{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30726203", "kind": "science-record", "revision": 7, "content_hash": "sha256:4aea0555b7f23f31ee40ed9535b430053348b735c9968fcacd5d9d52a69e2af9", "created_at": "2026-11-01T15:40:42Z", "updated_at": "2026-11-01T21:21:58Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Reprogramming of Trypanosoma cruzi metabolism triggered by parasite interaction with the host cell extracellular matrix.", "doi": "10.1371/journal.pntd.0007103", "pmid": "30726203", "authors": ["Eliciane C Mattos", "Gisele Canuto", "Nubia C Manchola", "Rubens D M Magalhães", "Thomas W M Crozier", "Douglas J Lamont", "Marina F M Tavares", "Walter Colli", "Michael A J Ferguson", "Maria Júlia M Alves"], "journal": "PLoS neglected tropical diseases", "year": 2019, "abstract": "Trypanosoma cruzi, the etiological agent of Chagas' disease, affects 8 million people predominantly living in socioeconomic underdeveloped areas. T. cruzi trypomastigotes (Ty), the classical infective stage, interact with the extracellular matrix (ECM), an obligatory step before invasion of almost all mammalian cells in different tissues. Here we have characterized the proteome and phosphoproteome of T. cruzi trypomastigotes upon interaction with ECM (MTy) and the data are available via ProteomeXchange with identifier PXD010970. Proteins involved with metabolic processes (such as the glycolytic pathway), kinases, flagellum and microtubule related proteins, transport-associated proteins and RNA/DNA binding elements are highly represented in the pool of proteins modified by phosphorylation. Further, important metabolic switches triggered by this interaction with ECM were indicated by decreases in the phosphorylation of hexokinase, phosphofructokinase, fructose-2,6-bisphosphatase, phosphoglucomutase, phosphoglycerate kinase in MTy. Concomitantly, a decrease in the pyruvate and lactate and an increase of glucose and succinate contents were detected by GC-MS. These observations led us to focus on the changes in the glycolytic pathway upon binding of the parasite to the ECM. Inhibition of hexokinase, pyruvate kinase and lactate dehydrogenase activities in MTy were observed and this correlated with the phosphorylation levels of the respective enzymes. Putative kinases involved in protein phosphorylation altered upon parasite incubation with ECM were suggested by in silico analysis. Taken together, our results show that in addition to cytoskeletal changes and protease activation, a reprogramming of the trypomastigote metabolism is triggered by the interaction of the parasite with the ECM prior to cell invasion and differentiation into amastigotes, the multiplicative intracellular stage of T. cruzi in the vertebrate host.", "claims": [{"id": "claim-method", "statement": "Statistical analysis for validation of the results was performed by T Student test (two-tail, 95%).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30726203", "locator": "sections[11] \"Proteome and Phosphoproteome data analysis\" paragraph 2", "quote": "Statistical analysis for validation of the results was performed by T Student test (two-tail, 95%)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics and phosphoproteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [74] partner repository with the dataset identifier PXD010970.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30726203", "locator": "sections[33] \"Acknowledgments\" paragraph 2", "quote": "The mass spectrometry proteomics and phosphoproteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [74] partner repository with the dataset identifier PXD010970."