An Update of the Virion Proteome of Kaposi Sarcoma-Associated Herpesvirus.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33276600", "kind": "science-record", "revision": 2, "content_hash": "sha256:66b4242bb887412d9045caf8f98b38a941754de3fa8a711c56cbe15625d1ce18", "created_at": "2026-11-01T15:41:17Z", "updated_at": "2026-11-01T18:53:54Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "An Update of the Virion Proteome of Kaposi Sarcoma-Associated Herpesvirus.", "doi": "10.3390/v12121382", "pmid": "33276600", "authors": ["Ramina Nabiee", "Basir Syed", "Jesus Ramirez Castano", "Rukhsana Lalani", "Jennifer E Totonchy"], "journal": "Viruses", "year": 2020, "abstract": "The virion proteins of Kaposi sarcoma-associated herpesvirus (KSHV) were initially characterized in 2005 in two separate studies that combined the detection of 24 viral proteins and a few cellular components via LC-MS/MS or MALDI-TOF. Despite considerable advances in the sensitivity and specificity of mass spectrometry instrumentation in recent years, leading to significantly higher yields in detections, the KSHV virion proteome has not been revisited. In this study, we have re-examined the protein composition of purified KSHV virions via ultra-high resolution Qq time-of-flight mass spectrometry (UHR-QqTOF). Our results confirm the detection of all previously reported virion proteins, in addition to 17 other viral proteins, some of which have been characterized as virion-associated using other methods, and 10 novel proteins identified as virion-associated for the first time in this study. These results add KSHV ORF9, ORF23, ORF35, ORF48, ORF58, ORF72/vCyclin, K3, K9/vIRF1, K10/vIRF4, and K10.5/vIRF3 to the list of KSHV proteins that can be incorporated into virions. The addition of these proteins to the KSHV virion proteome provides novel and important insight into early events in KSHV infection mediated by virion-associated proteins. Data are available via ProteomeXchange with identifier PXD022626.", "claims": [{"id": "claim-data-access", "statement": "Data are available via ProteomeXchange with identifier PXD022626.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33276600", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with identifier PXD022626."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:33276600"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:PXD022626"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:PXD022626"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33276600", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/v12121382", "sha256": "sha256:9e1a8c4d3ada0bdc31e224bbebc73f2b13b680216ca0e32d8ab460677340fcc6", "bytes": 37938, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/v12121382", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7761624", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD022626", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=PXD022626", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD022626", "version": null, "note": "Data are available via ProteomeXchange with identifier PXD022626.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange with identifier PXD022626.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "An Updated overview of the Virion Proteome of Kaposi Sarcoma Associated Herpesvirus", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD022626 not downloaded", "asset:data:geo:PXD022626 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["PXD022626"], "resolved_accessions": ["PXD022626"], "statements": ["Data are available via ProteomeXchange with identifier PXD022626."], "basis": "The paper names PXD022626 in ProteomeXchange Consortium and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:33276600", "data:geo:PXD022626"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD022626"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T19:17:36Z", "independence": "single_reader"}, "evidence_check": {"method": "absent", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 29191, "completion_tokens": 1848, "cached_tokens": 792}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:33276600", "type": "paper", "label": "pmid:33276600"}, {"id": "source:pmid:33276600", "type": "manuscript", "label": "PMID 33276600 full text"}, {"id": "data:geo:PXD022626", "type": "dataset", "label": "GEO PXD022626"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33276600", "type": "paper", "label": "pmid:33276600"}, {"id": "source:pmid:33276600", "type": "manuscript", "label": "PMID 33276600 full text"}, {"id": "data:geo:PXD022626", "type": "dataset", "label": "GEO PXD022626"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33276600", "type": "extraction", "used": ["source:pmid:33276600"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD022626", "type": "accession_resolution", "used": ["data:geo:PXD022626"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:33276600", "parent_hash": "sha256:3432299053259d787b41b91e95e2644706049dbb2a0ee429862ecc027102fba8", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:PXD022626 licence not read", "asset:data:geo:PXD022626 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["vances in the sensitivity and specificity of mass spectrometry instrumentation in recent years, leading to", "via ultra-high resolution Qq time-of-flight mass spectrometry (UHR-QqTOF). Our results confirm the detecti", "l proteins and a few cellular components via LC-MS/MS or MALDI-TOF. Despite considerable advances"], "order_basis": "paper_text_order:242", "id": "assay:1"}]}