Daisy Pooler , KTH Royal Institute of Technology, Sweden
• Pragti , Indian Institute of Technology Indore, India
• Stephanie Schneider , McMaster University, Canada
• Ekaterina Selivanovitch , Cornell University, United States
• Hanchen Shen , Hong Kong University of Science and Technology, China
• Lilian Sophie Szych , Freie Universität Berlin, Germany
• Alexander Umanzor , University of Minnesota, Twin Cities, United States
• Ken Aldren Usman , Institute for Frontier Materials, Deakin University - Waurn Ponds, Australia
• Sara T. R. Velasquez , University of Twente, Netherlands
• Gayatri Viswanathan , Iowa State University, United States
• Kunyu Wang , University of Pennsylvania, United States
• Athi Welsh , University of Cape Town, South Africa
• Kyra Yap , Stanford University, United States
• Yirui Zhang , Stanford University, United States
• Junyi Zhao , Washington University in St. Louis, United States

In addition to the 35 in-person participants, CAS provides virtual programming and other career benefits to 65 additional outstanding selectees through the CAS Future Leaders Top 100 program.

“I am thrilled to be selected for the 2024 CAS Future Leaders program alongside such an esteemed group of interdisciplinary scientists. I look forward to gaining new leadership skills and building lasting connections with peers who are as passionate as I am about science and leadership," said Michelle Brann from the Harvard & Smithsonian Center for Astrophysics.

Learn more about the 2024 CAS Future Leaders program at www.cas.org/about/futureleaders .

CAS connects the world's scientific knowledge to accelerate breakthroughs that improve lives. We empower global innovators to efficiently navigate today’s complex data landscape and make confident decisions in each phase of the innovation journey. As a specialist in scientific knowledge management, our team builds the largest authoritative collection of human-curated scientific data in the world and provides essential information solutions, services, and expertise. Scientists, patent professionals, and business leaders across industries rely on CAS to help them uncover opportunities, mitigate risks, and unlock shared knowledge so they can get from inspiration to innovation faster. CAS is a division of the American Chemical Society. Connect with us at  cas.org .

Share This Article

Related press releases, cas and molecule.one announce a strategic collaboration to accelerate drug discovery.

The two organizations are joining forces to develop pioneering AI-based solutions for efficient chemical synthesis planning to accelerate the development of novel pharmaceuticals.

CAS Welcomes Early-Career Scientists for the 2023 Future Leaders Program

CAS welcomed 35 of the brightest early-career scientists from around the world to kick off the 2023 CAS Future Leaders program. The unique, week-long program will help participants develop a highly valuable set of skills: the ability to lead people, communicate effectively, and present research in an accessible and captivating manner.

You May Also Be Interested In...

CAS convenes life sciences advisory board to reimagine the future of scientific discovery

CAS, a division of the American Chemical Society specializing in scientific information solutions, announced today its CAS Life Sciences Advisory Board. The board comprises a world-class panel of global thought leaders, directing the CAS scientific journey to align authoritative content with groundbreaking predictive technologies that span the spectrum of life sciences workflows

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings

Preview improvements coming to the PMC website in October 2024. Learn More or Try it out now .

• Advanced Search
• Journal List
• Curr Neuropharmacol
• v.16(6); 2018 Jul

Computer Aided Drug Design and its Application to the Development of Potential Drugs for Neurodegenerative Disorders

Mohammad hassan baig, khurshid ahmad, gulam rabbani, mohd danishuddin.

Neurodegenerative disorders (NDs) are diverse group of disorders characterized by escalating loss of neurons (structural and functional). The development of potential therapeutics for NDs presents an important challenge, as traditional treatments are inefficient and usually are unable to stop or retard the process of neurodegeneration. Computer-Aided Drug Design (CADD) has emerged as an efficient means of developing candidate drugs for the treatment of many disease types. Applications of CADD approach to drug discovery are progressing day by day. The recent tendency in drug design is to rationally design potent therapeutics with multi-targeting effects, higher efficacies, and fewer side effects, especially in terms of toxicity.

A wide literature search was performed for writing this review. An updated view on different types of NDs, their effect on human population and a brief introduction to CADD, various approaches involved in this technique, ranging from structural-based to ligand-based drug design has been discussed. The successful application of CADD approaches for the treatment of neurodegenerative disorders is also included in this review.

In this review, we have briefly described about CADD and its use in the development of the therapeutic drug candidates against NDs. The successful applications, limitations and future prospects of this approach have also been discussed.

CADD can assist researchers studying interactions between drugs and receptors. We believe this review will be helpful for better understanding of CADD and its applications towards the discovery of new drug candidates against various fatal NDs.

1. BACKGROUND

The development of novel potential therapies for the treatment of NDs represents an important means of extending life span and quality of life in the elderly [ 1 ]. The development of potential therapeutics for NDs presents an important challenge, as traditional treatments are inefficient and usually are unable to stop or retard the process of neurodegeneration [ 2 ], which is highly complex and includes many neuropathological conditions and cognitive function losses, such as, memory and learning losses. NDs cause neuron loss and brain aging, which eventually lead to death. In fact, it has been estimated that more than 25% of global deaths and disabilities are caused by brain-associated disorders [ 3 ], such as, Alzheimer’s disease (AD), Parkinson’s disease (PD), Huntington’s disease (HD) and amyotrophic lateral sclerosis (ALS) [ 4 , 5 ]. Available treatments are limited, and no truly effective drug is available for many NDs. Furthermore, the number of drugs approved is limited by the high failure rates of lead compounds in clinical trials [ 6 ].

Identifying novel, potential drugs for NDs is difficult using traditional approaches of drug discovery [ 7 ]. However, during the last decade, computers have been used to aid and accelerate the process of drug discovery, and this process is now referred to as computer-aided drug design (CADD) or computer-assisted molecular design (CAMD).

Computer-Aided Drug Design (CADD) emerged as an efficient means of identifying potential lead compounds and for aiding the developments of possible drugs for a wide range of diseases [ 8 , 9 ]. Today, a number of computational approaches are being used to identify potential lead molecules from huge compound libraries.

Applications of CADD approach to drug discovery are progressing on a daily basis. The recent tendency in drug design is to rationally design potent therapeutics with

multi-targeting effects, higher efficacies, and fewer side effects, especially in terms of toxicity. In this review, we provide a brief introduction to CADD and include details of structure-based drug design (SBDD) and ligand-based drug design (LBDD), and their uses to identify potential drug candidates for NDs. In addition, we provide an up-to-date summary of the successes and limitations of CADD against NDs and discuss its future prospects.

2. COMPUTER AIDED DRUG DESIGN (CADD)

To introduce a new drug to the market is a costly affair that involves considerable time and money. The average time taken to discover/develop a drug is around 10-15 years and the cost stands at around US$ 800 million [ 10 - 12 ]. Not surprisingly, pharmaceutical companies focus on reducing development times and budgets without adversely affecting quality. In the 1990’s, a large number of developments were undertaken using combinatorial and high-throughput screening technologies, which accelerated drug discovery [ 13 - 15 ]. These technologies were widely adopted because they enabled the rapid synthesis and screening of large libraries, but unfortunately, no significant success was achieved and little progress toward the development of new molecular entities was made [ 16 , 17 ].

A combination of advanced computational techniques, biological science, and chemical synthesis was introduced to facilitate the discovery process, and this combinational approach enhanced the scale of discovery. Eventually, the term computer-aided drug design (CADD) was adopted for the use of computers in drug discovery [ 17 , 18 ]. Advanced computational applications have been shown to be effective tools and notable successes have been achieved using these techniques. CADD is a specialized discipline, whereby different computational methods are used to simulate interactions between receptors and drugs in order to determine binding affinities [ 19 ]. However, the technique is not limited to studies of chemical interactions and binding affinity predictions, as it has many more applications ranging from the design of compounds with desired physiochemical properties to the management of digital repositories of compounds. An overview of CADD is provided in Fig. ( 1 ) . CADD may be broadly categorized embracing both structure- and ligand-based drug design. Fig. ( 2 ) illustrates various approaches applied in CADD.

Overview of CADD process.

Various approaches applied in CADD.

Virtual screening (VS) is a computational technique used for screening large datasets of molecules, and has been successfully used to complement High Throughput Screening (HTS) for drug discovery [ 8 , 20 , 21 ]. The major aim of VS is to enable the rapid, cost-effective evaluation of huge virtual compound databases to screen for effective leads for synthesis and further study [ 22 ]. Virtual database screening can be applied to screen large libraries of compounds using various computational approaches to identify those entities likely to bind to a molecular target of interest [ 23 , 24 ]. To a large extent, VS mitigates the problem of drug synthesis because it utilizes large libraries of pre-synthesized compounds.

2.1. Structure-based Drug Design (SBDD)

Structure-based drug design utilizes protein three-dimensional (3D) structural information to design new biologically active molecules [ 25 ]. Thus, the identification of a target molecule and the determination of its structure is the main, initial step of SBDD [ 23 , 26 ]. The identified target may be an enzyme associated with a disease of interest. Based on binding affinity determinations, potential compounds are determined which attenuates the activity of target by its inhibition. Thus, SBDD utilizes information about a biological target and identifies potentially new medications. As such SBDD constitutes a marked advancement in the computational techniques used in the biophysics, medicinal chemistry, statistics, biochemistry, and other fields [ 27 ]. Scientific advancements have resulted in a large number of techniques for predicting protein structures. These state-of-the-art technologies enable the determination of the structures of large numbers of proteins by using cryo-electron microscopy (EM), nuclear magnetic resonance (NMR), X-ray crystallography and computational methods like homology modeling and molecular dynamic (MD) simulation [ 28 ].

2.1.1. Homology Modeling

Determining the structure of a target molecule follows the identification of a specific drug target [ 29 ]. Despite the availability of advanced techniques, the structures of a large number of proteins have not been identified [ 30 ]. Homology modelling helps in this situation because it can be used to generate the structures of proteins on information available for similar proteins [ 31 ].

Structural information about an identified target is a prerequisite for SBDD, but the structures of several identified neurodegenerative drug targets have yet not been determined [ 32 , 33 ]. A large number of studies have been conducted using the homology modelling approach to generate structures of identified target molecules. Structural information is also required to gain insights of protein activities. Dhanavade et al . generated the structure of cysteine protease, which degrades amyloid beta peptide, an important causative agent of Alzheimer’s disease [ 34 ]. Several in silico experiments have been conducted using the modeled structure of cysteine protease to investigate the nature of its binding site.

2.1.2. Molecular Docking

Molecular docking is a computational process widely used for rapidly predicting the binding modes and affinities of small molecules against their target molecules (usually proteins) [ 35 , 36 ]. This in silico process has achieved a position of great importance in the drug discovery field [ 21 , 36 - 38 ]. Molecular docking has emerged over the last two decades and is now considered an indispensable tool for CADD and in the structural biology field, and has been shown to be more efficient than traditional drug discovery methods. Molecular docking has been greatly facilitated by dramatic growth in computer power and the increasing availability of small molecule and protein databases. Fig. ( 3 ) illustrates the basic principle of molecular docking. Recent advancements in computer methods and access to 3D structural information of biological targets are set to increase the effectiveness of this technique and facilitate its large-scale application to studies of molecular interactions involved in ligand-protein binding. Generally, small molecules can be docked in three different ways, that is; (a) by rigid docking, where both target and ligands are treated as rigid entities; (b) by flexible docking, where both ligand and target are considered to be flexible; and (c) by flexible ligand docking, where the ligand is considered to be flexible and the target is considered rigid [ 39 ]. Many molecular docking programs have been developed during recent years, such as, AutoDock [ 40 ], Dock [ 41 ], FlexX [ 42 ], Glide [ 43 ], Gold [ 44 ], Surflex [ 45 ], ICM, and LigandFit [ 46 ], and been used successfully in many computer based drug discovery projects. Table ​ 1 1 provides a list of major molecular docking tools in practice. Typically, the major goal of molecular docking is to identify ligands that bind most favorably within receptor binding sites and to determine its most energetically favored binding orientations (poses). The term “binding pose” is the orientation/confirmation of a ligand relative to its receptor. A binding pose either refers to a conformation of a ligand molecule within the binding site of its target protein which has been confirmed experimentally, or a computationally modelled hypothetical conformation. The search algorithm and the scoring function are two important components for determining protein-ligand interactions [ 47 ]. The search algorithm is responsible for searching different poses and conformations of a ligand within a given target protein and the scoring function estimates the binding affinities of generated poses, ranks them, and identifies the most favorable receptor/ligand binding modes [ 47 , 48 ]. An ideal search algorithm should be fast and effective, and the scoring function must be capable of determining the physicochemical properties of molecules and the thermodynamics of interactions.