}], "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:30726203"], "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:PXD010970"], "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:PXD010970"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30726203", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pntd.0007103", "sha256": "sha256:182b0494ac0c56339cc48f99c65c21ebe0f196e0ffa9355a7fa4a53fbbef1efb", "bytes": 82915, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pntd.0007103", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6380580", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD010970", "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=PXD010970", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD010970", "version": null, "note": "The mass spectrometry proteomics and phosphoproteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [74] partner repository with the dataset identifier PXD010970.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics and phosphoproteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [74] partner repository with the dataset identifier PXD010970.", "access_statement_kind": "repository_route_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Reprograming of Trypanosoma cruzi metabolism triggered by parasite interaction with the host cell extracellular matrix", "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:30726203:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6ddee33e84a617750ac5d71379135544481d2120176c323d75c36e3b85f546aa", "bytes": 3206, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[26]/table-wrap[1]#pntd.0007103.t001", "version": null, "note": "Identification of metabolic enzymes modified by phosphorylation after incubation of trypomastigotes with ECM for 120 min.Complete information for each phosphopeptide is shown in S2 Table.", "structure": {"pmcid": "PMC6380580", "section_index": 26, "section_title": "Quantitative proteome and phosphoproteome of T. cruzi trypomastigotes", "row_count": 17, "column_count": 9}, "table": {"label": "Table 1", "caption": "Identification of metabolic enzymes modified by phosphorylation after incubation of trypomastigotes with ECM for 120 min.Complete information for each phosphopeptide is shown in S2 Table.", "rows": [["Phosphopeptide", "TriTryp ID", "Protein Name", "Ratio MTy/Ty", "p-value", "Phospho-Residue", "Putative kinase", "Putative phospho-peptide", "Kinase Score"], ["vVRsHAAPLNEVTQEDLK", "TcCLB.506699.34", "6-phospho-1-fructokinase (pseudogene); putative", "0.711441246", "0.033051", "4S", "Other/WEE/Myt1/PKMYT1", "****VVRSHAAPLNE", "5.583"], ["sVLSSSQsSRPSATDSTLNVLTPLLDNYTIPITR", "TcCLB.508569.130", "6-phosphofructo-2-kinase/fructose-2;6-biphosphatase; putative", "0.783549259", "0.032736", "8S", "CAMK/CAMKL/QIK/SIK1", "SVLSSSQSSRPSATD", "4.074"], ["rIEYLTEVYSTLSStCQSPGGPSDDEVTLGDVSR", "TcCLB.508569.130", "6-phosphofructo-2-kinase/fructose-2;6-biphosphatase; putative", "0.730889744", "0.006718", "15T", "CK1/VRK/VRK2", "VYSTLSSTCQSPGGP", "5.225"], ["sVLSSSQsSRPSATDSTLNVLTPLLDNYTIPITR", "TcCLB.508569.130", "6-phosphofructo-2-kinase/fructose-2;6-biphosphatase; putative", "0.783549259", "0.032736", "1S", "TKL/STKR/STKR1/BMPR1B", "*******SVLSSSQS", "5.158"], ["sVLSsSQSSRPSATDSTLNVLTPLLDNYTIPITR", "TcCLB.508569.130", "6-phosphofructo-2-kinase/fructose-2;6-biphosphatase; putative", "0.67076967", "0.028006", "1S", "TKL/STKR/STKR1/BMPR1B", "*******SVLSSSQS", "5.158"], ["sVLSsSQSSRPSATDSTLNVLTPLLDNYTIPITR", "TcCLB.508569.130", "6-phosphofructo-2-kinase/fructose-2;6-biphosphatase; putative", "0.67076967", "0.028006", "5S", "TKL/STKR/STKR1/TGFbR1", "***SVLSSSQSSRPS", "5.333"], ["sSSVDyTQDTPLFALSPVDGR", "TcCLB.503855.30", "adenylosuccinate