Deep Single-Shot NanoLC-MS Proteome Profiling with a 1500 Bar UHPLC System, Long Fully Porous Columns, and HRAM MS.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36068014", "kind": "science-record", "revision": 2, "content_hash": "sha256:656c0002db166a67803e64f4f7f496ad7edfbdbd45499aea2eb7cd3d5ec62a65", "created_at": "2026-11-01T18:15:16Z", "updated_at": "2026-11-01T19:00:09Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Deep Single-Shot NanoLC-MS Proteome Profiling with a 1500 Bar UHPLC System, Long Fully Porous Columns, and HRAM MS.", "doi": "10.1021/acs.jproteome.2c00270", "pmid": "36068014", "authors": ["Runsheng Zheng", "Karel Stejskal", "Christopher Pynn", "Karl Mechtler", "Alexander Boychenko"], "journal": "Journal of proteome research", "year": 2022, "abstract": "This study demonstrates how the latest ultrahigh-performance liquid chromatography (UHPLC) technology can be combined with high-resolution accurate-mass (HRAM) mass spectrometry (MS) and long columns packed with fully porous particles to improve bottom-up proteomics analysis with nanoflow liquid chromatography-mass spectrometry (nanoLC-MS) methods. The increased back pressures from the UHPLC system enabled the use of 75 μm I.D. × 75 cm columns packed with 2 μm particles at a typical 300 nL/min flow rate as well as elevated and reduced flow rates. The constant pressure pump operation at 1500 bar reduced sample loading and column washing/equilibration stages and overall overhead time, which maximizes MS utilization time. The versatility of flow rate optimization to balance the sensitivity, throughput with sample loading amount, and capability of using longer gradients contributes to a greater number of peptide and protein identifications for single-shot bottom-up proteomics experiments. The routine proteome profiling and precise quantification of >7000 proteins with single-shot nanoLC-MS analysis open possibilities for large-scale discovery studies with a deep dive into the protein level alterations. Data are available via ProteomeXchange with identifier PXD035665.", "claims": [{"id": "claim-data-access", "statement": "Data are available via ProteomeXchange with identifier PXD035665.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36068014", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with identifier PXD035665."}], "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:36068014"], "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:PXD035665"], "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:PXD035665"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36068014", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1021/acs.jproteome.2c00270", "sha256": "sha256:b330911d93e909ebd7178b6a15390ec1ab2348c5b700d4feffa750dba3ad6f76", "bytes": 27151, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1021/acs.jproteome.2c00270", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9552226", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD035665", "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=PXD035665", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD035665", "version": null, "note": "Data are available via ProteomeXchange with identifier PXD035665.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange with identifier PXD035665.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Deep single-shot nanoLCMS proteome profiling with 1500 bar UHPLC system, long fully porous columns, and HRAM MS", "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:PXD035665 not downloaded", "asset:data:geo:PXD035665 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": ["PXD035665"], "resolved_accessions": ["PXD035665"], "statements": ["Data are available via ProteomeXchange with identifier PXD035665."], "basis": "The paper names PXD035665 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:36068014", "data:geo:PXD035665"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD035665"]}, "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": "2026-11-01T18:03:47Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8651, "completion_tokens": 884, "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:36068014", "type": "paper", "label": "pmid:36068014"}, {"id": "source:pmid:36068014", "type": "manuscript", "label": "PMID 36068014 full text"}, {"id": "data:geo:PXD035665", "type": "dataset", "label": "GEO PXD035665"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36068014", "type": "paper", "label": "pmid:36068014"}, {"id": "source:pmid:36068014", "type": "manuscript", "label": "PMID 36068014 full text"}, {"id": "data:geo:PXD035665", "type": "dataset", "label": "GEO PXD035665"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36068014", "type": "extraction", "used": ["source:pmid:36068014"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD035665", "type": "accession_resolution", "used": ["data:geo:PXD035665"], "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:36068014", "parent_hash": "sha256:45ef80a6626ec15528238668c9d092ca2b5b8f98990fda6b956ac4b332c0606e", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:PXD035665 licence not read", "asset:data:geo:PXD035665 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ed with high-resolution accurate-mass (HRAM) mass spectrometry (MS) and long columns packed with fully poro", "analysis with nanoflow liquid chromatography-mass spectrometry (nanoLC-MS) methods. The increased back pres", "fully porous particles to improve bottom-up proteomics analysis with nanoflow liquid chromatography", "in identifications for single-shot bottom-up proteomics experiments. The routine proteome profiling"], "order_basis": "paper_text_order:231", "id": "assay:1"}, {"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": ["imental Procedures Sample Preparation Pierce HeLa Digest/PRTC Standard (Thermo Fisher Scientif", "subsequently transferred to another vial of HeLa Digest/PRTC Standard, which was again sonica", "ce a final sample concentration of 400 ng/μL HeLa containing 200 fmol/μL PRTC. Data Processing"], "order_basis": "paper_text_order:1408", "id": "assay:2"}]}