Unsupervised construction of computational graphs for gene expression data with explicit structural inductive biases, Bioinformatics [Paper]

Biologically informed deep neural network for prostate cancer discovery, Nature [Paper]

A Biologically Interpretable Graph Convolutional Network to Link Genetic Risk Pathways and Imaging Phenotypes of Disease, ICLR 2022 poster [Paper]

The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care, Nature Medicine (2018) [Paper]

Representation and Reinforcement Learning for Personalized Glycemic Control in Septic Patients, NIPS workshop (ML4H) (2017) [Paper]

Chemical-Reaction-Aware Molecule Representation Learning, arxiv (2021) [Paper]

A Gentle Introduction to Graph Neural Networks, Distill (2021) [Paper]

UNIFYING LIKELIHOOD-FREE INFERENCE WITH BLACK-BOX SEQUENCE DESIGN AND BEYOND [Paper]

Summary

• New de novo biological sequence design algorithm for a limited evaluation process
• Based on black-box optimization formulation
• Performed on TF binding sites, 5’ UTR, Antimicrobial peptides, and Fluorescence proteins.

Hello world! Will post a review of interesting paper.