Microarray dataset on the genome-wide expression profile of an M. smegmatis amtR mutant (JR258) compared to M. smegmatis mc2155.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27942565", "kind": "science-record", "revision": 2, "content_hash": "sha256:bb0665a56369b46f2ff59f831b5cad2674814336bc81ac2a3132413da33d3f0b", "created_at": "2026-11-01T15:40:21Z", "updated_at": "2026-11-01T18:48:28Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Microarray dataset on the genome-wide expression profile of an M. smegmatis amtR mutant (JR258) compared to M. smegmatis mc2155.", "doi": "10.1016/j.dib.2016.11.049", "pmid": "27942565", "authors": ["Michael Petridis", "Gregory M Cook"], "journal": "Data in brief", "year": 2017, "abstract": "The dataset presented here describes a microarray experiment to identify the AmtR regulon of Mycobacterium smegmatis comparing the transcription profile of a M. smegmatis amtR mutant to M. smegmatis wild-type. The raw and processed microarray data are available in the ArrayExpress database under Accession Number E-MTAB-4857 and interpretation of this data is found in the research article \"Structure and function of AmtR in Mycobacterium smegmatis: implications for post-transcriptional regulation of urea metabolism through a small antisense RNA\" (Petridis et al., in press) [1].", "claims": [{"id": "claim-data-access", "statement": "Data within this article are available in the ArrayExpress database (https://www.ebi.ac.uk/arrayexpress/) under Accession NumberE-MTAB-4857.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27942565", "locator": "sections[2] \"table-wrap\" paragraph 1", "quote": "Data within this article are available in the ArrayExpress database (https://www.ebi.ac.uk/arrayexpress/) under Accession NumberE-MTAB-4857."}], "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:27942565"], "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:E-MTAB-4857"], "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:E-MTAB-4857"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27942565", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2016.11.049", "sha256": "sha256:9e9924eedd43cf7c685485f742493bda2c8e6944dcb3a62d7b7422461673c86c", "bytes": 6035, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2016.11.049", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5137332", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:E-MTAB-4857", "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=E-MTAB-4857", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-4857", "version": null, "note": "Data within this article are available in the ArrayExpress database (https://www.ebi.ac.uk/arrayexpress/) under Accession NumberE-MTAB-4857.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data within this article are available in the ArrayExpress database (https://www.ebi.ac.uk/arrayexpress/) under Accession NumberE-MTAB-4857.", "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": "2026-10-31T18:29:01Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:E-MTAB-4857 not downloaded", "asset:data:geo:E-MTAB-4857 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": ["E-MTAB-4857"], "resolved_accessions": ["E-MTAB-4857"], "statements": ["Data within this article are available in the ArrayExpress database (https://www.ebi.ac.uk/arrayexpress/) under Accession NumberE-MTAB-4857."], "basis": "The paper names E-MTAB-4857 in ArrayExpress and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:27942565", "data:geo:E-MTAB-4857"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:E-MTAB-4857"]}, "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": "2026-10-31T18:08:58Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 6369, "completion_tokens": 1089, "cached_tokens": 2312}}, "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:27942565", "type": "paper", "label": "pmid:27942565"}, {"id": "source:pmid:27942565", "type": "manuscript", "label": "PMID 27942565 full text"}, {"id": "data:geo:E-MTAB-4857", "type": "dataset", "label": "GEO E-MTAB-4857"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:27942565", "type": "paper", "label": "pmid:27942565"}, {"id": "source:pmid:27942565", "type": "manuscript", "label": "PMID 27942565 full text"}, {"id": "data:geo:E-MTAB-4857", "type": "dataset", "label": "GEO E-MTAB-4857"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-27942565", "type": "extraction", "used": ["source:pmid:27942565"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-E-MTAB-4857", "type": "accession_resolution", "used": ["data:geo:E-MTAB-4857"], "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:27942565", "parent_hash": "sha256:9ab23f4c5b803d5e765ddca31169fc61339919fc507bd1c33b9f7869d79ed703", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:E-MTAB-4857 licence not read", "asset:data:geo:E-MTAB-4857 not downloaded", "execution.not_run", "method", "operations", "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": ["Microarray dataset on the genome-wide expression profil", ". smegmatis wild-type. The raw and processed microarray data are available in the ArrayExpress datab", "The dataset presented here describes a microarray experiment to identify the AmtR regulon of M"], "order_basis": "paper_text_order:0", "id": "assay:1"}]}