Generating Detailed Spectral Libraries for Canine Proteomes Obtained from Serum and Urine.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37105983", "kind": "science-record", "revision": 1, "content_hash": "sha256:9ae6022771c5f423304786268ca0c1817b9154d0edb42000010451587aa4a20b", "created_at": "2026-11-01T19:01:46Z", "updated_at": "2026-11-01T19:01:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Generating Detailed Spectral Libraries for Canine Proteomes Obtained from Serum and Urine.", "doi": "10.1038/s41597-023-02139-6", "pmid": "37105983", "authors": ["Hee-Sung Ahn", "Jeonghun Yeom", "Jiyoung Yu", "Yumi Oh", "JeongYeon Hong", "Minjung Kim", "Kyunggon Kim"], "journal": "Scientific data", "year": 2023, "abstract": "Domestic dogs (Canis lupus familiaris) are popular companion animals. Increase in medical expenses associated with them and demand for extending their lifespan in a healthy manner has created the need to develop new diagnostic technology. Companion dogs also serve as important animal models for non-clinical research as they can provide various biological phenotypes. Proteomics have been increasingly used on dogs and humans to identify novel biomarkers of various diseases. Despite the growing applications of proteomics in liquid biopsy in veterinary medicine, no publicly available spectral assay libraries have been created for the proteome of canine serum and urine. In this study, we generated spectral assay libraries for the two-representative liquid-biopsy samples using mid-pH fractionation that allows in-depth understanding of proteome coverage. The resultant canine serum and urine spectral assay libraries include 1,132 and 4,749 protein groups and 5,483 and 25,228 peptides, respectively. We built these complimentary accessible resources for proteomic biomarker discovery studies through ProteomeXchange with the identifier PXD034770.", "claims": [{"id": "claim-data-access", "statement": "The two spectral libraries (.xls and .kit) produced from raw mass spectrometry data (.raw) and DIALib-QC evaluation reports for both were saved to the ProteomeXchange Consortium through PRIDE with the dataset identifier PXD03477046.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37105983", "locator": "sections[11] \"Data Records\" paragraph 2", "quote": "The two spectral libraries (.xls and .kit) produced from raw mass spectrometry data (.raw) and DIALib-QC evaluation reports for both were saved to the ProteomeXchange Consortium through PRIDE with the dataset identifier PXD03477046."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The canine serum and urine spectral assay libraries contain 1,132 and 4,749 protein groups and 5,483 and 25,228 peptides, respectively.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37105983", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The resultant canine serum and urine spectral assay libraries include 1,132 and 4,749 protein groups and 5,483 and 25,228 peptides, respectively."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The canine serum and urine spectral assay libraries contain 1,132 and 4,749 protein groups and 5,483 and 25,228 peptides, respectively.", "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:37105983"], "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:PXD034770"], "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:PXD034770"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37105983", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41597-023-02139-6", "sha256": "sha256:1c429516fdde59ce62398f76b8ba3914fe1e20add203125430d58c9298e0e03d", "bytes": 19114, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41597-023-02139-6", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10140049", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD034770", "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=PXD034770", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD034770", "version": null, "note": "The two spectral libraries (.xls and .kit) produced from raw mass spectrometry data (.raw) and DIALib-QC evaluation reports for both were saved to the ProteomeXchange Consortium through PRIDE with the dataset identifier PXD03477046.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The two spectral libraries (.xls and .kit) produced from raw mass spectrometry data (.raw) and DIALib-QC evaluation reports for both were saved to the ProteomeXchange Consortium through PRIDE with the dataset identifier PXD03477046.", "access_statement_kind": "repository_route_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Proteomic profiling of canine (dog) serum and urine", "resolution_checked_at": "2026-11-01T18:46:41Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD034770 not downloaded", "asset:data:geo:PXD034770 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": ["PXD034770"], "resolved_accessions": ["PXD034770"], "statements": ["The two spectral libraries (.xls and .kit) produced from raw mass spectrometry data (.raw) and DIALib-QC evaluation reports for both were saved to the ProteomeXchange Consortium through PRIDE with the dataset identifier PXD03477046."], "basis": "The paper names PXD034770 in Proteomics Identification Database (PRIDE) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:37105983", "data:geo:PXD034770"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD034770"]}, "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": "2026-11-01T18:37:47Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 5, "usage": {"prompt_tokens": 6591, "completion_tokens": 890, "cached_tokens": 264}}, "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:37105983", "type": "paper", "label": "pmid:37105983"}, {"id": "source:pmid:37105983", "type": "manuscript", "label": "PMID 37105983 full text"}, {"id": "data:geo:PXD034770", "type": "dataset", "label": "GEO PXD034770"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37105983", "type": "paper", "label": "pmid:37105983"}, {"id": "source:pmid:37105983", "type": "manuscript", "label": "PMID 37105983 full text"}, {"id": "data:geo:PXD034770", "type": "dataset", "label": "GEO PXD034770"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37105983", "type": "extraction", "used": ["source:pmid:37105983"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD034770", "type": "accession_resolution", "used": ["data:geo:PXD034770"], "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": null, "parent_hash": null, "fork_of": null, "generation": 0}, "gaps": ["asset:data:geo:PXD034770 licence not read", "asset:data:geo:PXD034770 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"]}