Sequencing illustrates the transcriptional response of Legionella pneumophila during infection and identifies seventy novel small non-coding RNAs.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:21408607", "kind": "science-record", "revision": 3, "content_hash": "sha256:97c128991604e9f13dd2252c978a4897bc71835c5780d50531ce7109ac766959", "created_at": "2026-11-01T15:40:01Z", "updated_at": "2026-11-01T21:19:37Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Sequencing illustrates the transcriptional response of Legionella pneumophila during infection and identifies seventy novel small non-coding RNAs.", "doi": "10.1371/journal.pone.0017570", "pmid": "21408607", "authors": ["Barbara A Weissenmayer", "James G D Prendergast", "Amanda J Lohan", "Brendan J Loftus"], "journal": "PloS one", "year": 2011, "abstract": "Second generation sequencing has prompted a number of groups to re-interrogate the transcriptomes of several bacterial and archaeal species. One of the central findings has been the identification of complex networks of small non-coding RNAs that play central roles in transcriptional regulation in all growth conditions and for the pathogen's interaction with and survival within host cells. Legionella pneumophila is a gram-negative facultative intracellular human pathogen with a distinct biphasic lifestyle. One of its primary environmental hosts in the free-living amoeba Acanthamoeba castellanii and its infection by L. pneumophila mimics that seen in human macrophages. Here we present analysis of strand specific sequencing of the transcriptional response of L. pneumophila during exponential and post-exponential broth growth and during the replicative and transmissive phase of infection inside A. castellanii. We extend previous microarray based studies as well as uncovering evidence of a complex regulatory architecture underpinned by numerous non-coding RNAs. Over seventy new non-coding RNAs could be identified; many of them appear to be strain specific and in configurations not previously reported. We discover a family of non-coding RNAs preferentially expressed during infection conditions and identify a second copy of 6S RNA in L. pneumophila. We show that the newly discovered putative 6S RNA as well as a number of other non-coding RNAs show evidence for antisense transcription. The nature and extent of the non-coding RNAs and their expression patterns suggests that these may well play central roles in the regulation of Legionella spp. specific traits and offer clues as to how L. pneumophila adapts to its intracellular niche. The expression profiles outlined in the study have been deposited into Genbank's Gene Expression Omnibus (GEO) database under the series accession GSE27232.", "claims": [{"id": "claim-method", "statement": "Differential expression was calculated from raw read counts using the MATR method implemented in the DEGseq R package (PMID: 19855105).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:21408607", "locator": "sections[20] \"Differential expression\" paragraph 2", "quote": "Differential expression was calculated from raw read counts using the MATR method implemented in the DEGseq R package (PMID: 19855105)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The expression profiles outlined in the study have been deposited into Genbank's Gene Expression Omnibus (GEO) database under the series accession GSE27232.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:21408607", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The expression profiles outlined in the study have been deposited into Genbank's Gene Expression Omnibus (GEO) database under the series accession GSE27232."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Headline result: “Over seventy new non-coding RNAs could be identified; many of them appear to be strain specific and in configurations not previously reported.” Differential expression was calculated from raw read counts using the MATR method implemented in the DEGseq R package, and the expression profiles are accessible through GEO under accession GSE27232.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:21408607", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Over seventy new non-coding RNAs could be identified; many of them appear to be strain specific and in configurations not previously reported."}, {"asset": "source:pmid:21408607", "locator": "sections[20] \"Differential expression\" paragraph 2", "quote": "Differential expression was calculated from raw read counts using the MATR method implemented in the DEGseq R package (PMID: 19855105)."}, {"asset": "source:pmid:21408607", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The expression profiles outlined in the study have been deposited into Genbank's Gene Expression Omnibus (GEO) database under the series accession GSE27232."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Headline result: “Over seventy new non-coding RNAs could be identified; many of them appear to be strain specific and in configurations not previously reported.” Differential expression was calculated from raw read counts using the MATR method implemented in the DEGseq R package, and the expression profiles are accessible through GEO under accession GSE27232.", "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:21408607"], "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:GSE27232"], "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:GSE27232"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:21408607", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0017570", "sha256": "sha256:6babeb3a9747bb0391a918a5302cc68de240881012e4aa2f600ad332e6b1d9ba", "bytes": 53892, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0017570", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC3048289", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE27232", "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=GSE27232", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27232", "version": null, "note": "The expression profiles outlined in the study have been deposited into Genbank's Gene Expression Omnibus (GEO) database under the series accession GSE27232.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression profiles outlined in the study have been deposited into Genbank's Gene Expression Omnibus (GEO) database under the series accession GSE27232.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM673298", "GSM673299", "GSM673300", "GSM673301", "GSM673302"], "sample_count": 5, "group_sizes": null, "group_sizes_basis": null, "platform": "13156", "taxon": "Legionella pneumophila", "title": "Strand specific sequencing illustrates the complex transcriptional response of Legionella pneumophila during infection", "resolution_checked_at": "2026-11-01T15:37:51Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE27232 not downloaded", "asset:data:geo:GSE27232 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "MATR method implemented in the DEGseq R package", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Differential expression was calculated from raw read counts using the MATR method implemented in the DEGseq R package (PMID: 19855105)."}}], "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 (MATR method implemented in the DEGseq R package), 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": ["GSE27232"], "resolved_accessions": ["GSE27232"], "statements": ["The expression profiles outlined in the study have been deposited into Genbank's Gene Expression Omnibus (GEO) database under the series accession GSE27232."], "basis": "The paper names GSE27232 in Genbank's 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:21408607", "data:geo:GSE27232"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE27232"]}, "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": "2026-10-31T18:21:00Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 110597, "completion_tokens": 3589, "cached_tokens": 56001}}, "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:21408607", "type": "paper", "label": "pmid:21408607"}, {"id": "source:pmid:21408607", "type": "manuscript", "label": "PMID 21408607 full text"}, {"id": "data:geo:GSE27232", "type": "dataset", "label": "GEO GSE27232"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:21408607", "type": "paper", "label": "pmid:21408607"}, {"id": "source:pmid:21408607", "type": "manuscript", "label": "PMID 21408607 full text"}, {"id": "data:geo:GSE27232", "type": "dataset", "label": "GEO GSE27232"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-21408607", "type": "extraction", "used": ["source:pmid:21408607"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE27232", "type": "accession_resolution", "used": ["data:geo:GSE27232"], "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:21408607", "parent_hash": "sha256:b5fbc3e32271bf1ec3ec6502c95e41b5553ce32617dd55dd90df7eede12cd157", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE27232 licence not read", "asset:data:geo:GSE27232 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": ["on inside A. castellanii. We extend previous microarray based studies as well as uncovering evidence"], "order_basis": "paper_text_order:1042", "id": "assay:1"}]}