Dataset of natural antisense transcripts in P. vivax clinical isolates derived using custom designed strand-specific microarray.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26484095", "kind": "science-record", "revision": 4, "content_hash": "sha256:e8a6dc0ea9e87b6cbc7a4d7201dc11f9746179c7c778e019eef30f3c1e288364", "created_at": "2026-11-01T15:40:11Z", "updated_at": "2026-11-01T21:20:09Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dataset of natural antisense transcripts in P. vivax clinical isolates derived using custom designed strand-specific microarray.", "doi": "10.1016/j.gdata.2014.06.024", "pmid": "26484095", "authors": ["P A Boopathi", "Amit Kumar Subudhi", "Shilpi Garg", "Sheetal Middha", "Jyoti Acharya", "Deepak Pakalapati", "Vishal Saxena", "Mohammed Aiyaz", "Bipin Chand", "Raja C Mugasimangalam", "Sanjay K Kochar", "Parmendra Sirohi", "Dhanpat K Kochar", "Ashis Das"], "journal": "Genomics data", "year": 2014, "abstract": "Natural antisense transcripts (NATs) have been detected in many organisms and shown to regulate gene expression. Similarly, NATs have also been observed in malaria parasites with most studies focused on Plasmodium falciparum. There were no reports on the presence of NATs in Plasmodium vivax, which has also been shown to cause severe malaria like P. falciparum, until a recent study published by us. To identify in vivo prevalence of antisense transcripts in P. vivax clinical isolates, we performed whole genome expression profiling using a custom designed strand-specific microarray that contains probes for both sense and antisense strands. Here we describe the experimental methods and analysis of the microarray data available in Gene Expression Omnibus (GEO) under GSE45165. Our data provides a resource for exploring the presence of antisense transcripts in P. vivax isolated from patients showing varying clinical symptoms. Related information about the description and interpretation of the data can be found in a recent publication by Boopathi and colleagues in Infection, Genetics and Evolution 2013.", "claims": [{"id": "claim-method", "statement": "For genes with multiple probes, median of raw signal intensity and background intensity was considered.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26484095", "locator": "sections[7] \"Data analysis\" paragraph 2", "quote": "For genes with multiple probes, median of raw signal intensity and background intensity was considered."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Summary of the array details has been submitted and available under GEO accession number GPL16492.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26484095", "locator": "sections[6] \"244K custom array designing\" paragraph 2", "quote": "Summary of the array details has been submitted and available under GEO accession number GPL16492."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:26484095"], "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:26484095", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2014.06.024", "sha256": "sha256:c82c102356d11b322f760f150a5236c5654512cc7ea08fb5684af6795e93f47c", "bytes": 10403, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2014.06.024", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4535868", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:26484095:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4b6f6c5a2ca67f5537f72b9aa09445adc685b088a46a2618018637904897f9ca", "bytes": 875, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0010", "version": null, "note": null, "structure": {"pmcid": "PMC4535868", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Specifications"], ["Organism/cell line/tissue", "Plasmodium vivax"], ["Source", "P. vivax parasites from patients' blood"], ["Sequencer or array type", "Agilent custom P. vivax 244K array. (AMADID: 019103)"], ["Data format", "Raw data: txt files, normalized data: SOFT, MINiMAL, TXT"], ["Experimental factors", "Complicated and uncomplicated P. vivax malaria"], ["Experimental features", "Identification of sense and antisense transcripts in P. vivax isolated from patients showing differing clinical symptoms."], ["Consent", "The patient samples were collected on informed consent by the team of clinicians at S. P. Medical College, Bikaner, India according to hospital guidelines."], ["Sample source location", "Bikaner, Rajasthan, India."]], "row_count": 9, "column_count": 2, "numeric_cells": 1, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0010"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "median aggregation of raw signal intensity and background intensity across multiple probes", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For genes with multiple probes, median of raw signal intensity and background intensity was considered."}}], "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": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (median aggregation of raw signal intensity and background intensity across multiple probes), 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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["Summary of the array details has been submitted and available under GEO accession number GPL16492."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:26484095", "asset:table:pmid:26484095:1"], "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": null, "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 0, "usage": {}}, "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:26484095", "type": "paper", "label": "pmid:26484095"}, {"id": "source:pmid:26484095", "type": "manuscript", "label": "PMID 26484095 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26484095", "type": "paper", "label": "pmid:26484095"}, {"id": "source:pmid:26484095", "type": "manuscript", "label": "PMID 26484095 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26484095", "type": "extraction", "used": ["source:pmid:26484095"], "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:26484095", "parent_hash": "sha256:b8a134705933fdb9f8aa2375bf195d12230542a2091f5b4ece80b4d99e4ff5ac", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "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": ["erived using custom designed strand-specific microarray.", "ling using a custom designed strand-specific microarray that contains probes for both sense and anti", "the experimental methods and analysis of the microarray data available in Gene Expression Omnibus (G"], "order_basis": "paper_text_order:72", "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": 0.77, "evidence": ["a recent study published by us. To identify in vivo prevalence of antisense transcripts in P. vi"], "order_basis": "paper_text_order:498", "id": "assay:2"}]}