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 detailsWhat makes this advanced
Introductory courses describe the central dogma as a diagram. This one treats it as a set of machines with kinetics, error rates and regulation, and asks how each step is actually measured in a wet lab. Where a mechanism is still contested, the course says so rather than presenting a tidy answer.
Reading primary literature
Two sessions are spent on nothing but reading papers: how to find the figure that carries the claim, how to identify the control that would falsify it, and how to describe a limitation without dismissing the work.
Format
Ten weeks, one extended written unit per week, and a final experimental plan that you defend in writing. There is no requirement to have access to a laboratory — the plan is assessed as scientific reasoning.
Syllabus
Weeks 1–2
Genome maintenance
DNA structure, replication machinery, fidelity, and how damage is detected and repaired.
Weeks 3–4
Transcription
RNA polymerase, initiation and elongation, promoter architecture, and what "gene expression" measures.
Weeks 5–6
RNA processing and control
Splicing, capping, polyadenylation, RNA stability, and non-coding RNAs as regulators.
Weeks 7–8
Translation
Ribosome mechanics, codon usage, post-translational modification, and protein folding quality control.
Weeks 9–10
Regulation and assays
Chromatin state, enhancer logic, and a critical comparison of the assays that measure each layer.
01/Keep going
Python for Bioinformatics
Go from your first script to a working sequence-analysis pipeline in Python — reading FASTA and FASTQ, working with Biopython, and reproducing a result end to end.
Course detailsResearch hub
Method explainers that pair with this course: how the calculations work, and where their assumptions stop holding.
Read the hub