lyase; putative (ADSL)", "2.15819457", "0.045825", "6Y", "TK/Src/SrcA/YES", "**SSSVDYTQDTPLF", "4.044"], ["sSSVDyTQDTPLFALSPVDGR", "TcCLB.503855.30", "adenylosuccinate lyase; putative (ADSL)", "2.15819457", "0.045825", "1S", "TKL/STKR/STKR1/TGFbR1", "*******SSSVDYTQ", "5.333"], ["gFSCQPVEGAmyAFPTIELPEK", "TcCLB.506529.430", "alanine aminotransferase; putative;", "0.792580123", "0.027477", "12Y", "TK/Eph/EphB1", "QPVEGAMYAFPTIEL", "10.317"], ["tVPLGFTFsFPTEQK", "TcCLB.508951.20", "hexokinase; putative", "0.760998922", "0.000207", "9S", "CAMK/CAMKL/AMPK/AMPKA2", "VPLGFTFSFPTEQK*", "9.162"], ["tVPLGFTFsFPTEQK", "TcCLB.508951.20", "hexokinase; putative", "0.760998922", "0.000207", "1T", "TKL/MLK/ILK/ILK", "*******TVPLGFTF", "3.003"], ["tVPLGFtFSFPTEQK", "TcCLB.508951.20", "hexokinase; putative", "0.566939414", "0.02174", "1T", "TKL/MLK/ILK/ILK", "*******TVPLGFTF", "3.003"], ["aDGtPVPIGFTIMQTLEQHVR", "TcCLB.510215.10", "NADH-dependent fumarate reductase; putative", "1.514693923", "0.041197", "4T", "CMGC/MAPK/JNK/JNK2", "****ADGTPVPIGFT", "31.509"], ["gAFILTAsHNPGGPEEDFGIK", "TcCLB.511911.130", "phosphoglucomutase", "0.743481685", "0.012082", "8S", "CK1/VRK/VRK2", "GAFILTASHNPGGPE", "5.225"], ["gVTmAAAAACGDDsVPGYEAGATLKPVAER", "TcCLB.511419.40", "phosphoglycerate kinase; putative", "0.692608695", "0.014714", "14S", "AGC/GRK/BARK/BARK1", "AAACGDDSVPGYEAG", "5.269"], ["iDPLQVDHLmHPNIEPGAAKsNKPIGK", "TcCLB.510101.140", "pyruvate phosphate dikinase; putative", "0.556518184", "0.014326", "21S", "Other/PEK/HRI/EIF2AK1", "IEPGAAKSNKPIGK*", "4.658"]], "row_count": 17, "column_count": 9, "numeric_cells": 86, "header_rows": 1, "locator": "section[26]/table-wrap[1]#pntd.0007103.t001"}}, {"id": "asset:table:pmid:30726203:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:68c2f32319a55569ed04f2d0a1b3f6557c10bd82151cd53695070fa31d180b8d", "bytes": 4167, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[29]/table-wrap[1]#pntd.0007103.t002", "version": null, "note": "Identification of kinases and phosphatases modified by phosphorylation after incubation of trypomastigotes with ECM for 120 min.Complete information is shown in S2 Table.", "structure": {"pmcid": "PMC6380580", "section_index": 29, "section_title": "Phosphorylation level of hexokinase, pyruvate kinase and lactate dehydrogenase-like may contribute to the control of glucose metabolism in trypomastigotes incubated with ECM", "row_count": 23, "column_count": 9}, "table": {"label": "Table 2", "caption": "Identification of kinases and phosphatases modified by phosphorylation after incubation of trypomastigotes with ECM for 120 min.Complete information is shown in S2 Table.", "rows": [["Phosphopeptide", "TriTryp ID", "Protein Name", "Ratio MTy/Ty", "p-value", "Phospho-Residue", "Putative kinase", "Putative phospho-peptide", "Kinase Score"], ["iSTGGKDEPALVSLVLAGDFNsDAGSPPIR", "TcCLB.504073.10", "endonuclease/exonuclease/phosphatase; putative", "0.779478808", "0.000646", "22S", "CAMK/CAMKL/QIK/SIK2", "VLAGDFNSDAGSPPI", "7.514"], ["kLSPSEPNVAyICSR", "TcCLB.507993.80", "glycogen synthase kinase 3; putative", "0.779756115", "0.042338", "11Y", "TK/Tec/ITK", "PSEPNVAYICSR***", "2.44"], ["aFVPLIPVAQNANPTPESPFLLsPEKDR", "TcCLB.504213.90", "inositol