XieResearchGroup

CODE-AE

Coherent Deconfounding Autoencoder (CODE-AE) can extract both common biological signals shared by incoherent samples and private representations unique to each data set, transfer knowledge learned from cell line data to tissue data, and separate confounding factors from them

DISAE

MSA-Regularized Protein Sequence Transformer toward Predicting Genome-Wide Chemical-Protein Interactions: Application to GPCRome Deorphanization

DeepREAL

DeepREAL: A Deep Learning Powered Multi-scale Modeling Framework Towards Predicting Out-of-distribution Receptor Activity of Ligand Binding

MolGNN_fewshot

PortalLearning

MultiDCP

CLEIT

Cross-LEvel Information Transmission network (CLEIT) aims to represent the asymmetrical multi-level organization of the biological system by integrating multiple incoherent omics data. It first learns the latent representation of the high-level domain then uses it as ground-truth embedding to improve the representation learning of the low-level domain in the form of contrastive loss.

JDINAC

Joint density-based Differential Interaction Network Analysis and Classification

Lab-wiki-Gitbook

PrePROTAC

PrePROTAC project

seqCrispr

PLANS

Self Training Drug Side Effects Detector

WINTF

weighted, imputed, neighbor-regularized matrix tri-factorization algorithm

AttnToCrispr

CPA

Source code for our paper "Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation" (IJCAI 2020)

drug_combine

Interesting-DL-Materials

List of Interesting Deep Learning Materials

L1000-bayesian

L1000 peak deconvolution based on Bayesian analysis

L1000-repurposing

Drug repurposing with L1000 data

Lab-wiki

Wiki of Xie's Lab

MXMNet

Source code for our paper "Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures"

pathway_repurposing