Impact of aspirin on the transcriptome of Streptococcus pneumoniae D39.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28289603", "kind": "science-record", "revision": 4, "content_hash": "sha256:e7fc63f459370e596c124717cb285bf0cbd929d4e931dc3948b4da5d365edd06", "created_at": "2026-11-01T15:40:24Z", "updated_at": "2026-11-01T21:20:51Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Impact of aspirin on the transcriptome of Streptococcus pneumoniae D39.", "doi": "10.1016/j.gdata.2017.02.013", "pmid": "28289603", "authors": ["Muhammad Afzal", "Sulman Shafeeq"], "journal": "Genomics data", "year": 2017, "abstract": "Aspirin or acetylsalicylic acid (ASA) is a medicine used to treat pain, fever, and inflammation. Here, we for the very first time reported the genome-wide transcriptional profiling of aspirin-regulated genes in Streptococcus pneumoniae in the presence of 5 mM aspirin in chemically-defined medium (CDM) using microarray analysis. Our results showed that expression of several genes was differentially expressed in the presence of aspirin. These genes were further grouped into COG (Clusters of Orthologous Groups) functional categories based on the putative functions of the corresponding proteins. Most of affected genes belong to COG category E (Amino acid transport and metabolism), G (Carbohydrate transport and metabolism), J (Translation, ribosomal structure and biogenesis), and I (Lipid transport and metabolism). Transcriptional profiling data of aspirin-regulated genes was deposited to Gene Expression Omnibus (GEO) database under accession number GSE94514.", "claims": [{"id": "claim-method", "statement": "CyberT implementation of a variant of t-test (http://bioinformatics.biol.rug.nl/cybert/index.shtml) was performed and false discovery rates (FDRs) were calculated as described [3].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28289603", "locator": "sections[6] \"Microarray data analysis\" paragraph 2", "quote": "CyberT implementation of a variant of t-test (http://bioinformatics.biol.rug.nl/cybert/index.shtml) was performed and false discovery rates (FDRs) were calculated as described [3]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw and processed DNA microarray dataset are accessible under the following link: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE94514.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28289603", "locator": "sections[2] \"Direct link to deposited data\" paragraph 2", "quote": "The raw and processed DNA microarray dataset are accessible under the following link: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE94514."}], "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:28289603"], "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:GSE94514"], "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:GSE94514"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28289603", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2017.02.013", "sha256": "sha256:92365a844ba8ac833aa553c094245bcb5c9a7b895be922a29dc1e6e1591521e7", "bytes": 10973, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2017.02.013", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5338716", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE94514", "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=GSE94514", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE94514", "version": null, "note": "The raw and processed DNA microarray dataset are accessible under the following link: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE94514.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw and processed DNA microarray dataset are accessible under the following link: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE94514.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2477254", "GSM2477255"], "sample_count": 2, "group_sizes": null, "group_sizes_basis": null, "platform": "11484", "taxon": "Streptococcus pneumoniae D39", "title": "Transcriptome response of the Streptococcus pneumoniae D39 wild-type to Aspirin", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:28289603:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:800df3f8a5441a07782fc55a62d8938603b2a056f4f4e5ebba4e9c4723383344", "bytes": 610, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0015", "version": null, "note": null, "structure": {"pmcid": "PMC5338716", "section_index": 1, "section_title": "Specifications", "row_count": 8, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Organism/cell line/tissue", "Streptococcus pneumoniae D39"], ["Sex", "N/A"], ["Sequencer or array type", "Oligo-based DNA microarray"], ["Data