Constructing an extracellular matrix-related prognostic model for idiopathic pulmonary fibrosis based on machine learning.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37858084", "kind": "science-record", "revision": 4, "content_hash": "sha256:a720e588832cf90be78dc7b34bdc8ea9e1ba335936c7276899540b1b163c1bb9", "created_at": "2026-11-01T19:02:42Z", "updated_at": "2026-11-01T22:10:29Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Constructing an extracellular matrix-related prognostic model for idiopathic pulmonary fibrosis based on machine learning.", "doi": "10.1186/s12890-023-02699-8", "pmid": "37858084", "authors": ["Hong Luo", "Jisong Yan", "Xia Zhou"], "journal": "BMC pulmonary medicine", "year": 2023, "abstract": "BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a chronic and progressive interstitial lung disease. Multiple research has revealed that the extracellular matrix (ECM) may be associated with the development and prognosis of IPF, however, the underlying mechanisms remain incompletely understood.\nMETHODS: We included GSE70866 dataset from the GEO database and established an ECM-related prognostic model utilizing LASSO, Random forest and Support vector machines algorithms. To compare immune cell infiltration levels between the high and low risk groups, we employed the ssGSEA algorithm. Enrichment analysis was conducted to explore pathway differences between the high-risk and low-risk groups. Finally, the model genes were validated using an external validation set consisting of IPF cases, as well as single-cell data analysis.\nRESULTS: Based on machine learning algorithms, we constructed an ECM-related risk model. IPF patients in the high-risk group had a worse overall survival rate than those in the low-risk group. The model's AUC predictive values were 0.786, 0.767, and 0.768 for the 1-, 2-, and 3-year survival rates, respectively. The validation cohort validated these findings, demonstrating our model's effective prognostication. Chemokine-related pathways were enriched through enrichment analysis. Moreover, immune cell infiltration varied significantly between the two groups. Finally, the validation results indicate that the expression levels of all the model genes exhibited significant differential expression.\nCONCLUSIONS: Based on CST6, PPBP, CSPG4, SEMA3B, LAMB2, SERPINB4 and CTF1, our study developed and validated an ECM-related risk model that accurately predicts the outcome of IPF patients.", "claims": [{"id": "claim-method", "statement": "We applied multivariate Cox analysis to establish a prognostic risk model consisting of 7 EAGs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37858084", "locator": "sections[10] \"Determination of prognostic risk model of EAGs in IPF\" paragraph 2", "quote": "We applied multivariate Cox analysis to establish a prognostic risk model consisting of 7 EAGs."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets generated and analysed during the current study are available in GEO (https://www.ncbi.nlm.nih.gov/geo), which are public functional genomics data repositories.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37858084", "locator": "sections[24] \"notes\" paragraph 1", "quote": "The datasets generated and analysed during the current study are available in GEO (https://www.ncbi.nlm.nih.gov/geo), which are public functional genomics data repositories."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Based on CST6, PPBP, CSPG4, SEMA3B, LAMB2, SERPINB4 and CTF1, our study developed and validated an ECM-related risk model that accurately predicts the outcome of IPF patients.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37858084", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "Based on CST6, PPBP, CSPG4, SEMA3B, LAMB2, SERPINB4 and CTF1, our study developed and validated an ECM-related risk model that accurately predicts the outcome of IPF patients."