Basic principle of molecular docking.

List of major available molecular docking tools.

A large number of trials are being conducted to identify binding modes of ligands and selection of the most energetically favored poses. In order to achieve this, molecular docking tools are used to generate a set of different ligand binding poses and a scoring function is used to estimate the binding affinities of generated poses to identify the best binding mode. The energy change caused by ligand/receptor complex formation, is given by the Gibbs free energy (ΔG) and the binding constant (Kd) [ 49 , 50 ]. The binding energy of a complex is predicted by evaluating physicochemical features involved in ligand-receptor binding, which include desolvation, intermolecular interactions, and entropic effects [ 51 ]. Sehgal et al . identified a number of compounds active against HSPB8 based on molecular docking results [ 52 ].

2.2. Ligand Based Drug Design (LBDD)

LBDD offers a general approach for elucidating relationships between the structural and physicochemical properties of compounds/ligands and their biological activities. This approach is applied when 3D structural information of a target protein is unavailable. In this process the available information of ligands and their biological activity is used for the development of new potential drug candidates. LBDD is widely used in pharmaceutical research, as more than 50% of approved drugs targeting membrane proteins (for which 3D structures are often not available, such as, GPCR). It is based on the assumption that compounds with similar structural features share common biological activities and interact/inhibit common target molecules [ 36 , 37 ].

The representation of molecules is the basis of LBDD approach. Molecular descriptors are numerical values used to represent the structural and physicochemical properties of molecules [ 53 , 54 ]. The molecular descriptor field is strikingly interdisciplinary and includes a number of different theories [ 55 ]. Active molecules are represented by the 0D-4D class of molecular descriptors [ 56 ]. Constitutional and count descriptors are 0D molecular descriptors, chemical fingerprints or lists of structural fragments, such as, SMILES and SLN, are 1D descriptors, graph invariants in which atoms are denoted as nodes and bonds as edges are 2D-descriptors, geometrical, WHIM and others are 3D descriptors, and those derived from CoMFA or DRID methods are classified as 4D descriptors [ 57 ]. Similarity searching is a key aspect of the LBDD method. This technique uses a known active compound as a query compound to find similar compounds and then rank compounds identified in a database. Based on this belief, structurally similar molecules exhibit similar biological activities and physicochemical properties. Numerical descriptors are applied and similarity coefficient is defined to quantify the degree of similarity (similarity/ dissimilarity). Fingerprint-based similarity or 2D similarity measures are widely used for similarity searching. A number of coefficients are applied in similarity searching with different fingerprint molecular databases (Cosine, Euclidian distance, Forbes, Tanimoto coefficients etc .).

The Tanimoto coefficient is most popular and widely accepted similarity index for binary variables, despite its well-documented size bias. It may be defined as:

where overlap ab , overlap aa , and overlap bb are the volume overlaps of molecule a with molecule b , of molecule a with itself, and of molecule b with itself, respectively. Values of T c range from 0 (no similarity) to 1 (a perfect match).

LBDD is generally categorized as Quantitative Structure Activity Relationship (QSAR) or pharmacophore modeling.

2.2.1. QSAR and its Role in Drug Discovery

The QSAR method and pharmacophore modeling are the most popular approaches to ligand-based drug design [ 58 , 59 ]. QSAR methods are based on the belief that molecular structures are directly associated with biological activities, and thus, that molecular or structural variations alter biological activities. QSAR is defined as a process involving the construction of computational or mathematical models using chemometric techniques to identify significant correlations between a series of structures and functions [ 60 ]. For QSAR, the primary hypothesis is that “compounds with similar structural or physiochemical properties show similar activities”. To identify potential leads, a library of lead compounds with the desired biological activities is produced. A model is then developed to predict the quantitative relation between the structural and physico-chemical features of these compounds and their biological activities. A statistical model generated using such relations is then used to mathematically optimize the biological properties of sets of compounds and maximize relevant biological activities. QSAR is used to modify existing compounds and improve their activities, and has been widely used in drug discovery to improve existing drugs for NDs. A study conducted by Dong et al . successfully designed a new series of PDE-4 inhibitors using the QSAR approach [ 61 ]. Bhadoriya et al . successfully implemented QSAR to the discovery of more potent anti-Alzheimer’s agents [ 62 ]. In latter, QSAR studies were carried out on a series of 34 fused 5,6-bicyclic heterocycles to identify the structural characteristics needed to inhibit Aβ42.

2.3. Pharmacophore Modelling

A pharmacophore is an assembly (3D arrangement) of 'steric' and 'electronic' features required for optimal supramolecular interaction with a specific biological target structure and to prompt/block its biological response [ 63 ]. Ligand-based pharmacophore model generation is based on available information on the biological activities of compounds/ligands. A pharmacophore does not symbolize an actual molecule/ligand or real connection between functional groups, but rather provides an abstract description of molecular features that are vital for molecular interactions between molecules and macromolecular ligands.

Pharmacophore modeling is widely used to identify potential lead molecules quickly. During the recent era of drug design, many therapeutically potent and well accepted drug targets with unknown active site geometries have been identified. Pharmacophore modeling provides an efficient means of rapidly screening huge databases of compounds. The elucidation of common pharmacophore features is conducted by aligning conformational models and active compounds three dimensionally. A superimposition algorithm assembles training set compounds (3D structure) in the same position/arrangement of their respective chemical properties/features. Pharmacophoric features are positioned such that all/maximum compounds share a common chemical functionality. To refine a shared pharmacophore feature, information regarding inactive compounds can be included in the model generation process. A number of tools and software have been developed for pharmacophore development, such as, Phase, Catalyst/Discovery Studio, MOE, and LigandScout [ 64 ].

3. SUCCESSFUL CADD APPROACHES TO THE TREATMENT OF NEURODEGENERATIVE DISORDERS

The success of CADD has resulted in its being recognized as an important technique in the research and pharmaceutical fields. There are many examples of the successful application of CADD, but here we describe its successes with respect to the design of drugs for the treatment of NDs. Amyloid-β is an important therapeutic target in Alzheimer’s disease [ 65 ]. Chen et al . used an in silico approach to study a series of peptides against the fibrillar form of Aβ, and reported two highly active compounds [ 66 ]. These peptides were subsequently found to inhibit the neurotoxic effects of Aβ on neuroblastoma cells.

BACE-1 is an enzyme that has been reported to be essential for β-amyloid generation [ 67 ]. Research suggests inhibition of this enzyme stops the production of β-amyloid, and thus, prevents NDs like Alzheimer's disease [ 68 ]. This finding has made BACE-1 an important therapeutic target for NDs. During the last few years, several computational approaches have been used to study the structural behavior of BACE-1 and to design their inhibitors [ 69 - 71 ].

ROCK-I and NOX2 are among the most attractive potential therapeutic targets for several NDs [ 72 - 75 ]. Inhibition of these two enzymes constitutes treatment for neurological diseases like autism spectral disorder, Alzheimer, and fragile X syndrome. Alokam et al . reported the successful use of CADD to design dual inhibitors for these enzymes [ 76 ], by employing a combination of pharmacophores and using a molecular docking approach to identify chemical entities. In vitro validation of selected chemical entities demonstrated their inhibitory potentials against ROCK-I and NOX2.

HDAC6 is a member of the class IIb Histone deacetylases (HDACs) family and is usually found in cytosol in association with non-histone proteins [ 77 , 78 ]. HDAC6 has been widely reported to be a crucial therapeutic drug target for several NDs [ 79 - 81 ]. The implementation of CADD has been reported to result in the design of a potential inhibitor of this enzyme. In one study conducted by Goracci et al ., a virtual screening approach was used to identify potential inhibitors for HDAC6, and these were then subjected to in vitro testing. The results obtained showed inhibitors had low cytotoxicities, suggesting potential for drug development [ 82 ]. Several other reports have described the successful use of CADD in the NDs.

4. Limitations

Despite a number of successful applications of CADD to modern drug design, it has its limitations. In particular, like any computer assisted hypothetical system results must be validated in actual systems, and many lead molecules identified using CADD have failed to exhibit desired activities in biological systems [ 83 , 84 ]. Several parameters must be met before potential compound to be approved as potent lead/drug, as it has to pass several pharmacological criteria. In fact, an average of only 40% of lead/drug candidates passes the different phases of clinical trials and obtains approval for clinical use.

Any computational tool based on pre-defined algorithms and scripts has its limitations, and the computational tools/methods used in CADD, such as, molecular docking, virtual screening, QSAR, pharmacophore modeling, and molecular dynamics, have their own limitations [ 49 , 85 - 88 ]. Furthermore, ADME and many toxicity prediction tools are not supported by solid experimental data, and many examples of the failure of these computational approaches can be found in the literature [ 89 , 90 ].

To overcome limitations and improve accuracy in terms of predicting potent leads, regular updates of tools and algorithms are needed. Database reliability and high quality validated experimental molecules is to be developed and updated because many pharmacophores do not pass biological activity process due to non-availability of good quality data sets. Databases should contain detail data on genomics and proteomics, high quality sequence information, physicochemical properties, and structures.

In the present era of drug discovery, the application of CADD counts up the most important accountability, and provides computational tools and algorithms that save time, costs, and reduce the risk of detecting non-viable developmental leads. The discovery of a new lead/drug using recent CADD paradigms requires a systematic understanding of the molecular and pathological conditions induced by diseases. Early diagnosis of NDs remains a huge challenge for researchers and clinicians. However, CADD can assist researchers studying interactions between drugs and receptors. The pharmacoinformatic approach is being applied to modern drug discovery and is providing much basic knowledge regarding drug-receptor interactions. Novel technologies and computational algorithms are required to move the CADD approach forward, as new developments are likely to lead to tools for disease identification and the screening of potential lead compounds. The emerging field of neurological studies, which includes neuroproteomics and neurogenomics, may aid understanding of the neuronal alterations associated with NDs. Furthermore, the application of technologies associated with neuroproteomics, neurogenomics, and next generation sequencing, and genome wide association studies may result in the identification of novel therapeutic targets and ultimately improve our ability to treat NDs.

Acknowledgements

This work was supported by the grant K16281 awarded to Korea Institute of Oriental Medicine (KIOM) from Ministry of Education, Science and Technology (MEST), Republic of Korea.

List OF Abbreviations

Consent for publication.

Not applicable.

Conflict of Interest

The authors declare no conflict of interest, financial or otherwise.

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• My Account Login
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Open access
• Published: 26 March 2024

Predicting and improving complex beer flavor through machine learning

• Michiel Schreurs   ORCID: orcid.org/0000-0002-9449-5619 1 , 2 , 3   na1 ,
• Supinya Piampongsant 1 , 2 , 3   na1 ,
• Miguel Roncoroni   ORCID: orcid.org/0000-0001-7461-1427 1 , 2 , 3   na1 ,
• Lloyd Cool   ORCID: orcid.org/0000-0001-9936-3124 1 , 2 , 3 , 4 ,
• Beatriz Herrera-Malaver   ORCID: orcid.org/0000-0002-5096-9974 1 , 2 , 3 ,
• Christophe Vanderaa   ORCID: orcid.org/0000-0001-7443-5427 4 ,
• Florian A. Theßeling 1 , 2 , 3 ,
• Łukasz Kreft   ORCID: orcid.org/0000-0001-7620-4657 5 ,
• Alexander Botzki   ORCID: orcid.org/0000-0001-6691-4233 5 ,
• Philippe Malcorps 6 ,
• Luk Daenen 6 ,
• Tom Wenseleers   ORCID: orcid.org/0000-0002-1434-861X 4 &
• Kevin J. Verstrepen   ORCID: orcid.org/0000-0002-3077-6219 1 , 2 , 3  

Nature Communications volume  15 , Article number:  2368 ( 2024 ) Cite this article

27k Accesses

720 Altmetric

Metrics details

• Chemical engineering
• Gas chromatography
• Machine learning
• Metabolomics
• Taste receptors

The perception and appreciation of food flavor depends on many interacting chemical compounds and external factors, and therefore proves challenging to understand and predict. Here, we combine extensive chemical and sensory analyses of 250 different beers to train machine learning models that allow predicting flavor and consumer appreciation. For each beer, we measure over 200 chemical properties, perform quantitative descriptive sensory analysis with a trained tasting panel and map data from over 180,000 consumer reviews to train 10 different machine learning models. The best-performing algorithm, Gradient Boosting, yields models that significantly outperform predictions based on conventional statistics and accurately predict complex food features and consumer appreciation from chemical profiles. Model dissection allows identifying specific and unexpected compounds as drivers of beer flavor and appreciation. Adding these compounds results in variants of commercial alcoholic and non-alcoholic beers with improved consumer appreciation. Together, our study reveals how big data and machine learning uncover complex links between food chemistry, flavor and consumer perception, and lays the foundation to develop novel, tailored foods with superior flavors.

