Acetic acid is a superior ion pairing modifier for sub-nanogram and single cell proteomics.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37577694", "kind": "science-record", "revision": 3, "content_hash": "sha256:b35ab41e78544aef7a8535c0fe3c336c90bad776150ac8479c984ad7d73f7927", "created_at": "2026-11-01T19:02:22Z", "updated_at": "2026-11-01T21:31:21Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Acetic acid is a superior ion pairing modifier for sub-nanogram and single cell proteomics.", "doi": "10.1101/2023.08.01.551522", "pmid": "37577694", "authors": ["Colten D Eberhard", "Benjamin C Orsburn"], "journal": "bioRxiv : the preprint server for biology", "year": 2024, "abstract": "A recent study demonstrated a substantial increase in peptide signal and corresponding proteome coverage when employing 0.5% acetic acid (AA) as the ion pairing modifier in place of the 0.1% formic acid traditionally used in shotgun proteomics. In this study, we investigated the effect of modifier in the context of sub-nanogram and single cell proteomics (SCP). We first evaluated a tryptic digest standard down to 20 picograms total load on column on a TIMSTOF SCP system. In line with the previous results, we observed a signal increase when using AA, leading to increased proteome coverage at every peptide load assessed. Relative improvements were more apparent at lower concentrations, with a 20 picogram peptide digest demonstrating a striking 1.8-fold increase to over 2,000 protein groups identified in a 30 minute analysis. Furthermore, we find that this increase in signal can be leveraged to reduce ramp times, leading to 1.7x more scans across each peak and improvements in quantification as measured by %CVs. When evaluating single cancer cells, approximately 13% more peptide groups were identified on average when employing AA in the place of FA. All vendor raw and processed data are available through ProteomeXchange as PXD046002 and PXD051590.", "claims": [{"id": "claim-method", "statement": "It should be noted that a two-tailed t-test still found this increase to be significant even when the two lowest cells analyzed with FA buffer were removed from consideration (data not shown).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37577694", "locator": "sections[10] \"AA increases protein sequence coverage in isolated single human cells\" paragraph 2", "quote": "It should be noted that a two-tailed t-test still found this increase to be significant even when the two lowest cells analyzed with FA buffer were removed from consideration (data not shown)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All vendor raw and processed data are available through ProteomeXchange as PXD046002 and PXD051590.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37577694", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "All vendor raw and processed data are available through ProteomeXchange as PXD046002 and PXD051590."}], "state": "complete"}, {"id": "claim-target-result", "statement": "In line with the previous results, we observed a signal increase when using AA, leading to increased proteome coverage at every peptide load assessed.", "kind": "quantitative", "target": {"value": 1.8, "unit": "fold change", "tolerance": null, "source": "Relative improvements were more apparent at lower concentrations, with a 20 picogram peptide digest demonstrating a striking 1.8-fold increase to over 2,000 protein groups identified in a 30 minute analysis."}, "evidence": [{"asset": "source:pmid:37577694", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "In line with the previous results, we observed a signal increase when using AA, leading to increased proteome coverage at every peptide load assessed."}, {"asset": "source:pmid:37577694", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Relative improvements were more apparent at lower concentrations, with a 20 picogram peptide digest demonstrating a striking 1.8-fold increase to over 2,000 protein groups identified in a 30 minute analysis."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "In line with the previous results, we observed a signal increase when using AA, leading to increased proteome coverage at every peptide load assessed.", "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:37577694"], "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:PXD046002"], "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:PXD046002"], "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:37577694", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1101/2023.08.01.551522", "sha256": "sha256:7847f376c2db5fa844076cb7c8c745065a1f46e1d128f215f05d130727c59279", "bytes": 17890, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1101/2023.08.01.551522", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10418182", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD046002", "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=PXD046002", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD046002", "version": null, "note": "All vendor raw and processed data are available through ProteomeXchange as PXD046002 and PXD051590.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All vendor raw and processed data are available through ProteomeXchange as PXD046002 and PXD051590.", "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": "2026-11-01T19:09:50Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD051590", "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=PXD051590", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD051590", "version": null, "note": "All vendor raw and processed data are available through ProteomeXchange as PXD046002 and PXD051590.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All vendor raw and processed data are available through ProteomeXchange as PXD046002 and PXD051590.", "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": "2026-11-01T19:09:50Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:PXD046002 not downloaded", "asset:data:geo:PXD046002 licence not read", "asset:data:geo:PXD051590 not downloaded", "asset:data:geo:PXD051590 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "two-tailed t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "It should be noted that a two-tailed t-test still found this increase to be significant even when the two lowest cells analyzed with FA buffer were removed from consideration (data not shown)."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": null, "expected_value": 1.8, "unit": "fold change", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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": "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 (two-tailed t-test), 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": ["PXD046002", "PXD051590"], "resolved_accessions": [], "statements": ["All vendor raw and processed data are available through ProteomeXchange as PXD046002 and PXD051590."], "basis": "The paper names PXD046002, PXD051590, but the accession does not resolve in the repository (not_in_proteomexchange, 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:37577694", "data:geo:PXD046002"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD046002"]}, "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": "2026-11-01T18:50:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 5855, "completion_tokens": 1346, "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:37577694", "type": "paper", "label": "pmid:37577694"}, {"id": "source:pmid:37577694", "type": "manuscript", "label": "PMID 37577694 full text"}, {"id": "data:geo:PXD046002", "type": "dataset", "label": "GEO PXD046002"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37577694", "type": "paper", "label": "pmid:37577694"}, {"id": "source:pmid:37577694", "type": "manuscript", "label": "PMID 37577694 full text"}, {"id": "data:geo:PXD046002", "type": "dataset", "label": "GEO PXD046002"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37577694", "type": "extraction", "used": ["source:pmid:37577694"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD046002", "type": "accession_resolution", "used": ["data:geo:PXD046002"], "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:37577694", "parent_hash": "sha256:06c088af40f67aae0284f1af7b4e908b8b0e20dcdd641dc030e453b522e8b22a", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD046002 licence not read", "asset:data:geo:PXD046002 not downloaded", "asset:data:geo:PXD051590 licence not read", "asset:data:geo:PXD051590 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_unresolved"]}