Human cerebrospinal fluid data for use as spectral library, for biomarker research.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32775566", "kind": "science-record", "revision": 2, "content_hash": "sha256:a32902d4bdb1c744d6e0d2efe48e52de39b7433576e208266d1cba03f0f3cc95", "created_at": "2026-11-01T15:41:07Z", "updated_at": "2026-11-01T18:52:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Human cerebrospinal fluid data for use as spectral library, for biomarker research.", "doi": "10.1016/j.dib.2020.106048", "pmid": "32775566", "authors": ["Lukas M Schilde", "Simone Steinbach", "Bettina Serschnitzki", "Fabian Maass", "Mathias Bähr", "Paul Lingor", "Katrin Marcus", "Caroline May"], "journal": "Data in brief", "year": 2020, "abstract": "Spectral libraries generated by data dependent acquisition (DDA) are a useful tool for the analysis of data created by data independent acquisition (DIA) in mass spectrometry. The quality of DIA analysis is dependent on the quality of the spectral library. We used cerebrospinal fluid (CSF) of patients with Parkinson's disease and healthy controls to create a spectral library of human CSF proteome. To this date, there is no validated CSF biomarker for Parkinson's disease. This data set may therefore be valuable for the future analysis of CSF proteins. Part of the samples consisted of fractions that were separated by gel electrophoresis. After tryptic digestion, all samples were spiked with indexed retention time (iRT) peptides and were measured using a DDA mass spectrometry approach. The here provided data set can be used as a CSF-specific spectral library. Data files generated from the described workflow are hosted in the public repository ProteomeXchange under the identifier PXD013487.", "claims": [{"id": "claim-data-access", "statement": "The resulting raw-files were converted into the mzML-format and uploaded alongside the excel-file in the public repository PRIDE ProteomeXchange under the identifier PXD013487.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32775566", "locator": "sections[12] \"Mass spectrometry settings\" paragraph 4", "quote": "The resulting raw-files were converted into the mzML-format and uploaded alongside the excel-file in the public repository PRIDE ProteomeXchange under the identifier PXD013487."}], "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:32775566"], "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:PXD013487"], "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:PXD013487"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32775566", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2020.106048", "sha256": "sha256:d135b11c08632520ce24a2c6fb988729376c2a2c4d425a55fb81105a12bd7d1e", "bytes": 14472, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2020.106048", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7399102", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD013487", "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=PXD013487", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD013487", "version": null, "note": "The resulting raw-files were converted into the mzML-format and uploaded alongside the excel-file in the public repository PRIDE ProteomeXchange under the identifier PXD013487.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The resulting raw-files were converted into the mzML-format and uploaded alongside the excel-file in the public repository PRIDE ProteomeXchange under the identifier PXD013487.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Human cerebrospinal fluid analysis by HPLC-MS/MS", "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:PXD013487 not downloaded", "asset:data:geo:PXD013487 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": ["PXD013487"], "resolved_accessions": ["PXD013487"], "statements": ["The resulting raw-files were converted into the mzML-format and uploaded alongside the excel-file in the public repository PRIDE ProteomeXchange under the identifier PXD013487."], "basis": "The paper names PXD013487 in PRIDE ProteomeXchange and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:32775566", "data:geo:PXD013487"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD013487"]}, "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": "2026-10-31T18:21:38Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 13165, "completion_tokens": 810, "cached_tokens": 776}}, "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:32775566", "type": "paper", "label": "pmid:32775566"}, {"id": "source:pmid:32775566", "type": "manuscript", "label": "PMID 32775566 full text"}, {"id": "data:geo:PXD013487", "type": "dataset", "label": "GEO PXD013487"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32775566", "type": "paper", "label": "pmid:32775566"}, {"id": "source:pmid:32775566", "type": "manuscript", "label": "PMID 32775566 full text"}, {"id": "data:geo:PXD013487", "type": "dataset", "label": "GEO PXD013487"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32775566", "type": "extraction", "used": ["source:pmid:32775566"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD013487", "type": "accession_resolution", "used": ["data:geo:PXD013487"], "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:32775566", "parent_hash": "sha256:93300c98d821a6fa4ab491b8b07077367867b31452d606aa58d2e3342b1bb3e5", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:PXD013487 licence not read", "asset:data:geo:PXD013487 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": ["ted by data independent acquisition (DIA) in mass spectrometry. The quality of DIA analysis is dependent on", "(iRT) peptides and were measured using a DDA mass spectrometry approach. The here provided data set can be"], "order_basis": "paper_text_order:196", "id": "assay:1"}, {"role": "data_generation", "definition_id": "clinical_cohort", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["ibrary. We used cerebrospinal fluid (CSF) of patients with Parkinson's disease and healthy controls to"], "order_basis": "paper_text_order:333", "id": "assay:2"}]}