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Based on CST6, PPBP, CSPG4, SEMA3B, LAMB2, SERPINB4 and CTF1, our study developed and validated an ECM-related risk model that accurately predicts the outcome of IPF patients.", "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:37858084"], "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:GSE129605"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:machine_learning_random_forest", "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:GSE129605"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:machine_learning_random_forest"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37858084", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12890-023-02699-8", "sha256": "sha256:0b074e313b0a72be0f6bff60ba7d685282640d9d20f4e149f807268383299e05", "bytes": 29525, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12890-023-02699-8", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10585847", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE129605", "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=GSE129605", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE129605", "version": null, "note": "The datasets generated and analysed during the current study are available in GEO (https://www.ncbi.nlm.nih.gov/geo), which are public functional genomics data repositories.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and analysed during the current study are available in GEO (https://www.ncbi.nlm.nih.gov/geo), which are public functional genomics data repositories.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3716976", "GSM3716977", "GSM3716978", "GSM3716979", "GSM3716980", "GSM3716981", "GSM3716982", "GSM3716983", "GSM3716984", "GSM3716985", "GSM3716986"], "sample_count": 11, "group_sizes": null, "group_sizes_basis": null, "platform": "19057", "taxon": "Mus musculus", "title": "Defining the Activated Fibroblast Population in Lung Fibrosis Using Single Cell Sequencing", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE27957", "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=GSE27957", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27957", "version": null, "note": "The datasets generated and analysed during the current study are available in GEO (https://www.ncbi.nlm.nih.gov/geo), which are public functional genomics data repositories.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and analysed during the current study are available in GEO (https://www.ncbi.nlm.nih.gov/geo), which are public functional genomics data repositories.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM691362", "GSM691363", "GSM691364", "GSM691365", "GSM691366", "GSM691367", "GSM691368", "GSM691369", "GSM691370", "GSM691371", "GSM691372", "GSM691373", "GSM691374", "GSM691375", "GSM691376", "GSM691377", "GSM691378", "GSM691379", "GSM691380", "GSM691381", "GSM691382", "GSM691383", "GSM691384", "GSM691385", "GSM691386", "GSM691387", "GSM691388", "GSM691389", "GSM691390", "GSM691391", "GSM691392", "GSM691393", "GSM691394", "GSM691395", "GSM691396", "GSM691397", "GSM691398", "GSM691399", "GSM691400", "GSM691401", "GSM691402", "GSM691403", "GSM691404", "GSM691405", "GSM691406"], "sample_count": 45, "group_sizes": null, "group_sizes_basis": null, "platform": "5175", "taxon": "Homo sapiens", "title": "Peripheral Blood Mononuclear Cell Gene Expression Profiles May Predict Poor Outcome in Idiopathic Pulmonary Fibrosis [Affymetrix]", "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:GSE28042", "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=GSE28042", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE28042", "version": null, "note": "The datasets generated and analysed during the current study are available in GEO (https://www.ncbi.nlm.nih.gov/geo), which are public functional genomics data repositories.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and analysed during the current study are available in GEO (https://www.ncbi.nlm.nih.gov/geo), which are public functional genomics data repositories.