Shanlin Ke

HANAMI improves drug-gene-disease motif prediction by integrating heterogeneous biomedical data and using graph contrastive learning, achieving up to 6% better performance than existing methods.

The paper constructs a urinary microbiome catalog and identifies antimicrobial peptides from it that inhibit uropathogenic E. coli.

The study identifies oral microbial signatures associated with IBD and PSC and their potential translocation to the gut, supported by external validation.

This study uses computational methods and metagenomic data to identify microbial strains that can inhibit CDI, supporting the design of live biotherapeutic products.

This paper introduces a computational method to identify causal gut microbes responsible for colonization resistance against pathogens, validated using mouse infection data.