Similar content being viewed by others

BitterSweet: Building machine learning models for predicting the bitter and sweet taste of small molecules

Rudraksh Tuwani, Somin Wadhwa & Ganesh Bagler

Sensory lexicon and aroma volatiles analysis of brewing malt

Xiaoxia Su, Miao Yu, … Tianyi Du

Predicting odor from molecular structure: a multi-label classification approach

Kushagra Saini & Venkatnarayan Ramanathan

Introduction

Predicting and understanding food perception and appreciation is one of the major challenges in food science. Accurate modeling of food flavor and appreciation could yield important opportunities for both producers and consumers, including quality control, product fingerprinting, counterfeit detection, spoilage detection, and the development of new products and product combinations (food pairing) 1 , 2 , 3 , 4 , 5 , 6 . Accurate models for flavor and consumer appreciation would contribute greatly to our scientific understanding of how humans perceive and appreciate flavor. Moreover, accurate predictive models would also facilitate and standardize existing food assessment methods and could supplement or replace assessments by trained and consumer tasting panels, which are variable, expensive and time-consuming 7 , 8 , 9 . Lastly, apart from providing objective, quantitative, accurate and contextual information that can help producers, models can also guide consumers in understanding their personal preferences 10 .

Despite the myriad of applications, predicting food flavor and appreciation from its chemical properties remains a largely elusive goal in sensory science, especially for complex food and beverages 11 , 12 . A key obstacle is the immense number of flavor-active chemicals underlying food flavor. Flavor compounds can vary widely in chemical structure and concentration, making them technically challenging and labor-intensive to quantify, even in the face of innovations in metabolomics, such as non-targeted metabolic fingerprinting 13 , 14 . Moreover, sensory analysis is perhaps even more complicated. Flavor perception is highly complex, resulting from hundreds of different molecules interacting at the physiochemical and sensorial level. Sensory perception is often non-linear, characterized by complex and concentration-dependent synergistic and antagonistic effects 15 , 16 , 17 , 18 , 19 , 20 , 21 that are further convoluted by the genetics, environment, culture and psychology of consumers 22 , 23 , 24 . Perceived flavor is therefore difficult to measure, with problems of sensitivity, accuracy, and reproducibility that can only be resolved by gathering sufficiently large datasets 25 . Trained tasting panels are considered the prime source of quality sensory data, but require meticulous training, are low throughput and high cost. Public databases containing consumer reviews of food products could provide a valuable alternative, especially for studying appreciation scores, which do not require formal training 25 . Public databases offer the advantage of amassing large amounts of data, increasing the statistical power to identify potential drivers of appreciation. However, public datasets suffer from biases, including a bias in the volunteers that contribute to the database, as well as confounding factors such as price, cult status and psychological conformity towards previous ratings of the product.

Classical multivariate statistics and machine learning methods have been used to predict flavor of specific compounds by, for example, linking structural properties of a compound to its potential biological activities or linking concentrations of specific compounds to sensory profiles 1 , 26 . Importantly, most previous studies focused on predicting organoleptic properties of single compounds (often based on their chemical structure) 27 , 28 , 29 , 30 , 31 , 32 , 33 , thus ignoring the fact that these compounds are present in a complex matrix in food or beverages and excluding complex interactions between compounds. Moreover, the classical statistics commonly used in sensory science 34 , 35 , 36 , 37 , 38 , 39 require a large sample size and sufficient variance amongst predictors to create accurate models. They are not fit for studying an extensive set of hundreds of interacting flavor compounds, since they are sensitive to outliers, have a high tendency to overfit and are less suited for non-linear and discontinuous relationships 40 .

In this study, we combine extensive chemical analyses and sensory data of a set of different commercial beers with machine learning approaches to develop models that predict taste, smell, mouthfeel and appreciation from compound concentrations. Beer is particularly suited to model the relationship between chemistry, flavor and appreciation. First, beer is a complex product, consisting of thousands of flavor compounds that partake in complex sensory interactions 41 , 42 , 43 . This chemical diversity arises from the raw materials (malt, yeast, hops, water and spices) and biochemical conversions during the brewing process (kilning, mashing, boiling, fermentation, maturation and aging) 44 , 45 . Second, the advent of the internet saw beer consumers embrace online review platforms, such as RateBeer (ZX Ventures, Anheuser-Busch InBev SA/NV) and BeerAdvocate (Next Glass, inc.). In this way, the beer community provides massive data sets of beer flavor and appreciation scores, creating extraordinarily large sensory databases to complement the analyses of our professional sensory panel. Specifically, we characterize over 200 chemical properties of 250 commercial beers, spread across 22 beer styles, and link these to the descriptive sensory profiling data of a 16-person in-house trained tasting panel and data acquired from over 180,000 public consumer reviews. These unique and extensive datasets enable us to train a suite of machine learning models to predict flavor and appreciation from a beer’s chemical profile. Dissection of the best-performing models allows us to pinpoint specific compounds as potential drivers of beer flavor and appreciation. Follow-up experiments confirm the importance of these compounds and ultimately allow us to significantly improve the flavor and appreciation of selected commercial beers. Together, our study represents a significant step towards understanding complex flavors and reinforces the value of machine learning to develop and refine complex foods. In this way, it represents a stepping stone for further computer-aided food engineering applications 46 .

To generate a comprehensive dataset on beer flavor, we selected 250 commercial Belgian beers across 22 different beer styles (Supplementary Fig.  S1 ). Beers with ≤ 4.2% alcohol by volume (ABV) were classified as non-alcoholic and low-alcoholic. Blonds and Tripels constitute a significant portion of the dataset (12.4% and 11.2%, respectively) reflecting their presence on the Belgian beer market and the heterogeneity of beers within these styles. By contrast, lager beers are less diverse and dominated by a handful of brands. Rare styles such as Brut or Faro make up only a small fraction of the dataset (2% and 1%, respectively) because fewer of these beers are produced and because they are dominated by distinct characteristics in terms of flavor and chemical composition.

Extensive analysis identifies relationships between chemical compounds in beer

For each beer, we measured 226 different chemical properties, including common brewing parameters such as alcohol content, iso-alpha acids, pH, sugar concentration 47 , and over 200 flavor compounds (Methods, Supplementary Table  S1 ). A large portion (37.2%) are terpenoids arising from hopping, responsible for herbal and fruity flavors 16 , 48 . A second major category are yeast metabolites, such as esters and alcohols, that result in fruity and solvent notes 48 , 49 , 50 . Other measured compounds are primarily derived from malt, or other microbes such as non- Saccharomyces yeasts and bacteria (‘wild flora’). Compounds that arise from spices or staling are labeled under ‘Others’. Five attributes (caloric value, total acids and total ester, hop aroma and sulfur compounds) are calculated from multiple individually measured compounds.

As a first step in identifying relationships between chemical properties, we determined correlations between the concentrations of the compounds (Fig.  1 , upper panel, Supplementary Data  1 and 2 , and Supplementary Fig.  S2 . For the sake of clarity, only a subset of the measured compounds is shown in Fig.  1 ). Compounds of the same origin typically show a positive correlation, while absence of correlation hints at parameters varying independently. For example, the hop aroma compounds citronellol, and alpha-terpineol show moderate correlations with each other (Spearman’s rho=0.39 and 0.57), but not with the bittering hop component iso-alpha acids (Spearman’s rho=0.16 and −0.07). This illustrates how brewers can independently modify hop aroma and bitterness by selecting hop varieties and dosage time. If hops are added early in the boiling phase, chemical conversions increase bitterness while aromas evaporate, conversely, late addition of hops preserves aroma but limits bitterness 51 . Similarly, hop-derived iso-alpha acids show a strong anti-correlation with lactic acid and acetic acid, likely reflecting growth inhibition of lactic acid and acetic acid bacteria, or the consequent use of fewer hops in sour beer styles, such as West Flanders ales and Fruit beers, that rely on these bacteria for their distinct flavors 52 . Finally, yeast-derived esters (ethyl acetate, ethyl decanoate, ethyl hexanoate, ethyl octanoate) and alcohols (ethanol, isoamyl alcohol, isobutanol, and glycerol), correlate with Spearman coefficients above 0.5, suggesting that these secondary metabolites are correlated with the yeast genetic background and/or fermentation parameters and may be difficult to influence individually, although the choice of yeast strain may offer some control 53 .

Spearman rank correlations are shown. Descriptors are grouped according to their origin (malt (blue), hops (green), yeast (red), wild flora (yellow), Others (black)), and sensory aspect (aroma, taste, palate, and overall appreciation). Please note that for the chemical compounds, for the sake of clarity, only a subset of the total number of measured compounds is shown, with an emphasis on the key compounds for each source. For more details, see the main text and Methods section. Chemical data can be found in Supplementary Data  1 , correlations between all chemical compounds are depicted in Supplementary Fig.  S2 and correlation values can be found in Supplementary Data  2 . See Supplementary Data  4 for sensory panel assessments and Supplementary Data  5 for correlation values between all sensory descriptors.

Interestingly, different beer styles show distinct patterns for some flavor compounds (Supplementary Fig.  S3 ). These observations agree with expectations for key beer styles, and serve as a control for our measurements. For instance, Stouts generally show high values for color (darker), while hoppy beers contain elevated levels of iso-alpha acids, compounds associated with bitter hop taste. Acetic and lactic acid are not prevalent in most beers, with notable exceptions such as Kriek, Lambic, Faro, West Flanders ales and Flanders Old Brown, which use acid-producing bacteria ( Lactobacillus and Pediococcus ) or unconventional yeast ( Brettanomyces ) 54 , 55 . Glycerol, ethanol and esters show similar distributions across all beer styles, reflecting their common origin as products of yeast metabolism during fermentation 45 , 53 . Finally, low/no-alcohol beers contain low concentrations of glycerol and esters. This is in line with the production process for most of the low/no-alcohol beers in our dataset, which are produced through limiting fermentation or by stripping away alcohol via evaporation or dialysis, with both methods having the unintended side-effect of reducing the amount of flavor compounds in the final beer 56 , 57 .

Besides expected associations, our data also reveals less trivial associations between beer styles and specific parameters. For example, geraniol and citronellol, two monoterpenoids responsible for citrus, floral and rose flavors and characteristic of Citra hops, are found in relatively high amounts in Christmas, Saison, and Brett/co-fermented beers, where they may originate from terpenoid-rich spices such as coriander seeds instead of hops 58 .

Tasting panel assessments reveal sensorial relationships in beer

To assess the sensory profile of each beer, a trained tasting panel evaluated each of the 250 beers for 50 sensory attributes, including different hop, malt and yeast flavors, off-flavors and spices. Panelists used a tasting sheet (Supplementary Data  3 ) to score the different attributes. Panel consistency was evaluated by repeating 12 samples across different sessions and performing ANOVA. In 95% of cases no significant difference was found across sessions ( p  > 0.05), indicating good panel consistency (Supplementary Table  S2 ).

Aroma and taste perception reported by the trained panel are often linked (Fig.  1 , bottom left panel and Supplementary Data  4 and 5 ), with high correlations between hops aroma and taste (Spearman’s rho=0.83). Bitter taste was found to correlate with hop aroma and taste in general (Spearman’s rho=0.80 and 0.69), and particularly with “grassy” noble hops (Spearman’s rho=0.75). Barnyard flavor, most often associated with sour beers, is identified together with stale hops (Spearman’s rho=0.97) that are used in these beers. Lactic and acetic acid, which often co-occur, are correlated (Spearman’s rho=0.66). Interestingly, sweetness and bitterness are anti-correlated (Spearman’s rho = −0.48), confirming the hypothesis that they mask each other 59 , 60 . Beer body is highly correlated with alcohol (Spearman’s rho = 0.79), and overall appreciation is found to correlate with multiple aspects that describe beer mouthfeel (alcohol, carbonation; Spearman’s rho= 0.32, 0.39), as well as with hop and ester aroma intensity (Spearman’s rho=0.39 and 0.35).

