A Compendium of Murine (Phospho)Peptides Encompassing Different Isobaric Labeling and Data Acquisition Strategies.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34043369", "kind": "science-record", "revision": 3, "content_hash": "sha256:95ff3c02bb31b9d6d7d9cbcf7340f3969ba6269f858392f2c8223e1383bfd86e", "created_at": "2026-11-01T17:35:21Z", "updated_at": "2026-11-01T21:25:25Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A Compendium of Murine (Phospho)Peptides Encompassing Different Isobaric Labeling and Data Acquisition Strategies.", "doi": "10.1021/acs.jproteome.1c00247", "pmid": "34043369", "authors": ["Olesja Popow", "Xinyue Liu", "Kevin M Haigis", "Steven P Gygi", "Joao A Paulo"], "journal": "Journal of proteome research", "year": 2021, "abstract": "Targeted mass spectrometry-based assays typically rely on previously acquired large data sets for peptide target selection. Such repositories are widely available for unlabeled peptides. However, they are less common for isobaric tagged peptides. Here we have assembled two series of six data sets originating from a mouse embryonic fibroblast cell line (NIH/3T3). One series is of peptides derived from a tryptic digest of a whole cell proteome and a second from enriched phosphopeptides. These data sets encompass three labeling approaches (unlabeled, TMT11-labeled, and TMTpro16-labeled) and two data acquisition strategies (ion trap MS2 with and without FAIMS-based gas phase separation). We identified a total of 1 509 526 peptide-spectrum matches which covered 11 482 proteins from the whole cell proteome tryptic digest, and 188 849 phosphopeptides from the phosphopeptide enrichment. The data sets were of similar depth, and while overlap across data sets was modest, protein overlap was high, thus reinforcing the comprehensiveness of these data sets. The data also supported FAIMS as a means to increase data set depth. These data sets provide a rich resource of peptides that may be used as starting points for targeted assays. Future data sets may be compiled for any genome-sequenced organism using the technologies and strategies highlighted herein. The data have been deposited in the ProteomeXchange Consortium with data set identifier PXD024298.", "claims": [{"id": "claim-method", "statement": "PSM filtering was performed using a linear discriminant analysis, as described previously32 and then assembled further to a final protein-level FDR of 1%.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34043369", "locator": "sections[10] \"Data Analysis\" paragraph 2", "quote": "PSM filtering was performed using a linear discriminant analysis, as described previously32 and then assembled further to a final protein-level FDR of 1%."}], "state": "complete"}, {"id": "claim-data-access", "statement": "RAW files will be made available upon request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34043369", "locator": "sections[11] \"Data Access\" paragraph 2", "quote": "RAW files will be made available upon request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We identified a total of 1 509 526 peptide-spectrum matches which covered 11 482 proteins from the whole cell proteome tryptic digest, and 188 849 phosphopeptides from the phosphopeptide enrichment.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:34043369", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We identified a total of 1 509 526 peptide-spectrum matches which covered 11 482 proteins from the whole cell proteome tryptic digest, and 188 849 phosphopeptides from the phosphopeptide enrichment."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "We identified a total of 1 509 526 peptide-spectrum matches which covered 11 482 proteins from the whole cell proteome tryptic digest, and 188 849 phosphopeptides from the phosphopeptide enrichment.", "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:34043369"], "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:PXD024298"], "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:PXD024298"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34043369", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1021/acs.jproteome.1c00247", "sha256": "sha256:5b33c117d8640b2e4f772f9fd4f1d347be811e92f4a373cd8f0e395b145484bd", "bytes": 40719, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1021/acs.jproteome.1c00247", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8254770", "source": "ncbi_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD024298", "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=PXD024298", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD024298", "version": null, "note": "RAW files will be made available upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "RAW files will be made available upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "A compendium of murine (phospho)peptides encompassing different isobaric labeling and data acquisition strategies", "resolution_checked_at": "2026-11-01T17:30:50Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD024298 not downloaded", "asset:data:geo:PXD024298 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "linear discriminant analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "PSM filtering was performed using a linear discriminant analysis, as described previously32 and then assembled further to a final protein-level FDR of 1%."}}], "targets": [], "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 (linear discriminant 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": ["PXD024298"], "resolved_accessions": ["PXD024298"], "statements": ["RAW files will be made available upon request."], "basis": "The paper names PXD024298 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:34043369", "data:geo:PXD024298"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD024298"]}, "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": "2026-11-01T17:02:12Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 11199, "completion_tokens": 1440, "cached_tokens": 188}}, "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:34043369", "type": "paper", "label": "pmid:34043369"}, {"id": "source:pmid:34043369", "type": "manuscript", "label": "PMID 34043369 full text"}, {"id": "data:geo:PXD024298", "type": "dataset", "label": "GEO PXD024298"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34043369", "type": "paper", "label": "pmid:34043369"}, {"id": "source:pmid:34043369", "type": "manuscript", "label": "PMID 34043369 full text"}, {"id": "data:geo:PXD024298", "type": "dataset", "label": "GEO PXD024298"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34043369", "type": "extraction", "used": ["source:pmid:34043369"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD024298", "type": "accession_resolution", "used": ["data:geo:PXD024298"], "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:34043369", "parent_hash": "sha256:c373b5b17bf3393153e8ad08bbcde6b7065ad18ae75fa7e73816d7add2945213", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD024298 licence not read", "asset:data:geo:PXD024298 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": ["A Compendium of Murine (Phospho)Peptides Encompassing Different Iso", "o series of six data sets originating from a mouse embryonic fibroblast cell line (NIH/3T3). On"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["Targeted mass spectrometry-based assays typically rely on previously ac"], "order_basis": "paper_text_order:115", "id": "assay:2"}]}