A draft map of rhesus monkey tissue proteome for biomedical research.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:25974132", "kind": "science-record", "revision": 6, "content_hash": "sha256:f3574df65352a4a62c8ada71f5dcde7112ab30a1c7e499bb392ed8e9f170e60c", "created_at": "2026-11-01T15:40:08Z", "updated_at": "2026-11-01T21:20:00Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A draft map of rhesus monkey tissue proteome for biomedical research.", "doi": "10.1371/journal.pone.0126243", "pmid": "25974132", "authors": ["Jin-Gyun Lee", "Kimberly Q McKinney", "Yong-Yook Lee", "Hae-Na Chung", "Antonis J Pavlopoulos", "Kook Y Jung", "Woong-Ki Kim", "Marcelo J Kuroda", "David K Han", "Sunil Hwang"], "journal": "PloS one", "year": 2015, "abstract": "Though the rhesus monkey is one of the most valuable non-human primate animal models for various human diseases because of its manageable size and genetic and proteomic similarities with humans, proteomic research using rhesus monkeys still remains challenging due to the lack of a complete protein sequence database and effective strategy. To investigate the most effective and high-throughput proteomic strategy, comparative data analysis was performed employing various protein databases and search engines. The UniProt databases of monkey, human, bovine, rat and mouse were used for the comparative analysis and also a universal database with all protein sequences from all available species was tested. At the same time, de novo sequencing was compared to the SEQUEST search algorithm to identify an optimal work flow for monkey proteomics. Employing the most effective strategy, proteomic profiling of monkey organs identified 3,481 proteins at 0.5% FDR from 9 male and 10 female tissues in an automated, high-throughput manner. Data are available via ProteomeXchange with identifier PXD001972. Based on the success of this alternative interpretation of MS data, the list of proteins identified from 12 organs of male and female subjects will benefit future rhesus monkey proteome research.", "claims": [{"id": "claim-method", "statement": "Gene and hierarchical analysis were performed using TreeView (v1.60) software provided by Eisen Lab (http://rana.lbl.gov/EisenSoftware.htm).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25974132", "locator": "sections[13] \"Validation of proteomic dataset\" paragraph 2", "quote": "Gene and hierarchical analysis were performed using TreeView (v1.60) software provided by Eisen Lab (http://rana.lbl.gov/EisenSoftware.htm)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "These raw data files will be available in the public data repository (http://www.proteomexchange.org/) for further data comparison and analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25974132", "locator": "sections[14] \"Conclusions\" paragraph 3", "quote": "These raw data files will be available in the public data repository (http://www.proteomexchange.org/) for further data comparison and analysis."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Employing the most effective strategy, proteomic profiling of monkey organs identified 3,481 proteins at 0.5% FDR from 9 male and 10 female tissues in an automated, high-throughput manner.", "kind": "quantitative", "target": {"value": 0.5, "unit": "per cent", "tolerance": null, "source": "Employing the most effective strategy, proteomic profiling of monkey organs identified 3,481 proteins at 0.5% FDR from 9 male and 10 female tissues in an automated, high-throughput manner."}, "evidence": [{"asset": "source:pmid:25974132", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "At the same time, de novo sequencing was compared to the SEQUEST search algorithm to identify an optimal work flow for monkey proteomics."}, {"asset": "source:pmid:25974132", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Employing the most effective strategy, proteomic profiling of monkey organs identified 3,481 proteins at 0.5% FDR from 9 male and 10 female tissues in an automated, high-throughput manner."}, {"asset": "source:pmid:25974132", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with identifier PXD001972."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Employing the most effective strategy, proteomic profiling of monkey organs identified 3,481 proteins at 0.5% FDR from 9 male and 10 female tissues in an automated, high-throughput manner.", "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:25974132"], "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:PXD001972"], "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:PXD001972"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:25974132", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0126243", "sha256": "sha256:c64ae4830c1cfcf204856f0b0440ebd341718bba81efd7ce0946e3cf4e6ec722", "bytes": 38698, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0126243", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4431823", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD001972", "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=PXD001972", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD001972", "version": null, "note": "These raw data files will be available in the public data repository (http://www.proteomexchange.org/) for further data comparison and analysis.