GSA: Genome Sequence Archive<sup/>.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28387199", "kind": "science-record", "revision": 2, "content_hash": "sha256:7087802707ebe6f2fb6f0cd2ce6541566e00fbad4e54b510f559888eccd7b9d1", "created_at": "2026-11-01T15:40:25Z", "updated_at": "2026-11-01T18:48:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "GSA: Genome Sequence Archive<sup/>.", "doi": "10.1016/j.gpb.2017.01.001", "pmid": "28387199", "authors": ["Yanqing Wang", "Fuhai Song", "Junwei Zhu", "Sisi Zhang", "Yadong Yang", "Tingting Chen", "Bixia Tang", "Lili Dong", "Nan Ding", "Qian Zhang", "Zhouxian Bai", "Xunong Dong", "Huanxin Chen", "Mingyuan Sun", "Shuang Zhai", "Yubin Sun", "Lei Yu", "Li Lan", "Jingfa Xiao", "Xiangdong Fang", "Hongxing Lei", "Zhang Zhang", "Wenming Zhao"], "journal": "Genomics, proteomics & bioinformatics", "year": 2017, "abstract": "With the rapid development of sequencing technologies towards higher throughput and lower cost, sequence data are generated at an unprecedentedly explosive rate. To provide an efficient and easy-to-use platform for managing huge sequence data, here we present Genome Sequence Archive (GSA; http://bigd.big.ac.cn/gsa or http://gsa.big.ac.cn), a data repository for archiving raw sequence data. In compliance with data standards and structures of the International Nucleotide Sequence Database Collaboration (INSDC), GSA adopts four data objects (BioProject, BioSample, Experiment, and Run) for data organization, accepts raw sequence reads produced by a variety of sequencing platforms, stores both sequence reads and metadata submitted from all over the world, and makes all these data publicly available to worldwide scientific communities. In the era of big data, GSA is not only an important complement to existing INSDC members by alleviating the increasing burdens of handling sequence data deluge, but also takes the significant responsibility for global big data archive and provides free unrestricted access to all publicly available data in support of research activities throughout the world.", "claims": [{"id": "claim-data-access", "statement": "GSA accepts data submissions from all over the world, covers the spectrum of sequence reads generated by a variety of sequencing platforms, and accommodates several commonly-used file formats, like FASTQ, BAM, and VCF.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28387199", "locator": "sections[5] \"Data archive and statistics\" paragraph 2", "quote": "GSA accepts data submissions from all over the world, covers the spectrum of sequence reads generated by a variety of sequencing platforms, and accommodates several commonly-used file formats, like FASTQ, BAM, and VCF."}], "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:28387199"], "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:28387199", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gpb.2017.01.001", "sha256": "sha256:7fd9d70ab2eddf414a066231a07fa3e6cd37bada318179fbd40f131c51e15a52", "bytes": 16110, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gpb.2017.01.001", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5339404", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "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": "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 (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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["GSA accepts data submissions from all over the world, covers the spectrum of sequence reads generated by a variety of sequencing platforms, and accommodates several commonly-used file formats, like FASTQ, BAM, and VCF."], "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:28387199"], "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": null, "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:28387199", "type": "paper", "label": "pmid:28387199"}, {"id": "source:pmid:28387199", "type": "manuscript", "label": "PMID 28387199 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28387199", "type": "paper", "label": "pmid:28387199"}, {"id": "source:pmid:28387199", "type": "manuscript", "label": "PMID 28387199 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28387199", "type": "extraction", "used": ["source:pmid:28387199"], "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:28387199", "parent_hash": "sha256:6883efe804e90343ff57ade15c9ed60998a1180a509d5f6d515ffdcca60297be", "fork_of": null, "generation": 1}, "gaps": ["execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}