| 8/26 | Introduction slides | | |
| Sequence Modelling and Generation with Transformer slides | | |
| 9/2 | Modeling Structure with Graph Neural Networks slides | | |
| Single-cell biology Research Overview slides | | |
| 9/9 | 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 | |
| Multi-domain Distribution Learning for De Novo Drug Design | A 3D Generative Model for Structure-Based Drug Design; Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets; Structure-based drug design with equivariant diffusion models; Reinforced genetic algorithm for structure-based drug design | |
| 9/16 | Simulating 500 million years of evolution with a language model | ESM2 and ProGen2 | |
| Importance Weighted Expectation-Maximization for Protein Sequence Design | Proximal Exploration for Model-guided Protein Sequence Design | |
| 9/23 | Robust deep learning based protein sequence design using ProteinMPNN | A Deep SE(3)-Equivariant Model for Learning Inverse Protein Folding | |
| Generative Enzyme Design Guided by Functionally Important Sites and Small-Molecule Substrates | Scaffolding protein functional sites using deep learning | |
| 9/30 | Highly accurate protein structure prediction with AlphaFold (AlphaFold2) | Protein Structure Prediction: AlphaFold/AlphaFold2 | |
| De novo design of protein structure and function with RFdiffusion | Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem; PPDiff: Diffusing in Hybrid Sequence-Structure Space for Protein-Protein Complex Design | |
| 10/7 | De novo design of luciferases using deep learning | | |
| Accurate structure prediction of biomolecular interactions with AlphaFold 3 | RosettaFold3, RosettaFoldAllAtom | |
| 10/14 | Fall break, no class | | |
| 10/21 | Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling | DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome; Nucleotide Transformer; Hyenadna: Long-range genomic sequence modeling at single nucleotide resolution; Dnabert-2: Efficient foundation model and benchmark for multi-species genome | |
| Predicting DNA structure using a deep learning method | | |
| 10/28 | CodonBERT: Large Language Models for mRNA design and optimization | | |
| AlphaGenome: advancing regulatory variant effect prediction with a unified DNA sequence model | A sequence-based global map of regulatory activity for deciphering human genetics | |
| 11/4 | Base-resolution models of transcription-factor binding reveal soft motif syntax | | |
| Design of highly functional genome editors by modeling the universe of CRISPR-Cas sequences | | |
| 11/11 | A programmable reaction-diffusion system for spatiotemporal cell signaling circuit design | | |
| Transfer learning enables predictions in network biology | | |
| 11/18 | scGPT: toward building a foundation model for single-cell multi-omics using generative AI | scGPT: toward building a foundation model for single-cell multi-omics using generative AI; Universal Cell Embeddings: A Foundation Model for Cell Biology | |
| FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation | Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back | |
| 11/25 | A small-molecule TNIK inhibitor targets fibrosis in preclinical and clinical models | | |
| thanksgiving, no class | | |
| 12/2 | Conditional Antibody Design as 3D Equivariant Graph Translation | End-to-End Full-Atom Antibody Design; Conditional Antibody Design as 3D Equivariant Graph Translation; Atomically accurate de novo design of single-domain antibodies | |
| A generative deep learning approach to de novo antibiotic design | | |