In depth search of the Sequence Read Archive database reveals global distribution of the emerging pathogenic fungus Scedosporium aurantiacum.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35244718", "kind": "science-record", "revision": 4, "content_hash": "sha256:3bf91ff86dbfbcb3ab07ec3dc9198faca38d2db41e795516d892bd55bbcdd31e", "created_at": "2026-11-01T17:37:00Z", "updated_at": "2026-11-01T22:06:01Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "In depth search of the Sequence Read Archive database reveals global distribution of the emerging pathogenic fungus Scedosporium aurantiacum.", "doi": "10.1093/mmy/myac019", "pmid": "35244718", "authors": ["Laszlo Irinyi", "Michael Roper", "Wieland Meyer"], "journal": "Medical mycology", "year": 2022, "abstract": "Scedosporium species are emerging opportunistic fungal pathogens causing various infections mainly in immunocompromised patients, but also in immunocompetent individuals, following traumatic injuries. Clinical manifestations range from local infections, such as subcutaneous mycetoma or bone and joint infections, to pulmonary colonization and severe disseminated diseases. They are commonly found in soil and other environmental sources. To date S. aurantiacum has been reported only from a handful of countries. To identify the worldwide distribution of this species we screened publicly available sequencing data from fungal metabarcoding studies in the Sequence Read Archive (SRA) of The National Centre for Biotechnology Information (NCBI) by multiple BLAST searches. S. aurantiacum was found in 26 countries and two islands, throughout every climatic region. This distribution is like that of other Scedosporium species. Several new environmental sources of S. aurantiacum including human and bovine milk, chicken and canine gut, freshwater, and feces of the giant white-tailed rat (Uromys caudimaculatus) were identified. This study demonstrated that raw sequence data stored in the SRA database can be repurposed using a big data analysis approach to answer biological questions of interest.\nLAY SUMMARY: To understand the distribution and natural habitat of S. aurantiacum, species-specific DNA sequences were searched in the SRA database. Our large-scale data analysis illustrates that S. aurantiacum is more widely distributed than previously thought and new environmental sources were identified.", "claims": [{"id": "claim-data-access", "statement": "All data used in this study are publicly available in the SRA database (https://www.ncbi.nlm.nih.gov/sra).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35244718", "locator": "sections[2] \"Methods\" paragraph 2", "quote": "All data used in this study are publicly available in the SRA database (https://www.ncbi.nlm.nih.gov/sra)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The database search identified 1706 SRA sequence data sets containing either the ITS1 or ITS2 region of S. aurantiacum.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:35244718", "locator": "sections[3] \"Results\" paragraph 2", "quote": "The described database search identified 1706 SRA sequence data sets that contained either the ITS1 or ITS2 region of S. aurantiacum (Supplementary Table 1)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The database search identified 1706 SRA sequence data sets containing either the ITS1 or ITS2 region of S. aurantiacum.", "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:35244718"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35244718", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/mmy/myac019", "sha256": "sha256:38211c828f0c51d4fdc207acdc36010643df797d6e27c829f52b6b8b025f57aa", "bytes": 20185, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/mmy/myac019", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8994208", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "sequence_alignment", "specific": "blast", "label": "Sequence alignment / homology", "dsl_operations": ["sequence_align", "alignment_identity"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["sequence_records"], "evidence": {"score": 0.7, "band": "medium", "quote": "BLAST"}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["sequence_align", "alignment_identity"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: blast."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["All data used in this study are publicly available in the SRA database (https://www.ncbi.nlm.nih.gov/sra)."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["sequence_align", "alignment_identity"], "assets": ["source:pmid:35244718"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:36:30Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 5944, "completion_tokens": 1013, "cached_tokens": 128}}, "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:35244718", "type": "paper", "label": "pmid:35244718"}, {"id": "source:pmid:35244718", "type": "manuscript", "label": "PMID 35244718 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35244718", "type": "paper", "label": "pmid:35244718"}, {"id": "source:pmid:35244718", "type": "manuscript", "label": "PMID 35244718 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35244718", "type": "extraction", "used": ["source:pmid:35244718"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:35244718", "parent_hash": "sha256:c68079615e0275116d64cffe72444dcaf7143ada566a014079ffda3129b1279a", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.642, "evidence": ["shwater, and feces of the giant white-tailed rat (Uromys caudimaculatus) were identified. Thi"], "order_basis": "paper_text_order:1181", "id": "assay:1"}, {"role": "analysis", "definition_id": "sequence_alignment", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["sequence_align", "alignment_identity"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["BLAST"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}