Transcriptome datasets of macrophages infected with different strains of Leptospira spp.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29326966", "kind": "science-record", "revision": 8, "content_hash": "sha256:05ede7660eb96654c2f56d39f78d9f66d45b54a9848c7fdaa3fc560464912707", "created_at": "2026-11-01T15:40:31Z", "updated_at": "2026-11-01T22:43:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Transcriptome datasets of macrophages infected with different strains of Leptospira spp.", "doi": "10.1016/j.dib.2017.12.042", "pmid": "29326966", "authors": ["Erivelto Corrêa de Araújo Junior", "Leandro Encarnação Garcia", "Larissa Martins Melo", "Jaqueline Poleto Bragato", "Valéria Marçal Félix de Lima", "Juliana Regina Peiró", "Flavia Lombardi Lopes", "Márcia Marinho"], "journal": "Data in brief", "year": 2018, "abstract": "The datasets reported herein provide information about microarray experiment of macrophage cell line J774A.1 infected with three different strains of Leptospira spp. Transcriptomic profiles were generated using Affymetrix® Mouse Gene 2.1 ST Array Strip. Data was normalized and statically process, p-value < 0.01, FDR < 0.05 and log2 fold change (± 2). The microarray raw data are available in Gene Expression Omnibus (GEO) under accession number GSE105141.", "claims": [{"id": "claim-method", "statement": "Differential expression of each gene was determined by ANOVA with two criteria, a fold change of ± 2 comparing all infected groups to the non-infected control and filtered by FDR-corrected p-value < 0.05", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29326966", "locator": "sections[12] \"Statistical analysis\" paragraph 2", "quote": "Differential expression of each gene was determined by ANOVA with two criteria, a fold change of ± 2 comparing all infected groups to the non-infected control and filtered by FDR-corrected p-value < 0.05"}], "state": "complete"}, {"id": "claim-data-access", "statement": "Microarray data are available from Gene Expression Omnibus database with GEO accession number GSE105141", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29326966", "locator": "sections[1] \"p\" paragraph 1", "quote": "Microarray data are available from Gene Expression Omnibus database with GEO accession number GSE105141"}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using ANOVA-based differential-expression analysis with fold-change and FDR filters, the study found significant expression changes in more than 800 genes after virulent or attenuated L. interrogans infection and in 200 genes after saprophyte L. biflexa infection; the source microarray data are available in GEO under accession GSE105141.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29326966", "locator": "sections[10] \"Identification of differentially expressed genes\" paragraph 2", "quote": "Infection by L. interrogans (virulent and attenuated bacteria) caused statistically significant changes in gene expression in more than 800 genes, when compared to non-infected control cells (Fig. 3a–b)."}, {"asset": "source:pmid:29326966", "locator": "sections[10] \"Identification of differentially expressed genes\" paragraph 2", "quote": "Saprophyte L. biflexa modulated 200 genes when compared to control (Fig. 3c)."}, {"asset": "source:pmid:29326966", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The microarray raw data are available in Gene Expression Omnibus (GEO) under accession number GSE105141."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Using ANOVA-based differential-expression analysis with fold-change and FDR filters, the study found significant expression changes in more than 800 genes after virulent or attenuated L. interrogans infection and in 200 genes after saprophyte L. biflexa infection; the source microarray data are available in GEO under accession GSE105141.", "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:29326966"], "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:GSE105141"], "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:GSE105141"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29326966", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2017.12.042", "sha256": "sha256:b2f9a996f09619e9f854ef572f5db3ae0c2d190b365ea9afaed743b8d898f2f7", "bytes": 11514, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2017.12.042", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5758930", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE105141", "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=GSE105141", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE105141", "version": null, "note": "Microarray data are available from Gene Expression Omnibus database with GEO accession number GSE105141", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Microarray data are available from Gene Expression Omnibus database with GEO accession number GSE105141", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2823123", "GSM2823124", "GSM2823125", "GSM2823126", "GSM2823127", "GSM2823128", "GSM2823129", "GSM2823130", "GSM2823131", "GSM2823132", "GSM2823133", "GSM2823134"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "17400", "taxon": "Mus musculus", "title": "Transcriptome analysis of murine macrophages infected with different strains of Leptospira spp", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:29326966:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:38901b35013439396a6b0d463026ee27f79c36fe8334b616e44eda921bcd190b", "bytes": 977, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0010", "version": null, "note": null, "structure": {"pmcid": "PMC5758930", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology"], ["More specific subject area", "Gene expression"], ["Type of data", "Table and Figures"], ["How data was acquired", "Microarray Affymetrix® Mouse Gene 2.1 ST Array Strip"], ["Data format", "Raw (CEL.)"], ["Experimental factors", "cell lines non-infected x cell lines infected with Leptospira spp."], ["Experimental features", "Total RNA, with RIN 10, was extracted from whole macrophage cell line infected and control. Each sample contains three biological replicates and each replicates consists of three culture well."], ["Data source location", "Department of Support, Production