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM693750", "GSM693751", "GSM693752", "GSM693753", "GSM693754", "GSM693755", "GSM693756", "GSM693757", "GSM693758", "GSM693759", "GSM693760", "GSM693761", "GSM693762", "GSM693763", "GSM693764", "GSM693765", "GSM693766", "GSM693767", "GSM693768", "GSM693769", "GSM693770", "GSM693771", "GSM693772", "GSM693773", "GSM693774", "GSM693775", "GSM693776", "GSM693777", "GSM693778", "GSM693779", "GSM693780", "GSM693781", "GSM693782", "GSM693783", "GSM693784", "GSM693785", "GSM693786", "GSM693787", "GSM693788", "GSM693789", "GSM693790", "GSM693791", "GSM693792", "GSM693793", "GSM693794", "GSM693795", "GSM693796", "GSM693797", "GSM693798", "GSM693799", "GSM693800", "GSM693801", "GSM693802", "GSM693803", "GSM693804", "GSM693805", "GSM693806", "GSM693807", "GSM693808", "GSM693809", "GSM693810", "GSM693811", "GSM693812", "GSM693813", "GSM693814", "GSM693815", "GSM693816", "GSM693817", "GSM693818", "GSM693819", "GSM693820", "GSM693821", "GSM693822", "GSM693823", "GSM693824", "GSM698440", "GSM698441", "GSM698442", "GSM698443", "GSM698444", "GSM698445", "GSM698446", "GSM698447", "GSM698448", "GSM698449", "GSM698450", "GSM698451", "GSM698452", "GSM698453", "GSM698454", "GSM698455", "GSM698456", "GSM698457", "GSM698458"], "sample_count": 94, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Peripheral Blood Mononuclear Cell Gene Expression Profiles May Predict Poor Outcome in Idiopathic Pulmonary Fibrosis [Agilent]", "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:GSE70866", "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=GSE70866", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE70866", "version": null, "note": "The datasets generated and analysed during the current study are available in GEO (https://www.ncbi.nlm.nih.gov/geo), which are public functional genomics data repositories.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets generated and analysed during the current study are available in GEO (https://www.ncbi.nlm.nih.gov/geo), which are public functional genomics data repositories.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1820719", "GSM1820720", "GSM1820721", "GSM1820722", "GSM1820723", "GSM1820724", "GSM1820725", "GSM1820726", "GSM1820727", "GSM1820728", "GSM1820729", "GSM1820730", "GSM1820731", "GSM1820732", "GSM1820733", "GSM1820734", "GSM1820735", "GSM1820736", "GSM1820737", "GSM1820738", "GSM1820739", "GSM1820740", "GSM1820741", "GSM1820742", "GSM1820743", "GSM1820744", "GSM1820745", "GSM1820746", "GSM1820747", "GSM1820748", "GSM1820749", "GSM1820750", "GSM1820751", "GSM1820752", "GSM1820753", "GSM1820754", "GSM1820755", "GSM1820756", "GSM1820757", "GSM1820758", "GSM1820759", "GSM1820760", "GSM1820761", "GSM1820762", "GSM1820763", "GSM1820764", "GSM1820765", "GSM1820766", "GSM1820767", "GSM1820768", "GSM1820769", "GSM1820770", "GSM1820771", "GSM1820772", "GSM1820773", "GSM1820774", "GSM1820775", "GSM1820776", "GSM1820777", "GSM1820778", "GSM1820779", "GSM1820780", "GSM1820781", "GSM1820782", "GSM1820783", "GSM1820784", "GSM1820785", "GSM1820786", "GSM1820787", "GSM1820788", "GSM1820789", "GSM1820790", "GSM1820791", "GSM1820792", "GSM1820793", "GSM1820794", "GSM1820795", "GSM1820796", "GSM1820797", "GSM1820798", "GSM1820799", "GSM1820800", "GSM1820801", "GSM1820802", "GSM1820803", "GSM1820804", "GSM1820805", "GSM1820806", "GSM1820807", "GSM1820808", "GSM1820809", "GSM1820810", "GSM1820811", "GSM1820812", "GSM1820813", "GSM1820814", "GSM1820815", "GSM1820816", "GSM1820817", "GSM1820818", "GSM1820819", "GSM1820820", "GSM1820821", "GSM1820822", "GSM1820823", "GSM1820824", "GSM1820825", "GSM1820826", "GSM1820827", "GSM1820828", "GSM1820829", "GSM1820830", "GSM1820831", "GSM1820832", "GSM1820833", "GSM1820834", "GSM1820835", "GSM1820836", "GSM1820837", "GSM1820838", "GSM1820839", "GSM1820840", "GSM1820841", "GSM1820842", "GSM1820843", "GSM1820844", "GSM1820845", "GSM1820846", "GSM1820847", "GSM1820848", "GSM1820849", "GSM1820850", "GSM1820851", "GSM1820852", "GSM1820853", "GSM1820854", "GSM1820855", "GSM1820856", "GSM1820857", "GSM1820858", "GSM1820859", "GSM1820860", "GSM1820861", "GSM1820862", "GSM1820863", "GSM1820864", "GSM1820865", "GSM1820866", "GSM1820867", "GSM1820868", "GSM1820869", "GSM1820870", "GSM1820871", "GSM1820872", "GSM1820873", "GSM1820874", "GSM1820875", "GSM1820876", "GSM1820877", "GSM1820878", "GSM1820879", "GSM1820880", "GSM1820881", "GSM1820882", "GSM1820883", "GSM1820884", "GSM1820885", "GSM1820886", "GSM1820887", "GSM1820888", "GSM1820889", "GSM1820890", "GSM1820891", "GSM1820892", "GSM1820893", "GSM1820894", "GSM1820895", "GSM1820896", "GSM1820897", "GSM1820898", "GSM1820899", "GSM1820900", "GSM1820901", "GSM1820902", "GSM1820903", "GSM1820904", "GSM1820905", "GSM1820906", "GSM1820907", "GSM1820908", "GSM1820909", "GSM1820910", "GSM1820911", "GSM1820912", "GSM1820913", "GSM1820914"], "sample_count": 