PhaLP 2.0: extending the community-oriented phage lysin database with a SUBLYME pipeline for metagenomic discovery
Source: PubMed Central Open Access, NCBI / U.S. National Library of Medicine
Abstract As biology becomes increasingly data-driven, so does the field of phage lysins, enzymes that degrade bacterial cell walls and offer promising alternatives to traditional antibiotics. Five years ago, we introduced PhaLP, a centralized resource forgeyticrotein sequences and associated metadata to support global research efforts. Here, we present PhaLP 2.0, an enhanced database designed to address key challenges in computational lysin research by integrating newly identified lysins from thousands of metagenomes. To expand the known diversity of lysins beyond that of cultured phages, we developed SUBLYME, a protein-embedding-based machine-learningoftware designed toncover and classifyacteriophagesins fromtagenomic datasets. Using embeddings derived from the well-curated sequences of the original PhaLP database, we trained support vector machines to distinguish lysins from non-lysins in viromes and classify them as endolysins or virion-associated lysins. The models achieved an average F1 score of 98% on held-out clusters. SUBLYME enabled the discovery of 743 000 new lysin sequences from EnVhogDB, a virome-derived protein database, increasing the number of known lysin clusters 40-fold, from 1000 to 40 000. SUBLYME and PhaLP 2.0 are accessible online atand, respectively. Together, these advances establish PhaLP 2.0 as a comprehensive and scalable portal for lysin discovery, classification, and sequence analysis, paving the way for future antibacterial applications and evolu
Abstract
Abstract As biology becomes increasingly data-driven, so does the field of phage lysins, enzymes that degrade bacterial cell walls and offer promising alternatives to traditional antibiotics. Five years ago, we introduced PhaLP, a centralized resource forgeyticrotein sequences and associated metadata to support global research efforts. Here, we present PhaLP 2.0, an enhanced database designed to address key challenges in computational lysin research by integrating newly identified lysins from thousands of metagenomes. To expand the known diversity of lysins beyond that of cultured phages, we developed SUBLYME, a protein-embedding-based machine-learningoftware designed toncover and classifyacteriophagesins fromtagenomic datasets. Using embeddings derived from the well-curated sequences of the original PhaLP database, we trained support vector machines to distinguish lysins from non-lysins in viromes and classify them as endolysins or virion-associated lysins. The models achieved an average F1 score of 98% on held-out clusters. SUBLYME enabled the discovery of 743 000 new lysin sequences from EnVhogDB, a virome-derived protein database, increasing the number of known lysin clusters 40-fold, from 1000 to 40 000. SUBLYME and PhaLP 2.0 are accessible online atand, respectively. Together, these advances establish PhaLP 2.0 as a comprehensive and scalable portal for lysin discovery, classification, and sequence analysis, paving the way for future antibacterial applications and evolutionary insights.