Stars
Codes for paper: Evaluating the Utilities of Large Language Models in Single-cell Data Analysis.
The Riemannian Causal Embedding (RiCE) algorithm for discovering networks from time series
Publication-ready NN-architecture schematics.
Interactive visualizations of the geometric intuition behind diffusion models.
A foundation model for single-cell epigenomic data
[NeurIPS 2024] Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA
The code for "Learning Molecular Representation in a Cell"
Benchmark gene representations from different model families
PHATE (Potential of Heat-diffusion for Affinity-based Transition Embedding) is a tool for visualizing high dimensional data.
Spatiotemporal modeling of spatial transcriptomics
PreMode predicts mode-of-action of missense variants by deep graph representation learning of protein sequence and structural context
Single-Cell Analysis of Inter-Individual Variability by Interpretable Tensor Decomposition
Supervised Pathway DEConvolution of InTerpretable Gene ProgRAms
Repository for Protein-Vec, a protein embedding mixture of experts model
Foldseek enables fast and sensitive comparisons of large structure sets.
Infers a phylogenetic tree from protein structures
Improving Contrastive Learning by Visualizing Feature Transformation, ICCV 2021 Oral
Code and files related to random side projects
Deep learning meets molecular dynamics.
Code accompanying the paper "Discriminative Clustering with Representation Learning for any Ratio of Labeled to Unlabeled Data"