Fan Has Paper on Cross-Species Inference Accepted to Nucleic Acids Research

Mar 04, 2019

Jason Fan, a research graduate assistant in the Center for Bioinformatics and Computational Biology (CBCB), recently had a paper on cross-species inference accepted to the journal Nucleic Acids Research.

“Functional Protein Representations from Biological Networks Enable Diverse Cross-Species Inference,” examines a kernel-based method, MUNK, to integrate sequences and network structures to create functional protein representations, embedding proteins from different species in the same vector space.

Fan co-authored the paper with Max Leiserson, an assistant professor of computer science and a member of CBCB, along with collaborators from the University of Washington, University of North Carolina Medical School, Boston University, Princeton University and Northeastern University.

As part of their work, their research showed proteins from different species that are close in MUNK-space and are functionally similar. Next, they used these representations to share knowledge of synthetic lethal interactions between species. Importantly, they found that the results using MUNK-representations were at least as accurate as existing algorithms for these tasks. By generalizing the notion of a phenolog ("orthologous phenotype") to use functionally similar proteins (i.e. those with similar representations), they were able to demonstrate the utility of this broadened notion by using it to identify known phenologs and novel non-obvious ones supported by current research.

To read the full paper, go here.