AI for Drug Discovery
Learn how machine learning is used to find drug targets, screen compounds and predict ADMET properties — with hands-on work on real protein–ligand data.
Course detailsWhy Python, and why with real sequences
Most bioinformatics is not exotic — it is a great deal of careful, repetitive work with sequence files that has to be done identically every time. Python is the most widely used language for that job, and the one with the deepest set of maintained life-science libraries.
Every exercise in this course runs on real public sequence data: genes and genomes you can look up yourself, so you can check your output against the reference record when something looks wrong.
How the weeks work
Each week is a short written lesson, a worked example, and a task that you complete on your own data. By the end of week six you will have a small command-line tool of your own design that reads a FASTA file and reports the analyses you chose to implement.
Syllabus
Week 1
Python that does biology
Values, strings, lists, dictionaries, loops, and files — taught entirely on sequence data.
Week 2
Sequence files
FASTA and FASTQ, quality scores, streaming large files, Biopython's SeqIO.
Weeks 3–4
Analysis toolkit
Translation, reading frames, GC content, restriction sites, pairwise alignment and parsing BLAST-style output.
Week 5
Data and plots
Tables with pandas, publication-quality figures, and how to avoid plotting a misleading axis.
Week 6
Reproducible pipeline
Turning notebooks into a script, adding a real command line, and writing the README that makes your analysis reusable.
01/Keep going
Molecular Biology Masterclass
A rigorous pass through the central dogma — replication, transcription, translation, gene regulation and the modern assays used to measure each of them.
Course detailsResearch hub
Method explainers that pair with this course: how the calculations work, and where their assumptions stop holding.
Read the hub