yulun-rayn

batchnorm-lstm

NumPy implementation of Batch-Normalized LSTM

CPA

The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell level. CPA performs OOD predictions of unseen combinations of drugs, learns interpretable embeddings, estimates dose-response curves, and provides uncertainty estimates.

CS294-158

DGAPN

This repository implements Distilled Graph Attention Policy Network (DGAPN), a curiosity-driven reinforcement learning model to generate novel graph-structured chemical representations.

graphVCI

This repository implements Graph Variational Causal Inference (graphVCI), a framework that integrates prior knowledge of relational information into variational causal inference for the prediction of perturbation effect on gene expressions at single-cell and marginal level.

SGAnCP4ADD

Resources for "Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery"

sGAT

This repository implements Spatial Graph Attention Network (sGAT), a graph deep learning model that embeds node and edge attributes as well as spatial structures for prediction tasks.

TabularPrediction

A repository hosting popular tabular prediction baselines.

tmle3trans

Robust transportation of point estimators & survival curves from clinical trial to real world with TMLE

variational-causal-inference

This repository implements Variational Causal Inference (VCI), a variational Bayesian causal inference framework for high-dimensional treatment effect predictions and estimations.

yulun-rayn/graphVCI

This repository implements Graph Variational Causal Inference (graphVCI), a framework that integrates prior knowledge of relational information into variational causal inference for the prediction of perturbation effect on gene expressions at single-cell and marginal level.

yulun-rayn/DGAPN

This repository implements Distilled Graph Attention Policy Network (DGAPN), a curiosity-driven reinforcement learning model to generate novel graph-structured chemical representations.

yulun-rayn/variational-causal-inference

This repository implements Variational Causal Inference (VCI), a variational Bayesian causal inference framework for high-dimensional treatment effect predictions and estimations.

yulun-rayn/sGAT

This repository implements Spatial Graph Attention Network (sGAT), a graph deep learning model that embeds node and edge attributes as well as spatial structures for prediction tasks.

yulun-rayn/TabularPrediction

A repository hosting popular tabular prediction baselines.

yulun-rayn/batchnorm-lstm

NumPy implementation of Batch-Normalized LSTM

yulun-rayn/CS294-158

yulun-rayn/SGAnCP4ADD

Resources for "Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery"

yulun-rayn/CPA

The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell level. CPA performs OOD predictions of unseen combinations of drugs, learns interpretable embeddings, estimates dose-response curves, and provides uncertainty estimates.

yulun-rayn/CS285

CS285: Deep Reinforcement Learning - Homework (Fall 2020, UC Berkeley)

yulun-rayn/CS288

CS288: Natural Language Processing - Homework (Spring 2023, UC Berkeley)

yulun-rayn/DGAQN

This repository implements Graph Attention Q-Network (GAQN) and exploration with Random Network Distillation for generating novel graph-structured chemical representations.

yulun-rayn/tmle3trans

Robust transportation of point estimators & survival curves from clinical trial to real world with TMLE

yulun-rayn/exaLearnMol

yulun-rayn/HS

Project HS - LBNL