Dataset of Cavendish banana transcriptome in response to chitosan coating application.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32181300", "kind": "science-record", "revision": 3, "content_hash": "sha256:616a4d725ba2a5bed2a52fea02f7e458c98eb118e0591c8feafea78b07e48c40", "created_at": "2026-11-01T15:40:58Z", "updated_at": "2026-11-01T18:52:07Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dataset of Cavendish banana transcriptome in response to chitosan coating application.", "doi": "10.1016/j.dib.2020.105337", "pmid": "32181300", "authors": ["Fenny Martha Dwivany", "Husna Nugrahapraja", "Eiichiro Fukusaki", "Sastia Prama Putri", "Cindy Novianti", "Septhy Kusuma Radjasa", "Tessa Fauziah", "Lutfi Dewi Nirmala Sari"], "journal": "Data in brief", "year": 2020, "abstract": "Banana is a climacteric fruit and its ripening process is greatly influenced by presence of ethylene. This physiological climacteric characteristic of banana fruit leads to a fast ripening and a short shelf-life. Application of edible coating such as chitosan aims to prolong fruit shelf life. The knowledge on gene expression will help to understand the fruit ripening process itself and chitosan effect on global gene expression. Global gene expression data of chitosan treated and control of Cavendish banana during fruit ripening were provided. Total RNA was isolated from banana pulp for differential gene expression analysis. The RNA-sequencing generated ranged from 16,155,947 to 23,587,110 total reads, with 75.8%-83.8% of reads were mapped against the genome reference. In total, 33,797-35,944 transcripts were detected. The transcriptomics data discussed in this publication are accessible through NCBI's Gene Expression Omnibus with GEO Series accession number GSE139457. These data provide information to identify candidate genes involved in fruit ripening in response to chitosan coating to design a better banana postharvest management.", "claims": [{"id": "claim-data-access", "statement": "NCBI's Gene Expression Omnibus (GEO) with GEO series accession number GSE139457https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139457Raw data are available at NCBI's Sequence Read Archive (SRA) database (accession number SRP227182) https://trace.ncbi.nlm.nih.gov/Traces/sra/?study=SRP227182", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32181300", "locator": "sections[1] \"p\" paragraph 1", "quote": "NCBI's Gene Expression Omnibus (GEO) with GEO series accession number GSE139457https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139457Raw data are available at NCBI's Sequence Read Archive (SRA) database (accession number SRP227182) https://trace.ncbi.nlm.nih.gov/Traces/sra/?study=SRP227182"}], "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:32181300"], "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:GSE139457"], "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:GSE139457"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32181300", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2020.105337", "sha256": "sha256:53b43f65cfdbbb44907cd324e2fc00859de01304c0c0ceeb50ed73467a63a6e9", "bytes": 9348, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2020.105337", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7066065", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE139457", "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=GSE139457", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE139457", "version": null, "note": "NCBI's Gene Expression Omnibus (GEO) with GEO series accession number GSE139457https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139457Raw data are available at NCBI's Sequence Read Archive (SRA) database (accession number SRP227182) https://trace.ncbi.nlm.nih.gov/Traces/sra/?study=SRP227182", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NCBI's Gene Expression Omnibus (GEO) with GEO series accession number GSE139457https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139457Raw data are available at NCBI's Sequence Read Archive (SRA) database (accession number SRP227182) https://trace.ncbi.nlm.nih.gov/Traces/sra/?study=SRP227182", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4141871", "GSM4141872", "GSM4141873", "GSM4141874", "GSM4141875", "GSM4141876", "GSM4141877", "GSM4141878", "GSM4141879", "GSM4141880", "GSM4141881", "GSM4141882"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "21415", "taxon": "Musa acuminata AAA Group", "title": "Transcriptomics Library Data of Chitosan-coated Cavendish Banana", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRP227182", "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=SRP227182", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRP227182", "version": null, "note": "NCBI's Gene Expression Omnibus (GEO) with GEO series accession number GSE139457https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139457Raw data are available at NCBI's Sequence Read Archive (SRA) database (accession number SRP227182) https://trace.ncbi.nlm.nih.gov/Traces/sra/?study=SRP227182", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "NCBI's