A highly resolved integrated transcriptomic atlas of human breast cancers.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40161579", "kind": "science-record", "revision": 2, "content_hash": "sha256:12301d9bba135b2eee3e9a62868b930b659942de0b7aaa264b84d2fd838dba60", "created_at": "2026-11-01T10:25:50Z", "updated_at": "2026-11-01T14:01:38Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "A highly resolved integrated transcriptomic atlas of human breast cancers.", "doi": "10.1101/2025.03.13.643025", "pmid": "40161579", "authors": null, "journal": "bioRxiv : the preprint server for biology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:40161579"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:40161579", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40161579' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40161579", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1101/2025.03.13.643025", "sha256": "sha256:14567da23da55d37d810f8bdc6e6e9f8fb4a39183fae6cfdebef29d9fb22b60e", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1101/2025.03.13.643025", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40161579:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a605f3d3fd8e510d9acfe8189b97e91955ac8cbcd2bbc48aec4215bc098950c1", "bytes": 907, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[33]/table-wrap[1]#T1", "version": null, "note": "Summary of Datasets used in Atlas", "structure": {"pmcid": "PMC11952505", "section_index": 33, "section_title": "(untitled)", "row_count": 11, "column_count": 6}, "table": {"label": "Table 1:", "caption": "Summary of Datasets used in Atlas", "rows": [["Dataset", "# Patients", "# Cells", "System", "PMID", "Data Link"], [""], ["Pal et al. 2021", "33", "224,823", "10× 3’", "33950524", "GSE161529"], ["Bassez et al. 2021", "31", "78,549", "10× 5’", "33958794", "Lambrechts lab"], ["Wu et al. 2021", "26", "99,876", "10× 3’ v2", "34493872", "GSE176078"], ["Wang et al. 2024", "14", "48,553", "10× 3’ v2", "38382468", "GSE248288"], ["Qian et al. 2020", "14", "40,665", "10× 3’ v2 & 10× 5’ v2", "32561858", "Lambrechts lab"], ["Tietscher et al. 2023", "12", "97,301", "10× 3’ v3", "36609566", "E-MTAB-10607"], ["Liu et al. 2023", "4", "27,490", "10× 3’ v3", "36594618", "GSE225600"], ["Gao et al. 2021", "4", "3,943", "10× 3’ v2 & 10× 5’ v2", "33462507", "GSE148673"], ["Total", "138", "621,200", "", "", ""]], "row_count": 11, "column_count": 6, "numeric_cells": 48, "header_rows": 2, "locator": "section[33]/table-wrap[1]#T1"}}], "gaps": ["asset:source:pmid:40161579 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40161579", "asset:table:pmid:40161579:1"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40161579"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "4a2d0bb64be52ad351e90a6a60d52191bcbc28bb794b654c7fc96eaa034492db", "source_hash": "14567da23da55d37d810f8bdc6e6e9f8fb4a39183fae6cfdebef29d9fb22b60e", "raw_response_sha256": "sha256:34780adc5367584002b73c4c79a57db3c6e697510d9c44162f83968b88f1ce7a", "raw_response_chars": 5615}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "74f220d6c0e556257456ae3de761c7001329ed7eddf71d45043c9aa3835466c4", "source_hash": "14567da23da55d37d810f8bdc6e6e9f8fb4a39183fae6cfdebef29d9fb22b60e", "raw_response_sha256": "sha256:5432d88d868bfa74f2701e40707a80a263d926dba79d2386b5b945c9be1b6d6f", "raw_response_chars": 30609}], "target_providers": [], "agreement": false, "disagreements": {"target_result": {"minimax": "An integrated single-cell transcriptomic atlas of human breast cancer totaling > 600,000 cells across 138 patients.", "minimax_alt": "In this study, we developed an integrated single cell transcriptomic (scRNAseq) atlas of human breast cancer (BC), the largest resource of its kind, totaling > 600,000 cells across 138 patients.", "decisive": false}, "work_type": {"minimax": "physical_data_generation", "minimax_alt": "analysis_only_for_target", "decisive": true}, "physical_methods": {"minimax": ["single-cell RNA sequencing (scRNAseq)"], "minimax_alt": [], "decisive": false}, "analysis_methods": {"minimax": ["entropy-based cell type diversity metric (CTDS)", "sccomp differential abundance analysis with bimodal_mean_variability_association = TRUE", "K2Taxonomer", "brcasurv", "GSVA", "Cox proportional hazards model", "FDR correction", "Fisher’s method for combining p-values"], "minimax_alt": ["Rigorous integration and annotation of publicly available scRNAseq data", "Taxonomic analysis of each compartment using K2Taxonomer"], "decisive": false}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": [{"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}]}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:af483488abcd5fa1a2f2cc5d785af4a3dee6c514e1fa4c062325bd2060999158", "type": "sep_package", "label": "SEP v1 package for pmid:40161579"}], "activities": [{"id": "activity:conversion:pmid:40161579", "type": "conversion", "used": ["package:af483488abcd5fa1a2f2cc5d785af4a3dee6c514e1fa4c062325bd2060999158"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:40161579", "parent_hash": "sha256:60060f8e17bc87f4d57380a525ddc640007b0ad5c51bd6ed2153b4d26f2e90c0", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40161579 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40161579' does not resolve to a declared asset", "targets"]}