AI Roadmaps
← All roadmaps
IntermediateRoadmap 25 · 12 steps · 5h 11m of video

AI for Science

How AI is changing biology and chemistry: protein folding, AlphaFold, protein language models, protein design, molecules in Python, and AI weather models.

Before this: Deep Learning (transformers help). Graph Neural Networks helps for the molecule steps. No biology background needed; step 1 covers it.

  1. 8 min
    Step 1

    Protein structure and folding

    The biology you need: amino acids fold into 3D shapes.

    Protein Structure and Folding

    Amoeba Sisters

  2. 8 min
    Step 2

    The protein folding problem

    Why predicting shape from sequence was a 50-year puzzle.

    What is the Protein Folding Problem?

    The Sheekey Science Show

  3. 25 min
    Step 3

    The AlphaFold story

    How DeepMind cracked protein folding and why it matters.

    AlphaFold - The Most Useful Thing AI Has Ever Done

    Veritasium

  4. 13 min
    Step 4

    How AlphaFold works

    Evolution, attention, and geometry inside the model.

    how AlphaFold *actually* works

    Looking Glass Universe

  5. 10 min
    Step 5

    Predict a structure with ColabFold

    Fold your own protein for free in a notebook.

    Faster AlphaFold protein structure predictions using ColabFold

    UCSF ChimeraX

    sokrypton/ColabFold★ 3k
  6. 34 min
    Step 6

    Protein language models

    Language model ideas applied to amino acid sequences.

    Protein Language Models

    RosettaCommons

  7. 44 min
    Step 7

    Design new proteins with RFdiffusion

    Diffusion models generate proteins that never existed.

    RFDiffusion: Accurate protein design using structure prediction and diffusion generative models

    ML for protein engineering seminar series

    RosettaCommons/RFdiffusion★ 3.1k
  8. 14 min
    Step 8

    AI in drug discovery

    Where AI helps find and test new medicines.

    Revolutionizing drug discovery with artificial intelligence

    RAZOR Science Show

  9. 17 min
    Step 9

    Molecules in Python with RDKit

    Read SMILES, draw molecules, and compute properties.

    Chemistry with Python - an Introduction to RDKit

    Bernhard Wannasek

    rdkit/rdkit★ 3.7k
  10. 16 min
    Step 10

    Molecular property prediction with GNNs

    Treat molecules as graphs to predict how they behave.

    Molecular Property Prediction with Graph Neural Networks

    Center for Computer-Assisted Synthesis

    deepchem/deepchem★ 7.2k
  11. 59 min
    Step 11

    AI weather forecasting with GraphCast

    A graph network that beats classic 10-day forecasts.

    GraphCast: Learning skillful medium-range global weather forecasting

    Greg Bronevetsky

    google-deepmind/weathernext★ 7.8k
  12. 1h 04m
    Step 12

    Accelerating science with AI

    Demis Hassabis on what AI can do for science next.

    Accelerating Scientific Discovery with AI - lecture by Sir Demis Hassabis

    CambridgeComputerLab

Build it

Watching isn't learning. Pick one and put it on GitHub.

Browse all roadmaps →