Proteome data of female Anopheles stephensi antennae.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31049374", "kind": "science-record", "revision": 3, "content_hash": "sha256:17117059729c3dbff7b8605d4bb8b9eb42215dfe394127f37045d21157259f15", "created_at": "2026-11-01T15:40:44Z", "updated_at": "2026-11-01T18:50:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Proteome data of female Anopheles stephensi antennae.", "doi": "10.1016/j.dib.2019.103911", "pmid": "31049374", "authors": ["Ajeet Kumar Mohanty", "Gourav Dey", "Manish Kumar", "Sreelakshmi K Sreenivasamurthy", "Sandeep Garg", "T S Keshava Prasad", "Ashwani Kumar"], "journal": "Data in brief", "year": 2019, "abstract": "Antennae of female Anopheles stephensi mosquitoes were dissected and lysed with 1% SDS. Proteins were extracted using ultra sonication and analyzed on high resolution mass spectrometer. Proteomic data was analyzed using two search algorithms SEQUEST and Mascot, resulting in the identification of 22,729 peptides corresponding to 3262 proteins. These proteins were characterized using different bioinformatics tools. VectorBase resource was used to assign Gene Ontology (GO) terms. Using Biomart tool ortholog information was fetched from the VectorBase database. Raw mass spectrometric data was deposited in ProteomeXchange Consortium via PRIDE partner repository in the public dataset PXD001128. Proteins involved in insecticide resistance and odorant binding were the most abundant in the antennae. The proteins identified in this study could be targeted for developing novel vector control strategy.", "claims": [{"id": "claim-data-access", "statement": "Data are available here and via a web application (ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001128.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31049374", "locator": "sections[1] \"p\" paragraph 1", "quote": "Data are available here and via a web application (ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001128."}], "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:31049374"], "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:PXD001128"], "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:PXD001128"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31049374", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2019.103911", "sha256": "sha256:b7ec06c86490d302d7adb6efa27eeb7407612ef4121fa88405aae35e4292d10b", "bytes": 12197, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2019.103911", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6479098", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD001128", "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=PXD001128", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD001128", "version": null, "note": "Data are available here and via a web application (ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001128.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available here and via a web application (ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001128.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Integrating transcriptomics and proteomics data for accurate assembly and annotation of genomes", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31049374:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2193dd20e2ee7bf5bd678b95fd6610084e776e100d749aa6a1db4b8eeea295ba", "bytes": 1759, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#undtbl1", "version": null, "note": "Specifications table", "structure": {"pmcid": "PMC6479098", "section_index": 1, "section_title": "p", "row_count": 10, "column_count": 2}, "table": {"label": null, "caption": "Specifications table", "rows": [["Subject area", "Biology"], ["More specific subject area", "Mosquito proteomics"], ["Type of data", "Tables, Graphs and figures"], ["How data was acquired", "LTQ-Orbitrap Velos mass spectrometer (Thermo Scientific)Proteome Discoverer 2.4 and MASCOT search engine (Matrix Science, London, UK; version 2.2)Protein database Anopheles stephensi Indian strain (www.VectorBase.org/, release date February 25, 2014)"], ["Data format", "Analyzed output data"], ["Experimental factors", "Antennae obtained from the laboratory reared female Anopheles stephensi mosquitoes"], ["Experimental features", "In-gel trypsin digestion of proteins followed by LC-MS/MS analysis using LTQ-Orbitrap Velos mass spectrometer (Thermo Scientific)."], ["Data source location", "Goa and Bengaluru, India"], ["Data accessibility", "Data are available here and via a web application (ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001128."], ["Related research article", "Title: Integrating transcriptomic and proteomic data for accurate assembly and annotation of genomes.Author list: Prasad TS, Mohanty AK, Kumar M, Sreenivasamurthy S, Dey G, Nirujogi RS, Pinto SM, Madugundu AK, Patil AH, Advani J, Manda SS, Gupta MK, Dwivedi SB, Kelkar DS, Hall B, Jiang X, Peery A, Rajagopalan P, Yelamanchi SD, Solanki HS, Raja R, Sathe GJ, Chavan S, Verma R, Patel KM, Jain AP, Syed N, Datta KK, Khan AA, Dammalli M, Jayaram S, Radhakrishnan A, Mitchell CJ, Na CH, Kumar N, Sinnis P, Sharakhov IV, Wang C, Gowda H, Tu Z, Kumar A, Pandey A.Status: Published"]], "row_count": 10, "column_count": 2, "numeric_cells": 2, "header_rows": 0, "locator": "section[1]/table-wrap[1]#undtbl1"}}, {"id": "asset:table:pmid:31049374:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:149857a1b578465b4b61cd280ecf62f85a32004b0da5bef2095c320d6987824b", "bytes": 585, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[2]#undtbl2", "version": null, "note": null, "structure": {"pmcid": "PMC6479098", "section_index": 1, "section_title": "p", "row_count": 1, "column_count": 1}, "table": {"label": null, "caption": null, "rows": [["Value of the data•This data set is the largest catalogue of proteins identified from the antennae of female Anopheles stephensi.•Data provides information about antennae proteins involved in different biological and molecular functions. Overall it enables better understanding of olfactory behaviour of this organ.•This data could be utilized in future for the development of novel targets for control of disease transmission."]], "row_count": 1, "column_count": 1, "numeric_cells": 0, "header_rows": 0, "locator": "section[1]/table-wrap[2]#undtbl2"}}], "gaps": ["asset:data:geo:PXD001128 not downloaded", "asset:data:geo:PXD001128 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": ["PXD001128"], "resolved_accessions": ["PXD001128"], "statements": ["Data are available here and via a web application (ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001128."], "basis": "The paper names PXD001128 in ProteomeXchange Consortium via PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:31049374", "data:geo:PXD001128", "asset:table:pmid:31049374:1", "asset:table:pmid:31049374:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD001128"]}, "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": "2026-10-31T18:14:32Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 10250, "completion_tokens": 1048, "cached_tokens": 784}}, "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:31049374", "type": "paper", "label": "pmid:31049374"}, {"id": "source:pmid:31049374", "type": "manuscript", "label": "PMID 31049374 full text"}, {"id": "data:geo:PXD001128", "type": "dataset", "label": "GEO PXD001128"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31049374", "type": "paper", "label": "pmid:31049374"}, {"id": "source:pmid:31049374", "type": "manuscript", "label": "PMID 31049374 full text"}, {"id": "data:geo:PXD001128", "type": "dataset", "label": "GEO PXD001128"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31049374", "type": "extraction", "used": ["source:pmid:31049374"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD001128", "type": "accession_resolution", "used": ["data:geo:PXD001128"], "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:31049374", "parent_hash": "sha256:e0e34611273eb06b45b9e91197ff5f7725808faacce8cea2406eb7d28450c079", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:PXD001128 licence not read", "asset:data:geo:PXD001128 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["as fetched from the VectorBase database. Raw mass spectrometric data was deposited in ProteomeXchange Consor", "alyzed on high resolution mass spectrometer. Proteomic data was analyzed using two search algorithm"], "order_basis": "paper_text_order:195", "id": "assay:1"}]}