{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T04:04:04Z","timestamp":1791432244845,"version":"4.3.3"},"reference-count":47,"publisher":"National Academy of Sciences","issue":"25","license":[{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["GBMF13344"],"award-info":[{"award-number":["GBMF13344"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100027426","name":"Schmidt Futures","doi-asserted-by":"publisher","award":["G-24-67500"],"award-info":[{"award-number":["G-24-67500"]}],"id":[{"id":"10.13039\/100027426","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.pnas.org"],"crossmark-restriction":true},"short-container-title":["Proc. Natl. Acad. Sci. U.S.A."],"published-print":{"date-parts":[[2026,6,23]]},"abstract":"<jats:p>Protein\u2013protein interactions (PPIs) underpin biological function, yet proteome-scale interaction prediction remains bottlenecked by the quadratic computational complexity of all-vs.-all pairwise comparisons. Here, we present FlashPPI, a contrastive learning framework, grounded in residue-level interactions, that enables linear-time prediction of physical protein interfaces across a microbial proteome. By leveraging a genomic language model that captures cross-protein coevolutionary signals from metagenomic sequences, FlashPPI aligns interacting partners in a shared latent space. We demonstrate a four-fold performance increase over existing sequence-based methods, while reducing proteome-wide screening time from days to minutes. Crucially, FlashPPI achieves comparable screening performance to state-of-the-art structure-folding models at a fraction of the computational cost. Finally, we integrate FlashPPI into an interactive web platform that combines predicted networks with functional annotations and genomic context, making proteome-wide network analysis rapid and accessible for microbial discovery.<\/jats:p>","DOI":"10.1073\/pnas.2610619123","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:08:59Z","timestamp":1781712539000},"update-policy":"https:\/\/doi.org\/10.1073\/pnas.cm10313","source":"Crossref","is-referenced-by-count":5,"title":["Linear-time prediction of proteome-scale microbial protein interactions"],"prefix":"10.1073","volume":"123","author":[{"given":"Andre","family":"Cornman","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/001dv4j44","id-type":"ROR","asserted-by":"publisher"}],"name":"Tatta Bio","place":["Cambridge"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matt","family":"Tranzillo","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/001dv4j44","id-type":"ROR","asserted-by":"publisher"}],"name":"Tatta Bio","place":["Cambridge"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolo G.","family":"Zulaybar","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/001dv4j44","id-type":"ROR","asserted-by":"publisher"}],"name":"Tatta Bio","place":["Cambridge"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Imane","family":"Bouzit","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/042nb2s44","id-type":"ROR","asserted-by":"publisher"}],"name":"Microbiology Graduate Program, Massachusetts Institute of Technology","place":["Cambridge"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0554-5598","authenticated-orcid":false,"given":"Yunha","family":"Hwang","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/001dv4j44","id-type":"ROR","asserted-by":"publisher"}],"name":"Tatta Bio","place":["Cambridge"]},{"id":[{"id":"https:\/\/ror.org\/042nb2s44","id-type":"ROR","asserted-by":"publisher"}],"name":"Department of Biology, Massachusetts Institute of Technology","place":["Cambridge"]},{"id":[{"id":"https:\/\/ror.org\/042nb2s44","id-type":"ROR","asserted-by":"publisher"}],"name":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology","place":["Cambridge"]},{"id":[{"id":"https:\/\/ror.org\/042nb2s44","id-type":"ROR","asserted-by":"publisher"}],"name":"Schwarzman College of Computing, Massachusetts Institute of Technology","place":["Cambridge"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"341","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"e_1_3_4_1_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-020-0718-6"},{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.67667"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06583-7"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1089\/106652703322756168"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature03239"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac1000"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaw6718"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cels.2021.08.010"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-64512-w"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41564-024-01791-x"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.adt1630"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac258"},{"key":"e_1_3_4_13_2","doi-asserted-by":"crossref","unstructured":"A. Cornman et al. \u201cThe OMG dataset: An open MetaGenomic corpus for mixed-modality genomic language modeling\u201d in The Thirteenth International Conference on Learning Representations Y. Yue A. Garg N. Peng F. Sha R. Yu Eds. (OpenReview.net 2025).","DOI":"10.1101\/2024.08.14.607850"},{"key":"e_1_3_4_14_2","unstructured":"A. Radford et al. \u201cLearning transferable visual models from natural language supervision\u201d in Proceedings of the 38th International Conference on Machine Learning M. Meila T. Zhang Eds. (PMLR 2021) vol. 139 pp. 8748\u20138763."