Gene Expression Omnibus (GEO) with GEO series accession number GSE139457https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139457Raw data are available at NCBI's Sequence Read Archive (SRA) database (accession number SRP227182) https://trace.ncbi.nlm.nih.gov/Traces/sra/?study=SRP227182", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32181300:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4bf72085e8698a079942465328ed873035cd43c8a593343dec5915975651d598", "bytes": 1448, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#undtbl1", "version": null, "note": "Specification Table", "structure": {"pmcid": "PMC7066065", "section_index": 1, "section_title": "p", "row_count": 10, "column_count": 2}, "table": {"label": null, "caption": "Specification Table", "rows": [["Subject Area", "Biological Sciences"], ["Specific subject area", "Fruit ripening"], ["Type of data", "Transcriptomics data (abundance measurements generated from RNA-seq data)"], ["How data were acquired", "Illumina HiSeq. 2000 platform"], ["Data format", "Raw: fastq.gz filesProcessed Data: Tab-delimited text files with FPKM values"], ["Parameters for data collection", "Transcriptomics of Cavendish banana pulp from uncoated and chitosan coated conditions"], ["Description of data collection", "Total RNA was derived from pulp of uncoated and chitosan coated Cavendish banana and was sequenced by using Illumina Hiseq 2000"], ["Data source location", "Bandung, West Java, Indonesia (6°53′28.9″S 107°36′38.3″E)"], ["Data accessibility", "NCBI's Gene Expression Omnibus (GEO) with GEO series accession number GSE139457https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139457Raw data are available at NCBI's Sequence Read Archive (SRA) database (accession number SRP227182) https://trace.ncbi.nlm.nih.gov/Traces/sra/?study=SRP227182"], ["Related research article", "Lustriane, F.M. Dwivany, V. Suendo, M. Reza, Effect of chitosan and chitosan nanoparticles on post harvest quality on banana fruits, J Plant Biotechnol 43 (2018) 36–44. https://doi.org/10.5010/JPB.2018.45.1.036 [1]"]], "row_count": 10, "column_count": 2, "numeric_cells": 5, "header_rows": 0, "locator": "section[1]/table-wrap[1]#undtbl1"}}, {"id": "asset:table:pmid:32181300:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:24e1bf712ab93fc56ef84132b2ab19a66672f386af3bed22c0c2b1aebc40eb38", "bytes": 489, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[2]#undtbl2", "version": null, "note": null, "structure": {"pmcid": "PMC7066065", "section_index": 1, "section_title": "p", "row_count": 1, "column_count": 1}, "table": {"label": null, "caption": null, "rows": [["Value of the Data•These data provide the first information of global gene expression in response to chitosan coating during banana ripening.•These data are crucial to identify candidate genes involved in fruit ripening in response to chitosan coating.•These data will be useful to design a better management of banana postharvest."]], "row_count": 1, "column_count": 1, "numeric_cells": 0, "header_rows": 0, "locator": "section[1]/table-wrap[2]#undtbl2"}}, {"id": "asset:table:pmid:32181300:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4713ebdc5d555d6c402dace90c4194584767e7cd6c468a9e014d237ee63324bf", "bytes": 1916, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#tbl1", "version": null, "note": "Output statistics of the transcriptome from day 1 control (1K), day 1 chitosan-coated (1A), day 7 control (7K), and day 7 chitosan-coated (7A) of Musa acuminata (AAA Group) ‘Cavendish’ fruit in each replicate (replicate a, b, and c) of paired-end expreriment.", "structure": {"pmcid": "PMC7066065", "section_index": 2, "section_title": "Data description", "row_count": 25, "column_count": 5}, "table": {"label": "Table 1", "caption": "Output statistics of the transcriptome from day 1 control (1K), day 1 chitosan-coated (1A), day 7 control (7K), and day 7 chitosan-coated (7A) of Musa acuminata (AAA Group) ‘Cavendish’ fruit in each replicate (replicate a, b, and c) of paired-end expreriment.", "rows": [["No.", "Samples ID", "Total Reads", "Total Nucleotides", "GC Percentage"], ["1.", "1K_a_1.fastq.gz", "16,710,129", "1,687,723,029", "51"], ["2.", "1K_a_2.fastq.gz", "16,710,129", "1,687,723,029", "51"], ["3.", "1K_b_1.fastq.gz", "18,934,874", "1,912,422,274", "51"], ["4.", "1K_b_2.fastq.gz", "18,934,874", "1,912,422,274", "51"], ["5.", "1K_c_1.fastq.gz", "18,217,207", "1,839,937,907", "49"], ["6.", "1K_c_2.fastq.gz", "18,217,207", "1,839,937.907", "48"], ["7.", "1A_a_1.fastq.gz", "18,726,200", "1,891,346,200", "49"], ["8.", "1A_a_2.fastq.gz", "18,726,200", "1.891.346.200", "49"], ["9.", "1A_b_1.fastq.gz", "20,302,208", "2,050,523,008", "49"], ["10.", "1A_b_2.fastq.gz", "20,302,208", "2,050,523,008", "49"], ["11.", "1A_c_1.fastq.gz", "16,155,947", "1,631,750,647", "51"], ["12.", "1A_c_2.fastq.gz", "16,155,947", "1,631,750,647", "51"], ["13.", "7K_a_1.fastq.gz", "23,587,110", "2,382,298,110", "50"], ["14.", "7K_a_2.fastq.gz", "23,587,110", "2,382,298,110", "50"], ["15.", "7K_b_1.fastq.gz", "16,699,855", "1,686,685,355", "51"], ["16.", "7K_b_2.fastq.gz", "16,699,855", "1,686,685,355", "51"], ["17.", "7K_c_1.fastq.gz", "18,626,323", "1,881,258,623", "48"], ["18.", "7K_c_2.fastq.gz", "18,626,323", "1,881,258,623", "48"], ["19.", "7A_a_1.fastq.gz", "18,734,174", "1,892,151,574", "50"], ["20.", "7A_a_2.fastq.gz", "18,734,174", "1,892,151,574", "50"], ["21.", "7A_b_1.fastq.gz", "19,532,908", "1,972,823,708", "50"], ["22.", "7A_b_2.fastq.gz", "19,532,908", "1,972,823,708", "50"], ["23.", "7A_c_1.fastq.gz", "20,828,843", "2,103,713,143", "49"], ["24.", "7A_c_2.fastq.gz", "20,828,843", "2,103,713,143", "49"]], "row_count": 