slider1
Biomolecular Artificial Intelligence & Digital Biochemistry
slider2
Computational Structural Biology & Machine Learning for Biomolecules
slider3
Molecular Machine Learning & Chemoinformatics for Drug Discovery
slider4
Computational Structure-based Drug Discovery
slider5
Molecular Modeling & Molecular Dynamics Simulation for Biomolecules

BAID RESEARCH BACKGROUND

The Biomolecular Artificial Intelligence & Digital Biochemistry (BAID) team is an interdisciplinary research group committed to addressing critical challenges in biomolecular science and biomedicine, such as the inefficiency of traditional drug discovery pipelines, limited understanding of molecular mechanisms, and data scarcity in therapeutic development. To overcome these issues, our research goal is to discover, design, and develop innovative advanced AI models and computational frameworks that can accelerate scientific discoveries and therapeutic innovations.

By bridging biochemistry, molecular biology, chemistry, pharmaceutical sciences, and computer science, we employ cutting-edge computational biology and artificial intelligence techniques across three core research lines: (I) Molecular Representation Learning & Computations, (II) Molecular Discovery & Design, and (III) Molecular Modeling & Simulation.

Through this integrative and translational approach, we aspire to conduct transformative research that makes impactful contributions to advancing the frontiers of biomolecular science and biomedicine.

We appreciate the funding and support from

pmu-b_logo

“Our mission is to transform the dynamic landscapes of biomolecular science and biomedicine by discovering, designing, and developing advanced AI models and computational frameworks, striding toward real-world impacts and accelerated scientific discoveries.”

NEWS

isef_book.jpg
isef_2022-scaled.jpg
  • 2025

    Bundit Boonyarit – Received the ThaiSC (NSTDA) Voucher Program 2 award (as recipient) under the Research Project Budget Supplement Category for High Performance Computing (HPC) Credits valued up to 99,900 Baht (6,600 SHr) [PI: Assoc. Prof. Dr. Thanyada Rungrotmongkol]

  • 2025

    Bundit Boonyarit – Received VISTEC Honors for Outstanding Achievements that Brought Recognition to the Institute (Apr 2024 – Mar 2025)

  • 2025

    Bundit Boonyarit – Received Research Grant (as Co-PI) under project of "CanDrugAI: End-to-End AI-Driven Anticancer Drug Discovery & Development" (2025–2027) from the National Science Research and Innovation Fund (NSRF) via the Program Management Unit for Human Resources & Institutional Development, Research and Innovation (PMU-B) [Grant Number: B38G680006]

  • 2024

    Bundit Boonyarit – Received Remarkable Ranking in the Top 20 (17th Place Out of 79 Participating Teams) for the Tox24 Challenge

  • 2024

    Bundit Boonyarit – Received Best Oral Presentation in Computational Biology Session, The 27th International Annual Symposium on Computational Science and Engineering (ANSCSE27)

  • 2023

    Bundit Boonyarit – Research Advisor for ISEF Finalists and Received Fourth Place Award in Computational Biology and Bioinformatics, Regeneron ISEF 2023

  • 2022

    Bundit Boonyarit – Research Advisor for ISEF Finalists and Received First Place Award in Computational Biology and Bioinformatics, Regeneron ISEF 2022

  • 2021

    Bundit Boonyarit – Research Advisor for ISEF Finalists and Received First Place Award in Computational Biology and Bioinformatics, Regeneron ISEF 2021

BAID RESEARCH

The research focuses on discovering, designing, and developing computational frameworks and ML/DL models by integrating cutting-edge AI and computational approaches, striding forward in advancing both fundamental understanding and translational applications across biomolecular science and biomedicine.

The current research lines encompass the following areas:

  • Molecular Representation Learning & Computations

    Designs and develops computational frameworks and models to represent and interpret complex molecular and biological data.

  • Molecular Discovery & Design

    Discovers and designs novel therapeutic and biological molecules to specific biological activities and targets.

