Discover kundajelab/coda Open Source project

A toolkit to learn how to model and interpret regulatory sequence data using deep learning.

814

dragonn

ATAC-seq and DNase-seq processing pipeline

253

atac_dnase_pipelines

Toolkit to train base-resolution deep neural networks on functional genomics data and to interpret them

160

bpnet

TF MOtif Discovery from Importance SCOres

141

tfmodisco

Bias factorized, base-resolution deep learning models of chromatin accessibility (chromBPNet)

121

chrombpnet

AQUAS TF and histone ChIP-seq pipeline

112

chipseq_pipeline

Java

105

dfim

Deep Feature Interaction Maps (DFIM)

This package computes informative enrichment and quality measures for ChIP-seq/DNase-seq/FAIRE-seq/MNase-seq data. It can also be used to obtain robust estimates of the predominant fragment length or characteristic tag shift values in these assays.

phantompeakqualtools

ChromDragoNN

Code for the paper "Integrating regulatory DNA sequence and gene expression to predict genome-wide chromatin accessibility across cellular contexts"

Software to compute reproducibility and quality scores for Hi-C data

3DChromatin_ReplicateQC

Collaboration with Montine, Chang, and Montgomery labs on Alzheimers / Parkinson's ATAC-seq analysis

alzheimers_parkinsons

Simple and efficient access to genomic data for deep learning models.

genomelake

A python library for creating simulated regulatory DNA sequences

simdna

Algorithms for abstention, calibration and domain adaptation to label shift.

abstention

CS273B Deep Learning for Genomics Course Materials

cs273b

ENCODE_downloader

Downloader for ENCODE

Companion to "A genome-wide almanac of co-essential modules assigns function to uncharacterized genes" (https://doi.org/10.1101/827071)

coessentiality

Software for comparing contact maps from HiC, CaptureC and other 3D genome data.

genomedisco

training_camp

Genetics training camp

Accompanying repository for GkmExplain paper

gkmexplain

In-silico Saturation Mutagenesis implementation with 10x or more speedup for certain architectures.

fastISM

ataqc

basepairmodels

labelshiftexperiments

Label shift experiments

Sequence data label generation and ingestion into deep learning models

seqdataloader

bpnet-manuscript

BPNet manuscript code.

Code accompanying the paper "Deciphering regulatory DNA sequences and noncoding genetic variants using neural network models of massively parallel reporter assays"

MPRA-DragoNN

Dynamic sequence track for HiGlass

higlass-dynseq

JavaScript

DeepBindToKeras

Convert DeepBind models to Keras

ProCapNet

Repository for modeling PRO-cap data with the BPNet-like model, ProCapNet.

mpra

ENCODE_scatac

variant-scorer

A framework to score and analyze variant effects genome-wide using ChromBPNet models

Transcriptional Regulation (Optimized) Neural Nets (TRoNN)

tronn

Cardiogenesis_Repo

Cardiogenesis Repo

I have put my modified version of the deepbind code here.

deepbind

scATAC-reprog

Code for the analysis performed in the paper "Transcription factor stoichiometry, motif affinity and syntax regulate single-cell chromatin dynamics during fibroblast reprogramming to pluripotency" by Nair, Ameen et al.

veryolddontuse_deeplift_modisco_tutorial

Code from the chromatin variation 3d project

chromovar3d

JavaScript

chip-nexus-pipeline

ChIP-nexus pipeline

keras accessibility models: code to train, predict, interpret

kerasAC

DART-Eval

DMSO

Scripts for dataset processing and QC for the mesoderm differentiation project.

mesoderm

HTML

1kg_ld_utils

utils/notes for LD calculation from 1000 genomes panel

Genomics layers for Keras 2

keras-genomics

lsgkm+gkmexplain with regression functionality. Builds off kundajelab/lsgkm (which has gkmexplain), which in turn builds off Dongwon-Lee/lsgkm (the original lsgkm repo)

lsgkm-svr

yuzu

yuzu is a compressed-sensing based approach for quickly calculating in-silico mutagenesis saliency.

modular 2D boosting code with stabilization and hierarchies

PFBoost

Gene browser using coessentiality and related data

coessentiality-browser

Python script to upload files to Zenodo

zenodo_upload

Framework for interrogating transcription-factor motifs and their syntax/grammars from neural-network interpretations

neural_motif_discovery

Collecting commonly-repeated sequence visualization code here

vizsequence

A place to track my scripts with git.

av_scripts

bpnet-refactor

extraction of data embeddings from deep learning model layers; computation of embedding distance and visualization with umap/tsne

dynseq-pages

locusselect

A nucleotide-resolution, context-specific sequence annotation of the dynamic regulatory landscape of the human and mouse genomes

atlas_resources

scoring/ranking code for tf binding challenge

tf_binding_challenge

Pipeline for gecco RNA-seq analysis

bulk-rna-seq

python_reading_group

Multi-tileset data fetcher for HiGlass

higlass-multi-tileset

JavaScript

retina-models

BPNet models for retina single-cell multiome data

Code repository for the TF-Atlas project

TF-Atlas

Repository for creating the CRISPR controls termed "safe harbor" regions from Morgens et al., 2017, Nat Comms.

crispr_safe_targeting_regions

Benchmarking interpretation methods

interpret-benchmark

kCCA

Flexible deep learning framework

momma_dragonn

feature_interactions

BigDataScript (BDS) pipelines and modules

bds_pipeline_modules

Multi task batch generator for training deep learning models on CHIP-seq, CHIP-exo, CHIP-nexus, ATAC-seq, RNA-seq (or any other -seq)

mseqgen

SVM_pipelines

toolkit for setting up compute environment on gcp for jamborees

jamboree-toolkit

A collection of Deep Learning architectures and loss functions from across the genomics literature

genomics-DL-archsandlosses

affinity_distillation

Sequence priorization using gkm-explain.

SeqPriorizationCATLAS

How to train BPNets on ATAC-seq data using the Basepairmodels repo from Stanford's Kundaje Lab.

chromBPNet-tutorial

PREUSS: predicting RNA editing using sequence and structure

PREUSS

CTCFMutants