polyphosphate kinase-like protein; putative", "0.674636314", "0.034507", "23S", "AGC/GRK/BARK/BARK1", "PESPFLLSPEKDR**", "5.269"], ["aFVPLIPVAQNANPTPESPFLLsPEKDR", "TcCLB.504213.90", "inositol polyphosphate kinase-like protein; putative", "0.372851136", "0.006706", "23S", "AGC/GRK/BARK/BARK1", "PESPFLLSPEKDR**", "5.269"], ["eDTQDQNKtHyVTHR", "TcCLB.511573.40", "mitogen-activated protein kinase; putative", "0.752549702", "0.031487", "9T", "STE/STE7/MEK3/MAP2K3", "DTQDQNKTHYVTHR*", "4.309"], ["eDTQDQNKtHyVTHR", "TcCLB.511573.40", "mitogen-activated protein kinase; putative", "0.752549702", "0.031487", "11Y", "TK/Src/SRM/PTK6", "QDQNKTHYVTHR***", "4.177"], ["nTFELTNGTPTIAGVSFVSNSsPTGGAPSFFR", "TcCLB.510105.130", "phosphatidylinositol-4-phosphate 5-kinase type II beta; putative", "0.711653701", "0.001718", "22S", "Other/PLK/SAK/PLK4", "VSFVSNSSPTGGAPS", "4.9"], ["tFtLCGTPEYLAPEVIQSR", "TcCLB.509805.10", "protein kinase A catalytic subunit; putative", "1.269816312", "0.038173", "3T", "Other/CAMKK/Meta/CaMKK2", "*****TFTLCGTPEY", "7.822"], ["tFtLCGTPEYLAPEVIQSR", "TcCLB.509805.10", "protein kinase A catalytic subunit; putative", "1.269816312", "0.038173", "1T", "STE/STE20/TAO/TAOK1", "*******TFTLCGTP", "9"], ["aAEVSVGEsNTPANTPNNSR", "TcCLB.503757.40", "protein kinase ck2 regulatory subunit; putative", "0.758482269", "0.049888", "9S", "AGC/GRK", "AEVSVGESNTPANTP", "7.991"], ["qAGVGNPPPLSPLQALCSPtATGLSPVLLGEKGDHHLPVSK", "TcCLB.509231.20", "protein kinase; putative", "0.760798278", "0.04098", "20T", "CMGC/DYRK/DYRK1/DYRK1B", "LQALCSPTATGLSPV", "7.575"], ["tTVASAATAVASVTsPPLLSSAVSSK", "TcCLB.509099.150", "protein kinase; putative", "0.784036858", "0.010475", "15S", "CMGC/MAPK/JNK/JNK3", "TAVASVTSPPLLSSA", "11.042"], ["rVLtPSGGFDDTYSSGIELFDEIHR", "TcCLB.510257.130", "protein kinase; putative", "0.764883202", "0.007529", "4T", "CMGC/MAPK/p38/MAPK13", "****RVLTPSGGFDD", "4.706"], ["iIDFGSSCYLTDNLSsYVQSR", "TcCLB.506869.60", "protein kinase; putative", "1.468291844", "0.04288", "16S", "STE/STE20/FRAY/OSR1", "YLTDNLSSYVQSR**", "1.307"], ["iIDFGSSCYLTDNLsSYVQSR", "TcCLB.506869.60", "protein kinase; putative", "1.261821895", "0.044097", "15S", "STE/STE7/MEK3/MAP2K4", "CYLTDNLSSYVQSR*", "1.325"], ["tTVASAATAVASVTsPPLLSSAVSSK", "TcCLB.509099.150", "protein kinase; putative", "0.784036858", "0.010475", "1T", "TKL/MLK/MLK/ZAK", "*******TTVASAAT", "9.25"], ["iGLGGIGTFTSSsSSPK", "TcCLB.510089.130", "protein kinase; putative", "0.70009069", "0.028877", "13S", "TKL/STKR/STKR1/TGFbR1", "IGTFTSSSSSPK***", "5.333"], ["gGHPLHQENQmsEEDEDVEALPHSVSQR", "TcCLB.484949.9", "serine/threonine protein kinase; putative", "0.629335525", "0.0197", "12S", "CMGC/CK2", "LHQENQMSEEDEDVE", "9.894"], ["tPETTLGGVLAEVAPsLISHSFPLELGESqTAAHQELHPDLGR", "TcCLB.484949.9", "serine/threonine protein kinase; putative", "0.750070579", "0.029801", "1T", "CMGC/MAPK/p38/MAPK13", "*******TPETTLGG", "4.706"], ["tPETTLGGVLAEVAPsLISHSFPLELGESqTAAHQELHPDLGR", "TcCLB.484949.9", "serine/threonine protein kinase; putative", "0.750070579", "0.029801", "16S", "Other/NEK/NEK9/NEK9", "VLAEVAPSLISHSFP", "7.983"], ["lLLHPSHnGAAALASASIEsPVGR", "TcCLB.507757.50", "serine/threonine-protein phosphatase PP1; putative", "0.65305933", "0.024747", "20S", "STE/STE11/MEKK1/MAP3K1", "LASASIESPVGR***", "3.517"], ["lLLHPSHNGAAALAsASIESPVGR", "TcCLB.507757.50", "serine/threonine-protein phosphatase PP1; putative", "0.61302874", "0.017711", "15S", "STE/STE20/KHS/HPK1", "NGAAALASASIESPV", "5.683"]], "row_count": 23, "column_count": 9, "numeric_cells": 118, "header_rows": 1, "locator": "section[29]/table-wrap[1]#pntd.0007103.t002"}}], "gaps": ["asset:data:geo:PXD010970 not downloaded", "asset:data:geo:PXD010970 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "T Student test (two-tail, 95%)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Statistical analysis for validation of the results was performed by T Student test (two-tail, 95%)."