Similar to the chemical analyses, sensorial analyses confirmed typical features of specific beer styles (Supplementary Fig.  S4 ). For example, sour beers (Faro, Flanders Old Brown, Fruit beer, Kriek, Lambic, West Flanders ale) were rated acidic, with flavors of both acetic and lactic acid. Hoppy beers were found to be bitter and showed hop-associated aromas like citrus and tropical fruit. Malt taste is most detected among scotch, stout/porters, and strong ales, while low/no-alcohol beers, which often have a reputation for being ‘worty’ (reminiscent of unfermented, sweet malt extract) appear in the middle. Unsurprisingly, hop aromas are most strongly detected among hoppy beers. Like its chemical counterpart (Supplementary Fig.  S3 ), acidity shows a right-skewed distribution, with the most acidic beers being Krieks, Lambics, and West Flanders ales.

Tasting panel assessments of specific flavors correlate with chemical composition

We find that the concentrations of several chemical compounds strongly correlate with specific aroma or taste, as evaluated by the tasting panel (Fig.  2 , Supplementary Fig.  S5 , Supplementary Data  6 ). In some cases, these correlations confirm expectations and serve as a useful control for data quality. For example, iso-alpha acids, the bittering compounds in hops, strongly correlate with bitterness (Spearman’s rho=0.68), while ethanol and glycerol correlate with tasters’ perceptions of alcohol and body, the mouthfeel sensation of fullness (Spearman’s rho=0.82/0.62 and 0.72/0.57 respectively) and darker color from roasted malts is a good indication of malt perception (Spearman’s rho=0.54).

Heatmap colors indicate Spearman’s Rho. Axes are organized according to sensory categories (aroma, taste, mouthfeel, overall), chemical categories and chemical sources in beer (malt (blue), hops (green), yeast (red), wild flora (yellow), Others (black)). See Supplementary Data  6 for all correlation values.

Interestingly, for some relationships between chemical compounds and perceived flavor, correlations are weaker than expected. For example, the rose-smelling phenethyl acetate only weakly correlates with floral aroma. This hints at more complex relationships and interactions between compounds and suggests a need for a more complex model than simple correlations. Lastly, we uncovered unexpected correlations. For instance, the esters ethyl decanoate and ethyl octanoate appear to correlate slightly with hop perception and bitterness, possibly due to their fruity flavor. Iron is anti-correlated with hop aromas and bitterness, most likely because it is also anti-correlated with iso-alpha acids. This could be a sign of metal chelation of hop acids 61 , given that our analyses measure unbound hop acids and total iron content, or could result from the higher iron content in dark and Fruit beers, which typically have less hoppy and bitter flavors 62 .

Public consumer reviews complement expert panel data

To complement and expand the sensory data of our trained tasting panel, we collected 180,000 reviews of our 250 beers from the online consumer review platform RateBeer. This provided numerical scores for beer appearance, aroma, taste, palate, overall quality as well as the average overall score.

Public datasets are known to suffer from biases, such as price, cult status and psychological conformity towards previous ratings of a product. For example, prices correlate with appreciation scores for these online consumer reviews (rho=0.49, Supplementary Fig.  S6 ), but not for our trained tasting panel (rho=0.19). This suggests that prices affect consumer appreciation, which has been reported in wine 63 , while blind tastings are unaffected. Moreover, we observe that some beer styles, like lagers and non-alcoholic beers, generally receive lower scores, reflecting that online reviewers are mostly beer aficionados with a preference for specialty beers over lager beers. In general, we find a modest correlation between our trained panel’s overall appreciation score and the online consumer appreciation scores (Fig.  3 , rho=0.29). Apart from the aforementioned biases in the online datasets, serving temperature, sample freshness and surroundings, which are all tightly controlled during the tasting panel sessions, can vary tremendously across online consumers and can further contribute to (among others, appreciation) differences between the two categories of tasters. Importantly, in contrast to the overall appreciation scores, for many sensory aspects the results from the professional panel correlated well with results obtained from RateBeer reviews. Correlations were highest for features that are relatively easy to recognize even for untrained tasters, like bitterness, sweetness, alcohol and malt aroma (Fig.  3 and below).

RateBeer text mining results can be found in Supplementary Data  7 . Rho values shown are Spearman correlation values, with asterisks indicating significant correlations ( p  < 0.05, two-sided). All p values were smaller than 0.001, except for Esters aroma (0.0553), Esters taste (0.3275), Esters aroma—banana (0.0019), Coriander (0.0508) and Diacetyl (0.0134).

Besides collecting consumer appreciation from these online reviews, we developed automated text analysis tools to gather additional data from review texts (Supplementary Data  7 ). Processing review texts on the RateBeer database yielded comparable results to the scores given by the trained panel for many common sensory aspects, including acidity, bitterness, sweetness, alcohol, malt, and hop tastes (Fig.  3 ). This is in line with what would be expected, since these attributes require less training for accurate assessment and are less influenced by environmental factors such as temperature, serving glass and odors in the environment. Consumer reviews also correlate well with our trained panel for 4-vinyl guaiacol, a compound associated with a very characteristic aroma. By contrast, correlations for more specific aromas like ester, coriander or diacetyl are underrepresented in the online reviews, underscoring the importance of using a trained tasting panel and standardized tasting sheets with explicit factors to be scored for evaluating specific aspects of a beer. Taken together, our results suggest that public reviews are trustworthy for some, but not all, flavor features and can complement or substitute taste panel data for these sensory aspects.

Models can predict beer sensory profiles from chemical data

The rich datasets of chemical analyses, tasting panel assessments and public reviews gathered in the first part of this study provided us with a unique opportunity to develop predictive models that link chemical data to sensorial features. Given the complexity of beer flavor, basic statistical tools such as correlations or linear regression may not always be the most suitable for making accurate predictions. Instead, we applied different machine learning models that can model both simple linear and complex interactive relationships. Specifically, we constructed a set of regression models to predict (a) trained panel scores for beer flavor and quality and (b) public reviews’ appreciation scores from beer chemical profiles. We trained and tested 10 different models (Methods), 3 linear regression-based models (simple linear regression with first-order interactions (LR), lasso regression with first-order interactions (Lasso), partial least squares regressor (PLSR)), 5 decision tree models (AdaBoost regressor (ABR), extra trees (ET), gradient boosting regressor (GBR), random forest (RF) and XGBoost regressor (XGBR)), 1 support vector regression (SVR), and 1 artificial neural network (ANN) model.

To compare the performance of our machine learning models, the dataset was randomly split into a training and test set, stratified by beer style. After a model was trained on data in the training set, its performance was evaluated on its ability to predict the test dataset obtained from multi-output models (based on the coefficient of determination, see Methods). Additionally, individual-attribute models were ranked per descriptor and the average rank was calculated, as proposed by Korneva et al. 64 . Importantly, both ways of evaluating the models’ performance agreed in general. Performance of the different models varied (Table  1 ). It should be noted that all models perform better at predicting RateBeer results than results from our trained tasting panel. One reason could be that sensory data is inherently variable, and this variability is averaged out with the large number of public reviews from RateBeer. Additionally, all tree-based models perform better at predicting taste than aroma. Linear models (LR) performed particularly poorly, with negative R 2 values, due to severe overfitting (training set R 2  = 1). Overfitting is a common issue in linear models with many parameters and limited samples, especially with interaction terms further amplifying the number of parameters. L1 regularization (Lasso) successfully overcomes this overfitting, out-competing multiple tree-based models on the RateBeer dataset. Similarly, the dimensionality reduction of PLSR avoids overfitting and improves performance, to some extent. Still, tree-based models (ABR, ET, GBR, RF and XGBR) show the best performance, out-competing the linear models (LR, Lasso, PLSR) commonly used in sensory science 65 .

GBR models showed the best overall performance in predicting sensory responses from chemical information, with R 2 values up to 0.75 depending on the predicted sensory feature (Supplementary Table  S4 ). The GBR models predict consumer appreciation (RateBeer) better than our trained panel’s appreciation (R 2 value of 0.67 compared to R 2 value of 0.09) (Supplementary Table  S3 and Supplementary Table  S4 ). ANN models showed intermediate performance, likely because neural networks typically perform best with larger datasets 66 . The SVR shows intermediate performance, mostly due to the weak predictions of specific attributes that lower the overall performance (Supplementary Table  S4 ).

Model dissection identifies specific, unexpected compounds as drivers of consumer appreciation

Next, we leveraged our models to infer important contributors to sensory perception and consumer appreciation. Consumer preference is a crucial sensory aspects, because a product that shows low consumer appreciation scores often does not succeed commercially 25 . Additionally, the requirement for a large number of representative evaluators makes consumer trials one of the more costly and time-consuming aspects of product development. Hence, a model for predicting chemical drivers of overall appreciation would be a welcome addition to the available toolbox for food development and optimization.

Since GBR models on our RateBeer dataset showed the best overall performance, we focused on these models. Specifically, we used two approaches to identify important contributors. First, rankings of the most important predictors for each sensorial trait in the GBR models were obtained based on impurity-based feature importance (mean decrease in impurity). High-ranked parameters were hypothesized to be either the true causal chemical properties underlying the trait, to correlate with the actual causal properties, or to take part in sensory interactions affecting the trait 67 (Fig.  4A ). In a second approach, we used SHAP 68 to determine which parameters contributed most to the model for making predictions of consumer appreciation (Fig.  4B ). SHAP calculates parameter contributions to model predictions on a per-sample basis, which can be aggregated into an importance score.

A The impurity-based feature importance (mean deviance in impurity, MDI) calculated from the Gradient Boosting Regression (GBR) model predicting RateBeer appreciation scores. The top 15 highest ranked chemical properties are shown. B SHAP summary plot for the top 15 parameters contributing to our GBR model. Each point on the graph represents a sample from our dataset. The color represents the concentration of that parameter, with bluer colors representing low values and redder colors representing higher values. Greater absolute values on the horizontal axis indicate a higher impact of the parameter on the prediction of the model. C Spearman correlations between the 15 most important chemical properties and consumer overall appreciation. Numbers indicate the Spearman Rho correlation coefficient, and the rank of this correlation compared to all other correlations. The top 15 important compounds were determined using SHAP (panel B).

Both approaches identified ethyl acetate as the most predictive parameter for beer appreciation (Fig.  4 ). Ethyl acetate is the most abundant ester in beer with a typical ‘fruity’, ‘solvent’ and ‘alcoholic’ flavor, but is often considered less important than other esters like isoamyl acetate. The second most important parameter identified by SHAP is ethanol, the most abundant beer compound after water. Apart from directly contributing to beer flavor and mouthfeel, ethanol drastically influences the physical properties of beer, dictating how easily volatile compounds escape the beer matrix to contribute to beer aroma 69 . Importantly, it should also be noted that the importance of ethanol for appreciation is likely inflated by the very low appreciation scores of non-alcoholic beers (Supplementary Fig.  S4 ). Despite not often being considered a driver of beer appreciation, protein level also ranks highly in both approaches, possibly due to its effect on mouthfeel and body 70 . Lactic acid, which contributes to the tart taste of sour beers, is the fourth most important parameter identified by SHAP, possibly due to the generally high appreciation of sour beers in our dataset.

Interestingly, some of the most important predictive parameters for our model are not well-established as beer flavors or are even commonly regarded as being negative for beer quality. For example, our models identify methanethiol and ethyl phenyl acetate, an ester commonly linked to beer staling 71 , as a key factor contributing to beer appreciation. Although there is no doubt that high concentrations of these compounds are considered unpleasant, the positive effects of modest concentrations are not yet known 72 , 73 .

