School of Scientific Computing & Informatics · Chemo- & materials informatics
Materials Informatics & Machine Learning for Chemistry
Materials and chemical discovery are increasingly guided by data and machine learning. This course teaches how materials are represented as data, how property models are built and validated, and how they guide the next experiment.
Course overview
Materials Informatics covers crystal and molecular representations, public databases such as the Materials Project, and featurisation with matminer, followed by property-prediction models and their validation.
You close the loop with active learning and Bayesian optimisation, where a model chooses the most informative next experiment, and study the pitfalls of small, biased materials datasets.
Learning outcomes
By the end of the course you will be able to:
- Represent crystals and molecules for machine learning
- Query and curate data from the Materials Project and other databases
- Build and validate property-prediction models
- Use active learning and Bayesian optimisation to plan experiments
- Recognise and mitigate dataset bias and leakage
Skills you will practise
Eligibility and prerequisites
Who can apply
- Students and graduates in any science, engineering, pharmacy, medicine, agriculture, geography or computing programme (B.Sc., B.Tech., B.E., BCA, M.Sc., M.Tech., MCA, PhD)
- Researchers, faculty and working professionals in research, healthcare, biotech, pharma or IT who want to apply computing to science
- Final-year students may apply before their results are declared
Prerequisites
- Machine Learning for Biology or Scientific Computing with Python
- Undergraduate chemistry or physics
Best suited to
- Chemistry, materials and chemical-engineering students
- Researchers in catalysis, batteries, polymers or formulation
- Data scientists entering materials R&D
Module-wise syllabus
6 modules. Each pairs instructor-led sessions with a hands-on lab on public data.
Topics
- Crystal structures and symmetry
- Composition and structure features
- pymatgen
Topics
- Materials Project and OQMD
- DFT-derived data and its errors
- Curation
Topics
- Featurisation with matminer
- Tree ensembles and kernel models
- Graph networks for crystals
Topics
- Uncertainty estimates
- Active learning
- Bayesian optimisation
Topics
- Small and biased datasets
- Leakage between similar materials
- Reporting standards
Topics
- Dataset
- Model
- Recommendation
Practical sessions and projects
Capstone project
Guide a discovery campaign
Build a validated property model and use it to recommend which materials or molecules to make next, with uncertainty.
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.
- Materials as data
Load crystal structures, analyse symmetry and compute basic descriptors.
- Materials databases
Assemble a curated band-gap dataset through the Materials Project API.
- Property prediction
Predict band gaps and compare composition-only with structure-aware models.
- Choosing the next experiment
Run a simulated discovery campaign and measure how quickly the model finds top materials.
- Pitfalls and validation
Show how a clustered split changes reported accuracy.
- Project: a data-driven discovery study
Build and validate a model and recommend candidates for synthesis with uncertainty.
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
- Materials Project: Property datasets.materialsproject.org (CC BY 4.0)
- Matbench benchmarks: Benchmarking models.matbench.materialsproject.org
Core reading
- Jain A et al. (2013). The Materials Project: a materials genome approach to accelerating materials innovation. APL Materials 1:011002.
- Butler KT et al. (2018). Machine learning for molecular and materials science. Nature 559:547–555.
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 Materials Informatics & Machine Learning for Chemistry, 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 Materials Informatics & Machine Learning for Chemistry
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
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.
Continue learning