{"doi":"10.1101/2024.10.24.619987","title":"V- and VL-Scores Uncover Viral Signatures and Origins of Protein Families","abstract":"Viruses are key drivers of microbial diversity, nutrient cycling, and co-evolution in ecosystems, yet their study is hindered due to challenges in culturing. Traditional gene-centric methods, which focus on a few hallmark genes like for capsids, miss much of the viral genome, leaving key viral proteins and functions undiscovered. Here, we introduce two powerful annotation-free metrics, V-score and VL-score, designed to quantify the virus-likeness of protein families and genomes and create an open-access searchable database, V-Score-Search. By applying V- and VL-scores to public databases (KEGG, Pfam, and eggNOG), we link 38−77% of protein families with viruses, a 9−16x increase over current estimates. These metrics outperform existing approaches, enabling precise detection of viral genomes, prophages, and host-derived auxiliary viral genes (AVGs) from fragmented sequences, and significantly improving genome binning. Remarkably, we identify up to 17x more AVGs, dominated by non-metabolic proteins of unknown function. This innovation unlocks new insights into virus signatures and host interactions, with wide-ranging implications from genomics to biotechnology.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2024,"id":489217,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":2,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9498,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1028153,"name":"James C. Kosmopoulos","orcid":"0000-0001-7070-5418","position":1,"is_corresponding":false},{"id":1334584,"name":"Etan Dieppa Colon","orcid":null,"position":2,"is_corresponding":false},{"id":1334585,"name":"Peter John Badciong","orcid":null,"position":3,"is_corresponding":false},{"id":40438,"name":"Karthik Anantharaman","orcid":"0000-0002-9584-2491","position":4,"is_corresponding":false},{"id":1189919,"name":"Kun Zhou","orcid":"0000-0003-3638-0298","position":0,"is_corresponding":true}],"reference_count":84,"raw_metadata":null,"created_at":"2026-07-19T02:08:23.929823Z","pmid":"39554153","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}