Evaluation of PAC and FASP Performance: DIA-Based Quantitative Proteomic Analysis.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38791181", "kind": "science-record", "revision": 3, "content_hash": "sha256:ed27af697927820800f0497b1e85b3745052bf8c1b10fb6ecffb6e2fd09af1b5", "created_at": "2026-11-01T19:20:45Z", "updated_at": "2026-11-01T21:33:09Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Evaluation of PAC and FASP Performance: DIA-Based Quantitative Proteomic Analysis.", "doi": "10.3390/ijms25105141", "pmid": "38791181", "authors": ["Maria Stella Murfuni", "Licia E Prestagiacomo", "Annarita Giuliano", "Caterina Gabriele", "Sara Signoretti", "Giovanni Cuda", "Marco Gaspari"], "journal": "International journal of molecular sciences", "year": 2024, "abstract": "The aim of this study was to compare filter-aided sample preparation (FASP) and protein aggregation capture (PAC) starting from a three-species protein mix (Human, Soybean and Pisum sativum) and two different starting amounts (1 and 10 µg). Peptide mixtures were analyzed by data-independent acquisition (DIA) and raw files were processed by three commonly used software: Spectronaut, MaxDIA and DIA-NN. Overall, the highest number of proteins (mean value of 5491) were identified by PAC (10 µg), while the lowest number (4855) was identified by FASP (1 µg). The latter experiment displayed the worst performance in terms of both specificity (0.73) and precision (0.24). Other tested conditions showed better diagnostic accuracy, with specificity values of 0.95-0.99 and precision values between 0.61 and 0.86. In order to provide guidance on the data analysis pipeline, the accuracy diagnostic of three software was investigated: (i) the highest sensitivity was obtained with Spectronaut (median of 0.67) highlighting the ability of Spectronaut to quantify low-abundance proteins, (ii) the best precision value was obtained by MaxDIA (median of 0.84), but with a reduced number of identifications compared to Spectronaut and DIA-NN data, and (iii) the specificity values were similar (between 0.93 and 0.99). The data are available on ProteomeXchange with the identifier PXD044349.", "claims": [{"id": "claim-method", "statement": "Significantly different proteins between PmixA and PmixB were detected by Student’s t-test corrected for multiple hypothesis testing with a Permutation-based FDR equal to 0.05.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38791181", "locator": "sections[17] \"3.9. Statistical Analysis\" paragraph 3", "quote": "Significantly different proteins between PmixA and PmixB were detected by Student’s t-test corrected for multiple hypothesis testing with a Permutation-based FDR equal to 0.05."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics data have been deposited in the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via PRIDE partner repository with the dataset identifier PXD044349. Reviewer account details: (i) reviewer_pxd044349@ebi.ac.uk (username) and (ii) cI1g0Yjw (password).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38791181", "locator": "sections[24] \"Data Availability Statement\" paragraph 2", "quote": "The mass spectrometry proteomics data have been deposited in the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via PRIDE partner repository with the dataset identifier PXD044349. Reviewer account details: (i) reviewer_pxd044349@ebi.ac.uk (username) and (ii) cI1g0Yjw (password)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Overall, the highest number of proteins (mean value of 5491) were identified by PAC (10 µg), while the lowest number (4855) was identified by FASP (1 µg).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38791181", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Overall, the highest number of proteins (mean value of 5491) were identified by PAC (10 µg), while the lowest number (4855) was identified by FASP (1 µg)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Overall, the highest number of proteins (mean value of 5491) were identified by PAC (10 µg), while the lowest number (4855) was identified by FASP (1 µg).", "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:38791181"], "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:PXD044349"], "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:PXD044349"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38791181", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/ijms25105141", "sha256": "sha256:262ad440dd6fc3c6d76f5d768271020e94db5b147645c2a731e1da4d91fbd9f6", "bytes": 42911, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/ijms25105141", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11121386", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD044349", "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=PXD044349", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD044349", "version": null, "note": "The mass spectrometry proteomics data have been deposited in the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via PRIDE partner repository with the dataset identifier PXD044349. Reviewer account details: (i) reviewer_pxd044349@ebi.ac.uk (username) and (ii) cI1g0Yjw (password).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data have been deposited in the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via PRIDE partner repository with the dataset identifier PXD044349. Reviewer account details: (i) reviewer_pxd044349@ebi.ac.uk (username) and (ii) cI1g0Yjw (password).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Evaluation of PAC and FASP performance", "resolution_checked_at": "2026-11-01T20:16:17Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD044349 not downloaded", "asset:data:geo:PXD044349 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Student’s t-test corrected for multiple hypothesis testing with a permutation-based FDR", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Significantly different proteins between PmixA and PmixB were detected by Student’s t-test corrected for multiple hypothesis testing with a Permutation-based FDR equal to 0.05."}}], "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 (Student’s t-test corrected for multiple hypothesis testing with a permutation-based FDR), 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": ["PXD044349"], "resolved_accessions": ["PXD044349"], "statements": ["The mass spectrometry proteomics data have been deposited in the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via PRIDE partner repository with the dataset identifier PXD044349. Reviewer account details: (i) reviewer_pxd044349@ebi.ac.uk (username) and (ii) cI1g0Yjw (password)."], "basis": "The paper names PXD044349 in ProteomeXchange Consortium via 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:38791181", "data:geo:PXD044349"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD044349"]}, "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": "2026-11-01T19:19:34Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13073, "completion_tokens": 1028, "cached_tokens": 128}}, "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:38791181", "type": "paper", "label": "pmid:38791181"}, {"id": "source:pmid:38791181", "type": "manuscript", "label": "PMID 38791181 full text"}, {"id": "data:geo:PXD044349", "type": "dataset", "label": "GEO PXD044349"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38791181", "type": "paper", "label": "pmid:38791181"}, {"id": "source:pmid:38791181", "type": "manuscript", "label": "PMID 38791181 full text"}, {"id": "data:geo:PXD044349", "type": "dataset", "label": "GEO PXD044349"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38791181", "type": "extraction", "used": ["source:pmid:38791181"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD044349", "type": "accession_resolution", "used": ["data:geo:PXD044349"], "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:38791181", "parent_hash": "sha256:8cb6a077813db24f0551972a5d8cfb6f65486c14d230f66bbf8bd678e922ee19", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD044349 licence not read", "asset:data:geo:PXD044349 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]}