<HashMap><database>biostudies-literature</database><scores/><additional><submitter>Peng FZ</submitter><funding>U.S. Department of Health &amp;amp; Human Services | NIH | National Institute of General Medical Sciences</funding><funding>U.S. Department of Health &amp; Human Services | NIH | National Institute of General Medical Sciences (NIGMS)</funding><pagination>945-949</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC12074982</full_dataset_link><repository>biostudies-literature</repository><omics_type>Unknown</omics_type><volume>22(5)</volume><pubmed_abstract>Current protein language models (LMs) accurately encode protein properties but have yet to represent post-translational modifications (PTMs), which are crucial for proteomic diversity and influence protein structure, function and interactions. To address this gap, we develop PTM-Mamba, a PTM-aware protein LM that integrates PTM tokens using bidirectional Mamba blocks fused with ESM-2 protein LM embeddings via a newly developed gating mechanism. PTM-Mamba uniquely models both wild-type and PTM sequences, enabling downstream tasks such as disease association and druggability prediction, PTM effect prediction on protein-protein interactions and zero-shot PTM discovery. In total, our work establishes PTM-Mamba as a foundational tool for PTM-aware protein modeling and design.</pubmed_abstract><journal>Nature methods</journal><pubmed_title>PTM-Mamba: a PTM-aware protein language model with bidirectional gated Mamba blocks.</pubmed_title><pmcid>PMC12074982</pmcid><funding_grant_id>1R35GM1555282-01</funding_grant_id><pubmed_authors>Schussheim B</pubmed_authors><pubmed_authors>Wang C</pubmed_authors><pubmed_authors>Chatterjee P</pubmed_authors><pubmed_authors>Vincoff S</pubmed_authors><pubmed_authors>Peng FZ</pubmed_authors><pubmed_authors>Chen T</pubmed_authors></additional><is_claimable>false</is_claimable><name>PTM-Mamba: a PTM-aware protein language model with bidirectional gated Mamba blocks.</name><description>Current protein language models (LMs) accurately encode protein properties but have yet to represent post-translational modifications (PTMs), which are crucial for proteomic diversity and influence protein structure, function and interactions. To address this gap, we develop PTM-Mamba, a PTM-aware protein LM that integrates PTM tokens using bidirectional Mamba blocks fused with ESM-2 protein LM embeddings via a newly developed gating mechanism. PTM-Mamba uniquely models both wild-type and PTM sequences, enabling downstream tasks such as disease association and druggability prediction, PTM effect prediction on protein-protein interactions and zero-shot PTM discovery. In total, our work establishes PTM-Mamba as a foundational tool for PTM-aware protein modeling and design.</description><dates><release>2025-01-01T00:00:00Z</release><publication>2025 May</publication><modification>2026-06-02T07:06:43.332Z</modification><creation>2026-04-15T03:15:26.839Z</creation></dates><accession>S-EPMC12074982</accession><cross_references><pubmed>40211004</pubmed><doi>10.1038/s41592-025-02656-9</doi></cross_references></HashMap>