Machine Learning for Molecules

This course studies machine learning methods for molecular science. It covers scientific foundations, neural architectures, probabilistic generative models, and representative applications in drug discovery, materials science, proteins, genomics, and virtual cells.

Course format

This is a flipped, discussion-based course. Recorded lectures will be uploaded at least two days before each class.

Before class, students watch the assigned lecture and submit questions through a shared Google Sheet. Class time is devoted to addressing these questions, clarifying difficult concepts, and discussing the material rather than repeating the recorded lecture.

Q&A sheet: Open the shared question tracker.

Students may also answer questions submitted by their classmates. Helpful answers earn participation points; enter your name in the Answered by column to receive credit.

Each class also begins with a general icebreaker question posted in the Icebreakers tab of the same sheet. Students may add a short response, and selected responses will be used to open the in-class discussion.

For invited lectures, live participation is strongly encouraged. Students who cannot attend live may watch the recording instead.

Grading

Students are assessed individually based on:

The quality and consistency of their questions submitted before class.
Helpful answers to classmates’ questions, which may earn additional participation points.
A final individual study note that explains and synthesizes selected course material.

Teaching team

Instructor: Prof. Sungsoo Ahn, KAIST
Invited lecturer: Prof. Sungbin Lim, Korea University

Schedule

Class meets every Monday and Wednesday from 10:30 AM to 12:00 PM, beginning Aug. 31.

