RawBeans: A Simple, Vendor-Independent, Raw-Data Quality-Control Tool.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33657803", "kind": "science-record", "revision": 5, "content_hash": "sha256:f19fc4eeae0331eb83f09b381c6730676b2e8396e7b572c8981e30c81247c758", "created_at": "2026-11-01T15:41:26Z", "updated_at": "2026-11-01T18:54:37Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "RawBeans: A Simple, Vendor-Independent, Raw-Data Quality-Control Tool.", "doi": "10.1021/acs.jproteome.0c00956", "pmid": "33657803", "authors": ["David Morgenstern", "Rotem Barzilay", "Yishai Levin"], "journal": "Journal of proteome research", "year": 2021, "abstract": "Every laboratory performing mass-spectrometry-based proteomics strives to generate high-quality data. Among the many factors that impact the outcome of any experiment in proteomics is the LC-MS system performance, which should be monitored within each specific experiment and also long term. This process is termed quality control (QC). We present an easy-to-use tool that rapidly produces a visual, HTML-based report that includes the key parameters needed to monitor the LC-MS system performance, with a focus on monitoring the performance within an experiment. The tool, named RawBeans, generates a report for individual files or for a set of samples from a whole experiment. We anticipate that it will help proteomics users and experts evaluate raw data quality independent of data processing. The tool is available at https://bitbucket.org/incpm/prot-qc/downloads. The mass-spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifier PXD022816.", "claims": [{"id": "claim-data-access", "statement": "The mass-spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifier PXD022816.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33657803", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The mass-spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifier PXD022816."}], "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:33657803"], "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:PXD021832"], "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:PXD021832"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33657803", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1021/acs.jproteome.0c00956", "sha256": "sha256:f85d862321f0c3a1b52c698b6bff48815f998aef3a0d7958718b35787ee65da9", "bytes": 18506, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1021/acs.jproteome.0c00956", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8041395", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD021832", "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=PXD021832", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD021832", "version": null, "note": "The mass-spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifier PXD022816.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass-spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifier PXD022816.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Proteomic approache of the response to iron-limited condition in Staphylococcus lugdunensis", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD022816", "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=PXD022816", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD022816", "version": null, "note": "The mass-spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifier PXD022816.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass-spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifier PXD022816.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "RawBeans: a simple, vendor independent, raw-data quality control tool", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD023653", "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=PXD023653", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD023653", "version": null, "note": "The mass-spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifier PXD022816.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass-spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifier PXD022816.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Elp2 mutations perturb the epitranscriptome and lead to a complex neurodevelopmental phenotype", "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:33657803:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:64bb133b22ff066317946c676734ba2b671e5e92daaebd38d5ebad7516669575", "bytes": 1624, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#tbl1", "version": null, "note": "List of the Tabs in the RawBeans HTML Report and a Brief Description of Each Tab", "structure": {"pmcid": "PMC8041395", "section_index": 3, "section_title": "Results", "row_count": 14, "column_count": 2}, "table": {"label": "Table 1", "caption": "List of the Tabs in the RawBeans HTML Report and a Brief Description of Each Tab", "rows": [["tab name", "explanation"], ["MS2 counts", "Number of triggered MS/MS spectra per raw file. It includes a test for peak splitting (tribrid instruments only)."], ["Top-N", "Number of triggered MS/MS events per data-dependent cycle, shown as histograms in Log10 scale."], ["Charge distribution", "Histograms of the precursor charge state based on the triggered MS/MS events."], ["Injection Time", "Histograms of MS/MS injection time in Log10 scale."], ["Retention Time vs TopN", "Graphs of the number of MS/MS events per data-dependent cycle versus the retention time per raw file."], ["Injection vs Retention", "MS1 injection time per retention time for each raw file."], ["Total Ion Current", "Sum of MS1 signals per raw file based on all full MS1 scans. Presented in linear scale."], ["MS2-intensities", "Graphs of the number of fragment ions versus the most intense fragment ion (in log10 scale)."], ["MS2 Precursor Ratio", "Binned ratios of the precursor ion to the next highest fragment ion intensity per MS/MS scan."], ["Triggered M/Z distribution", "Density plots of the precursor m/z based on the triggered MS/MS events."], ["FWHM", "Chromatographic full width at half-height. A crude measurement of peak width."], ["Peak Symmetry", "Chromatographic peak symmetry. A crude measurement to show global peak tailing."], ["Mass Deviation", "Mass error throughout the run time based on the masses entered in the GUI."]], "row_count": 14, "column_count": 2, "numeric_cells": 3, "header_rows": 1, "locator": "section[3]/table-wrap[1]#tbl1"}}], "gaps": ["asset:data:geo:PXD021832 not downloaded", "asset:data:geo:PXD021832 licence not read", "asset:data:geo:PXD022816 not downloaded", "asset:data:geo:PXD022816 licence not read", "asset:data:geo:PXD023653 not downloaded", "asset:data:geo:PXD023653 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": ["PXD022816", "PXD023653", "PXD021832"], "resolved_accessions": ["PXD022816", "PXD023653", "PXD021832"], "statements": ["The mass-spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the data set identifier PXD022816."], "basis": "The paper names PXD022816, PXD023653, PXD021832 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:33657803", "data:geo:PXD021832", "asset:table:pmid:33657803:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD021832"]}, "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": "2026-10-31T18:27:20Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 14268, "completion_tokens": 1139, "cached_tokens": 792}}, "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:33657803", "type": "paper", "label": "pmid:33657803"}, {"id": "source:pmid:33657803", "type": "manuscript", "label": "PMID 33657803 full text"}, {"id": "data:geo:PXD021832", "type": "dataset", "label": "GEO PXD021832"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33657803", "type": "paper", "label": "pmid:33657803"}, {"id": "source:pmid:33657803", "type": "manuscript", "label": "PMID 33657803 full text"}, {"id": "data:geo:PXD021832", "type": "dataset", "label": "GEO PXD021832"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33657803", "type": "extraction", "used": ["source:pmid:33657803"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD021832", "type": "accession_resolution", "used": ["data:geo:PXD021832"], "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:33657803", "parent_hash": "sha256:658ce9d67222b4f6ddd206654cdb87277d9a2ee7b13436031f9acf3b45ba57eb", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:PXD021832 licence not read", "asset:data:geo:PXD021832 not downloaded", "asset:data:geo:PXD022816 licence not read", "asset:data:geo:PXD022816 not downloaded", "asset:data:geo:PXD023653 licence not read", "asset:data:geo:PXD023653 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "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": 0.77, "evidence": ["Materials and Methods A HeLa digestion standard (Pierce Thermo, USA) was"], "order_basis": "paper_text_order:1106", "id": "assay:1"}]}