To compare our approach to conventional statistics, we evaluated how well the 15 most important SHAP-derived parameters correlate with consumer appreciation (Fig.  4C ). Interestingly, only 6 of the properties derived by SHAP rank amongst the top 15 most correlated parameters. For some chemical compounds, the correlations are so low that they would have likely been considered unimportant. For example, lactic acid, the fourth most important parameter, shows a bimodal distribution for appreciation, with sour beers forming a separate cluster, that is missed entirely by the Spearman correlation. Additionally, the correlation plots reveal outliers, emphasizing the need for robust analysis tools. Together, this highlights the need for alternative models, like the Gradient Boosting model, that better grasp the complexity of (beer) flavor.

Finally, to observe the relationships between these chemical properties and their predicted targets, partial dependence plots were constructed for the six most important predictors of consumer appreciation 74 , 75 , 76 (Supplementary Fig.  S7 ). One-way partial dependence plots show how a change in concentration affects the predicted appreciation. These plots reveal an important limitation of our models: appreciation predictions remain constant at ever-increasing concentrations. This implies that once a threshold concentration is reached, further increasing the concentration does not affect appreciation. This is false, as it is well-documented that certain compounds become unpleasant at high concentrations, including ethyl acetate (‘nail polish’) 77 and methanethiol (‘sulfury’ and ‘rotten cabbage’) 78 . The inability of our models to grasp that flavor compounds have optimal levels, above which they become negative, is a consequence of working with commercial beer brands where (off-)flavors are rarely too high to negatively impact the product. The two-way partial dependence plots show how changing the concentration of two compounds influences predicted appreciation, visualizing their interactions (Supplementary Fig.  S7 ). In our case, the top 5 parameters are dominated by additive or synergistic interactions, with high concentrations for both compounds resulting in the highest predicted appreciation.

To assess the robustness of our best-performing models and model predictions, we performed 100 iterations of the GBR, RF and ET models. In general, all iterations of the models yielded similar performance (Supplementary Fig.  S8 ). Moreover, the main predictors (including the top predictors ethanol and ethyl acetate) remained virtually the same, especially for GBR and RF. For the iterations of the ET model, we did observe more variation in the top predictors, which is likely a consequence of the model’s inherent random architecture in combination with co-correlations between certain predictors. However, even in this case, several of the top predictors (ethanol and ethyl acetate) remain unchanged, although their rank in importance changes (Supplementary Fig.  S8 ).

Next, we investigated if a combination of RateBeer and trained panel data into one consolidated dataset would lead to stronger models, under the hypothesis that such a model would suffer less from bias in the datasets. A GBR model was trained to predict appreciation on the combined dataset. This model underperformed compared to the RateBeer model, both in the native case and when including a dataset identifier (R 2  = 0.67, 0.26 and 0.42 respectively). For the latter, the dataset identifier is the most important feature (Supplementary Fig.  S9 ), while most of the feature importance remains unchanged, with ethyl acetate and ethanol ranking highest, like in the original model trained only on RateBeer data. It seems that the large variation in the panel dataset introduces noise, weakening the models’ performances and reliability. In addition, it seems reasonable to assume that both datasets are fundamentally different, with the panel dataset obtained by blind tastings by a trained professional panel.

Lastly, we evaluated whether beer style identifiers would further enhance the model’s performance. A GBR model was trained with parameters that explicitly encoded the styles of the samples. This did not improve model performance (R2 = 0.66 with style information vs R2 = 0.67). The most important chemical features are consistent with the model trained without style information (eg. ethanol and ethyl acetate), and with the exception of the most preferred (strong ale) and least preferred (low/no-alcohol) styles, none of the styles were among the most important features (Supplementary Fig.  S9 , Supplementary Table  S5 and S6 ). This is likely due to a combination of style-specific chemical signatures, such as iso-alpha acids and lactic acid, that implicitly convey style information to the original models, as well as the low number of samples belonging to some styles, making it difficult for the model to learn style-specific patterns. Moreover, beer styles are not rigorously defined, with some styles overlapping in features and some beers being misattributed to a specific style, all of which leads to more noise in models that use style parameters.

Model validation

To test if our predictive models give insight into beer appreciation, we set up experiments aimed at improving existing commercial beers. We specifically selected overall appreciation as the trait to be examined because of its complexity and commercial relevance. Beer flavor comprises a complex bouquet rather than single aromas and tastes 53 . Hence, adding a single compound to the extent that a difference is noticeable may lead to an unbalanced, artificial flavor. Therefore, we evaluated the effect of combinations of compounds. Because Blond beers represent the most extensive style in our dataset, we selected a beer from this style as the starting material for these experiments (Beer 64 in Supplementary Data  1 ).

In the first set of experiments, we adjusted the concentrations of compounds that made up the most important predictors of overall appreciation (ethyl acetate, ethanol, lactic acid, ethyl phenyl acetate) together with correlated compounds (ethyl hexanoate, isoamyl acetate, glycerol), bringing them up to 95 th percentile ethanol-normalized concentrations (Methods) within the Blond group (‘Spiked’ concentration in Fig.  5A ). Compared to controls, the spiked beers were found to have significantly improved overall appreciation among trained panelists, with panelist noting increased intensity of ester flavors, sweetness, alcohol, and body fullness (Fig.  5B ). To disentangle the contribution of ethanol to these results, a second experiment was performed without the addition of ethanol. This resulted in a similar outcome, including increased perception of alcohol and overall appreciation.

Adding the top chemical compounds, identified as best predictors of appreciation by our model, into poorly appreciated beers results in increased appreciation from our trained panel. Results of sensory tests between base beers and those spiked with compounds identified as the best predictors by the model. A Blond and Non/Low-alcohol (0.0% ABV) base beers were brought up to 95th-percentile ethanol-normalized concentrations within each style. B For each sensory attribute, tasters indicated the more intense sample and selected the sample they preferred. The numbers above the bars correspond to the p values that indicate significant changes in perceived flavor (two-sided binomial test: alpha 0.05, n  = 20 or 13).

In a last experiment, we tested whether using the model’s predictions can boost the appreciation of a non-alcoholic beer (beer 223 in Supplementary Data  1 ). Again, the addition of a mixture of predicted compounds (omitting ethanol, in this case) resulted in a significant increase in appreciation, body, ester flavor and sweetness.

Predicting flavor and consumer appreciation from chemical composition is one of the ultimate goals of sensory science. A reliable, systematic and unbiased way to link chemical profiles to flavor and food appreciation would be a significant asset to the food and beverage industry. Such tools would substantially aid in quality control and recipe development, offer an efficient and cost-effective alternative to pilot studies and consumer trials and would ultimately allow food manufacturers to produce superior, tailor-made products that better meet the demands of specific consumer groups more efficiently.

A limited set of studies have previously tried, to varying degrees of success, to predict beer flavor and beer popularity based on (a limited set of) chemical compounds and flavors 79 , 80 . Current sensitive, high-throughput technologies allow measuring an unprecedented number of chemical compounds and properties in a large set of samples, yielding a dataset that can train models that help close the gaps between chemistry and flavor, even for a complex natural product like beer. To our knowledge, no previous research gathered data at this scale (250 samples, 226 chemical parameters, 50 sensory attributes and 5 consumer scores) to disentangle and validate the chemical aspects driving beer preference using various machine-learning techniques. We find that modern machine learning models outperform conventional statistical tools, such as correlations and linear models, and can successfully predict flavor appreciation from chemical composition. This could be attributed to the natural incorporation of interactions and non-linear or discontinuous effects in machine learning models, which are not easily grasped by the linear model architecture. While linear models and partial least squares regression represent the most widespread statistical approaches in sensory science, in part because they allow interpretation 65 , 81 , 82 , modern machine learning methods allow for building better predictive models while preserving the possibility to dissect and exploit the underlying patterns. Of the 10 different models we trained, tree-based models, such as our best performing GBR, showed the best overall performance in predicting sensory responses from chemical information, outcompeting artificial neural networks. This agrees with previous reports for models trained on tabular data 83 . Our results are in line with the findings of Colantonio et al. who also identified the gradient boosting architecture as performing best at predicting appreciation and flavor (of tomatoes and blueberries, in their specific study) 26 . Importantly, besides our larger experimental scale, we were able to directly confirm our models’ predictions in vivo.

Our study confirms that flavor compound concentration does not always correlate with perception, suggesting complex interactions that are often missed by more conventional statistics and simple models. Specifically, we find that tree-based algorithms may perform best in developing models that link complex food chemistry with aroma. Furthermore, we show that massive datasets of untrained consumer reviews provide a valuable source of data, that can complement or even replace trained tasting panels, especially for appreciation and basic flavors, such as sweetness and bitterness. This holds despite biases that are known to occur in such datasets, such as price or conformity bias. Moreover, GBR models predict taste better than aroma. This is likely because taste (e.g. bitterness) often directly relates to the corresponding chemical measurements (e.g., iso-alpha acids), whereas such a link is less clear for aromas, which often result from the interplay between multiple volatile compounds. We also find that our models are best at predicting acidity and alcohol, likely because there is a direct relation between the measured chemical compounds (acids and ethanol) and the corresponding perceived sensorial attribute (acidity and alcohol), and because even untrained consumers are generally able to recognize these flavors and aromas.

The predictions of our final models, trained on review data, hold even for blind tastings with small groups of trained tasters, as demonstrated by our ability to validate specific compounds as drivers of beer flavor and appreciation. Since adding a single compound to the extent of a noticeable difference may result in an unbalanced flavor profile, we specifically tested our identified key drivers as a combination of compounds. While this approach does not allow us to validate if a particular single compound would affect flavor and/or appreciation, our experiments do show that this combination of compounds increases consumer appreciation.

It is important to stress that, while it represents an important step forward, our approach still has several major limitations. A key weakness of the GBR model architecture is that amongst co-correlating variables, the largest main effect is consistently preferred for model building. As a result, co-correlating variables often have artificially low importance scores, both for impurity and SHAP-based methods, like we observed in the comparison to the more randomized Extra Trees models. This implies that chemicals identified as key drivers of a specific sensory feature by GBR might not be the true causative compounds, but rather co-correlate with the actual causative chemical. For example, the high importance of ethyl acetate could be (partially) attributed to the total ester content, ethanol or ethyl hexanoate (rho=0.77, rho=0.72 and rho=0.68), while ethyl phenylacetate could hide the importance of prenyl isobutyrate and ethyl benzoate (rho=0.77 and rho=0.76). Expanding our GBR model to include beer style as a parameter did not yield additional power or insight. This is likely due to style-specific chemical signatures, such as iso-alpha acids and lactic acid, that implicitly convey style information to the original model, as well as the smaller sample size per style, limiting the power to uncover style-specific patterns. This can be partly attributed to the curse of dimensionality, where the high number of parameters results in the models mainly incorporating single parameter effects, rather than complex interactions such as style-dependent effects 67 . A larger number of samples may overcome some of these limitations and offer more insight into style-specific effects. On the other hand, beer style is not a rigid scientific classification, and beers within one style often differ a lot, which further complicates the analysis of style as a model factor.

Our study is limited to beers from Belgian breweries. Although these beers cover a large portion of the beer styles available globally, some beer styles and consumer patterns may be missing, while other features might be overrepresented. For example, many Belgian ales exhibit yeast-driven flavor profiles, which is reflected in the chemical drivers of appreciation discovered by this study. In future work, expanding the scope to include diverse markets and beer styles could lead to the identification of even more drivers of appreciation and better models for special niche products that were not present in our beer set.

In addition to inherent limitations of GBR models, there are also some limitations associated with studying food aroma. Even if our chemical analyses measured most of the known aroma compounds, the total number of flavor compounds in complex foods like beer is still larger than the subset we were able to measure in this study. For example, hop-derived thiols, that influence flavor at very low concentrations, are notoriously difficult to measure in a high-throughput experiment. Moreover, consumer perception remains subjective and prone to biases that are difficult to avoid. It is also important to stress that the models are still immature and that more extensive datasets will be crucial for developing more complete models in the future. Besides more samples and parameters, our dataset does not include any demographic information about the tasters. Including such data could lead to better models that grasp external factors like age and culture. Another limitation is that our set of beers consists of high-quality end-products and lacks beers that are unfit for sale, which limits the current model in accurately predicting products that are appreciated very badly. Finally, while models could be readily applied in quality control, their use in sensory science and product development is restrained by their inability to discern causal relationships. Given that the models cannot distinguish compounds that genuinely drive consumer perception from those that merely correlate, validation experiments are essential to identify true causative compounds.

