Alternative Ion-Pairing Modifiers Should Be Investigated in Low-Input and Single-Cell Proteomics.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41277810", "kind": "science-record", "revision": 2, "content_hash": "sha256:38538493b74b9e3c4eb80c1a6488dced3c716f3514c085da641542c040f75355", "created_at": "2026-11-01T20:31:18Z", "updated_at": "2026-11-01T21:36:05Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Alternative Ion-Pairing Modifiers Should Be Investigated in Low-Input and Single-Cell Proteomics.", "doi": "10.1021/acs.jproteome.5c00930", "pmid": "41277810", "authors": ["Colten D Eberhard", "Cameron Braswell", "Benjamin C Orsburn"], "journal": "Journal of proteome research", "year": 2025, "abstract": "A recent study demonstrated a substantial increase in the 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. Given the strictly limited material and counterintuitive observations by others in the emerging field of single-cell proteomics, we chose to investigate this alternative modifier in the analysis of subnanogram proteome dilutions. When digest standards as low as 20 pg total load on the column were evaluated, AA led to increased proteome coverage at every peptide load assessed. Relative improvements were more apparent at lower concentrations, with a 20 pg peptide digest demonstrating a striking 1.8-fold increase to over 2000 protein groups identified in a 30 min analysis. Furthermore, we find that this increase in signal can be leveraged to reduce ramp times, leading to 1.7× more scans across each peak and improvements in quantification, as measured by %CVs. These results can be reproduced on multiple trapped ion mobility instruments. When evaluating single cancer cells, approximately 13% more peptide groups were identified on average when employing AA in the place of FA. These results suggest that ion pairing modifiers and other additives warrant re-evaluation in the context of low-input and single-cell proteomics. All vendor raw and processed data are available through ProteomeXchange as PXD046002 and PXD051590.", "claims": [{"id": "claim-method", "statement": "Statistical analyses were performed using a two-tailed t-test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41277810", "locator": "sections[9] \"AA Improves Proteomic Coverage on Subnanogram Injections of Peptides\" paragraph 3", "quote": "Statistical analyses were performed using a two-tailed t-test."}], "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:41277810", "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": "When digest standards as low as 20 pg total load on the column were evaluated, AA led to increased proteome coverage at every peptide load assessed.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41277810", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "When digest standards as low as 20 pg total load on the column were evaluated, AA led to increased proteome coverage at every peptide load assessed."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "When digest standards as low as 20 pg total load on the column were evaluated, AA led 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:41277810"], "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:41277810", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1021/acs.jproteome.5c00930", "sha256": "sha256:1ec039b37f751a1a1da54c2f152af8e509822b0216062db939e7f98c4b31905f", "bytes": 28765, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1021/acs.jproteome.5c00930", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12687309", "source": "europe_pmc_fulltext", "coverage": "whole_body", "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": "Statistical analyses were performed using a two-tailed t-test."}}], "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": "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:41277810", "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": "2026-11-01T20:06:29Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8984, "completion_tokens": 1478, "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:41277810", "type": "paper", "label": "pmid:41277810"}, {"id": "source:pmid:41277810", "type": "manuscript", "label": "PMID 41277810 full text"}, {"id": "data:geo:PXD046002", "type": "dataset", "label": "GEO PXD046002"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41277810", "type": "paper", "label": "pmid:41277810"}, {"id": "source:pmid:41277810", "type": "manuscript", "label": "PMID 41277810 full text"}, {"id": "data:geo:PXD046002", "type": "dataset", "label": "GEO PXD046002"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41277810", "type": "extraction", "used": ["source:pmid:41277810"], "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:41277810", "parent_hash": "sha256:e4961971aa2c87e0b0e802694d38c0e2d8d21159017593f9b0ec52119a33ec14", "fork_of": null, "generation": 1}, "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"]}