{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39712483", "kind": "science-record", "revision": 2, "content_hash": "sha256:027dc51cfd89e91b631b58d7a3f7a5a2de4daa2a15465f5378abe72f79347573", "created_at": "2026-11-01T20:30:02Z", "updated_at": "2026-11-01T21:34:35Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Exploring the impact of deubiquitination on melanoma prognosis through single-cell RNA sequencing.", "doi": "10.3389/fgene.2024.1509049", "pmid": "39712483", "authors": ["Su Peng", "Jiaheng Xie", "Xiaohu He"], "journal": "Frontiers in genetics", "year": 2024, "abstract": "Background: Cutaneous melanoma, characterized by the malignant proliferation of melanocytes, exhibits high invasiveness and metastatic potential. Thus, identifying novel prognostic biomarkers and therapeutic targets is essential.\nMethods: We utilized single-cell RNA sequencing data (GSE215120) from the Gene Expression Omnibus (GEO) database, preprocessing it with the Seurat package. Dimensionality reduction and clustering were executed through Principal Component Analysis (PCA) and Uniform Manifold Approximation and Projection (UMAP). Cell types were annotated based on known marker genes, and the AUCell algorithm assessed the enrichment of deubiquitination-related genes. Cells were categorized into DUB_high and DUB_low groups based on AUCell scores, followed by differential expression analysis. Importantly, we constructed a robust prognostic model utilizing various genes, which was evaluated in the TCGA cohort and an external validation cohort.\nResults: Our prognostic model, developed using Random Survival Forest (RSF) and Ridge Regression methods, demonstrated excellent predictive performance, evidenced by high C-index and AUC values across multiple cohorts. Furthermore, analyses of immune cell infiltration and tumor microenvironment scores revealed significant differences in immune cell distribution and microenvironment characteristics between high-risk and low-risk groups. Functional experiments indicated that TBC1D16 significantly impacts the migration and proliferation of melanoma cells.\nConclusion: This study highlights the critical role of deubiquitination in melanoma and presents a novel prognostic model that effectively stratifies patient risk. The model's strong predictive ability enhances clinical decision-making and provides a framework for future studies on the therapeutic potential of deubiquitination mechanisms in melanoma progression. Further validation and exploration of this model's applicability in clinical settings are warranted.", "claims": [{"id": "claim-method", "statement": "Among the 101 combinations tested, the Random Survival Forest (RSF) combined with Ridge regression emerged as the optimal model, achieving the highest concordance index (c-index) in the validation cohort (Figure 2).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39712483", "locator": "sections[19] \"Identification of the optimal prognostic model\" paragraph 3", "quote": "Among the 101 combinations tested, the Random Survival Forest (RSF) combined with Ridge regression emerged as the optimal model, achieving the highest concordance index (c-index) in the validation cohort (Figure 2)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39712483", "locator": "sections[24] \"Data availability statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Notably, the AUC values ranged from 0.52 to 0.85 across the cohorts, with the TCGA cohort achieving an AUC of 0.75 at the 5-year mark, indicating strong predictive capability.", "kind": "quantitative", "target": {"value": 0.75, "unit": "auc", "tolerance": null, "source": "Notably, the AUC values ranged from 0.52 to 0.85 across the cohorts, with the TCGA cohort achieving an AUC of 0.75 at the 5-year mark, indicating strong predictive capability."}, "evidence": [{"asset": "source:pmid:39712483", "locator": "sections[20] \"Survival analysis and model validation in multiple cohorts\" paragraph 4", "quote": "Notably, the AUC values ranged from 0.52 to 0.85 across the cohorts, with the TCGA cohort achieving an AUC of 0.75 at the 5-year mark, indicating strong predictive capability."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Notably, the AUC values ranged from 0.52 to 0.85 across the cohorts, with the TCGA cohort achieving an AUC of 0.75 at the 5-year mark, indicating strong predictive capability.", "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:39712483"], "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:GSE19234"], "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": {"hazard_ratio": "ied, and hazard ratios (HR) were calculated using"}, "inputs": ["data:geo:GSE19234"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39712483", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2024.1509049", "sha256": "sha256:c75264d8c5faf729a99a39a48cde21cd6a0cffd787e6448a085a4751ce842c12", "bytes": 