| 1 | 8/25 | Introduction slides | | |
| 8/27 | Sequence Modelling and Generation with Transformer slides | | |
| 2 | 9/1 | Modeling Structure with Graph Neural Networks slides | | |
| 9/3 | Variational Auto-Encoder slides | | |
| 3 | 9/8 | Diffusion Models slides; Small molecule drug design via MARS slides | MARS: Markov Molecular Sampling for Multi-objective Drug Discovery; Multi-Objective Molecule Generation using Interpretable Substructures | |
| 9/10 | Single-cell biology Research Overview slides | | |
| 4 | 9/15 | Drug Design | Multi-domain Distribution Learning for De Novo Drug Design; FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation | |
| 9/17 | Drug Design | A small-molecule TNIK inhibitor targets fibrosis in preclinical and clinical models; A generative AI-discovered TNIK inhibitor for idiopathic pulmonary fibrosis: a randomized phase 2a trial | |
| 5 | 9/22 | Protein Design | Simulating 500 million years of evolution with a language model (ESM3); Language Modeling Materializes a World Model of Protein Biology | |
| 9/24 | Structure Prediction | Highly accurate protein structure prediction with AlphaFold (AlphaFold2) | |
| 6 | 9/29 | Molecular Complex | Accurate structure prediction of biomolecular interactions with AlphaFold 3 | |
| 10/1 | Protein Design | Robust deep learning based protein sequence design using ProteinMPNN; Importance Weighted Expectation-Maximization for Protein Sequence Design | |
| 7 | 10/6 | Protein Design | Large language models generate functional protein sequences across diverse families; Adapting protein language models for structure-conditioned design | |
| 10/8 | Binder Design | De novo design of protein structure and function with RFdiffusion; One-shot design of functional protein binders with BindCraft | |
| 8 | 10/13, 10/15 | Fall Break | | |
| 9 | 10/20 | Enzyme Design | Generative Enzyme Design Guided by Functionally Important Sites and Small-Molecule Substrates; Co-designing sequence and structure of functional de novo enzymes with EnzyGen2 | |
| 10/22 | Binder Design | De novo Design of All-atom Biomolecular Interactions with RFdiffusion3; Zero-shot antibody design in a 24-well plate | bioRxiv | |
| 10 | 10/27 | Binder Design | Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute (Proteina-Complexa); Latent Generative Search unlocks de novo Design of Untapped Biomolecular Interactions at Scale | |
| 10/29 | Binder Design | PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design; BoltzGen: Toward Universal Binder Design | |
| 11 | 11/3 | No Class | | |
| 11/5 | DNA Models | Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling; Predicting genome-wide functional constraints with GPN-Star | |
| 12 | 11/10 | Genomics | Predicting DNA structure using a deep learning method; AlphaGenome: advancing regulatory variant effect prediction with a unified DNA sequence model | |
| 11/12 | Genome Design | Genome modelling and design across all domains of life with Evo 2 | |
| 13 | 11/17 | Genome/Cell | Design of highly functional genome editors by modeling the universe of CRISPR-Cas sequences; Predicting cellular responses to perturbation across diverse contexts with State | bioRxiv | |
| 11/19 | Single-cell Models | Transfer learning enables predictions in network biology; scGPT: toward building a foundation model for single-cell multi-omics using generative AI | |
| 14 | 11/24 | DNA Models | Base-resolution models of transcription-factor binding reveal soft motif syntax; Nucleotide Transformer: building and evaluating robust foundation models for human genomics | |
| 11/26 | Thanksgiving | | |
| 15 | 12/1 | Antibody/Antibiotic | Conditional Antibody Design as 3D Equivariant Graph Translation; A generative deep learning approach to de novo antibiotic design | |
| 12/3 | Drug Design | Atomic-level protein–ligand recognition with PBCNet2.0 for probe discovery | Nature Chemical Biology; Predicting locations of cryptic pockets from single protein structures using the PocketMiner graph neural network | Nature Communications | |