AI Engineering
AI engineering for science: machine-learning fundamentals, neural networks, LLM and RAG applications, evaluation, and applied AI in biology and drug discovery.
Read the guideHome Learning ecosystem Domain guides
Read the field
before you build in it.
The long-form guides inside the learning ecosystem. Each one covers the concepts in order, names the tools the work actually uses, and is honest about where the methods stop being reliable. Where a guide has a matching track, the track is where you build it.
01/Technology & engineering
Technology & engineering
The guides behind the software disciplines: how AI systems are built, evaluated and kept honest.
02/Life sciences & specialised biotech
Life sciences & specialised biotech
Where biology, computation and medicine meet: structure-based design and the path from target to candidate.
Molecular Docking
Molecular docking explained end to end: preparing proteins and ligands, reading PDB structures, choosing a binding site, running AutoDock Vina and judging a pose.
Read the guidePharmaceutical Research
Pharmaceutical research explained: drug discovery stages, target validation, lead optimisation, ADMET screening, preclinical methods and how to read the evidence.
Read the guideGuides explain the field. Tracks build the work.
Every guide here has a track beside it in the ecosystem, where the same subject becomes a sequence of project milestones with a review at the end.
Technology & engineering
Six tracks — web, Python, C++, Java, UI/UX and cyber security — for anyone building software, whatever their branch.
Open the familyLife sciences & biotech
Five specialised tracks: biotechnology, genomics, pharmaceutical research, bioinformatics and AI for the life sciences.
Open the familyProject milestones
How every track is taught: a written brief, a deliverable you submit, and a review against the brief before anything is marked complete.
Read the methodGuides explain the field. Courses do the work.
Every guide links into the free catalogue and the research hub, so you can go from reading about a method to running it on real data.