Computational Biology

End-to-end Small Molecule Entity Discovery
A model-agnostic enhancement pipeline for small molecule property prediction. It uses a encoder and a retriever to retrieve similar molecules out of the whole dataset as supportive evidence. It also introduces a refinement stage to utilize only supportive evidence for downstream task. It will soon be sealed as a toolkit.
May 15, 2022
Code
End-to-end Small Molecule Entity Discovery
Comprehensive and distinguishable graph-linked embedding for multi-omics single-cell data integration
It solve the indistinguishability of aggregating multi-omics data on the graph for the graph-linked embedding. Besides, it enriches the multi-omics information of graph embedding by using multiple aggregators in the GNN
Code
Comprehensive and distinguishable graph-linked embedding for multi-omics single-cell data integration