Copy number analysis of the low-copy repeats at the primate NPHP1 locus by array comparative genomic hybridization.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27222811", "kind": "science-record", "revision": 4, "content_hash": "sha256:71f5214cefdbca2f7e503e2ee9a777bb9e70909a852c1148af3bec63c0bcc72f", "created_at": "2026-11-01T15:40:18Z", "updated_at": "2026-11-01T21:20:32Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Copy number analysis of the low-copy repeats at the primate NPHP1 locus by array comparative genomic hybridization.", "doi": "10.1016/j.gdata.2016.04.008", "pmid": "27222811", "authors": ["Bo Yuan", "Pengfei Liu", "Jeffrey Rogers", "James R Lupski"], "journal": "Genomics data", "year": 2016, "abstract": "Array comparative genomic hybridization (aCGH) has been widely used to detect copy number variants (CNVs) in both research and clinical settings. A customizable aCGH platform may greatly facilitate copy number analyses in genomic regions with higher-order complexity, such as low-copy repeats (LCRs). Here we present the aCGH analyses focusing on the 45 kb LCRs [1] at the NPHP1 region with diverse copy numbers in humans. Also, the interspecies aCGH analysis comparing human and nonhuman primates revealed dynamic copy number transitions of the human 45 kb LCR orthologues during primate evolution and therefore shed light on the origin of complexity at this locus. The original aCGH data are available at GEO under GSE73962.", "claims": [{"id": "claim-method", "statement": "ADM-2 algorithm with threshold 4.0 was used to call CNVs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27222811", "locator": "sections[6] \"aCGH — experimental procedures\" paragraph 2", "quote": "ADM-2 algorithm with threshold 4.0 was used to call CNVs."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original aCGH data are available at GEO under GSE73962.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27222811", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The original aCGH data are available at GEO under GSE73962."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A customized aCGH analysis revealed dynamic copy-number transitions of the human 45 kb LCR orthologues during primate evolution; copy number was estimated from normalized log2 ratios using the ADM-2 algorithm, and the original data are available at GEO under GSE73962.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:27222811", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Also, the interspecies aCGH analysis comparing human and nonhuman primates revealed dynamic copy number transitions of the human 45 kb LCR orthologues during primate evolution and therefore shed light on the origin of complexity at this locus."}, {"asset": "source:pmid:27222811", "locator": "sections[6] \"aCGH — experimental procedures\" paragraph 2", "quote": "Copy number was determined by normalized log2 ratio (LR) of Cy5/Cy3 fluorescence signal of each probe. ADM-2 algorithm with threshold 4.0 was used to call CNVs."}, {"asset": "source:pmid:27222811", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The original aCGH data are available at GEO under GSE73962."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "A customized aCGH analysis revealed dynamic copy-number transitions of the human 45 kb LCR orthologues during primate evolution; copy number was estimated from normalized log2 ratios using the ADM-2 algorithm, and the original data are available at GEO under GSE73962.", "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:27222811"], "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:GSE73962"], "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:GSE73962"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27222811", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2016.04.008", "sha256": "sha256:b7435013c3a083a4bf527b3631dcdc050bc193dc496bda1df447dfe4e3a2b62e", "bytes": 9534, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2016.04.008", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4872932", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE73962", "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=GSE73962", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE73962", "version": null, "note": "The original aCGH data are available at GEO under GSE73962.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original aCGH data are available at GEO under GSE73962.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1906780", "GSM1906781", "GSM1906782", "GSM1906783", "GSM1906784", "GSM1906785", "GSM1906786", "GSM1906787", "GSM1906788", "GSM1906789", "GSM1906790", "GSM1906791", "GSM1906792", "GSM1906793", "GSM1906794", "GSM1906795", "GSM1906796", "GSM1906797", "GSM1906798", "GSM1906799", "GSM1906800", "GSM1906801", "GSM1906802", "GSM1906803", "GSM1906804", "GSM1906805", "GSM1906806", "GSM1906807", "GSM1906808", "GSM1906809", "GSM1906810", "GSM1906811"], "sample_count": 32, "group_sizes": null, "group_sizes_basis": null, "platform": "21019", "taxon": "Pan troglodytes; Papio anubis; Macaca mulatta; Gorilla gorilla; Pongo abelii; Homo sapiens", "title": "Comparative genomic analyses of the human NPHP1 locus reveal complex genomic architecture and its regional evolution in primates", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:27222811:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2c15472be017223b686e2430c94471467d30dd41042030ba1f26dea3c258941b", "bytes": 652, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0005", "version": null, "note": null, "structure": {"pmcid": "PMC4872932", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Specifications"], ["Organism/cell line/tissue", "Papio anubis, Macaca mulatta, Pongo abelii, Gorilla gorilla, Pan troglodytes, Homo sapiens"], ["Sex", "NA"], ["Sequencer or array type", "Agilent customized aCGH with 8x60K format"], ["Data format", "Analyzed"], ["Experimental factors", "Normal"], ["Experimental features", "Copy number estimation of the human 45 kb LCRs or its nonhuman primate orthologues in the test samples using NA10851 as control"], ["Consent", "NA"], ["Sample source location", "Houston, TX USA"]], "row_count": 9, "column_count": 2, "numeric_cells": 2, "header_rows": 0, "locator": "section[1]/table-wrap[1]#t0005"}}], "gaps": ["asset:data:geo:GSE73962 not downloaded", "asset:data:geo:GSE73962 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "ADM-2 algorithm with threshold 4.0", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "ADM-2 algorithm with threshold 4.0 was used to call CNVs."}}], "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": "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 (ADM-2 algorithm with threshold 4.0), 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": ["GSE73962"], "resolved_accessions": ["GSE73962"], "statements": ["The original aCGH data are available at GEO under GSE73962."], "basis": "The paper names GSE73962 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:27222811", "data:geo:GSE73962", "asset:table:pmid:27222811:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE73962"]}, "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": "2026-10-31T18:28:28Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 22535, "completion_tokens": 2044, "cached_tokens": 13568}}, "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:27222811", "type": "paper", "label": "pmid:27222811"}, {"id": "source:pmid:27222811", "type": "manuscript", "label": "PMID 27222811 full text"}, {"id": "data:geo:GSE73962", "type": "dataset", "label": "GEO GSE73962"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:27222811", "type": "paper", "label": "pmid:27222811"}, {"id": "source:pmid:27222811", "type": "manuscript", "label": "PMID 27222811 full text"}, {"id": "data:geo:GSE73962", "type": "dataset", "label": "GEO GSE73962"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-27222811", "type": "extraction", "used": ["source:pmid:27222811"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE73962", "type": "accession_resolution", "used": ["data:geo:GSE73962"], "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:27222811", "parent_hash": "sha256:663b61c6569a18aaaa76dfdd792a5245b3fa2c5c6ba4708fc16b59ba0e98a0e0", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE73962 licence not read", "asset:data:geo:GSE73962 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"]}