Decoding the Functional Interactome of Non-model Organisms with PHILHARMONIC
Lists
Only you see this
Abstract
We introduce PHILHARMONIC, a computational framework that couples deep learning de novo network inference with robust unsupervised spectral clustering algorithms to uncover functional relationships and high-level organization in non-model organisms. Our novel clustering approach produces highly informative functional modules by de-noising the predicted network. We also develop a novel algorithm called ReCIPE, which aims to reconnect disconnected clusters, increasing functional enrichment and biological interpretability. We initially perform remote homology-based functional annotation by leveraging hmmscan and GODomainMiner to assign initial functions to proteins at large evolutionary distances; our clusters then enable us to newly assign functions to uncharacterized proteins through “function by association.” We validate the ability of PHILHARMONIC to recover gold-standard functional enrichments in the well-annotated fruit fly D. melanogaster, and apply it to investigate stress response in the reef-building coral P. damicornis and its algal symbiont C. goreaui. Easy to run end-to-end and requiring only a sequenced proteome, PHILHARMONIC is an engine for biological hypothesis generation and discovery in non-model organisms.
BibTeX
@inproceedings{sledzieski2025decoding,
author = {Samuel Sledzieski and Charlotte Versavel and Rohit Singh and Faith Ocitti and Kapil Devkota and Lokender Kumar and Polina Shpilker and Liza Roger and Jinkyu Yang and Nastassja Lewinski and Hollie Putnam and Bonnie Berger and Judith Klein-Seetharaman and Lenore Cowen},
title = {{Decoding the Functional Interactome of Non-model Organisms with PHILHARMONIC}},
booktitle = {RECOMB},
year = {2025},
doi = {10.1007/978-3-031-90252-9\_19},
}Loading related content...