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "These raw data files will be available in the public data repository (http://www.proteomexchange.org/) for further data comparison and analysis.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Multi-organ proteomics of rhesus macaque for prototype proteome bank of non–human primate", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:25974132:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:db026767fcf4dc525a7028b8889f91735dce45fc60b1ad51689b3269eecb34ca", "bytes": 213, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#pone.0126243.t001", "version": null, "note": "Top 3 unique proteins identified from each tissue.", "structure": {"pmcid": "PMC4431823", "section_index": 12, "section_title": "A draft tissue proteome map of female and male rhesus monkey", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1", "caption": "Top 3 unique proteins identified from each tissue.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[12]/table-wrap[1]#pone.0126243.t001"}}, {"id": "asset:table:pmid:25974132:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e0f46c9e8de805422c7d55a68ff0435fa685e96a31f7bdc2e30a97727e7d25df", "bytes": 228, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#pone.0126243.t002", "version": null, "note": "Top 30 common proteins identified from all of the tissue samples.", "structure": {"pmcid": "PMC4431823", "section_index": 12, "section_title": "A draft tissue proteome map of female and male rhesus monkey", "row_count": 0, "column_count": 0}, "table": {"label": "Table 2", "caption": "Top 30 common proteins identified from all of the tissue samples.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[12]/table-wrap[2]#pone.0126243.t002"}}], "gaps": ["asset:data:geo:PXD001972 not downloaded", "asset:data:geo:PXD001972 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "hierarchical analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Gene and hierarchical analysis were performed using TreeView (v1.60) software provided by Eisen Lab (http://rana.lbl.gov/EisenSoftware.htm)."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": null, "expected_value": 0.5, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "gaps": ["method.reader_named_unmapped"]}, "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 (hierarchical analysis), 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": ["PXD001972"], "resolved_accessions": ["PXD001972"], "statements": ["These raw data files will be available in the public data repository (http://www.proteomexchange.org/) for further data comparison and analysis."], "basis": "The paper names PXD001972 in ProteomeXchange Consortium via the PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:25974132", "data:geo:PXD001972", "asset:table:pmid:25974132:1", "asset:table:pmid:25974132:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD001972"]}, "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": "2026-10-31T18:23:54Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 69754, "completion_tokens": 3741, "cached_tokens": 1832}}, "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:25974132", "type": "paper", "label": "pmid:25974132"}, {"id": "source:pmid:25974132", "type": "manuscript", "label": "PMID 25974132 full text"}, {"id": "data:geo:PXD001972", "type": "dataset", "label": "GEO PXD001972"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:25974132", "type": "paper", "label": "pmid:25974132"}, {"id": "source:pmid:25974132", "type": "manuscript", "label": "PMID 25974132 full text"}, {"id": "data:geo:PXD001972", "type": "dataset", "label": "GEO PXD001972"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-25974132", "type": "extraction", "used": ["source:pmid:25974132"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD001972", "type": "accession_resolution", "used": ["data:geo:PXD001972"], "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:25974132", "parent_hash": "sha256:100d01232cbdeb260ddff4ddfb86b72d0e77eaf725081b75018b6b602be88c0a", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD001972 licence not read", "asset:data:geo:PXD001972 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["databases of monkey, human, bovine, rat and mouse were used for the comparative analysis and a", "UniProt databases of monkey, human, bovine, rat and mouse were used for the comparative anal", "he databases of four mammals, human, bovine, mouse and rat (C) Comparison of de novo sequencing", "atabases of three non-human mammals (bovine, mouse and rat) were tested comparatively. As shown"], "order_basis": "paper_text_order:585", "id": "assay:1"}]}