Method for Independent Estimation of the False Localization Rate for Phosphoproteomics.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35640880", "kind": "science-record", "revision": 3, "content_hash": "sha256:80cb6297e98429c47774e1ab87ca25940f1eedd275e663efdc22352153ae17d1", "created_at": "2026-11-01T18:14:33Z", "updated_at": "2026-11-01T21:27:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Method for Independent Estimation of the False Localization Rate for Phosphoproteomics.", "doi": "10.1021/acs.jproteome.1c00827", "pmid": "35640880", "authors": ["Kerry A Ramsbottom", "Ananth Prakash", "Yasset Perez Riverol", "Oscar Martin Camacho", "Maria-Jesus Martin", "Juan Antonio Vizcaíno", "Eric W Deutsch", "Andrew R Jones"], "journal": "Journal of proteome research", "year": 2022, "abstract": "Phosphoproteomic methods are commonly employed to identify and quantify phosphorylation sites on proteins. In recent years, various tools have been developed, incorporating scores or statistics related to whether a given phosphosite has been correctly identified or to estimate the global false localization rate (FLR) within a given data set for all sites reported. These scores have generally been calibrated using synthetic datasets, and their statistical reliability on real datasets is largely unknown, potentially leading to studies reporting incorrectly localized phosphosites, due to inadequate statistical control. In this work, we develop the concept of scoring modifications on a decoy amino acid, that is, one that cannot be modified, to allow for independent estimation of global FLR. We test a variety of amino acids, on both synthetic and real data sets, demonstrating that the selection can make a substantial difference to the estimated global FLR. We conclude that while several different amino acids might be appropriate, the most reliable FLR results were achieved using alanine and leucine as decoys. We propose the use of a decoy amino acid to control false reporting in the literature and in public databases that re-distribute the data. Data are available via ProteomeXchange with identifier PXD028840.", "claims": [{"id": "claim-method", "statement": "We used the identification of phosphorylated decoy amino acids (e.g. worked example follows for alanine, pA), as these are known to be false localizations and can therefore be used to estimate the FLR.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35640880", "locator": "sections[6] \"Decoy FLR Method\" paragraph 2", "quote": "We used the identification of phosphorylated decoy amino acids (e.g. worked example follows for alanine, pA), as these are known to be false localizations and can therefore be used to estimate the FLR."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available via ProteomeXchange with identifier PXD028840.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35640880", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with identifier PXD028840."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "", "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:35640880"], "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:PXD000138"], "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:PXD000138"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35640880", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1021/acs.jproteome.1c00827", "sha256": "sha256:c4be5d82872ad0023a9f0342ca90b2ef953650d4bbbce534a4b8f22bdb9766d5", "bytes": 60125, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1021/acs.jproteome.1c00827", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9251759", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD000138", "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=PXD000138", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD000138", "version": null, "note": "Data are available via ProteomeXchange with identifier PXD028840.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange with identifier PXD028840.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Synthetic (Phospho)Peptide Library", "resolution_checked_at": "2026-11-01T18:06:51Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD000612", "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=PXD000612", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD000612", "version": null, "note": "Data are available via ProteomeXchange with identifier PXD028840.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange with identifier PXD028840.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Ultra-deep human phosphoproteome reveals different regulatory nature of Tyr and Ser/Thr-based signaling", "resolution_checked_at": "2026-11-01T18:06:51Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD007058", "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=PXD007058", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD007058", "version": null, "note": "Data are available via ProteomeXchange with identifier PXD028840.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange with identifier PXD028840.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "C4PR_LIV Evaluation of Parameters for Confident Phosphorylation Site Localization using an Orbitrap Fusion Tribrid Mass Spectrometer", "resolution_checked_at": "2026-11-01T17:30:50Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD008355", "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=PXD008355", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD008355", "version": null, "note": "Data are available via ProteomeXchange with identifier PXD028840.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange with identifier PXD028840.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "A systematic phosphoproteome screen to identify targets of the Target of Rapamycin (TOR) kinase in Arabidopsis thaliana", "resolution_checked_at": "2026-11-01T18:06:51Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD028840", "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=PXD028840", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD028840", "version": null, "note": "Data are available via ProteomeXchange with identifier PXD028840.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange with identifier PXD028840.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "A method for independent estimation of false localisation rate for phosphoproteomics", "resolution_checked_at": "2026-11-01T18:06:51Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD000138 not downloaded", "asset:data:geo:PXD000138 licence not read", "asset:data:geo:PXD000612 not downloaded", "asset:data:geo:PXD000612 licence not read", "asset:data:geo:PXD007058 not downloaded", "asset:data:geo:PXD007058 licence not read", "asset:data:geo:PXD008355 not downloaded", "asset:data:geo:PXD008355 licence not read", "asset:data:geo:PXD028840 not downloaded", "asset:data:geo:PXD028840 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "decoy FLR method", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We used the identification of phosphorylated decoy amino acids (e.g. worked example follows for alanine, pA), as these are known to be false localizations and can therefore be used to estimate the FLR."}}], "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 (decoy FLR method), 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": ["PXD028840", "PXD007058", "PXD000138", "PXD008355", "PXD000612"], "resolved_accessions": ["PXD028840", "PXD007058", "PXD000138", "PXD008355", "PXD000612"], "statements": ["Data are available via ProteomeXchange with identifier PXD028840."], "basis": "The paper names PXD028840, PXD007058, PXD000138, PXD008355, PXD000612 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:35640880", "data:geo:PXD000138"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD000138"]}, "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": "2026-11-01T17:47:54Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15745, "completion_tokens": 2089, "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:35640880", "type": "paper", "label": "pmid:35640880"}, {"id": "source:pmid:35640880", "type": "manuscript", "label": "PMID 35640880 full text"}, {"id": "data:geo:PXD000138", "type": "dataset", "label": "GEO PXD000138"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35640880", "type": "paper", "label": "pmid:35640880"}, {"id": "source:pmid:35640880", "type": "manuscript", "label": "PMID 35640880 full text"}, {"id": "data:geo:PXD000138", "type": "dataset", "label": "GEO PXD000138"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35640880", "type": "extraction", "used": ["source:pmid:35640880"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD000138", "type": "accession_resolution", "used": ["data:geo:PXD000138"], "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:35640880", "parent_hash": "sha256:355954e96c93ef34ac919d456d8496f7802e1533cfecaafdfc16b68850dd60a6", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD000138 licence not read", "asset:data:geo:PXD000138 not downloaded", "asset:data:geo:PXD000612 licence not read", "asset:data:geo:PXD000612 not downloaded", "asset:data:geo:PXD007058 licence not read", "asset:data:geo:PXD007058 not downloaded", "asset:data:geo:PXD008355 licence not read", "asset:data:geo:PXD008355 not downloaded", "asset:data:geo:PXD028840 licence not read", "asset:data:geo:PXD028840 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]}