School of Bioinformatics · Structural biology & drug discovery
Cheminformatics & QSAR Modelling
Cheminformatics turns molecules into numbers a computer can reason about. You learn to represent, search and model chemical structures with RDKit, and to build QSAR models validated to OECD principles.
Course overview
Cheminformatics & QSAR Modelling covers how molecules are represented, compared and modelled by computer: SMILES and standardisation, descriptors and fingerprints, similarity and substructure search, chemical-space analysis and quantitative structure–activity relationship models.
Most QSAR failures come from the data and the validation rather than the algorithm. You curate activity data from ChEMBL, split it so that structurally similar compounds do not leak between training and test sets, test against Y-randomised models and define the applicability domain within which predictions can be trusted.
Learning outcomes
By the end of the course you will be able to:
- Read, write and standardise SMILES with RDKit
- Compute descriptors and fingerprints and apply drug-likeness filters
- Run similarity and substructure searches and cluster a library
- Build QSAR models with scikit-learn against a baseline
- Validate models with cluster splits, Y-randomisation and an applicability domain
Skills you will practise
Eligibility and prerequisites
Who can apply
- Students and graduates of B.Sc., M.Sc., B.Tech., M.Tech., B.Pharm., M.Pharm., MBBS, BDS, B.V.Sc. or a PhD programme in the life sciences, biotechnology, bioinformatics, pharmacy, medicine, agriculture, chemistry, statistics or computer science
- Researchers, faculty and industry professionals moving into data-driven biology
- Final-year students may apply before their results are declared
Prerequisites
- Basic organic chemistry
- Python for Bioinformatics or equivalent
Best suited to
- Pharmacy, chemistry and biotechnology students
- Researchers working with compound libraries
- Anyone moving into AI for drug discovery
Module-wise syllabus
6 modules. Each pairs instructor-led sessions with a hands-on lab on public data.
Topics
- SMILES, InChI and SDF
- Standardisation and tautomers
- RDKit basics
Topics
- Physicochemical descriptors
- Morgan (ECFP) fingerprints
- Lipinski, Veber and PAINS filters
Topics
- Similarity and the Tanimoto coefficient
- Clustering with Butina
- Visualising chemical space
Topics
- Data curation from ChEMBL
- Random forests, kNN and linear models
- Regression versus classification
Topics
- Random versus cluster splits
- Y-randomisation
- OECD principles and the applicability domain
Topics
- ChEMBL dataset to model
- Model card
- Predicting new compounds responsibly
Practical sessions and projects
Capstone project
Build and defend a QSAR model
Curate a ChEMBL activity dataset, train a model, validate it properly and write a model card that states where it should not be used.
Assessed on the correctness of the analysis, the quality of the code and the reasoning in the write-up. A pass is required for the certificate.
- Representing molecules
Parse, standardise and de-duplicate a set of SMILES with RDKit, handling salts, charges and tautomers.
- Descriptors and fingerprints
Compute descriptors and Morgan fingerprints for a library and apply Lipinski, Veber and PAINS filters.
- Chemical space
Cluster a library with Butina clustering on Tanimoto similarity and visualise its chemical space.
- QSAR modelling
Curate EGFR IC₅₀ data from ChEMBL and train random-forest, kNN and linear models against a simple baseline.
- Validation
Compare random and cluster-based splits, run Y-randomisation and define an applicability domain for the final model.
- Project: a publishable QSAR model
Build, validate and document a QSAR model with a model card, then predict new compounds with applicability-domain flags.
Software, tools and datasets
Software and tools
All software is free and open source or free for academic use. Recommended computer: 8 GB RAM, 30 GB free disk, Linux, macOS or Windows with WSL2.
Datasets
- EGFR bioactivity data: Curating IC₅₀ values and training QSAR models.ChEMBL target CHEMBL203
- Approved-drug structures: Descriptor and drug-likeness exercises.ChEMBL and PubChem
- PubChem compound records: Identifiers, standardisation and similarity search.PubChem
Core reading
- OECD (2007). Guidance Document on the Validation of (Quantitative) Structure-Activity Relationship [(Q)SAR] Models. OECD Series on Testing and Assessment, No. 69.
- Tropsha A (2010). Best practices for QSAR model development, validation, and exploitation. Molecular Informatics 29:476–488.
- RDKit: Open-Source Cheminformatics Software, documentation (rdkit.org).
Duration, format and fees
- Next cohort
- Dates are sent with your admission offer
- Timetable
- Three evening or weekend sessions a week (IST), plus a lab clinic; intensive and weekend-only schedules on request
- Payment
- Secure online payment link with your admission offer (UPI, cards, net banking). Instalments on request for fees above ₹15,000.
- Refunds
- See the refund and cancellation policy.
Instructor
The instructor for each cohort is named in your admission offer and on this page when the cohort is announced. Vedicgen instructors are selected for hands-on research or industry experience in the subject they teach, and every course is reviewed by a second subject expert.
Questions about who teaches a cohort? [email protected]
Certificate
Learners who complete the course and pass its capstone receive a Vedicgen certificate of completion for Cheminformatics & QSAR Modelling, issued by Vivofold, stating the guided hours and skills assessed. Each certificate has a unique ID and QR code that anyone can check.
Apply for Cheminformatics & QSAR Modelling
Apply
Send the form below. It takes about five minutes.
Review
An adviser confirms your fit and format within two working days.
Offer
You receive dates, timetable and a secure payment link.
Onboard
Set-up guide, pre-reading and joining links.
Frequently asked questions
No. Docking is structure-based (it needs the protein structure); QSAR is ligand-based (it learns from measured activities). They complement each other, and many learners take both.
In the live cohort, modules are taught in instructor-led sessions with a weekly lab clinic where you work on real public data with help at hand; every session is recorded. The self-paced format uses the same lessons, labs and datasets with mentor review of your capstone. Both formats end with an assessed project reviewed for the code and the science.
A laptop with at least 8 GB of RAM and about 30 GB of free disk space, running Linux, macOS, or Windows with WSL2. Installation instructions are sent before the first session, and lab clinics help with any set-up problems.
Yes. Learners who complete the course and pass its assessment receive a Vedicgen certificate of completion, issued by Vivofold. Every certificate carries a unique ID and a QR code that anyone, including an employer or admissions office, can check on the certificate verification page.
Apply with the form on this page. Live and in-person cohorts run through the year; the dates, timetable and joining details of the next cohort are sent with your admission offer and listed on this page once announced. Self-paced enrolment opens as soon as your application is accepted.
Yes. No course runs longer than four weeks, and the length is customisable: choose the standard schedule, an intensive one- to two-week schedule, weekends only, or a custom timetable. Pick your preference on the application form; colleges and teams can book their own dates.
Part of a programme
Take this course as part of a programme and save.
Continue learning