  • Molecular Modeling & Simulation

    Simulates and models the structure, dynamics, and interactions of biomolecules to uncover molecular mechanisms and functions.

  • Computational Chemistry
  • Computational Biology
  • Structural Bioinformatics
  • Drug Discovery
  • Machine Learning
  • Deep Learning

Current Research Lines & Projects

  • Blue: Main Project

  • Green: Main & Collaborative Project

  • Yellow: Collaborative Project

Research Line I: Molecular Representation Learning & Computations

Track I: Drug Discovery & Development

  • Molecular Representation Learning for Anticancer Drug Discovery Targeting Kinase Proteins

    Develops advanced molecular representation learning techniques for deep learning models (e.g., graph neural networks) to improve property prediction and interpretation in anticancer drug development against kinase protein targets.

  • Multimodal Deep Learning Based on Multi-Omics for Cancer Drug Response Prediction

    Designs and develops multimodal deep learning architectures that integrate multi-omics data (e.g., genomics, transcriptomics, and proteomics) to predict cell-line-specific cancer drug responses, including monotherapy and combination therapy, advancing personalized and precision medicine.

  • Explainable AI-Driven Adverse Drug Reactions Prediction Toward Pediatric Drug Discovery & Development

    Develops an explainable AI model to predict adverse drug reactions in pediatric drug development by integrating chemical, pharmacological, and biological data, along with physics- and chemistry-based features. This approach accelerates the development of safer pediatric drugs, improves health outcomes, reduces ADR incidence, and supports child-specific therapeutic strategies.
    (in collaboration with Dr. Rossukon Kaewkhaw, Fac. Medicine Ramathibodi Hospital, Mahidol University)

Research Line II: Molecular Discovery & Design

Track I: Enzyme Engineering

  • Computational Enzyme Engineering to Enhance DeHa2 Efficiency for Fluorinated and Chlorinated Organohalogen Degradation

    Leverages integrated deep learning and molecular dynamics simulations to predict potentially efficient DeHa2 variants (haloacid dehalogenase) and analyze the geometry and interactions of the binding pocket under real-world conditions, aimed at enhancing the degradation of toxic fluorinated and chlorinated organohalogen compounds.
    (in collaboration with Dr. Chayasith Uttamapinant, School of Biomolecular Science and Engineering, VISTEC)

Track II: Drug Discovery & Development

  • Computational Discovery and Design of Novel Small Molecules Targeting Glypican-3 for Liver Cancer Therapeutic

    Leverages molecular docking and molecular dynamics simulations to discover, design, and optimize therapeutic small molecules aimed at enhancing bioactivity and targeting glypican-3 in liver cancer.
    (in collaboration with Dr. Chayanon Ngambenjawong, School of Biomolecular Science and Engineering, VISTEC)

Research Line III: Molecular Modeling & Simulation

Track I: Structural Biology

  • Computational Structural Biology of Ascard Archaea Proteins: Exploring Structure-Function Relationships and Evolutionary Conservation

    Leverages deep learning and molecular dynamics simulations to investigate the structure-function relationships of eukaryotic-like protein homologs in Asgard archaea. These integrated methods aim to uncover the evolutionary connections between archaeal and eukaryotic protein machineries, identifying conserved fundamental interactions that have persisted across evolution.
    (in collaboration with Prof. Robert (Bob) Charles Robinson, School of Biomolecular Science and Engineering, VISTEC)

Future Research Projects

  • Deep Learning for Epitranscriptomics Modification and Identification

    Develops deep learning models to identify RNA modifications and their functional roles in disease to support novel therapeutic target discovery and interventions.