and Animal Health, São Paulo State University, School of Veterinary Medicine, Araçatuba, SP, Brazil"], ["Data accessibility", "Microarray data are available from Gene Expression Omnibus database with GEO accession number GSE105141"]], "row_count": 9, "column_count": 2, "numeric_cells": 3, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0010"}}, {"id": "asset:table:pmid:29326966:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:38901b35013439396a6b0d463026ee27f79c36fe8334b616e44eda921bcd190b", "bytes": 977, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0010", "version": null, "note": null, "structure": {"pmcid": "PMC5758930", "section_index": 2, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology"], ["More specific subject area", "Gene expression"], ["Type of data", "Table and Figures"], ["How data was acquired", "Microarray Affymetrix® Mouse Gene 2.1 ST Array Strip"], ["Data format", "Raw (CEL.)"], ["Experimental factors", "cell lines non-infected x cell lines infected with Leptospira spp."], ["Experimental features", "Total RNA, with RIN 10, was extracted from whole macrophage cell line infected and control. Each sample contains three biological replicates and each replicates consists of three culture well."], ["Data source location", "Department of Support, Production and Animal Health, São Paulo State University, School of Veterinary Medicine, Araçatuba, SP, Brazil"], ["Data accessibility", "Microarray data are available from Gene Expression Omnibus database with GEO accession number GSE105141"]], "row_count": 9, "column_count": 2, "numeric_cells": 3, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0010"}}, {"id": "asset:table:pmid:29326966:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:136aa057244e24a00a7642334769a83316ad3c7ed153851c4aa4cc86618c8f98", "bytes": 933, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#t0005", "version": null, "note": "Spectrophotometric reading of RNA samples.", "structure": {"pmcid": "PMC5758930", "section_index": 8, "section_title": "RNA extraction and quantification", "row_count": 13, "column_count": 6}, "table": {"label": "Table 1", "caption": "Spectrophotometric reading of RNA samples.", "rows": [["Sample", "Concentration (ng/µL)", "A260", "A280", "260/280", "260/230"], ["Control1", "2151,3", "53,782", "25,983", "2,07", "2,20"], ["Control2", "2114,2", "52,855", "25,484", "2,07", "2,17"], ["Control3", "2497,3", "62, 433", "30,298", "2,06", "2,17"], ["Virulent1", "2200,2", "55,005", "26,412", "2,08", "2,18"], ["Virulent2", "2818,2", "70,456", "33,697", "2,09", "2,22"], ["Virulent3", "1786,1", "44,653", "21,311", "2,10", "2,18"], ["Attenuated1", "1883,4", "47,086", "22,535", "2,09", "2,18"], ["Attenuated2", "2397,8", "59,946", "28,917", "2,07", "2,21"], ["Attenuated3", "2156,5", "53,912", "25,968", "2,08", "2,20"], ["Saprófita1", "2064,7", "51,618", "24,734", "2,09", "2,04"], ["Saprófita2", "2742,1", "68,553", "32,727", "2,09", "2,12"], ["Saprófita3", "1689,1", "42,229", "20,214", "2,09", "2,17"]], "row_count": 13, "column_count": 6, "numeric_cells": 64, "header_rows": 1, "locator": "section[8]/table-wrap[1]#t0005"}}], "gaps": ["asset:data:geo:GSE105141 not downloaded", "asset:data:geo:GSE105141 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Differential expression of each gene was determined by ANOVA with two criteria, a fold change of ± 2 comparing all infected groups to the non-infected control and filtered by FDR-corrected p-value < 0.05"}}], "targets": [], "gaps": []}, "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE105141"], "resolved_accessions": ["GSE105141"], "statements": ["Microarray data are available from Gene Expression Omnibus database with GEO accession number GSE105141"], "basis": "The paper names GSE105141 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:29326966", "data:geo:GSE105141", "asset:table:pmid:29326966:1", "asset:table:pmid:29326966:2", "asset:table:pmid:29326966:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE105141"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:33:24Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 27288, "completion_tokens": 3393, "cached_tokens": 1816}}, "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:29326966", "type": "paper", "label": "pmid:29326966"}, {"id": "source:pmid:29326966", "type": "manuscript", "label": "PMID 29326966 full text"}, {"id": "data:geo:GSE105141", "type": "dataset", "label": "GEO GSE105141"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29326966", "type": "paper", "label": "pmid:29326966"}, {"id": "source:pmid:29326966", "type": "manuscript", "label": "PMID 29326966 full text"}, {"id": "data:geo:GSE105141", "type": "dataset", "label": "GEO GSE105141"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29326966", "type": "extraction", "used": ["source:pmid:29326966"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE105141", "type": "accession_resolution", "used": ["data:geo:GSE105141"], "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:29326966", "parent_hash": "sha256:2f0277024d4346e7973545764adfd9a8ec741a17608b7ec7376dca871add96fd", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE105141 licence not read", "asset:data:geo:GSE105141 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ts reported herein provide information about microarray experiment of macrophage cell line J774A.1 i", ", FDR < 0.05 and log2 fold change (± 2). The microarray raw data are available in Gene Expression Om", "Transcriptomic profiles were generated using Affymetrix® Mouse Gene 2.1 ST Array Strip. Data was nor"], "order_basis": "paper_text_order:99", "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": 0.99, "evidence": ["ic profiles were generated using Affymetrix® Mouse Gene 2.1 ST Array Strip. Data was normalized", "l design, materials and methods Cell culture Murine macrophage cell line J774A.1, provided by th"], "order_basis": "paper_text_order:267", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Differential expression of each gene was determined by ANOVA with two criteria, a fold change of ± 2 comparing all infected groups to the non-infected control and filtered by FDR-corrected p-value < 0.05"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]}