Chanwoo Kim's repositories
MHC_Kor_Assoc
Phenome-wide association study of the major histocompatibility complex region in the Korean population identifies novel association signals
regional_heritability_analysis
Regional Heritability Analysis is a software package for estimating regional heritability of small genomic segments.
UveitisJIA_MHC-fineMapping
Scripts and data used in analyses for "An amino acid motif in HLA-DRβ1 distinguishes patients with uveitis in juvenile idiopathic arthritis." Preprint: https://www.biorxiv.org/content/early/2017/08/14/140954
attributionpriors
Tools for training explainable models using attribution priors.
basenji
Sequential regulatory activity predictions with deep convolutional neural networks.
chanwkimlab
Config files for my GitHub profile.
CLAM
Data-efficient and weakly supervised computational pathology on whole slide images - Nature Biomedical Engineering
dart-fss-example
dart-fss-example
DEEP-HLA
Upload test
DuoClustering2018
R package with data sets and clustering results from Duò et al (F1000Research 2018)
fastshap
An amortized approach for calculating local Shapley value explanations
hess
Estimate local SNP heritability and genetic covariance from GWAS summary association statistics.
ldsc
LD Score Regression (LDSC)
path_explain
A repository for explaining feature attributions and feature interactions in deep neural networks.
PyDeepSEA
DeepSEA implements in PyTorch
scDD
R package to identify genes with differential distributions in single-cell RNA-seq
scde
R package for analyzing single-cell RNA-seq data
shap
A game theoretic approach to explain the output of any machine learning model.
Transformer-Explainability
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
treeexplainer-study
Code and documentation for experiments in the TreeExplainer paper
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.