JieZheng-ShanghaiTech/SL_benchmark

Stars
5
Rank 2,848,674 (Top 57 %)
Language
Jupyter Notebook
License
MIT License
Created 11 months ago
Updated 9 months ago

JieZheng-ShanghaiTech/SL_benchmark

JieZheng-ShanghaiTech

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Benchmarking study of machine learning methods for prediction of synthetic lethality

KG4SL

Synthetic lethality (SL) is a promising gold mine for the discovery of anti-cancer drug targets. KG4SL is the first graph neural network (GNN)-based model that uses knowledge graph for SL prediction.

PiLSL

PiLSL is a pairwise interaction learning-based graph neural network (GNN) model for prediction of synthetic lethality (SL) as anti-cancer drug targets. It learns the representation of pairwise interaction between two genes from a knowledge graph (KG).

HiCoEx

A supervised learning model based on Graph Neural Network to predict gene co-expression from chromatin contacts

Jupyter Notebook

TMELand

A software tool for modeling and visualization of Waddington's epigenetic landscape based on dynamical models of gene regulatory network (GRN).

KR4SL

SynLethDB

SynLethDB is a comprehensive database (and knowledgebase) for synthetic lethality, a promising strategy of cancer therapeutics and drug discovery

NSF4SL

NSF4SL is a negative-sample-free model for prediction of synthetic lethality (SL) based on a self-supervised contrastive learning framework.

PIKE-R2P

Jupyter Notebook

LukePi

MGE4SL

In this project, we developed a Multi-Graph Ensemble (MGE) framework combining graph neural network and existing knowledge about genes to predict synthetic lethal (SL) gene pairs.

MiT4SL

MiT4SL is the first machine learning model for cross cell line prediction of synthetic lethal (SL) gene pairs. It uses a novel method of triplet representation learning to encode cell line information by integrating multi-omics data of gene expression, PPI network and protein sequences, etc.