196, "group_sizes": null, "group_sizes_basis": null, "platform": "17077;14550", "taxon": "Homo sapiens", "title": "BAL cell gene expression is predictive of Mortality in Idiopathic Pulmonary Fibrosis and enriched for Genes of Airway Basal Cells (II)", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE129605 not downloaded", "asset:data:geo:GSE129605 licence not read", "asset:data:geo:GSE27957 not downloaded", "asset:data:geo:GSE27957 licence not read", "asset:data:geo:GSE28042 not downloaded", "asset:data:geo:GSE28042 licence not read", "asset:data:geo:GSE70866 not downloaded", "asset:data:geo:GSE70866 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Random forest"}}, {"id": "method-2", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Support vector machines"}}, {"id": "method-3", "family": null, "specific": null, "label": "multivariate Cox analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We applied multivariate Cox analysis to establish a prognostic risk model consisting of 7 EAGs."}}], "targets": [], "gaps": ["method.reader_named_unmapped", "method.machine_learning_random_forest"]}, "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": false, "required_operations": [], "missing_operations": ["machine_learning_random_forest"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_forest."}, "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": ["GSE70866", "GSE27957", "GSE28042", "GSE129605"], "resolved_accessions": ["GSE70866", "GSE27957", "GSE28042", "GSE129605"], "statements": ["The datasets generated and analysed during the current study are available in GEO (https://www.ncbi.nlm.nih.gov/geo), which are public functional genomics data repositories."], "basis": "The paper names GSE70866, GSE27957, GSE28042, GSE129605 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:37858084", "data:geo:GSE129605"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE129605"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:56:26Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8545, "completion_tokens": 1232, "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:37858084", "type": "paper", "label": "pmid:37858084"}, {"id": "source:pmid:37858084", "type": "manuscript", "label": "PMID 37858084 full text"}, {"id": "data:geo:GSE129605", "type": "dataset", "label": "GEO GSE129605"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37858084", "type": "paper", "label": "pmid:37858084"}, {"id": "source:pmid:37858084", "type": "manuscript", "label": "PMID 37858084 full text"}, {"id": "data:geo:GSE129605", "type": "dataset", "label": "GEO GSE129605"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37858084", "type": "extraction", "used": ["source:pmid:37858084"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE129605", "type": "accession_resolution", "used": ["data:geo:GSE129605"], "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:37858084", "parent_hash": "sha256:cedfc45f324337ab80ad0e85cca453fb9ea956541b9f97ce1918be02bf65edb5", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE129605 licence not read", "asset:data:geo:GSE129605 not downloaded", "asset:data:geo:GSE27957 licence not read", "asset:data:geo:GSE27957 not downloaded", "asset:data:geo:GSE28042 licence not read", "asset:data:geo:GSE28042 not downloaded", "asset:data:geo:GSE70866 licence not read", "asset:data:geo:GSE70866 not downloaded", "execution.not_run", "method.machine_learning_random_forest", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:machine_learning_random_forest"], "assays": [{"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Random forest"], "order_basis": "analysis_only", "id": "assay:1"}]}