Loading page content...
AI × BIOMOLECULAR SYSTEMS × BIOMEDICINE
Bundit BoonyaritPh.D. Candidate
Connecting molecules.Creating possibilities.
Bundit Boonyarit is a Ph.D. candidate in Information Science and Technology at the Vidyasirimedhi Institute of Science and Technology (VISTEC), Thailand. He holds a B.Sc. in Chemistry from Prince of Songkla University and an M.S. in Biochemistry from Kasetsart University. His interdisciplinary research bridges Biochemistry, Molecular Biology, Chemistry, Pharmaceutical Sciences, and Computer Science. He focuses on leveraging advanced artificial intelligence and computational techniques to develop novel computational frameworks and machine learning/deep learning models that drive innovations and discoveries in biomolecular science and biomedicine.
Interdisciplinary Convergence
Bridging Biochemistry, Molecular Biology, Chemistry, and Machine Learning.
Translational Impact
Novel ML/DL frameworks accelerating drug discovery and precision oncology.
Focus:Molecular RepresentationDrug Discovery & DesignBiomolecular Structures & FunctionsPrecision Oncology
VISTEC · Thailand
Affiliation
BAID Research Team
School of Information Science and Technology (IST), VISTEC
Core Mission & Paradigm
INTEGRATING CUTTING-EDGE ARTIFICIAL INTELLIGENCE WITH BIOMOLECULAR SCIENCE TO TRANSFORMDRUG DISCOVERYANDCELLULAR UNDERSTANDING.
01 —— CORE RESEARCH PILLARS
Bridging Biomolecules and Machine Intelligence
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.
PILLAR 001
Molecular Representation Learning & Computations
Designs and develops computational frameworks and models to represent and interpret complex molecular and biological data.
Graph Convolutional Networks (GCN)Graph Attention Networks (GAT)Spatial Graph EmbeddingsTransfer & Multi-task Learning
PILLAR 002
Molecular Discovery & Design
Discovers and designs novel therapeutic and biological molecules to specific biological activities and targets.
Synergistic Cancer Drug CombinationsKinase Inhibitor Discovery (EGFR/HER2)Multi-omics & Proteomics IntegrationHigh-Throughput Hit Compound Classification
PILLAR 003
Molecular Modeling & Simulation
Simulates and models the structure, dynamics, and interactions of biomolecules to uncover molecular mechanisms and functions.
Molecular Dynamics (MD) SimulationsStructure-Based Virtual Screening (SBVS)Protein-Ligand DockingEnzyme Kinetics & Catalysis
02 —— METHODOLOGY & APPLICATIONS
Computational Frameworks & Scientific Frontiers
Core scientific disciplines, computational modeling tools, and high-impact applications developed across our projects.
DISCOVERY DOMAINS
01
Graph Neural Networks
Molecular graph representation for deep learning overcoming extreme data scarcity in therapeutic target binding.
02
Precision Oncology
Deep learning predicting synergistic anticancer drug combinations from proteomics profiles.
03
Structural Docking & Simulations
Atomistic simulations and molecular docking of biomolecules exploring dynamics, interactions, and functions.
04
Kinase Inhibitor Design
High-throughput virtual screening & structure-based classification for protein kinase therapeutic targets.
05
Enzyme Engineering
Enzyme engineering with physics and data-driven based approaches for thermostability and kinetics.
03 —— KEY PUBLICATIONS
Recent Landmark Research Papers
Highlighting our peer-reviewed breakthroughs across molecular graph attention, synergistic drug design, and atomistic protein dynamics.
Structural Biology
The structure of an actin nucleus stabilized by villin
Uncovering fundamental actin polymerization mechanisms stabilized by villin through structural biology and MD simulations.
Read Paper & CitationsPeer-Reviewed
DL & Proteomics
SynProtX: Proteomics-based Deep Learning for Synergistic Drug Combinations
Large-scale proteomics-based deep learning framework predicting synergistic anticancer drug combinations for precision oncology.
Read Paper & CitationsPeer-Reviewed
GNN & Transfer Learning
GraphEGFR: Molecular Graph Attention for Data Scarcity
Multi-task and transfer learning framework with molecular graph attention mechanism overcoming data scarcity in EGFR inhibitors.
Read Paper & CitationsPeer-Reviewed
04 —— COLLABORATIVE TEAMS
Transformative Research Groups
Interdisciplinary research groups and student talent incubators driving biomolecular AI discoveries.
Research Group
BAID Research Team
Biomolecular Artificial Intelligence & Digital Biochemistry
The Biomolecular Artificial Intelligence & Digital Biochemistry (BAID) team is an interdisciplinary research group committed 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 impact and accelerated scientific discovery.
Student Mentorship Team
BioXcepTion Student Team (2018 – 2023)
High School Student Research & Mentorship
BioXcepTion is a high school student research team with a particular emphasis on Computational Biology, Computational Chemistry, and Artificial Intelligence.
Success isn't born from brilliance,
it’s built through implementation.