Transcriptome dataset of sago palm in peat soil.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35242906", "kind": "science-record", "revision": 3, "content_hash": "sha256:8dc423eec12d9e38f6d773477074c01ca3b77dd1e000afd5886b81b73b8e5d2d", "created_at": "2026-11-01T17:37:00Z", "updated_at": "2026-11-01T18:58:24Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Transcriptome dataset of sago palm in peat soil.", "doi": "10.1016/j.dib.2022.107908", "pmid": "35242906", "authors": ["Wei-Jie Yan", "Hasnain Hussain", "Hung Hui Chung", "Norzainizul Julaihi", "Rina Tommy"], "journal": "Data in brief", "year": 2022, "abstract": "Sago palm (Metroxylon sagu Rottb.) is an important agricultural starch-producing palm that contributes to Malaysia's economics, especially in the State of Sarawak, Malaysian Borneo. In this palm tree, the central part of the plant storage-starch. Under normal condition, sago palm develop its trunk after 4-5 years being planted. However, sago palms planted on deep-peat soil failed to develop their trunk even after 17 years of being planted. This phenomenon is known as 'non-trunking', which eliminates the economic value of the palms. Numerous research has been done to address the phenomenon, but the molecular mechanisms of sago palm responding toward the responsible stresses are still lacking. Therefore, in this study, leaf samples were collected from trunking (normal) and non-trunking sago palms planted on peat soil for total RNA extraction, followed by next-generation sequencing using the BGISEQ-500 platform. The raw reads were cleaned, and de novo assembled using TRINITY software package. A total of 40.11 Gb bases were sequenced from the sago palm leaf samples. The assembled sequence produced 102,447 unigenes, with N50 score 1809 bp and GC ratio of 44.34%. The alignment of unigenes with seven functional databases (NR, NT, GO, KOG, KEGG, SwissProt and InterPro) resulted in the annotation of 65,523 (63.96%) unigenes. Functional annotation results in the detection of 46,335 coding DNA sequences by Transdecoder. A total of 30,039 simple-sequence repeats distributed on 21,676 unigenes were detected using Primer3 software, and 2355 transcription factor coding unigenes were predicted using getorf and hmmseach software. This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "claims": [{"id": "claim-data-access", "statement": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35242906", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The assembled sequence produced 102,447 unigenes, with N50 score 1809 bp and GC ratio of 44.34%.", "kind": "quantitative", "target": {"value": 44.34, "unit": "per cent", "tolerance": null, "source": "The assembled sequence produced 102,447 unigenes, with N50 score 1809 bp and GC ratio of 44.34%."}, "evidence": [{"asset": "source:pmid:35242906", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The assembled sequence produced 102,447 unigenes, with N50 score 1809 bp and GC ratio of 44.34%."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The assembled sequence produced 102,447 unigenes, with N50 score 1809 bp and GC ratio of 44.34%.", "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:35242906"], "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:GSE189085"], "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:GSE189085"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35242906", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2022.107908", "sha256": "sha256:85effecde31bc19bd4c35f425426d4f44c77de8717df59d34ff55338db546ec2", "bytes": 14019, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2022.107908", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8857430", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE189085", "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=GSE189085", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE189085", "version": null, "note": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5694359", "GSM5694360", "GSM5694361", "GSM5694362", "GSM5694363", "GSM5694364"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "30974", "taxon": "Metroxylon sagu", "title": "Transcriptome analysis of Trunking and Non-trunking Metroxylon sagu leaf tissue", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PRJNA781491", "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=PRJNA781491", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PRJNA781491", "version": null, "note": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "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": "2026-11-01T18:06:52Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRX13165895", "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=SRX13165895", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRX13165895", "version": null, "note": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "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": "2026-11-01T18:06:45Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRX13165896", "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=SRX13165896", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRX13165896