25, "column_count": 5, "numeric_cells": 120, "header_rows": 1, "locator": "section[2]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:32181300:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6211b8c7f25324e72f9218f883e1a4cba2d9ac1a82153b0d6b9d4243094aecce", "bytes": 1013, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[2]#tbl2", "version": null, "note": "Mapping result and transcripts detection of the transcriptome from day 1 control (1K), day 1 chitosan-coated (1A), day 7 control (7K), and day 7 chitosan-coated (7A) of Musa acuminata (AAA Group) ‘Cavendish’ fruit.", "structure": {"pmcid": "PMC7066065", "section_index": 2, "section_title": "Data description", "row_count": 13, "column_count": 5}, "table": {"label": "Table 2", "caption": "Mapping result and transcripts detection of the transcriptome from day 1 control (1K), day 1 chitosan-coated (1A), day 7 control (7K), and day 7 chitosan-coated (7A) of Musa acuminata (AAA Group) ‘Cavendish’ fruit.", "rows": [["No.", "Sample", "Mapped Reads (%)", "Transcripts Detected", "Accession Number"], ["1.", "1K_a.txt", "82.7", "34,630", "GSM4141871"], ["2.", "1K_b.txt", "81.7", "34,830", "GSM4141872"], ["3.", "1K_c.txt", "77.6", "33,973", "GSM4141873"], ["4.", "1A_a.txt", "77.6", "34,226", "GSM4141874"], ["5.", "1A_b.txt", "79.0", "33,796", "GSM4141875"], ["6.", "1A_c.txt", "82.8", "34,966", "GSM4141876"], ["7.", "7K_a.txt", "83.8", "35,943", "GSM4141877"], ["8.", "7K_b.txt", "81.6", "35,683", "GSM4141878"], ["9.", "7K_c.txt", "75.8", "34,571", "GSM4141879"], ["10.", "7A_a.txt", "80.5", "35,363", "GSM4141880"], ["11.", "7A_b.txt", "81.2", "35,468", "GSM4141881"], ["12.", "7A_c.txt", "78.8", "34,340", "GSM4141882"]], "row_count": 13, "column_count": 5, "numeric_cells": 60, "header_rows": 1, "locator": "section[2]/table-wrap[2]#tbl2"}}], "gaps": ["asset:data:geo:GSE139457 not downloaded", "asset:data:geo:GSE139457 licence not read", "asset:data:geo:SRP227182 not downloaded", "asset:data:geo:SRP227182 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": ["GSE139457", "SRP227182"], "resolved_accessions": ["GSE139457"], "statements": ["NCBI's Gene Expression Omnibus (GEO) with GEO series accession number GSE139457https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE139457Raw data are available at NCBI's Sequence Read Archive (SRA) database (accession number SRP227182) https://trace.ncbi.nlm.nih.gov/Traces/sra/?study=SRP227182"], "basis": "The paper names GSE139457 in NCBI's Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:32181300", "data:geo:GSE139457", "asset:table:pmid:32181300:1", "asset:table:pmid:32181300:2", "asset:table:pmid:32181300:3", "asset:table:pmid:32181300:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE139457"]}, "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": "2026-10-31T18:18:42Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 9650, "completion_tokens": 999, "cached_tokens": 792}}, "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:32181300", "type": "paper", "label": "pmid:32181300"}, {"id": "source:pmid:32181300", "type": "manuscript", "label": "PMID 32181300 full text"}, {"id": "data:geo:GSE139457", "type": "dataset", "label": "GEO GSE139457"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32181300", "type": "paper", "label": "pmid:32181300"}, {"id": "source:pmid:32181300", "type": "manuscript", "label": "PMID 32181300 full text"}, {"id": "data:geo:GSE139457", "type": "dataset", "label": "GEO GSE139457"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32181300", "type": "extraction", "used": ["source:pmid:32181300"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE139457", "type": "accession_resolution", "used": ["data:geo:GSE139457"], "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:32181300", "parent_hash": "sha256:dc13241f85a53add4b2d8e99e2ce76ed293d1afa600e9a48fd7b14846500acd9", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE139457 licence not read", "asset:data:geo:GSE139457 not downloaded", "asset:data:geo:SRP227182 licence not read", "asset:data:geo:SRP227182 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Dataset of Cavendish banana transcriptome in response to chitosan coating application.", "33,797-35,944 transcripts were detected. The transcriptomics data discussed in this publication are acces", "r differential gene expression analysis. The RNA-sequencing generated ranged from 16,155,947 to 23,587,1"], "order_basis": "paper_text_order:0", "id": "assay:1"}]}