}}], "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": "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 (T Student test (two-tail, 95%)), 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": ["PXD010970"], "resolved_accessions": ["PXD010970"], "statements": ["The mass spectrometry proteomics and phosphoproteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [74] partner repository with the dataset identifier PXD010970."], "basis": "The paper names PXD010970 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:30726203", "data:geo:PXD010970", "asset:table:pmid:30726203:1", "asset:table:pmid:30726203:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD010970"]}, "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": "2026-10-31T18:41:20Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 66771, "completion_tokens": 907, "cached_tokens": 22144}}, "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:30726203", "type": "paper", "label": "pmid:30726203"}, {"id": "source:pmid:30726203", "type": "manuscript", "label": "PMID 30726203 full text"}, {"id": "data:geo:PXD010970", "type": "dataset", "label": "GEO PXD010970"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30726203", "type": "paper", "label": "pmid:30726203"}, {"id": "source:pmid:30726203", "type": "manuscript", "label": "PMID 30726203 full text"}, {"id": "data:geo:PXD010970", "type": "dataset", "label": "GEO PXD010970"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30726203", "type": "extraction", "used": ["source:pmid:30726203"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD010970", "type": "accession_resolution", "used": ["data:geo:PXD010970"], "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:30726203", "parent_hash": "sha256:66bba6adb38e10e8ebea6c9636301e0c9534cd2a355e5b9154ebc98891f2131a", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:PXD010970 licence not read", "asset:data:geo:PXD010970 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": ["le of phosphorylate the peptides detected by LC-MS/MS were predicted by the GPS 2.1 software. Only", "es for the 303 phosphopeptides identified by LC-MS/MS (S3 and S4 Tables). Most of the identified s", "lcano plot of total protein identified after LC-MS/MS. The Y-axis represents the -log 2 p-value (T", "ntified after phospho-enrichment followed by LC-MS/MS. Y and X-axis are the same as represented in"], "order_basis": "paper_text_order:4344", "id": "assay:1"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["y/Ty = 1.27). The phosphorylation of T197 of mouse PKA, located in the activation loop, which c"], "order_basis": "paper_text_order:6520", "id": "assay:2"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["LDH (C) enzymatic quantification assays. (a) Immunoblotting of 20 x105 to 1.2 x 105 trypomastigotes extr", "linear correlation between curve area of the immunoblotting bands (a) and trypomastigote numbers. (c) Es"], "order_basis": "paper_text_order:10769", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:30:40+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}