Despite the inherent limitations, dissection of our models enabled us to pinpoint specific molecules as potential drivers of beer aroma and consumer appreciation, including compounds that were unexpected and would not have been identified using standard approaches. Important drivers of beer appreciation uncovered by our models include protein levels, ethyl acetate, ethyl phenyl acetate and lactic acid. Currently, many brewers already use lactic acid to acidify their brewing water and ensure optimal pH for enzymatic activity during the mashing process. Our results suggest that adding lactic acid can also improve beer appreciation, although its individual effect remains to be tested. Interestingly, ethanol appears to be unnecessary to improve beer appreciation, both for blond beer and alcohol-free beer. Given the growing consumer interest in alcohol-free beer, with a predicted annual market growth of >7% 84 , it is relevant for brewers to know what compounds can further increase consumer appreciation of these beers. Hence, our model may readily provide avenues to further improve the flavor and consumer appreciation of both alcoholic and non-alcoholic beers, which is generally considered one of the key challenges for future beer production.

Whereas we see a direct implementation of our results for the development of superior alcohol-free beverages and other food products, our study can also serve as a stepping stone for the development of novel alcohol-containing beverages. We want to echo the growing body of scientific evidence for the negative effects of alcohol consumption, both on the individual level by the mutagenic, teratogenic and carcinogenic effects of ethanol 85 , 86 , as well as the burden on society caused by alcohol abuse and addiction. We encourage the use of our results for the production of healthier, tastier products, including novel and improved beverages with lower alcohol contents. Furthermore, we strongly discourage the use of these technologies to improve the appreciation or addictive properties of harmful substances.

The present work demonstrates that despite some important remaining hurdles, combining the latest developments in chemical analyses, sensory analysis and modern machine learning methods offers exciting avenues for food chemistry and engineering. Soon, these tools may provide solutions in quality control and recipe development, as well as new approaches to sensory science and flavor research.

Beer selection

250 commercial Belgian beers were selected to cover the broad diversity of beer styles and corresponding diversity in chemical composition and aroma. See Supplementary Fig.  S1 .

Chemical dataset

Sample preparation.

Beers within their expiration date were purchased from commercial retailers. Samples were prepared in biological duplicates at room temperature, unless explicitly stated otherwise. Bottle pressure was measured with a manual pressure device (Steinfurth Mess-Systeme GmbH) and used to calculate CO 2 concentration. The beer was poured through two filter papers (Macherey-Nagel, 500713032 MN 713 ¼) to remove carbon dioxide and prevent spontaneous foaming. Samples were then prepared for measurements by targeted Headspace-Gas Chromatography-Flame Ionization Detector/Flame Photometric Detector (HS-GC-FID/FPD), Headspace-Solid Phase Microextraction-Gas Chromatography-Mass Spectrometry (HS-SPME-GC-MS), colorimetric analysis, enzymatic analysis, Near-Infrared (NIR) analysis, as described in the sections below. The mean values of biological duplicates are reported for each compound.

HS-GC-FID/FPD

HS-GC-FID/FPD (Shimadzu GC 2010 Plus) was used to measure higher alcohols, acetaldehyde, esters, 4-vinyl guaicol, and sulfur compounds. Each measurement comprised 5 ml of sample pipetted into a 20 ml glass vial containing 1.75 g NaCl (VWR, 27810.295). 100 µl of 2-heptanol (Sigma-Aldrich, H3003) (internal standard) solution in ethanol (Fisher Chemical, E/0650DF/C17) was added for a final concentration of 2.44 mg/L. Samples were flushed with nitrogen for 10 s, sealed with a silicone septum, stored at −80 °C and analyzed in batches of 20.

The GC was equipped with a DB-WAXetr column (length, 30 m; internal diameter, 0.32 mm; layer thickness, 0.50 µm; Agilent Technologies, Santa Clara, CA, USA) to the FID and an HP-5 column (length, 30 m; internal diameter, 0.25 mm; layer thickness, 0.25 µm; Agilent Technologies, Santa Clara, CA, USA) to the FPD. N 2 was used as the carrier gas. Samples were incubated for 20 min at 70 °C in the headspace autosampler (Flow rate, 35 cm/s; Injection volume, 1000 µL; Injection mode, split; Combi PAL autosampler, CTC analytics, Switzerland). The injector, FID and FPD temperatures were kept at 250 °C. The GC oven temperature was first held at 50 °C for 5 min and then allowed to rise to 80 °C at a rate of 5 °C/min, followed by a second ramp of 4 °C/min until 200 °C kept for 3 min and a final ramp of (4 °C/min) until 230 °C for 1 min. Results were analyzed with the GCSolution software version 2.4 (Shimadzu, Kyoto, Japan). The GC was calibrated with a 5% EtOH solution (VWR International) containing the volatiles under study (Supplementary Table  S7 ).

HS-SPME-GC-MS

HS-SPME-GC-MS (Shimadzu GCMS-QP-2010 Ultra) was used to measure additional volatile compounds, mainly comprising terpenoids and esters. Samples were analyzed by HS-SPME using a triphase DVB/Carboxen/PDMS 50/30 μm SPME fiber (Supelco Co., Bellefonte, PA, USA) followed by gas chromatography (Thermo Fisher Scientific Trace 1300 series, USA) coupled to a mass spectrometer (Thermo Fisher Scientific ISQ series MS) equipped with a TriPlus RSH autosampler. 5 ml of degassed beer sample was placed in 20 ml vials containing 1.75 g NaCl (VWR, 27810.295). 5 µl internal standard mix was added, containing 2-heptanol (1 g/L) (Sigma-Aldrich, H3003), 4-fluorobenzaldehyde (1 g/L) (Sigma-Aldrich, 128376), 2,3-hexanedione (1 g/L) (Sigma-Aldrich, 144169) and guaiacol (1 g/L) (Sigma-Aldrich, W253200) in ethanol (Fisher Chemical, E/0650DF/C17). Each sample was incubated at 60 °C in the autosampler oven with constant agitation. After 5 min equilibration, the SPME fiber was exposed to the sample headspace for 30 min. The compounds trapped on the fiber were thermally desorbed in the injection port of the chromatograph by heating the fiber for 15 min at 270 °C.

The GC-MS was equipped with a low polarity RXi-5Sil MS column (length, 20 m; internal diameter, 0.18 mm; layer thickness, 0.18 µm; Restek, Bellefonte, PA, USA). Injection was performed in splitless mode at 320 °C, a split flow of 9 ml/min, a purge flow of 5 ml/min and an open valve time of 3 min. To obtain a pulsed injection, a programmed gas flow was used whereby the helium gas flow was set at 2.7 mL/min for 0.1 min, followed by a decrease in flow of 20 ml/min to the normal 0.9 mL/min. The temperature was first held at 30 °C for 3 min and then allowed to rise to 80 °C at a rate of 7 °C/min, followed by a second ramp of 2 °C/min till 125 °C and a final ramp of 8 °C/min with a final temperature of 270 °C.

Mass acquisition range was 33 to 550 amu at a scan rate of 5 scans/s. Electron impact ionization energy was 70 eV. The interface and ion source were kept at 275 °C and 250 °C, respectively. A mix of linear n-alkanes (from C7 to C40, Supelco Co.) was injected into the GC-MS under identical conditions to serve as external retention index markers. Identification and quantification of the compounds were performed using an in-house developed R script as described in Goelen et al. and Reher et al. 87 , 88 (for package information, see Supplementary Table  S8 ). Briefly, chromatograms were analyzed using AMDIS (v2.71) 89 to separate overlapping peaks and obtain pure compound spectra. The NIST MS Search software (v2.0 g) in combination with the NIST2017, FFNSC3 and Adams4 libraries were used to manually identify the empirical spectra, taking into account the expected retention time. After background subtraction and correcting for retention time shifts between samples run on different days based on alkane ladders, compound elution profiles were extracted and integrated using a file with 284 target compounds of interest, which were either recovered in our identified AMDIS list of spectra or were known to occur in beer. Compound elution profiles were estimated for every peak in every chromatogram over a time-restricted window using weighted non-negative least square analysis after which peak areas were integrated 87 , 88 . Batch effect correction was performed by normalizing against the most stable internal standard compound, 4-fluorobenzaldehyde. Out of all 284 target compounds that were analyzed, 167 were visually judged to have reliable elution profiles and were used for final analysis.

Discrete photometric and enzymatic analysis

Discrete photometric and enzymatic analysis (Thermo Scientific TM Gallery TM Plus Beermaster Discrete Analyzer) was used to measure acetic acid, ammonia, beta-glucan, iso-alpha acids, color, sugars, glycerol, iron, pH, protein, and sulfite. 2 ml of sample volume was used for the analyses. Information regarding the reagents and standard solutions used for analyses and calibrations is included in Supplementary Table  S7 and Supplementary Table  S9 .

NIR analyses

NIR analysis (Anton Paar Alcolyzer Beer ME System) was used to measure ethanol. Measurements comprised 50 ml of sample, and a 10% EtOH solution was used for calibration.

Correlation calculations

Pairwise Spearman Rank correlations were calculated between all chemical properties.

Sensory dataset

Trained panel.

Our trained tasting panel consisted of volunteers who gave prior verbal informed consent. All compounds used for the validation experiment were of food-grade quality. The tasting sessions were approved by the Social and Societal Ethics Committee of the KU Leuven (G-2022-5677-R2(MAR)). All online reviewers agreed to the Terms and Conditions of the RateBeer website.

Sensory analysis was performed according to the American Society of Brewing Chemists (ASBC) Sensory Analysis Methods 90 . 30 volunteers were screened through a series of triangle tests. The sixteen most sensitive and consistent tasters were retained as taste panel members. The resulting panel was diverse in age [22–42, mean: 29], sex [56% male] and nationality [7 different countries]. The panel developed a consensus vocabulary to describe beer aroma, taste and mouthfeel. Panelists were trained to identify and score 50 different attributes, using a 7-point scale to rate attributes’ intensity. The scoring sheet is included as Supplementary Data  3 . Sensory assessments took place between 10–12 a.m. The beers were served in black-colored glasses. Per session, between 5 and 12 beers of the same style were tasted at 12 °C to 16 °C. Two reference beers were added to each set and indicated as ‘Reference 1 & 2’, allowing panel members to calibrate their ratings. Not all panelists were present at every tasting. Scores were scaled by standard deviation and mean-centered per taster. Values are represented as z-scores and clustered by Euclidean distance. Pairwise Spearman correlations were calculated between taste and aroma sensory attributes. Panel consistency was evaluated by repeating samples on different sessions and performing ANOVA to identify differences, using the ‘stats’ package (v4.2.2) in R (for package information, see Supplementary Table  S8 ).

Online reviews from a public database

The ‘scrapy’ package in Python (v3.6) (for package information, see Supplementary Table  S8 ). was used to collect 232,288 online reviews (mean=922, min=6, max=5343) from RateBeer, an online beer review database. Each review entry comprised 5 numerical scores (appearance, aroma, taste, palate and overall quality) and an optional review text. The total number of reviews per reviewer was collected separately. Numerical scores were scaled and centered per rater, and mean scores were calculated per beer.

For the review texts, the language was estimated using the packages ‘langdetect’ and ‘langid’ in Python. Reviews that were classified as English by both packages were kept. Reviewers with fewer than 100 entries overall were discarded. 181,025 reviews from >6000 reviewers from >40 countries remained. Text processing was done using the ‘nltk’ package in Python. Texts were corrected for slang and misspellings; proper nouns and rare words that are relevant to the beer context were specified and kept as-is (‘Chimay’,’Lambic’, etc.). A dictionary of semantically similar sensorial terms, for example ‘floral’ and ‘flower’, was created and collapsed together into one term. Words were stemmed and lemmatized to avoid identifying words such as ‘acid’ and ‘acidity’ as separate terms. Numbers and punctuation were removed.

Sentences from up to 50 randomly chosen reviews per beer were manually categorized according to the aspect of beer they describe (appearance, aroma, taste, palate, overall quality—not to be confused with the 5 numerical scores described above) or flagged as irrelevant if they contained no useful information. If a beer contained fewer than 50 reviews, all reviews were manually classified. This labeled data set was used to train a model that classified the rest of the sentences for all beers 91 . Sentences describing taste and aroma were extracted, and term frequency–inverse document frequency (TFIDF) was implemented to calculate enrichment scores for sensorial words per beer.

