Human tear fluid proteome dataset for usage as a spectral library and for protein modeling.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31372408", "kind": "science-record", "revision": 3, "content_hash": "sha256:bac4faea580443f07b9c104a5fbf3c74e7e51f56a1165f0fa4dede50df4b8a0c", "created_at": "2026-11-01T15:40:48Z", "updated_at": "2026-11-01T18:51:07Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Human tear fluid proteome dataset for usage as a spectral library and for protein modeling.", "doi": "10.1016/j.dib.2019.103742", "pmid": "31372408", "authors": ["Annika Guntermann", "Simone Steinbach", "Bettina Serschnitzki", "Pia Grotegut", "Sabrina Reinehr", "Stephanie C Joachim", "Marc Schargus", "Katrin Marcus", "Caroline May"], "journal": "Data in brief", "year": 2019, "abstract": "This article provides a detailed dataset of human tear fluid proteins. Samples were fractionated by sodium dodecyl sulfate (SDS) gel electrophoresis resulting in 48 fractions that were spiked with an indexed retention time (iRT) peptide standard. These data are based on a data-dependent acquisition (DDA) mass spectrometric approach and can be used for example as a spectral library for tear fluid proteome analysis by data-independent acquisition (DIA). Moreover, the provided data set can be used with optimized HPLC and mass spectrometric settings for proteins/peptides of interest. Besides these aspects, this dataset can serve as a protein overview for gene ontology enrichment analysis and for modeling and benchmarking of multiple signaling pathways associated with the ocular surface in healthy or disease stages. The mass spectrometry proteomics data from the described workflow have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD011075.", "claims": [{"id": "claim-data-access", "statement": "The mass spectrometry proteomics data from the described workflow have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD011075.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31372408", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The mass spectrometry proteomics data from the described workflow have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD011075."}], "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:31372408"], "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:PXD011075"], "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:PXD011075"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31372408", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2019.103742", "sha256": "sha256:083c0de109e8a5615c34a91cbfb07a0299c06a08051b10376ad84db37bf5cb75", "bytes": 13253, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2019.103742", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6660621", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD011075", "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=PXD011075", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD011075", "version": null, "note": "The mass spectrometry proteomics data from the described workflow have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD011075.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data from the described workflow have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD011075.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Human tear fluid proteome dataset for usage as a spectral library and for protein modeling", "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:31372408:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:24d82abea78b36b848f4189803c1dfc9c315fafb28e292767a9b6c4d13b65d7b", "bytes": 442, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#tbl1", "version": null, "note": "Solvent gradient profile for the elution of amino acids.", "structure": {"pmcid": "PMC6660621", "section_index": 6, "section_title": "Amino acid analysis", "row_count": 10, "column_count": 3}, "table": {"label": "Table 1", "caption": "Solvent gradient profile for the elution of amino acids.", "rows": [["Time [min]", "% Eluent A", "% Eluent B"], ["0", "99.9", "0.1"], ["0.54", "99.9", "0.1"], ["5.74", "90.9", "0.1"], ["7.74", "78.8", "21.2"], ["8.04", "40.4", "59.6"], ["8.05", "10.0", "90"], ["8.64", "10.0", "90"], ["8.73", "99.9", "0.1"], ["9.50", "99.9", "0.1"]], "row_count": 10, "column_count": 3, "numeric_cells": 27, "header_rows": 1, "locator": "section[6]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:31372408:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:312999e2a123d01f81b280f8e2b29a1626ee52028eeab065ba64b37a0f57f842", "bytes": 473, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#tbl2", "version": null, "note": "Solvent gradient profile for elution of peptides.", "structure": {"pmcid": "PMC6660621", "section_index": 10, "section_title": "NanoHPLC settings", "row_count": 10, "column_count": 3}, "table": {"label": "Table 2", "caption": "Solvent gradient profile for elution of peptides.", "rows": [["Time [min]", "% Eluent A", "% Eluent B"], ["0.00", "95.00", "5.00"], ["7.00", "95.00", "5.00"], ["15.00", "85.00", "15.00"], ["122.00", "60.00", "40.00"], ["127.00", "40.00", "60.00"], ["128.00", "5.00", "95.00"], ["133.00", "5.00", "95.00"], ["138.00", "95.00", "5.00"], ["150.00", "95.00", "5.00"]], "row_count": 10, "column_count": 3, "numeric_cells": 27, "header_rows": 1, "locator": "section[10]/table-wrap[1]#tbl2"}}], "gaps": ["asset:data:geo:PXD011075 not downloaded", "asset:data:geo:PXD011075 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": ["PXD011075"], "resolved_accessions": ["PXD011075"], "statements": ["The mass spectrometry proteomics data from the described workflow have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD011075."], "basis": "The paper names PXD011075 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:31372408", "data:geo:PXD011075", "asset:table:pmid:31372408:1", "asset:table:pmid:31372408:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD011075"]}, "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": "2026-10-31T18:15:36Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 11562, "completion_tokens": 887, "cached_tokens": 384}}, "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:31372408", "type": "paper", "label": "pmid:31372408"}, {"id": "source:pmid:31372408", "type": "manuscript", "label": "PMID 31372408 full text"}, {"id": "data:geo:PXD011075", "type": "dataset", "label": "GEO PXD011075"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31372408", "type": "paper", "label": "pmid:31372408"}, {"id": "source:pmid:31372408", "type": "manuscript", "label": "PMID 31372408 full text"}, {"id": "data:geo:PXD011075", "type": "dataset", "label": "GEO PXD011075"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31372408", "type": "extraction", "used": ["source:pmid:31372408"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD011075", "type": "accession_resolution", "used": ["data:geo:PXD011075"], "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:31372408", "parent_hash": "sha256:66cbb8b5fa473eb5fdca5fad804ae0da41877638f78a80d49a3b258296352b99", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD011075 licence not read", "asset:data:geo:PXD011075 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": ["based on a data-dependent acquisition (DDA) mass spectrometric approach and can be used for example as a sp", "data set can be used with optimized HPLC and mass spectrometric settings for proteins/peptides of interest.", "ar surface in healthy or disease stages. The mass spectrometry proteomics data from the described workflow", "thy or disease stages. The mass spectrometry proteomics data from the described workflow have been d"], "order_basis": "paper_text_order:354", "id": "assay:1"}]}