Back close

Course Detail

Course Name Machine Learning for Cheminformatics and Bioinformatics
Course Code 24AIM211
Program B.Tech. in Artificial Intelligence (AI) and Data Science (Medical Engineering)
Semester IV
Credits 4
Campus Coimbatore


Unit 1

Molecular Structure Databases: Cambridge Structural Database (CSD), Protein Data Bank (PDB), File format and information in PDB and CSD databases; Molecular Modelling: Molecular Graphics, 3-D Models of Organics and Biomolecules, Potential Energy Surfaces; Case Study: Visualization of 3D Models with Gauss View/Avogadro/Chemcraft

Unit 2

Molecular Interactions: Energy potentials in Molecular Modelling (Force-Fields), Bonded Terms in Molecular Mechanics, Non-bonded Terms, Effective Pair Potential, Type of Molecular Interactions in molecular modelling, Applications of Molecular Modelling (Hands-on): Generating Energy parameters for small organic compounds, Modelling of solvents, Energy minimization and Calculating Thermodynamics Properties using Molecular Mechanics; Case Study: Force-Field Parametrization of simple Organic Molecules

Unit 3

The Principles of Drug Design: The Drug Discovery Pipeline and Costs of Drug Discovery, Lipinski’s Rules of 5, Drug Metabolism, Toxicity and Side Effects, ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) Models, Drug resistance and promiscuity, Drug Delivery systems, Pharmacophore Modelling and alignment, Lead Optimization, Ligand-Based and Structure-Based Design; Molecular Docking, Introduction, Scoring Functions, Applications of Docking; Case Study: Setting up a Molecular Docking for a simple biomolecule.

Unit 4

AI/ML in Drug and Materials Design: Linear Free Energy Relationships, Structure-Activity Relationships and the Similarity Principle, Virtual High-throughput Screening, Feature selection – Genetic Algorithms, Model Validation, Case Study: Modeling with random forests, PLS, SVM and Neural Networks.

Unit 5

Introduction to Bioinformatics: Phylogenetic trees; Homology modelling, Sequence alignment, global and local alignments; BLAST and Protein BLAST; Multiple Sequence Alignment with Clustal Omega; RNA Secondary Structure Prediction with mfold; naïve Bayesian models.

Course Objectives and Outcomes

Course Objectives:

  • Acquire proficiency in accessing and utilizing molecular structure databases such as Cambridge Structural Database (CSD) and Protein Data Bank (PDB) for biomolecular research.
  • Develop skills in molecular modeling, including the creation and visualization of 3D models using tools like Gauss View, Avogadro, and Chemcraft.
  • Gain an understanding of molecular interactions through the study of energy potentials, force-fields, and molecular mechanics, and apply this knowledge to model solvents and calculate thermodynamic properties.
  • Explore the principles of drug design, covering the drug discovery pipeline, Lipinski’s Rules of 5, ADMET models, drug resistance, and drug delivery systems, along with hands-on experience in molecular docking.
  • Learn about the application of artificial intelligence (AI) and machine learning (ML) in drug and materials design, including linear free energy relationships, structure-activity relationships, virtual high-throughput screening, and various machine learning models.
  • Introduce fundamental concepts in bioinformatics, including phylogenetic trees, homology modelling, sequence alignment, BLAST, multiple sequence alignment, and RNA secondary structure prediction.

Course Outcomes:

After completing this course, students should be able to
CO1: Navigate and utilize molecular structure databases for biomolecular research.
CO2: Create and visualize 3D molecular models using tools like Gauss View, Avogadro, and Chemcraft.
CO3: Apply the principles of molecular mechanics to model solvents, perform energy minimization, and calculate thermodynamic properties.
CO4: Understand and apply drug design principles, including molecular docking techniques, drug discovery pipeline, and pharmacophore modeling.
CO5: Apply AI and ML techniques to drug and materials design, using various models such as random forests, PLS, SVM, and neural networks.
CO6: Perform basic bioinformatics analyses, including phylogenetic analysis, homology modeling, sequence alignment, BLAST, multiple sequence alignment, and RNA secondary structure prediction.

CO-PO Mapping

CO1 3 3 2
CO2 3 3
CO3 2 2 2 2
CO4 3 2 2 3 1 2 2 2 1 2 3 3
CO5 3 2 2 3 3 3
CO6 2 2 2 3 3

Textbooks & References

  1. Leach, A.R. Molecular Modelling Principles and Applications (Prentice Hall, Edition 2, 2001).
  2. Thomas Engel, Johann Gasteiger, Chemoinformatics: Basic Concepts and Methods (Wiley-VCH, 2018)
  3. Jürgen Bajorath (Editor), Chemoinformatics and Computational Chemical Biology (Methods in Molecular Biology) (Humana Press, 2004)
  4. Andrew R. & Leach, Valerie Gillet, An Introduction to Chemoinformatics (Springer International, New Delhi, 2009)
  5. N. Sukumar, Harishchander Anandaram and Pratiti Bhadra, “Computational Drug Discovery – A Primer” (Ion Cures Press, 2023). ISBN: 979-8850083663
  6. John L. Lamattina, Drug Truths: Dispelling the Myths about Pharma R&D (John Wiley, Hoboken, NJ, 2008)
  7. Barry Werth, The Billion Dollar Molecule: One Company’s Quest for the Perfect Drug (Simon & Schuster, 1995) Bioinformatics for Dummies.

DISCLAIMER: The appearance of external links on this web site does not constitute endorsement by the School of Biotechnology/Amrita Vishwa Vidyapeetham or the information, products or services contained therein. For other than authorized activities, the Amrita Vishwa Vidyapeetham does not exercise any editorial control over the information you may find at these locations. These links are provided consistent with the stated purpose of this web site.

Admissions Apply Now