Proteomic datasets of HeLa and SiHa cell lines acquired by DDA-PASEF and diaPASEF.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35198691", "kind": "science-record", "revision": 3, "content_hash": "sha256:b8559341de64b427dadfe089823a22ffb57af4315e11117226e3f4b73259211e", "created_at": "2026-11-01T17:36:57Z", "updated_at": "2026-11-01T18:58:20Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Proteomic datasets of HeLa and SiHa cell lines acquired by DDA-PASEF and diaPASEF.", "doi": "10.1016/j.dib.2022.107919", "pmid": "35198691", "authors": ["Zelu Huang", "Weijia Kong", "Bertrand Jernhan Wong", "Huanhuan Gao", "Tiannan Guo", "Xianming Liu", "Xiaoxian Du", "Limsoon Wong", "Wilson Wen Bin Goh"], "journal": "Data in brief", "year": 2022, "abstract": "We present four datasets on proteomics profiling of HeLa and SiHa cell lines associated with the research described in the paper \"PROTREC: A probability-based approach for recovering missing proteins based on biological networks\" [1]. Proteins in each cell line were acquired by two different data acquisition methods. The first was Data Dependent Acquisition-Parallel Accumulation Serial Fragmentation (DDA-PASEF) and the second was Parallel Accumulation-Serial Fragmentation combined with data-independent acquisition (diaPASEF) [2], [3]. Protein assembly was performed following search against the Swiss-Prot Human database using Peaks Studio for DDA datasets and Spectronaut for DIA datasets. The assembled result contains identified PSMs, peptides and proteins that are above threshold for each HeLa and SiHa sample. Coverage-wise, for DDA-PASEF, approximately 6,090 and 7,298 proteins were quantified for HeLa and SiHA sample, while13,339 and 8,773 proteins were quantified by diaPASEF for HeLa for SiHa sample, respectively. Consistency-wise, diaPASEF has fewer missing values (∼ 2%) compared to its DDA counterparts (∼5-7%). The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the iProX partner repository [4] with the dataset identifier PXD029773.", "claims": [{"id": "claim-data-access", "statement": "Repository name: ProteomeXchangeData identification number: PXD029773Direct URL to data: http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD029773", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35198691", "locator": "sections[1] \"Specifications Table\" paragraph 2", "quote": "Repository name: ProteomeXchangeData identification number: PXD029773Direct URL to data: http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD029773"}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:35198691"], "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": "blocked", "blocked_on": "data:accession_unresolved", "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:PXD029773"], "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:PXD029773"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_unresolved"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35198691", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2022.107919", "sha256": "sha256:d2f477f541ab8027dcc761de7ad5759a58f885ecf6cb1ef8a5a19b5aa9a4c4bf", "bytes": 20095, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2022.107919", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8844217", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD029773", "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=PXD029773", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD029773", "version": null, "note": "Repository name: ProteomeXchangeData identification number: PXD029773Direct URL to data: http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD029773", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Repository name: ProteomeXchangeData identification number: PXD029773Direct URL to data: http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD029773", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "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:PXD029773 not downloaded", "asset:data:geo:PXD029773 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": "data", "blocked_on": "data:accession_absent", "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": "R4", "reachable": false, "accessions": ["PXD029773"], "resolved_accessions": [], "statements": ["Repository name: ProteomeXchangeData identification number: PXD029773Direct URL to data: http://proteomecentral.proteomexchange.org/cgi/GetDataset?ID=PXD029773"], "basis": "The paper names PXD029773, but the accession does not resolve in the repository (not_in_proteomexchange), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:35198691", "data:geo:PXD029773"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD029773"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:35:22Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 6937, "completion_tokens": 1090, "cached_tokens": 256}}, "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:35198691", "type": "paper", "label": "pmid:35198691"}, {"id": "source:pmid:35198691", "type": "manuscript", "label": "PMID 35198691 full text"}, {"id": "data:geo:PXD029773", "type": "dataset", "label": "GEO PXD029773"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35198691", "type": "paper", "label": "pmid:35198691"}, {"id": "source:pmid:35198691", "type": "manuscript", "label": "PMID 35198691 full text"}, {"id": "data:geo:PXD029773", "type": "dataset", "label": "GEO PXD029773"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35198691", "type": "extraction", "used": ["source:pmid:35198691"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD029773", "type": "accession_resolution", "used": ["data:geo:PXD029773"], "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:35198691", "parent_hash": "sha256:dff15b35a08181f6b05b50d7a3031e6ce5e4af63da825f7c4ec3dc46a691be31", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD029773 licence not read", "asset:data:geo:PXD029773 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_unresolved"], "assays": [{"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Proteomic datasets of HeLa and SiHa cell lines acquired by DDA-PASEF an", "ent four datasets on proteomics profiling of HeLa and SiHa cell lines associated with the rese", "d proteins that are above threshold for each HeLa and SiHa sample. Coverage-wise, for DDA-PASE", "6,090 and 7,298 proteins were quantified for HeLa and SiHA sample, while13,339 and 8,773 prote"], "order_basis": "paper_text_order:0", "id": "assay:1"}]}