💻 Analysis codes and bioinformatics pipelines for paper "Increased local DNA methylation disorder in AMLs with DNMT3A-destabilizing variants and its clinical implication"

💻 Analysis codes and bioinformatic pipelines for paper "HIV-1-induced host genomic R-loops dictate HIV-1 integration site selection"

💻 Analysis codes and bioinformatics pipelines for paper "Viral long non-coding RNA sequestrates cGAS from HCMV DNA for immune evasion"

An unofficial re-implementation of AntiBERTy, an antibody-specific protein language model, in PyTorch.

An unofficial re-implementation of DiffAb, a diffusion-based generative model for antigen-specific antibody design and optimization.

Protein structure handling in Python made easy.

The official code implementation for Chromoformer in PyTorch. (Lee et al., Nature Communications. 2022)

An unofficial re-implementation of FoldingDiff, a diffusion-based generative model for protein backbone structure generation.

An unofficial re-implementation of DeepAb, an interpretable deep learning model for antibody structure prediction.

Process SRA bisulfite sequencing data easily with Bismark-MethylDackel pipeline.

An unofficial re-implementation of RoseTTAFold, a three-track deep learning model for protein structure prediction.

An unofficial re-implementation of PiFold, a fast inverse-folding algorithm for protein sequence design, in PyTorch.

☄️ Ultrafast DNA methylation heterogeneity calculation from bisulfite alignments (Lee et al., PLOS Computational Biology. 2023)

Implementation of BPNet, a base-resolution convolutional neural network for transcription-factor binding prediction, in PyTorch.

Implementation of ProteinBERT, a deep language model designed for proteins.

⚗️ Samsung AI Challenge for Scientific Discovery 5위 솔루션입니다.

Reimplementation of RaSP, a deep neural network for rapid protein stability prediction, in PyTorch.

Automated pipeline for preparing protein structure dataset only from a list of PDB ids.

Unofficial re-implementation of IgFold, a fast antibody structure prediction method, in PyTorch.

Implementation of GeoDiff, a geometric diffusion model for molecular conformation generation, in PyTorch.

Implementation of Tranception, a SOTA transformer model for protein fitness prediction, in PyTorch.

Implementation of evolutionary model of variant effect (EVE), a deep generative model of evolutionary data, in PyTorch.

Implementation of Abyssal, a deep neural network trained with a new "mega" dataset to predict the impact of an amino acid variant on protein stability.

Implementation of SpliceAI, Illumina's deep neural network to predict variant effects on splicing, in PyTorch.

🐍 Snakemake wrappers for bioinformatics.

Fitting 5-parameter 1D Ising models for regionwise information-theoretic properties of DNA methylation states. Implemented in Rust.

Snakemake pipeline for Rosetta 'cartesian-ddg' protocol for protein stability prediction upon mutations.