Biomedical Network Science Lab
Welcome to the Biomedical Network Science Lab!
The Biomedical Network Science (BIONETS) lab investigates molecular disease mechanisms using techniques from network science, combinatorial optimization, and artificial intelligence. We develop algorithms and tools to mine multi-omics data for such mechanisms and to individuate novel strategies for mechanistically grounded drug repurposing and causally effective treatments of complex diseases. We also develop privacy-preserving decentralized biomedical AI solutions, which enable cross-institutional studies on sensitive data.
Surya studied computer engineering at Arizona State University. On September 1, he joined the BIONETS lab as a PhD candidate.
Our paper "Federated Principal Component Analysis for Genome-Wide Association Studies" has been accepted at ICDM 2021.
AIMe is a community-driven reporting platform for biomedical AI systems. It aims to enhance the accessibility, reproducibility and usability of biomedical AI models, and allows future revisions by the community: https://aime-registry.org.
Our papers "The Minimum Edit Arborescence Problem and Its Use in Compressing Graph Collections" and "Metric Indexing for Graph Similarity Search" have been accepted at SISAP 2021.
We are delighted to announce that our ACM SIGIR 2021 paper "On the Privacy of Federated Pipelines" is now available in the ACM DL. Using an example from federated GWAS, we show that privacy-preservation in FL is non-transitive, highlighting the need for hybrid FL.