boxiangliu

locuscomparer

LocusCompareR is a R package with visualization tools for comparing two genetic association datasets.

ParaMed

Chinese to English medical translation

locuscompare

LocusCompare is an interactive visualization tool for comparing two genetic association datasets.

enformer-pytorch

manhattan

ggplot2-based Manhattan plot

enformer

Forked from https://github.com/deepmind/deepmind-research/

spliceAI-pytorch

Pytorch implementation of spliceAI

Intro-to-Genomics

Course material for "BIOS 201: Next-generation sequencing and applications"

Pangolin

Pangolin is a deep-learning method for predicting splice site strengths.

sim_anneal

Simulated annealing for codon optimization

abbrev

alphafold

Open source code for AlphaFold.

boxiangliu.github.io

Boxiang's academic website

cpi_contact

Compound Protein Contact Prediction

DLEPS

A Deep Learning based Efficacy Prediction System for drug discovery

esm

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

GRaSP

idr-notebooks

Jupyter Notebooks for the Image Data Resource

Markov-Random-Field-Project

This project has two parts. In part one, we use markov random field to denoise an image. In Part two, we use similar model for image segmentation.

mutational-semantics-neurips2020

Learning mutational semantics

onek1k_phase1

Contains code to analyze the OneK1K data and perform eQTL mapping of 14 cell types

pytorch-lr-finder

A learning rate range test implementation in PyTorch

pytorch-seq2seq

Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.

pytorch_lightning_mnist

MNIST model in Pytorch lightning

span-parser-pytorch

SpliZ

Nextflow implementation of SpliZ

SyntacticPointer

tape

Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.

trRosetta

A package to predict protein inter-residue geometries from sequence data