39744, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2024.1509049", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11659643", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE19234", "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=GSE19234", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19234", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM476606", "GSM476607", "GSM476608", "GSM476609", "GSM476610", "GSM476611", "GSM476612", "GSM476613", "GSM476614", "GSM476615", "GSM476616", "GSM476617", "GSM476618", "GSM476619", "GSM476620", "GSM476621", "GSM476622", "GSM476623", "GSM476624", "GSM476625", "GSM476626", "GSM476627", "GSM476628", "GSM476629", "GSM476630", "GSM476631", "GSM476632", "GSM476633", "GSM476634", "GSM476635", "GSM476636", "GSM476637", "GSM476638", "GSM476639", "GSM476640", "GSM476641", "GSM476642", "GSM476643", "GSM476644", "GSM476645", "GSM476646", "GSM476647", "GSM476648", "GSM476649"], "sample_count": 44, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Immune profile and mitotic index of metastatic melanoma lesions enhance clinical staging in predicting patient survival.", "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:GSE215120", "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=GSE215120", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE215120", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM6622292", "GSM6622293", "GSM6622294", "GSM6622295", "GSM6622296", "GSM6622297", "GSM6622298", "GSM6622299", "GSM6622300", "GSM6622301", "GSM6622302"], "sample_count": 11, "group_sizes": null, "group_sizes_basis": null, "platform": "20795", "taxon": "Homo sapiens", "title": "A single-cell analysis reveals tumor heterogeneity and immune environment of acral melanoma [scRNA-Seq]", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE22153", "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=GSE22153", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE22153", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM550966", "GSM550967", "GSM550968", "GSM550969", "GSM550970", "GSM550971", "GSM550972", "GSM550973", "GSM550974", "GSM550975", "GSM550976", "GSM550977", "GSM550978", "GSM550979", "GSM550980", "GSM550981", "GSM550982", "GSM550983", "GSM550984", "GSM550985", "GSM550986", "GSM550987", "GSM550988", "GSM550989", "GSM550990", "GSM550991", "GSM550992", "GSM550993", "GSM550994", "GSM550995", "GSM550996", "GSM550997", "GSM550998", "GSM550999", "GSM551000", "GSM551001", "GSM551002", "GSM551003", "GSM551004", "GSM551005", "GSM551006", "GSM551007", "GSM551008", "GSM551009", "GSM551010", "GSM551011", "GSM551012", "GSM551013", "GSM551014", "GSM551015", "GSM551016", "GSM551017", "GSM551018", "GSM551019", "GSM551020", "GSM551021", "GSM551022"], "sample_count": 57, "group_sizes": null, "group_sizes_basis": null, "platform": "6102", "taxon": "Homo sapiens", "title": "Gene Experssion Profiling-Based Identification of Molecular Subtypes in Stage IV Melanoma with Different Clinical Outcome (test set)", "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:GSE59455", "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=GSE59455", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE59455", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1437254", "GSM1437255", "GSM1437256", "GSM1437257", "GSM1437258", "GSM1437259", "GSM1437260", "GSM1437261", "GSM1437262", "GSM1437263", "GSM1437264", "GSM1437265", "GSM1437266", "GSM1437267", "GSM1437268", "GSM1437269", "GSM1437270", "GSM1437271", "GSM1437272", "GSM1437273", "GSM1437274", "GSM1437275", "GSM1437276", "GSM1437277", "GSM1437278", "GSM1437279", "GSM1437280", "GSM1437281", "GSM1437282", "GSM1437283", "GSM1437284", "GSM1437285", "GSM1437286", "GSM1437287", "GSM1437288", "GSM1437289", "GSM1437290", "GSM1437291", "GSM1437292", "GSM1437293", "GSM1437294", "GSM1437295", "GSM1437296", "GSM1437297", "GSM1437298", "GSM1437299", "GSM1437300", "GSM1437301", "GSM1437302", "GSM1437303", "GSM1437304", "GSM1437305", "GSM1437306", "GSM1437307", "GSM1437308", "GSM1437309", "GSM1437310", "GSM1437311", "GSM1437312", "GSM1437313", "GSM1437314", "GSM1437315", "GSM1437316", "GSM1437317", "GSM1437318", "GSM1437319", "GSM1437320", "GSM1437321", "GSM1437322", "GSM1437323", "GSM1437324", "GSM1437325", "GSM1437326", "GSM1437327", "GSM1437328", "GSM1437329", "GSM1437330", "GSM1437331", "GSM1437332", "GSM1437333", "GSM1437334", "GSM1437335", "GSM1437336", "GSM1437337", "GSM1437338", "GSM1437339", "GSM1437340", "GSM1437341", "GSM1437342", "GSM1437343", "GSM1437344", "GSM1437345", "GSM1437346", "GSM1437347", "GSM1437348", "GSM1437349", "GSM1437350", "GSM1437351", "GSM1437352", "GSM1437353", "GSM1437354", "GSM1437355", "GSM1437356", "GSM1437357", "GSM1437358", "GSM1437359", "GSM1437360", "GSM1437361", "GSM1437362", "GSM1437363", "GSM1437364", "GSM1437365", "GSM1437366", "GSM1437367", "GSM1437368", "GSM1437369", "GSM1437370", "GSM1437371", "GSM1437372", "GSM1437373", "GSM1437374", "GSM1437375", "GSM1437376", "GSM1437377", "GSM1437378", "GSM1437379", "GSM1437380", "GSM1437381", "GSM1437382", "GSM1437383", "GSM1437384", "GSM1437385", "GSM1437386", "GSM1437387", "GSM1437388", "GSM1437389", "GSM1437390", "GSM1437391", "GSM1437392", "GSM1437393", "GSM1437394"], "sample_count": 