The sex of the tasting subject was not considered when building our sensory database. Instead, results from different panelists were averaged, both for our trained panel (56% male, 44% female) and the RateBeer reviews (70% male, 30% female for RateBeer as a whole).

Beer price collection and processing

Beer prices were collected from the following stores: Colruyt, Delhaize, Total Wine, BeerHawk, The Belgian Beer Shop, The Belgian Shop, and Beer of Belgium. Where applicable, prices were converted to Euros and normalized per liter. Spearman correlations were calculated between these prices and mean overall appreciation scores from RateBeer and the taste panel, respectively.

Pairwise Spearman Rank correlations were calculated between all sensory properties.

Machine learning models

Predictive modeling of sensory profiles from chemical data.

Regression models were constructed to predict (a) trained panel scores for beer flavors and quality from beer chemical profiles and (b) public reviews’ appreciation scores from beer chemical profiles. Z-scores were used to represent sensory attributes in both data sets. Chemical properties with log-normal distributions (Shapiro-Wilk test, p  <  0.05 ) were log-transformed. Missing chemical measurements (0.1% of all data) were replaced with mean values per attribute. Observations from 250 beers were randomly separated into a training set (70%, 175 beers) and a test set (30%, 75 beers), stratified per beer style. Chemical measurements (p = 231) were normalized based on the training set average and standard deviation. In total, three linear regression-based models: linear regression with first-order interaction terms (LR), lasso regression with first-order interaction terms (Lasso) and partial least squares regression (PLSR); five decision tree models, Adaboost regressor (ABR), Extra Trees (ET), Gradient Boosting regressor (GBR), Random Forest (RF) and XGBoost regressor (XGBR); one support vector machine model (SVR) and one artificial neural network model (ANN) were trained. The models were implemented using the ‘scikit-learn’ package (v1.2.2) and ‘xgboost’ package (v1.7.3) in Python (v3.9.16). Models were trained, and hyperparameters optimized, using five-fold cross-validated grid search with the coefficient of determination (R 2 ) as the evaluation metric. The ANN (scikit-learn’s MLPRegressor) was optimized using Bayesian Tree-Structured Parzen Estimator optimization with the ‘Optuna’ Python package (v3.2.0). Individual models were trained per attribute, and a multi-output model was trained on all attributes simultaneously.

Model dissection

GBR was found to outperform other methods, resulting in models with the highest average R 2 values in both trained panel and public review data sets. Impurity-based rankings of the most important predictors for each predicted sensorial trait were obtained using the ‘scikit-learn’ package. To observe the relationships between these chemical properties and their predicted targets, partial dependence plots (PDP) were constructed for the six most important predictors of consumer appreciation 74 , 75 .

The ‘SHAP’ package in Python (v0.41.0) was implemented to provide an alternative ranking of predictor importance and to visualize the predictors’ effects as a function of their concentration 68 .

Validation of causal chemical properties

To validate the effects of the most important model features on predicted sensory attributes, beers were spiked with the chemical compounds identified by the models and descriptive sensory analyses were carried out according to the American Society of Brewing Chemists (ASBC) protocol 90 .

Compound spiking was done 30 min before tasting. Compounds were spiked into fresh beer bottles, that were immediately resealed and inverted three times. Fresh bottles of beer were opened for the same duration, resealed, and inverted thrice, to serve as controls. Pairs of spiked samples and controls were served simultaneously, chilled and in dark glasses as outlined in the Trained panel section above. Tasters were instructed to select the glass with the higher flavor intensity for each attribute (directional difference test 92 ) and to select the glass they prefer.

The final concentration after spiking was equal to the within-style average, after normalizing by ethanol concentration. This was done to ensure balanced flavor profiles in the final spiked beer. The same methods were applied to improve a non-alcoholic beer. Compounds were the following: ethyl acetate (Merck KGaA, W241415), ethyl hexanoate (Merck KGaA, W243906), isoamyl acetate (Merck KGaA, W205508), phenethyl acetate (Merck KGaA, W285706), ethanol (96%, Colruyt), glycerol (Merck KGaA, W252506), lactic acid (Merck KGaA, 261106).

Significant differences in preference or perceived intensity were determined by performing the two-sided binomial test on each attribute.

Reporting summary

Further information on research design is available in the  Nature Portfolio Reporting Summary linked to this article.

Data availability

The data that support the findings of this work are available in the Supplementary Data files and have been deposited to Zenodo under accession code 10653704 93 . The RateBeer scores data are under restricted access, they are not publicly available as they are property of RateBeer (ZX Ventures, USA). Access can be obtained from the authors upon reasonable request and with permission of RateBeer (ZX Ventures, USA).  Source data are provided with this paper.

Code availability

The code for training the machine learning models, analyzing the models, and generating the figures has been deposited to Zenodo under accession code 10653704 93 .

Tieman, D. et al. A chemical genetic roadmap to improved tomato flavor. Science 355 , 391–394 (2017).

Article   ADS   CAS   PubMed   Google Scholar  

Plutowska, B. & Wardencki, W. Application of gas chromatography–olfactometry (GC–O) in analysis and quality assessment of alcoholic beverages – A review. Food Chem. 107 , 449–463 (2008).

Article   CAS   Google Scholar  

Legin, A., Rudnitskaya, A., Seleznev, B. & Vlasov, Y. Electronic tongue for quality assessment of ethanol, vodka and eau-de-vie. Anal. Chim. Acta 534 , 129–135 (2005).

Loutfi, A., Coradeschi, S., Mani, G. K., Shankar, P. & Rayappan, J. B. B. Electronic noses for food quality: A review. J. Food Eng. 144 , 103–111 (2015).

Ahn, Y.-Y., Ahnert, S. E., Bagrow, J. P. & Barabási, A.-L. Flavor network and the principles of food pairing. Sci. Rep. 1 , 196 (2011).

Article   CAS   PubMed   PubMed Central   Google Scholar  

Bartoshuk, L. M. & Klee, H. J. Better fruits and vegetables through sensory analysis. Curr. Biol. 23 , R374–R378 (2013).

Article   CAS   PubMed   Google Scholar  

Piggott, J. R. Design questions in sensory and consumer science. Food Qual. Prefer. 3293 , 217–220 (1995).

Article   Google Scholar  

Kermit, M. & Lengard, V. Assessing the performance of a sensory panel-panellist monitoring and tracking. J. Chemom. 19 , 154–161 (2005).

Cook, D. J., Hollowood, T. A., Linforth, R. S. T. & Taylor, A. J. Correlating instrumental measurements of texture and flavour release with human perception. Int. J. Food Sci. Technol. 40 , 631–641 (2005).

Chinchanachokchai, S., Thontirawong, P. & Chinchanachokchai, P. A tale of two recommender systems: The moderating role of consumer expertise on artificial intelligence based product recommendations. J. Retail. Consum. Serv. 61 , 1–12 (2021).

Ross, C. F. Sensory science at the human-machine interface. Trends Food Sci. Technol. 20 , 63–72 (2009).

Chambers, E. IV & Koppel, K. Associations of volatile compounds with sensory aroma and flavor: The complex nature of flavor. Molecules 18 , 4887–4905 (2013).

Pinu, F. R. Metabolomics—The new frontier in food safety and quality research. Food Res. Int. 72 , 80–81 (2015).

Danezis, G. P., Tsagkaris, A. S., Brusic, V. & Georgiou, C. A. Food authentication: state of the art and prospects. Curr. Opin. Food Sci. 10 , 22–31 (2016).

Shepherd, G. M. Smell images and the flavour system in the human brain. Nature 444 , 316–321 (2006).

Meilgaard, M. C. Prediction of flavor differences between beers from their chemical composition. J. Agric. Food Chem. 30 , 1009–1017 (1982).

Xu, L. et al. Widespread receptor-driven modulation in peripheral olfactory coding. Science 368 , eaaz5390 (2020).

Kupferschmidt, K. Following the flavor. Science 340 , 808–809 (2013).

Billesbølle, C. B. et al. Structural basis of odorant recognition by a human odorant receptor. Nature 615 , 742–749 (2023).

Article   ADS   PubMed   PubMed Central   Google Scholar  

Smith, B. Perspective: Complexities of flavour. Nature 486 , S6–S6 (2012).

Pfister, P. et al. Odorant receptor inhibition is fundamental to odor encoding. Curr. Biol. 30 , 2574–2587 (2020).

Moskowitz, H. W., Kumaraiah, V., Sharma, K. N., Jacobs, H. L. & Sharma, S. D. Cross-cultural differences in simple taste preferences. Science 190 , 1217–1218 (1975).

Eriksson, N. et al. A genetic variant near olfactory receptor genes influences cilantro preference. Flavour 1 , 22 (2012).

Ferdenzi, C. et al. Variability of affective responses to odors: Culture, gender, and olfactory knowledge. Chem. Senses 38 , 175–186 (2013).

Article   PubMed   Google Scholar  

Lawless, H. T. & Heymann, H. Sensory evaluation of food: Principles and practices. (Springer, New York, NY). https://doi.org/10.1007/978-1-4419-6488-5 (2010).

Colantonio, V. et al. Metabolomic selection for enhanced fruit flavor. Proc. Natl. Acad. Sci. 119 , e2115865119 (2022).

Fritz, F., Preissner, R. & Banerjee, P. VirtualTaste: a web server for the prediction of organoleptic properties of chemical compounds. Nucleic Acids Res 49 , W679–W684 (2021).

Tuwani, R., Wadhwa, S. & Bagler, G. BitterSweet: Building machine learning models for predicting the bitter and sweet taste of small molecules. Sci. Rep. 9 , 1–13 (2019).

Dagan-Wiener, A. et al. Bitter or not? BitterPredict, a tool for predicting taste from chemical structure. Sci. Rep. 7 , 1–13 (2017).

Pallante, L. et al. Toward a general and interpretable umami taste predictor using a multi-objective machine learning approach. Sci. Rep. 12 , 1–11 (2022).

Malavolta, M. et al. A survey on computational taste predictors. Eur. Food Res. Technol. 248 , 2215–2235 (2022).

Lee, B. K. et al. A principal odor map unifies diverse tasks in olfactory perception. Science 381 , 999–1006 (2023).

Mayhew, E. J. et al. Transport features predict if a molecule is odorous. Proc. Natl. Acad. Sci. 119 , e2116576119 (2022).

Niu, Y. et al. Sensory evaluation of the synergism among ester odorants in light aroma-type liquor by odor threshold, aroma intensity and flash GC electronic nose. Food Res. Int. 113 , 102–114 (2018).

Yu, P., Low, M. Y. & Zhou, W. Design of experiments and regression modelling in food flavour and sensory analysis: A review. Trends Food Sci. Technol. 71 , 202–215 (2018).

Oladokun, O. et al. The impact of hop bitter acid and polyphenol profiles on the perceived bitterness of beer. Food Chem. 205 , 212–220 (2016).

Linforth, R., Cabannes, M., Hewson, L., Yang, N. & Taylor, A. Effect of fat content on flavor delivery during consumption: An in vivo model. J. Agric. Food Chem. 58 , 6905–6911 (2010).

Guo, S., Na Jom, K. & Ge, Y. Influence of roasting condition on flavor profile of sunflower seeds: A flavoromics approach. Sci. Rep. 9 , 11295 (2019).

Ren, Q. et al. The changes of microbial community and flavor compound in the fermentation process of Chinese rice wine using Fagopyrum tataricum grain as feedstock. Sci. Rep. 9 , 3365 (2019).

Hastie, T., Friedman, J. & Tibshirani, R. The Elements of Statistical Learning. (Springer, New York, NY). https://doi.org/10.1007/978-0-387-21606-5 (2001).

Dietz, C., Cook, D., Huismann, M., Wilson, C. & Ford, R. The multisensory perception of hop essential oil: a review. J. Inst. Brew. 126 , 320–342 (2020).

CAS   Google Scholar  

Roncoroni, Miguel & Verstrepen, Kevin Joan. Belgian Beer: Tested and Tasted. (Lannoo, 2018).

Meilgaard, M. Flavor chemistry of beer: Part II: Flavor and threshold of 239 aroma volatiles. in (1975).

Bokulich, N. A. & Bamforth, C. W. The microbiology of malting and brewing. Microbiol. Mol. Biol. Rev. MMBR 77 , 157–172 (2013).