},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaf1226"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.02030"},{"key":"e_1_3_4_17_2","doi-asserted-by":"crossref","unstructured":"Y. Akiyama Z. Zhang M. Mirdita M. Steinegger S. Ovchinnikov Scaling down protein language modeling with MSA pairformer. bioRxiv [Preprint] (2025). https:\/\/www.biorxiv.org\/content\/10.1101\/2025.08.02.668173v1 (Accessed 24 March 2026).","DOI":"10.1101\/2025.08.02.668173"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade2574"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2302580120"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1038\/s44320-026-00189-7"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1002\/cbic.202500433"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.3109\/10409238.2011.600437"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1111\/mmi.14409"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0510013103"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/147648"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.3390\/v8030066"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.80.5.1236"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43705-022-00111-w"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-56887-7"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1093\/embo-reports\/kvf176"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1105\/tpc.114.125641"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.94.2.479"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2011.11.055"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.1111\/1462-2920.16043"},{"key":"e_1_3_4_36_2","doi-asserted-by":"crossref","unstructured":"V. D. Blondel J. L. Guillaume R. Lambiotte E. Lefebvre Fast unfolding of communities in large networks. arXiv [Preprint] (2008). https:\/\/doi.org\/10.48550\/arXiv.0803.0476 (Accessed 24 March 2026).","DOI":"10.1088\/1742-5468\/2008\/10\/P10008"},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1002195"},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adv5109"},{"key":"e_1_3_4_39_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07487-w"},{"key":"e_1_3_4_40_2","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.3988"},{"key":"e_1_3_4_41_2","doi-asserted-by":"crossref","unstructured":"L. Gao Y. Zhang J. Han J. Callan \u201cScaling deep contrastive learning batch size under memory limited setup\u201d in Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021) A. Rogers et al. Eds. (Association for Computational Linguistics Online 2021) pp. 316\u2013321.","DOI":"10.18653\/v1\/2021.repl4nlp-1.31"},{"key":"e_1_3_4_42_2","doi-asserted-by":"crossref","unstructured":"M. Douze et al. The faiss library. IEEE Trans. Big Data 12 346\u2013361 (2026). 10.1109\/TBDATA.2025.3618474.","DOI":"10.1109\/TBDATA.2025.3618474"},{"key":"e_1_3_4_43_2","unstructured":"A. Cornman et al. tattabio\/flashppi. Hugging Face. https:\/\/huggingface.co\/tattabio\/flashppi. Deposited 27 February 2026."},{"key":"e_1_3_4_44_2","unstructured":"A. Cornman et al. tattabio\/flashppi_noecoli. Hugging Face. https:\/\/huggingface.co\/tattabio\/flashppi_noecoli. Deposited 27 February 2026."},{"key":"e_1_3_4_45_2","unstructured":"A. Cornman et al. tattabio\/FlashPPI. GitHub. https:\/\/github.com\/tattabio\/FlashPPI. Deposited 25 February 2026."},{"key":"e_1_3_4_46_2","unstructured":"A. Cornman et al. tattabio\/ecoli_pdb_benchmark. Hugging Face. https:\/\/huggingface.co\/datasets\/tattabio\/ecoli_pdb_benchmark. Deposited 27 February 2026."},{"key":"e_1_3_4_47_2","unstructured":"J. Zhang et al. Human PPI datasets. Cong Lab. https:\/\/conglab.swmed.edu\/humanPPI\/humanPPI_download.html. Accessed 12 July 2025."}],"container-title":["Proceedings of the National Academy of Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pnas.org\/doi\/pdf\/10.1073\/pnas.2610619123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:10:10Z","timestamp":1781712610000},"score":1,"resource":{"primary":{"URL":"https:\/\/pnas.org\/doi\/10.1073\/pnas.2610619123"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":47,"journal-issue":{"issue":"25","published-print":{"date-parts":[[2026,6,23]]}},"alternative-id":["10.1073\/pnas.2610619123"],"URL":"https:\/\/doi.org\/10.1073\/pnas.2610619123","relation":{},"ISSN":["0027-8424","1091-6490"],"issn-type":[{"value":"0027-8424","type":"print"},{"value":"1091-6490","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,17]]},"assertion":[{"value":"2026-03-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2610619123"}}