Research Grant

  • ThaiSC (NSTDA) Voucher Program 2 award – Research Project Budget Supplement (2025)

    for high performance computing (HPC) credits valued up to 99,900 Baht (6,600 SHr) under the project "CanDrugAI: End-to-End AI-Driven Anticancer Drug Discovery & Development" [PI: Assoc. Prof. Dr. Thanyada Rungrotmongkol, Fac. Science, Chulalongkorn University]

  • CanDrugAI: End-to-End AI-Driven Anticancer Drug Discovery & Development (2025–2027)

    Role: Co-PI | Sponsored by: National Science Research and Innovation Fund (NSRF) via the Program Management Unit for Human Resources & Institutional Development, Research and Innovation (PMU-B), Thailand | Grant Number: B38G680006 [PI: Assoc. Prof. Dr. Thanyada Rungrotmongkol, Fac. Science, Chulalongkorn University]

  • Graph Neural Networks
  • Molecular Representation Learning
  • Cancer Drug Response
  • Cancer Drug Combinations
  • Personalized Medicine
  • Multi-omics
  • Molecular Docking
  • Molecular Dynamics Simulation
  • Epitranscriptomics
  • Peptide-Based Therapeutics

RESEARCH PUBLICATIONS

Peer Reviewed Publications

Read
SynProtX: A Large-Scale Proteomics-Based Deep Learning Model for Predicting Synergistic Anticancer Drug Combinations

Boonyarit B, Kositchutima M, Phattalung TN, Yamprasert N, Thuwajit C, Rungrotmongkol T, & Nutanong S. (2025). GigaScience (Accepted on Jun 16, 2025)

Read
GraphEGFR: Multi-task and Transfer Learning Based on Molecular Graph Attention Mechanism and Fingerprints Improving Inhibitor Bioactivity Prediction for EGFR Family Proteins on Data Scarcity

Boonyarit B, Yamprasert N, Kaewnuratchadasorn P, Kinchakawat J, Prommin C, Rungrotmongkol T, & Nutanong S. (2024). Journal of Computational Chemistry, 45(23), 2001-2023.

Read
Structure-based virtual screening for potent inhibitors of GH-20 β-N-acetylglucosaminidase: classical and machine learning scoring functions, and molecular dynamics simulations

Phengsakun G, Boonyarit B, Rungrotmongkol T, & Suginta W. (2023). Computational Biology and Chemistry, 107856.

Read
Potential tripeptides against the tyrosine kinase domain of human epidermal growth factor receptor (HER) 2 through computational and kinase assay approaches

Seetaha S, Boonyarit B, Tongsima S, Songtawee N, & Choowongkomon K. (2020). Journal of Molecular Graphics and Modelling, 97, 107564.

Conference Proceedings

Read
Docking-based virtual screening and pharmacophore analysis of novel GH-20 β-N-acetylglucosaminidase inhibitors

Phengsakun G, Boonyarit B, & Suginta W. (2021). 7th International Conference on Biochemistry and Molecular Biology (BMB2021).

Read
Computational screening of tripeptides against kinase-domain for human epidermal growth factor receptor 2 (HER2)

Boonyarit B, Mokmak W, Tongsima S, & Choowongkomon K. (2016). The 42nd Congress on Science and Technology of Thailand (STT42), 495-504.

Non-Peer Reviewed Publication

Read
LigEGFR: Spatial graph embedding and molecular descriptors assisted bioactivity prediction of ligand molecules for epidermal growth factor receptor on a cell line-based dataset

Virakarin P, Saengnil N, Boonyarit B, Kinchagawat J, Laotaew R, Saeteng T, Nilsu T, Suvannang N, Rungrotmongkol T, & Nutanong S. (2020). bioRxiv.

RESEARCH TEAM

Current Members

Bundit (Aon) Boonyarit

Ph.D. Student

M.S. (Biochemistry), Kasetsart University, TH
B.Sc. (Chemistry), Prince of Songkla University, TH

Website

Thanyathorn (Ton) Kingrat

Full-time Research Assistant

B.Eng. (Computer Engineering), Mae Fah Luang University, TH

Website

Nopsinth (Will) Vithayapalert

Part-time Research Assistant

M.S. (Computational Finance, Management Science and Engineering), Stanford University, USA

B.S. (Operation Research, Management Science and Engineering), Stanford University, USA