format", "Raw and processed"], ["Experimental factors", "5 mM versus 0 mM Aspirin"], ["Experimental features", "Aspirin-dependent gene expression was explored by microarray comparison of S. pneumoniae D39 wild-type grown in CDM with 5 mM to 0 mM aspirin"], ["Consent", "N/A"], ["Sample source location", "Groningen, The Netherlands"]], "row_count": 8, "column_count": 2, "numeric_cells": 3, "header_rows": 0, "locator": "section[1]/table-wrap[1]#t0015"}}, {"id": "asset:table:pmid:28289603:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ae67ce647493efc06ddbb072179519c6e669de9abae974ed5e64ad35af853433", "bytes": 3414, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#t0005", "version": null, "note": "Summary of transcriptome comparison of S. pneumoniae D39 wild-type grown in CDM with and without 5 mM aspirin.", "structure": {"pmcid": "PMC5338716", "section_index": 7, "section_title": "Discussion", "row_count": 52, "column_count": 3}, "table": {"label": "Table 1", "caption": "Summary of transcriptome comparison of S. pneumoniae D39 wild-type grown in CDM with and without 5 mM aspirin.", "rows": [["D39 taga", "Functionb", "Ratioc"], ["spd_0775", "Hypothetical protein", "2.7"], ["spd_1932", "Maltodextrin phosphorylase, MalP", "2.6"], ["spd_1933", "4-alpha-Glucanotransferase, MalQ", "2.3"], ["spd_1834", "Alcohol dehydrogenase, iron-containing", "2.3"], ["spd_0459", "Heat shock protein, GrpE", "2.2"], ["spd_0460", "Chaperone protein, DnaK", "2.1"], ["spd_1636", "Alcohol dehydrogenase, zinc-containing", "2.1"], ["spd_2002", "Undecaprenol-phosphate-poly (glycerophosphate subunit) D-alanine transfer protein, DltD", "1.9"], ["spd_0868", "Protease maturation protein, putative", "1.9"], ["spd_0420", "Formate acetyltransferase, PflB", "1.8"], ["spd_1006", "Glucose-1-phosphate adenylyltransferase, GlgC", "1.8"], ["spd_1007", "Glucose-1-phosphate adenylyltransferase, GlgD", "1.8"], ["spd_0927", "Neopullulanase, NplT", "1.8"], ["spd_0379", "Transcriptional regulator, marr family protein", "− 1.8"], ["spd_0401", "Ribosomal protein L28", "− 1.8"], ["spd_0652", "Branched-chain amino acid ABC transporter, amino acid-binding protein, LivJ", "− 1.8"], ["spd_1726", "Pneumolysin, Ply", "− 1.8"], ["spd_0192", "Ribosomal protein S10", "− 1.8"], ["spd_0380", "3-Oxoacyl-(acyl-carrier-protein) synthase III, FabH", "− 1.8"], ["spd_0409", "Threonine dehydratase, IlvA", "− 1.8"], ["spd_1158", "NADP-specific glutamate dehydrogenase, GdhA", "− 1.9"], ["spd_0646", "Hypothetical protein", "− 1.9"], ["spd_0382", "trans-2-Enoyl-ACP reductase II, FabK", "− 1.9"], ["spd_1727", "Hypothetical protein", "− 1.9"], ["spd_0674", "Ribosomal protein S16", "− 1.9"], ["spd_0385", "3-Oxoacyl-[acyl-carrier-protein] synthase II, FabF", "− 1.9"], ["spd_0161", "Hypothetical protein", "− 1.9"], ["spd_0448", "Glutamine synthetase, type I, GlnA", "− 1.9"], ["spd_1370", "Ribosomal protein S6", "− 2"], ["spd_1525", "ABC transporter, ATP-binding protein", "− 2"], ["spd_0383", "Malonyl coa-acyl carrier protein transacylase, FabD", "− 2"], ["spd_0219", "Ribosomal protein L17", "− 2.1"], ["spd_1964", "Ribosomal protein L33", "− 2.2"], ["spd_0334", "Oligopeptide ABC transporter, oligopeptide-binding protein, AliA", "− 2.3"], ["spd_0447", "Transcriptional regulator, MerR family protein", "− 2.3"], ["spd_0251", "Ribosomal protein S12", "− 2.3"], ["spd_0387", "Beta-hydroxyacyl-(acyl-carrier-protein) dehydratase, FabZ", "− 2.3"], ["spd_0388", "Acetyl-coa carboxylase, biotin carboxylase, AccC", "− 2.3"], ["spd_0404", "Acetolactate synthase, large subunit, biosynthetic type, IlvB", "− 2.3"], ["spd_0390", "Acetyl-coa carboxylase, carboxyl transferase, alpha subunit, AccA", "− 2.3"], ["spd_0405", "Acetolactate synthase, small subunit, IlvN", "− 2.4"], ["spd_0408", "Hypothetical protein", "− 2.4"], ["spd_0407", "Hypothetical protein", "− 2.4"], ["spd_1963", "Ribosomal protein L32", "− 2.4"], ["spd_0389", "Acetyl-coa carboxylase, carboxyl transferase, beta subunit, AccD", "− 2.4"], ["spd_0274", "Ribosomal protein L13", "− 2.5"], ["spd_1524", "Transcriptional regulator, GntR family protein", "− 2.6"], ["spd_0386", "Acetyl-coa carboxylase, biotin carboxyl carrier protein, AccB", "− 2.8"], ["spd_0406", "Ketol-acid reductoisomerase, IlvC", "− 2.8"], ["spd_1526", "Hypothetical protein", "− 2.9"], ["spd_0275", "Ribosomal protein S9", "− 3"]], "row_count": 52, "column_count": 3, "numeric_cells": 117, "header_rows": 1, "locator": "section[7]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:28289603:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:48b3b836060982aa87d1905bf13390784f2fb453375c788193c234dbda1ca228", "bytes": 