Dzialo, M. C., Park, R., Steensels, J., Lievens, B. & Verstrepen, K. J. Physiology, ecology and industrial applications of aroma formation in yeast. FEMS Microbiol. Rev. 41 , S95–S128 (2017).

Article   PubMed   PubMed Central   Google Scholar  

Datta, A. et al. Computer-aided food engineering. Nat. Food 3 , 894–904 (2022).

American Society of Brewing Chemists. Beer Methods. (American Society of Brewing Chemists, St. Paul, MN, U.S.A.).

Olaniran, A. O., Hiralal, L., Mokoena, M. P. & Pillay, B. Flavour-active volatile compounds in beer: production, regulation and control. J. Inst. Brew. 123 , 13–23 (2017).

Verstrepen, K. J. et al. Flavor-active esters: Adding fruitiness to beer. J. Biosci. Bioeng. 96 , 110–118 (2003).

Meilgaard, M. C. Flavour chemistry of beer. part I: flavour interaction between principal volatiles. Master Brew. Assoc. Am. Tech. Q 12 , 107–117 (1975).

Briggs, D. E., Boulton, C. A., Brookes, P. A. & Stevens, R. Brewing 227–254. (Woodhead Publishing). https://doi.org/10.1533/9781855739062.227 (2004).

Bossaert, S., Crauwels, S., De Rouck, G. & Lievens, B. The power of sour - A review: Old traditions, new opportunities. BrewingScience 72 , 78–88 (2019).

Google Scholar  

Verstrepen, K. J. et al. Flavor active esters: Adding fruitiness to beer. J. Biosci. Bioeng. 96 , 110–118 (2003).

Snauwaert, I. et al. Microbial diversity and metabolite composition of Belgian red-brown acidic ales. Int. J. Food Microbiol. 221 , 1–11 (2016).

Spitaels, F. et al. The microbial diversity of traditional spontaneously fermented lambic beer. PLoS ONE 9 , e95384 (2014).

Blanco, C. A., Andrés-Iglesias, C. & Montero, O. Low-alcohol Beers: Flavor Compounds, Defects, and Improvement Strategies. Crit. Rev. Food Sci. Nutr. 56 , 1379–1388 (2016).

Jackowski, M. & Trusek, A. Non-Alcohol. beer Prod. – Overv. 20 , 32–38 (2018).

Takoi, K. et al. The contribution of geraniol metabolism to the citrus flavour of beer: Synergy of geraniol and β-citronellol under coexistence with excess linalool. J. Inst. Brew. 116 , 251–260 (2010).

Kroeze, J. H. & Bartoshuk, L. M. Bitterness suppression as revealed by split-tongue taste stimulation in humans. Physiol. Behav. 35 , 779–783 (1985).

Mennella, J. A. et al. A spoonful of sugar helps the medicine go down”: Bitter masking bysucrose among children and adults. Chem. Senses 40 , 17–25 (2015).

Wietstock, P., Kunz, T., Perreira, F. & Methner, F.-J. Metal chelation behavior of hop acids in buffered model systems. BrewingScience 69 , 56–63 (2016).

Sancho, D., Blanco, C. A., Caballero, I. & Pascual, A. Free iron in pale, dark and alcohol-free commercial lager beers. J. Sci. Food Agric. 91 , 1142–1147 (2011).

Rodrigues, H. & Parr, W. V. Contribution of cross-cultural studies to understanding wine appreciation: A review. Food Res. Int. 115 , 251–258 (2019).

Korneva, E. & Blockeel, H. Towards better evaluation of multi-target regression models. in ECML PKDD 2020 Workshops (eds. Koprinska, I. et al.) 353–362 (Springer International Publishing, Cham, 2020). https://doi.org/10.1007/978-3-030-65965-3_23 .

Gastón Ares. Mathematical and Statistical Methods in Food Science and Technology. (Wiley, 2013).

Grinsztajn, L., Oyallon, E. & Varoquaux, G. Why do tree-based models still outperform deep learning on tabular data? Preprint at http://arxiv.org/abs/2207.08815 (2022).

Gries, S. T. Statistics for Linguistics with R: A Practical Introduction. in Statistics for Linguistics with R (De Gruyter Mouton, 2021). https://doi.org/10.1515/9783110718256 .

Lundberg, S. M. et al. From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2 , 56–67 (2020).

Ickes, C. M. & Cadwallader, K. R. Effects of ethanol on flavor perception in alcoholic beverages. Chemosens. Percept. 10 , 119–134 (2017).

Kato, M. et al. Influence of high molecular weight polypeptides on the mouthfeel of commercial beer. J. Inst. Brew. 127 , 27–40 (2021).

Wauters, R. et al. Novel Saccharomyces cerevisiae variants slow down the accumulation of staling aldehydes and improve beer shelf-life. Food Chem. 398 , 1–11 (2023).

Li, H., Jia, S. & Zhang, W. Rapid determination of low-level sulfur compounds in beer by headspace gas chromatography with a pulsed flame photometric detector. J. Am. Soc. Brew. Chem. 66 , 188–191 (2008).

Dercksen, A., Laurens, J., Torline, P., Axcell, B. C. & Rohwer, E. Quantitative analysis of volatile sulfur compounds in beer using a membrane extraction interface. J. Am. Soc. Brew. Chem. 54 , 228–233 (1996).

Molnar, C. Interpretable Machine Learning: A Guide for Making Black-Box Models Interpretable. (2020).

Zhao, Q. & Hastie, T. Causal interpretations of black-box models. J. Bus. Econ. Stat. Publ. Am. Stat. Assoc. 39 , 272–281 (2019).

Article   MathSciNet   Google Scholar  

Hastie, T., Tibshirani, R. & Friedman, J. The Elements of Statistical Learning. (Springer, 2019).

Labrado, D. et al. Identification by NMR of key compounds present in beer distillates and residual phases after dealcoholization by vacuum distillation. J. Sci. Food Agric. 100 , 3971–3978 (2020).

Lusk, L. T., Kay, S. B., Porubcan, A. & Ryder, D. S. Key olfactory cues for beer oxidation. J. Am. Soc. Brew. Chem. 70 , 257–261 (2012).

Gonzalez Viejo, C., Torrico, D. D., Dunshea, F. R. & Fuentes, S. Development of artificial neural network models to assess beer acceptability based on sensory properties using a robotic pourer: A comparative model approach to achieve an artificial intelligence system. Beverages 5 , 33 (2019).

Gonzalez Viejo, C., Fuentes, S., Torrico, D. D., Godbole, A. & Dunshea, F. R. Chemical characterization of aromas in beer and their effect on consumers liking. Food Chem. 293 , 479–485 (2019).

Gilbert, J. L. et al. Identifying breeding priorities for blueberry flavor using biochemical, sensory, and genotype by environment analyses. PLOS ONE 10 , 1–21 (2015).

Goulet, C. et al. Role of an esterase in flavor volatile variation within the tomato clade. Proc. Natl. Acad. Sci. 109 , 19009–19014 (2012).

Article   ADS   CAS   PubMed   PubMed Central   Google Scholar  

Borisov, V. et al. Deep Neural Networks and Tabular Data: A Survey. IEEE Trans. Neural Netw. Learn. Syst. 1–21 https://doi.org/10.1109/TNNLS.2022.3229161 (2022).

Statista. Statista Consumer Market Outlook: Beer - Worldwide.

Seitz, H. K. & Stickel, F. Molecular mechanisms of alcoholmediated carcinogenesis. Nat. Rev. Cancer 7 , 599–612 (2007).

Voordeckers, K. et al. Ethanol exposure increases mutation rate through error-prone polymerases. Nat. Commun. 11 , 3664 (2020).

Goelen, T. et al. Bacterial phylogeny predicts volatile organic compound composition and olfactory response of an aphid parasitoid. Oikos 129 , 1415–1428 (2020).

Article   ADS   Google Scholar  

Reher, T. et al. Evaluation of hop (Humulus lupulus) as a repellent for the management of Drosophila suzukii. Crop Prot. 124 , 104839 (2019).

Stein, S. E. An integrated method for spectrum extraction and compound identification from gas chromatography/mass spectrometry data. J. Am. Soc. Mass Spectrom. 10 , 770–781 (1999).

American Society of Brewing Chemists. Sensory Analysis Methods. (American Society of Brewing Chemists, St. Paul, MN, U.S.A., 1992).

McAuley, J., Leskovec, J. & Jurafsky, D. Learning Attitudes and Attributes from Multi-Aspect Reviews. Preprint at https://doi.org/10.48550/arXiv.1210.3926 (2012).

Meilgaard, M. C., Carr, B. T. & Carr, B. T. Sensory Evaluation Techniques. (CRC Press, Boca Raton). https://doi.org/10.1201/b16452 (2014).

Schreurs, M. et al. Data from: Predicting and improving complex beer flavor through machine learning. Zenodo https://doi.org/10.5281/zenodo.10653704 (2024).

Download references

Acknowledgements

We thank all lab members for their discussions and thank all tasting panel members for their contributions. Special thanks go out to Dr. Karin Voordeckers for her tremendous help in proofreading and improving the manuscript. M.S. was supported by a Baillet-Latour fellowship, L.C. acknowledges financial support from KU Leuven (C16/17/006), F.A.T. was supported by a PhD fellowship from FWO (1S08821N). Research in the lab of K.J.V. is supported by KU Leuven, FWO, VIB, VLAIO and the Brewing Science Serves Health Fund. Research in the lab of T.W. is supported by FWO (G.0A51.15) and KU Leuven (C16/17/006).

Author information

These authors contributed equally: Michiel Schreurs, Supinya Piampongsant, Miguel Roncoroni.

Authors and Affiliations

VIB—KU Leuven Center for Microbiology, Gaston Geenslaan 1, B-3001, Leuven, Belgium

Michiel Schreurs, Supinya Piampongsant, Miguel Roncoroni, Lloyd Cool, Beatriz Herrera-Malaver, Florian A. Theßeling & Kevin J. Verstrepen

CMPG Laboratory of Genetics and Genomics, KU Leuven, Gaston Geenslaan 1, B-3001, Leuven, Belgium

Leuven Institute for Beer Research (LIBR), Gaston Geenslaan 1, B-3001, Leuven, Belgium

Laboratory of Socioecology and Social Evolution, KU Leuven, Naamsestraat 59, B-3000, Leuven, Belgium

Lloyd Cool, Christophe Vanderaa & Tom Wenseleers

VIB Bioinformatics Core, VIB, Rijvisschestraat 120, B-9052, Ghent, Belgium

Łukasz Kreft & Alexander Botzki

AB InBev SA/NV, Brouwerijplein 1, B-3000, Leuven, Belgium

Philippe Malcorps & Luk Daenen

You can also search for this author in PubMed   Google Scholar

Contributions

S.P., M.S. and K.J.V. conceived the experiments. S.P., M.S. and K.J.V. designed the experiments. S.P., M.S., M.R., B.H. and F.A.T. performed the experiments. S.P., M.S., L.C., C.V., L.K., A.B., P.M., L.D., T.W. and K.J.V. contributed analysis ideas. S.P., M.S., L.C., C.V., T.W. and K.J.V. analyzed the data. All authors contributed to writing the manuscript.

Corresponding author

Correspondence to Kevin J. Verstrepen .

Ethics declarations

Competing interests.

K.J.V. is affiliated with bar.on. The other authors declare no competing interests.

Peer review

Peer review information.

Nature Communications thanks Florian Bauer, Andrew John Macintosh and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. A peer review file is available.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary information, peer review file, description of additional supplementary files, supplementary data 1, supplementary data 2, supplementary data 3, supplementary data 4, supplementary data 5, supplementary data 6, supplementary data 7, reporting summary, source data, source data, rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Schreurs, M., Piampongsant, S., Roncoroni, M. et al. Predicting and improving complex beer flavor through machine learning. Nat Commun 15 , 2368 (2024). https://doi.org/10.1038/s41467-024-46346-0

Download citation

Received : 30 October 2023

Accepted : 21 February 2024

Published : 26 March 2024

DOI : https://doi.org/10.1038/s41467-024-46346-0

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

By submitting a comment you agree to abide by our Terms and Community Guidelines . If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Sign up for the Nature Briefing: Translational Research newsletter — top stories in biotechnology, drug discovery and pharma.