Course schedule by topic, dates, and focus
Topic Introduction
Dates Aug. 31 (Mon)
Focus Course overview and introductions. Course goals, structure, expectations, and logistics.
Topic AI for Science Basics
Dates Sep. 2 (Wed) Sep. 7 (Mon) Sep. 9 (Wed) Sep. 14 (Mon) Sep. 16 (Wed)
Focus Molecular and material representations. SMILES and InChI, graphs, fingerprints, 3D coordinates, chirality, crystals, and symmetry. Key papers: Duvenaud et al., Neural Molecular Fingerprints (2015) Quantum foundations. The Schrödinger equation, wavefunctions, orbitals, density functional theory, molecular orbitals, and band structure. Chemical and statistical foundations. Chemical forces, statistical mechanics, free energy, molecular dynamics, potential-energy surfaces, and reaction kinetics. Drug discovery. Small molecules and biologics, pharmacokinetics and pharmacodynamics, target identification, hit-to-lead optimization, clinical trials, and experimental assays. Key papers: Wallach et al., AtomNet (2015) Materials discovery. Properties, stability, synthesis, characterization, batteries, semiconductors, catalysis, and direct air capture. Key papers: Xie and Grossman, CGCNN (2018)
Topic Architectures
Dates Sep. 21 (Mon) Sep. 23 (Wed) Sep. 28 (Mon) Sep. 30 (Wed) Oct. 5 (Mon) No class — National Foundation Day (substitute holiday) Oct. 7 (Wed)
Focus Message-passing graph neural networks and graph transformers. Message passing, attention, positional encodings, and global token interactions; GCN, GraphSAGE, GIN, GAT, and Graphormer. Key papers: Gilmer et al., MPNNs (2017) Ying et al., Graphormer (2021) Molecular property prediction and benchmarks. Supervised prediction from fingerprints, graphs, and three-dimensional representations, with molecular benchmarks and foundation models. Key papers: Wu et al., MoleculeNet (2018) Zhou et al., Uni-Mol (2023) Geometric deep learning foundations. Geometric graphs, Euclidean groups, group actions and representations, invariance, equivariance, and spherical harmonics. Key papers: Bronstein et al., Geometric Deep Learning (2021) Invariant models. SchNet, DimeNet, and GemNet. Key papers: Schütt et al., SchNet (2018) Gasteiger et al., DimeNet (2020) Gasteiger et al., GemNet (2021) Vector-equivariant models. EGNN and PaiNN. Key papers: Satorras et al., EGNN (2021) Schütt et al., PaiNN (2021) Spherical tensor models. Irreducible representations, Clebsch-Gordan products, Tensor Field Networks, and NequIP. Key papers: Thomas et al., Tensor Field Networks (2018) Batzner et al., NequIP (2022) Modern interatomic-potential architectures. Modern machine-learning interatomic potentials for energy and force prediction; MACE, eSCN, eSEN, Orb-v3, and UMA. Key papers: Batatia et al., MACE (2022) Rhodes et al., Orb-v3 (2025) Wood et al., UMA (2025)
Topic Midterm
Dates Oct. 12 (Mon) No class — midterm examination period Oct. 14 (Wed) No class — midterm examination period
Focus Midterm examination period. No class.
Topic Generative Models
Dates Oct. 19 (Mon) Oct. 21 (Wed) Oct. 26 (Mon) Oct. 28 (Wed) Nov. 2 (Mon) Nov. 4 (Wed) Nov. 9 (Mon) Nov. 11 (Wed)
Focus Probabilistic modeling and continuous normalizing flows. Probability distributions, change of variables, likelihoods, transport maps, neural ODEs, and continuous normalizing flows. Key papers: Chen et al., Neural ODEs (2018) Grathwohl et al., FFJORD (2019) Stochastic dynamics and probability evolution. ODEs and SDEs, Brownian motion, Itô calculus, Fokker-Planck equations, Langevin dynamics, continuity equations, and numerical simulation. Score-based diffusion models. Forward and reverse diffusion, score functions, denoising score matching, reverse-time SDEs, and probability-flow ODEs. Key papers: Ho et al., Denoising Diffusion Probabilistic Models (2020) Song et al., Score-Based Generative Modeling through SDEs (2021) Flow matching and stochastic interpolants. Conditional probability paths, marginal velocity fields, simulation-free training objectives, and stochastic interpolants. Key papers: Lipman et al., Flow Matching for Generative Modeling (2023) Albergo et al., Stochastic Interpolants (2023) Geometric generative processes. Generative modeling on manifolds, tangent vector fields, rotations, SO(3), periodic coordinates, and equivariant probability paths. Key papers: Chen and Lipman, Flow Matching on General Geometries (2024) Discrete generative processes. Discrete diffusion and flow matching, continuous-time Markov chains, molecular graphs, sequences, and hybrid discrete-continuous states. Key papers: Campbell et al., Continuous-Time Discrete Denoising (2022) Gat et al., Discrete Flow Matching (2024) Conditional and controlled generation. Conditioning, guidance, energy-based steering, composition, constrained generation, and inverse problems; how these methods modify a base distribution for molecular design. Key papers: Dhariwal and Nichol, Classifier Guidance (2021) Ho and Salimans, Classifier-Free Guidance (2022) Modern molecular generative systems. Diffusion and flow models for molecular graphs, three-dimensional molecules, conformers, protein-ligand structures, protein structures, and crystals across continuous, discrete, geometric, and hybrid state spaces. Key papers: Hoogeboom et al., Equivariant Diffusion for Molecule Generation in 3D (2022) Corso et al., DiffDock (2023) Hassan et al., ET-Flow (2024)
Topic Case Studies
Dates Nov. 16 (Mon) Nov. 18 (Wed) Nov. 23 (Mon) Nov. 25 (Wed) Nov. 30 (Mon) Dec. 2 (Wed)
Focus Molecular modeling and simulation. Molecular dynamics, learned collective variables, free-energy estimation, enhanced sampling, time-coarsened dynamics, and learned atomic transport. Key papers: Noé et al., Boltzmann Generators (2019) Klein et al., Timewarp (2023) Nam et al., LiFlow (2025) Quantum chemistry and electronic structure. Neural wavefunctions, learned density functionals, machine-learning Hamiltonians, electron densities, orbitals, energies, and forces. Key papers: Pfau et al., FermiNet (2020) Kirkpatrick et al., DM21 (2021) Kim et al., QHFlow2 (2026) Crystal and materials discovery. Crystal representations, structure and property prediction, stability, generative discovery, and materials foundation models. Key papers: Merchant et al., GNoME (2023) Zeni et al., MatterGen (2025) Goal-directed and synthesis-aware molecular design. Property guidance, reinforcement learning, Bayesian optimization, and GFlowNets for goal-directed and multi-objective design; reaction prediction, retrosynthesis, route search, and reaction-based generation for synthetic feasibility, with oracle reliability and experimental feasibility as design constraints. Key papers: Koziarski et al., RGFN (2024) Seo et al., RxnFlow (2025) Gao et al., SynFormer (2025) Protein structure prediction. Sequence-to-structure models combine evolutionary information, protein language models, geometric reasoning, and confidence estimation. Key papers: Jumper et al., AlphaFold 2 (2021) Abramson et al., AlphaFold 3 (2024) Protein representation and design. Sequence-based representation learning and single-sequence folding with ESM-2 and ESMFold; structure-conditioned inverse folding with ProteinMPNN; generative backbone design with RFdiffusion. Key papers: Lin et al., ESM-2 and ESMFold (2023) Dauparas et al., ProteinMPNN (2022) Watson et al., RFdiffusion (2023) Genomics. DNA and RNA foundation models support long-range sequence modeling, functional annotation, regulatory and variant-effect prediction, and sequence design. Key papers: Brixi et al., Evo 2 (2026) Avsec et al., AlphaGenome (2026) Virtual cells. Single-cell representations, multimodal foundation models, perturbation prediction, and models of cell state and response. Key papers: Cui et al., scGPT (2024) Adduri et al., State (2025) Noutahi et al., Virtual Cells (2025)
Topic Invited Talks
Dates Dec. 7 (Mon) TBA Dec. 9 (Wed) TBA Dec. 14 (Mon) Juno Nam, MIT Dec. 16 (Wed) Minji Lee, Columbia University
Focus Juno Nam, MIT. Machine learning for molecular simulation, with a focus on free-energy modeling and enhanced sampling. Key papers: Nam et al., LiFlow (2025) Nam et al., Universal Thermodynamic Interatomic Potentials (2026) Minji Lee, Columbia University. Generative modeling for protein structure and design, including ConforNets and Genie 3. Key papers: Lee et al., ConforNets (2026) Lin et al., Genie 3 (2026)