1538, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[2]#t0010", "version": null, "note": "Number of genes significantly affected in D39 wild-type grown in CDM with 5 mM aspirin compared to that grown in CDM without aspirin. Genes affected at least 1.8 fold in the presence of aspirin are shown in COG functional categories.", "structure": {"pmcid": "PMC5338716", "section_index": 7, "section_title": "Discussion", "row_count": 21, "column_count": 4}, "table": {"label": "Table 2", "caption": "Number of genes significantly affected in D39 wild-type grown in CDM with 5 mM aspirin compared to that grown in CDM without aspirin. Genes affected at least 1.8 fold in the presence of aspirin are shown in COG functional categories.", "rows": [["Functional categories", "Total", "Up", "Down"], ["C: Energy production and conversion", "02", "02", "0"], ["E: Amino acid transport and metabolism", "08", "01", "07"], ["F: Nucleotide transport and metabolism", "0", "0", "0"], ["G: Carbohydrate transport and metabolism", "05", "05", "0"], ["H: Coenzyme transport and metabolism", "01", "0", "01"], ["I: Lipid transport and metabolism", "07", "0", "07"], ["J: Translation, ribosomal structure and biogenesis", "10", "0", "10"], ["K: Transcription", "03", "0", "03"], ["L: Replication, recombination and repair", "0", "0", "0"], ["M: Cell wall/membrane/envelope biogenesis", "01", "01", "0"], ["O: Posttranslational modification, protein turnover, chaperones", "03", "03", "0"], ["P: Inorganic ion transport and metabolism", "01", "0", "01"], ["Q: Secondary metabolites biosynthesis, transport and catabolism", "01", "0", "01"], ["R: General function prediction only", "01", "0", "01"], ["S: Function unknown", "01", "0", "01"], ["T: Signal transduction mechanisms", "0", "0", "0"], ["U: Intracellular trafficking, secretion, and vesicular transport", "0", "0", "0"], ["V: Defense mechanisms", "01", "0", "01"], ["Others", "06", "01", "05"], ["Total number of genes", "51", "13", "38"]], "row_count": 21, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[7]/table-wrap[2]#t0010"}}], "gaps": ["asset:data:geo:GSE94514 not downloaded", "asset:data:geo:GSE94514 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "CyberT implementation of a variant of t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "CyberT implementation of a variant of t-test (http://bioinformatics.biol.rug.nl/cybert/index.shtml) was performed and false discovery rates (FDRs) were calculated as described [3]."}}], "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 (CyberT implementation of a variant of 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": "R1", "reachable": true, "accessions": ["GSE94514"], "resolved_accessions": ["GSE94514"], "statements": ["The raw and processed DNA microarray dataset are accessible under the following link: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE94514."], "basis": "The paper names GSE94514 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:28289603", "data:geo:GSE94514", "asset:table:pmid:28289603:1", "asset:table:pmid:28289603:2", "asset:table:pmid:28289603:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE94514"]}, "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": "2026-10-31T18:09:16Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 10062, "completion_tokens": 843, "cached_tokens": 708}}, "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:28289603", "type": "paper", "label": "pmid:28289603"}, {"id": "source:pmid:28289603", "type": "manuscript", "label": "PMID 28289603 full text"}, {"id": "data:geo:GSE94514", "type": "dataset", "label": "GEO GSE94514"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28289603", "type": "paper", "label": "pmid:28289603"}, {"id": "source:pmid:28289603", "type": "manuscript", "label": "PMID 28289603 full text"}, {"id": "data:geo:GSE94514", "type": "dataset", "label": "GEO GSE94514"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28289603", "type": "extraction", "used": ["source:pmid:28289603"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE94514", "type": "accession_resolution", "used": ["data:geo:GSE94514"], "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:28289603", "parent_hash": "sha256:1fe7dba0ad0e247254486aaba1448b9f98b0750e7782d64ef1369da721756b56", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE94514 licence not read", "asset:data:geo:GSE94514 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": 0.93, "evidence": ["rin in chemically-defined medium (CDM) using microarray analysis. Our results showed that expression"], "order_basis": "paper_text_order:336", "id": "assay:1"}]}