", "version": null, "note": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "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": "2026-11-01T18:06:45Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRX13165897", "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=SRX13165897", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRX13165897", "version": null, "note": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "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": "2026-11-01T18:06:45Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRX13165898", "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=SRX13165898", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRX13165898", "version": null, "note": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "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": "2026-11-01T18:06:45Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRX13165899", "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=SRX13165899", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRX13165899", "version": null, "note": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085.", "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": "2026-11-01T18:06:45Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE189085 not downloaded", "asset:data:geo:GSE189085 licence not read", "asset:data:geo:PRJNA781491 not downloaded", "asset:data:geo:PRJNA781491 licence not read", "asset:data:geo:SRX13165895 not downloaded", "asset:data:geo:SRX13165895 licence not read", "asset:data:geo:SRX13165896 not downloaded", "asset:data:geo:SRX13165896 licence not read", "asset:data:geo:SRX13165897 not downloaded", "asset:data:geo:SRX13165897 licence not read", "asset:data:geo:SRX13165898 not downloaded", "asset:data:geo:SRX13165898 licence not read", "asset:data:geo:SRX13165899 not downloaded", "asset:data:geo:SRX13165899 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": null, "expected_value": 44.34, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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": ["PRJNA781491", "SRX13165895", "SRX13165896", "SRX13165897", "SRX13165898", "SRX13165899", "and SRX13165900", "GSE189085"], "resolved_accessions": ["GSE189085"], "statements": ["This work is registered under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive (SRA) database with accession numbers SRX13165895, SRX13165896, SRX13165897, SRX13165898, SRX13165899, and SRX13165900. Gene expression and annotation information are accessible in public functional genomics data repository Gene Expression Omnibus (GEO) with accession number GSE189085."], "basis": "The paper names GSE189085 in NCBI BioProject and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:35242906", "data:geo:GSE189085"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE189085"]}, "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": "2026-11-01T17:36:49Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 5263, "completion_tokens": 1470, "cached_tokens": 256}}, "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:35242906", "type": "paper", "label": "pmid:35242906"}, {"id": "source:pmid:35242906", "type": "manuscript", "label": "PMID 35242906 full text"}, {"id": "data:geo:GSE189085", "type": "dataset", "label": "GEO GSE189085"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35242906", "type": "paper", "label": "pmid:35242906"}, {"id": "source:pmid:35242906", "type": "manuscript", "label": "PMID 35242906 full text"}, {"id": "data:geo:GSE189085", "type": "dataset", "label": "GEO GSE189085"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35242906", "type": "extraction", "used": ["source:pmid:35242906"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE189085", "type": "accession_resolution", "used": ["data:geo:GSE189085"], "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:35242906", "parent_hash": "sha256:42d69dfbfa0dd568e98fc5a64fbc1ce30adc7f8b42fbb8fe3bb0e2846c0d2bc1", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE189085 licence not read", "asset:data:geo:GSE189085 not downloaded", "asset:data:geo:PRJNA781491 licence not read", "asset:data:geo:PRJNA781491 not downloaded", "asset:data:geo:SRX13165895 licence not read", "asset:data:geo:SRX13165895 not downloaded", "asset:data:geo:SRX13165896 licence not read", "asset:data:geo:SRX13165896 not downloaded", "asset:data:geo:SRX13165897 licence not read", "asset:data:geo:SRX13165897 not downloaded", "asset:data:geo:SRX13165898 licence not read", "asset:data:geo:SRX13165898 not downloaded", "asset:data:geo:SRX13165899 licence not read", "asset:data:geo:SRX13165899 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": ["Transcriptome dataset of sago palm in peat soil.", "d under NCBI BioProject PRJNA781491. The raw RNA sequencing data are available in Sequence Read Archive"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "amplicon_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["t soil for total RNA extraction, followed by next-generation sequencing using the BGISEQ-500 platform. The raw reads"], "order_basis": "paper_text_order:869", "id": "assay:2"}]}