141, "group_sizes": null, "group_sizes_basis": null, "platform": "8432", "taxon": "Homo sapiens", "title": "Whole genome expression data from formalin-fixed parrafin embedded (FFPE) primary and metastatic melanomas", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE19234 not downloaded", "asset:data:geo:GSE19234 licence not read", "asset:data:geo:GSE215120 not downloaded", "asset:data:geo:GSE215120 licence not read", "asset:data:geo:GSE22153 not downloaded", "asset:data:geo:GSE22153 licence not read", "asset:data:geo:GSE59455 not downloaded", "asset:data:geo:GSE59455 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "ied, and hazard ratios (HR) were calculated using"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "ied, and hazard ratios (HR) were calculated using"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "ied, and hazard ratios (HR) were calculated using"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-4", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Principal Component Analysis"}}, {"id": "method-5", "family": null, "specific": null, "label": "Random Survival Forest (RSF) combined with Ridge regression", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Among the 101 combinations tested, the Random Survival Forest (RSF) combined with Ridge regression emerged as the optimal model, achieving the highest concordance index (c-index) in the validation cohort (Figure 2)."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 0.75, "unit": "auc", "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.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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE215120", "GSE19234", "GSE22153", "GSE59455", "and GSE65904"], "resolved_accessions": ["GSE215120", "GSE19234", "GSE22153", "GSE59455"], "statements": ["The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding author."], "basis": "The paper names GSE215120, GSE19234, GSE22153, GSE59455 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:39712483", "data:geo:GSE19234"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE19234"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:43:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 10036, "completion_tokens": 1973, "cached_tokens": 128}}, "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:39712483", "type": "paper", "label": "pmid:39712483"}, {"id": "source:pmid:39712483", "type": "manuscript", "label": "PMID 39712483 full text"}, {"id": "data:geo:GSE19234", "type": "dataset", "label": "GEO GSE19234"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39712483", "type": "paper", "label": "pmid:39712483"}, {"id": "source:pmid:39712483", "type": "manuscript", "label": "PMID 39712483 full text"}, {"id": "data:geo:GSE19234", "type": "dataset", "label": "GEO GSE19234"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39712483", "type": "extraction", "used": ["source:pmid:39712483"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE19234", "type": "accession_resolution", "used": ["data:geo:GSE19234"], "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:39712483", "parent_hash": "sha256:0f010fbad01cc5706792a0d029df7231b5ce720eeb38ea3ed6b6977463357329", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE19234 licence not read", "asset:data:geo:GSE19234 not downloaded", "asset:data:geo:GSE215120 licence not read", "asset:data:geo:GSE215120 not downloaded", "asset:data:geo:GSE22153 licence not read", "asset:data:geo:GSE22153 not downloaded", "asset:data:geo:GSE59455 licence not read", "asset:data:geo:GSE59455 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ubiquitination on melanoma prognosis through single-cell RNA sequencing.", "c targets is essential. Methods: We utilized single-cell RNA sequencing data (GSE215120) from the Gene Expression Om", "rformed using GraphPad Prism and R software. Single-cell RNA sequencing analysis of cutaneous melanoma microenvironm", "lysis of cutaneous melanoma microenvironment Single-cell RNA sequencing analysis was performed on cutaneous melanoma"], "order_basis": "paper_text_order:26", "id": "assay:1"}, {"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": ["on on melanoma prognosis through single-cell RNA sequencing.", "essential. Methods: We utilized single-cell RNA sequencing data (GSE215120) from the Gene Expression Om", "g GraphPad Prism and R software. Single-cell RNA sequencing analysis of cutaneous melanoma microenvironm", "aneous melanoma microenvironment Single-cell RNA sequencing analysis was performed on cutaneous melanoma"], "order_basis": "paper_text_order:38", "id": "assay:2"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Kaplan-Meier"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T04:27:10+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}