Nattawin (Natt) Yamprasert

Part-time Research Assistant

Undergraduate Student in Computer Engineering, Sirindhorn International Institute of Technology (SIIT), Thammasat University, TH

Krong (Ton) Krongyuth

Research Intern

B.Sc. (Mathematics), Mahidol University, TH

Parichamol (Prachan) Tantisuphakornsakul

Student Researcher

High School Student, Kamnoetvidya Science Academy (KVIS), TH

(in collaboration with Dr. Chayasith Uttamapinant)

Punnapa (Ming) Pobsirikasem

Student Researcher

High School Student, Kamnoetvidya Science Academy (KVIS), TH

(in collaboration with Dr. Chayasith Uttamapinant)

POSITION OPENINGS

We welcome undergraduate interns who are eager to push the boundaries of knowledge in interdisciplinary and computational sciences, advancing the fields of biochemical, biomolecular, biomedical, pharmaceutical sciences through integrative AI and computational approaches.

Eligibility:

  1. An undergraduate student (≥ Year 2) with a strong academic record (GPAX ≥ 3.25/4.00) in one of the following or related fields:
    – Track I: Computer Science, Computer Engineering, Mathematics, Statistics, Machine Learning, Data Science, or Computational Sciences
    – Track II: Pharmaceutical Sciences, Medical Sciences, Biochemistry, Molecular Biology, or Chemistry
  2. Highly motivated, adaptable, and passionate about interdisciplinary and computational sciences research.
  3. Hands-on experience with Python programming and familiarity with ML/DL toolkits (e.g., TensorFlow, PyTorch).
  4. Understanding of ML/DL fundamentals, with an interest in applying advanced techniques to biomolecular science and/or biomedicine problems.
  5. Availability for full-time internship for at least 3 months or more.
  6. Bonus: Proven track record of achievement in specialized activities related to computer science or artificial intelligence.

How to Apply?:

To apply, please introduce yourself and submit the following documents (in either Thai or English) to Bundit Boonyarit via email at [email protected] or [email protected]:

  1. CV
  2. Academic Record
  3. Certificates or Records of Achievements
  4. Statement of Interest (Cover Letter)
  5. Supporting Document(s) (if any)

Selection Process:

The candidate will receive an email confirmation regarding the final selection process, which consists of two stages: (1) an assignment and (2) an interview.

If you are interested or have any queries, please feel free to reach out to [email protected] or [email protected]

RESEARCH COLLABORATIONS

Domestic Collaborations

vistec_logo
sccu_logo
rama_logo
cnmi_logo
si_logo
ENKKU_logo
ptt_logo

BioXcepTion

BioXcepTion is a high school student research team with a particular emphasis on Computational Biology, Computational Chemistry, and Artificial Intelligence.

(Click arrow for more information about our student research team)

ACADEMIC SOFTWARE

Our group is committed to developing open-source academic software and curated datasets that drive cutting-edge research in biomolecular science, biomedicine, and computational biology. Built upon robust Python-based deep learning and machine learning frameworks, our tools are designed with an emphasis on transparency and reproducibility. Each software package is developed in alignment with our research goals and made publicly available to foster collaboration across the scientific community.

SynProtX

SynProtX is a deep learning model leveraging large-scale proteomics, molecular graphs, and fingerprints to enhance the prediction of synergistic effects in anti-cancer drug combinations.

GitHub
Zenodo

GraphEGFR

GraphEGFR is a deep learning model specifically designed to enhance molecular representation for the prediction of inhibitor bioactivity (pIC50) against wild-type HER1, HER2, HER4, and mutant HER1 proteins.

GitHub
Zenodo

CONTACT

Bundit Boonyarit
Email: [email protected], [email protected]

Natural Language Processing and Representation Learning Lab (NRL)
School of Information Science and Technology (IST)
Vidyasirimedhi Institute of Science and Technology (VISTEC)

555 Moo 1, Pa Yup Nai, Wang Chan, Rayong 21210, THAILAND