Loading courses
23 courses. Python and R are free in full; every other course opens its first two chapters as a preview and unlocks entirely with a subscription.
Machine learning, deep learning and modern AI explained from zero maths, applied end-to-end to biological problems.
Zero maths assumed — to random forests, SVMs and neural nets
A full university-level ML curriculum for people with no programming or maths background. Builds the required mathematics from arithmetic upward, then covers preprocessing, every major supervised and unsupervised algorithm, deep learning, model evaluation, and applications across RNA-seq, GWAS, drug discovery and digital pathology.
Deep learning, LLMs, RAG and AI agents for life science
Modern AI explained from first principles for biologists: neural network foundations, transformers and attention, large language models, prompt engineering, retrieval-augmented generation over scientific literature, AI agents, generative protein and molecule design, and responsible AI in medicine.
Take a model from notebook to reproducible production system
The engineering discipline around scientific ML: version control, data versioning, experiment tracking, containers, Kubernetes, CI/CD, model registries, deployment, monitoring, drift detection and reproducibility standards for regulated research.
Practical AI assistants in day-to-day research work
A hands-on series on using AI tools responsibly in a working lab — where they help, where they quietly fail, ground rules for scientific use, and reproducible workflows for literature review, code assistance and data interpretation.