Prognostic model development for classification of colorectal adenocarcinoma by using machine learning model based on feature selection technique boruta.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37076536", "kind": "science-record", "revision": 4, "content_hash": "sha256:8ff13b8965d994c1c0c6935daff9d3ce285f653720a48d311d2f544c8d46442d", "created_at": "2026-11-01T19:01:44Z", "updated_at": "2026-11-01T22:51:43Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Prognostic model development for classification of colorectal adenocarcinoma by using machine learning model based on feature selection technique boruta.", "doi": "10.1038/s41598-023-33327-4", "pmid": "37076536", "authors": ["Neha Shree Maurya", "Shikha Kushwah", "Sandeep Kushwaha", "Aakash Chawade", "Ashutosh Mani"], "journal": "Scientific reports", "year": 2023, "abstract": "Colorectal cancer (CRC) is the third most prevalent cancer type and accounts for nearly one million deaths worldwide. The CRC mRNA gene expression datasets from TCGA and GEO (GSE144259, GSE50760, and GSE87096) were analyzed to find the significant differentially expressed genes (DEGs). These significant genes were further processed for feature selection through boruta and the confirmed features of importance (genes) were subsequently used for ML-based prognostic classification model development. These genes were analyzed for survival and correlation analysis between final genes and infiltrated immunocytes. A total of 770 CRC samples were included having 78 normal and 692 tumor tissue samples. 170 significant DEGs were identified after DESeq2 analysis along with the topconfects R package. The 33 confirmed features of importance-based RF prognostic classification model have given accuracy, precision, recall, and f1-score of 100% with 0% standard deviation. The overall survival analysis had finalized GLP2R and VSTM2A genes that were significantly downregulated in tumor samples and had a strong correlation with immunocyte infiltration. The involvement of these genes in CRC prognosis was further confirmed on the basis of their biological function and literature analysis. The current findings indicate that GLP2R and VSTM2A may play a significant role in CRC progression and immune response suppression.", "claims": [{"id": "claim-method", "statement": "Thereafter, the threshold implemented to identify the DEGs between normal and CRC tumor samples using the edgeR by glmRT method was FDR cut-off of 0.01 and |log 2‐FC|> 1.5. The gene expression count data for GEO datasets were processed through DESeq217 R Bioconductor package. To obtain a significant list of DEGs from GEO datasets \"topconfects\"18 Bioconductor R package was employed which ranks the genes based on the confidence score bound to log fold change value.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37076536", "locator": "sections[13] \"Identification of significant DEGs\" paragraph 2", "quote": "Thereafter, the threshold implemented to identify the DEGs between normal and CRC tumor samples using the edgeR by glmRT method was FDR cut-off of 0.01 and |log 2‐FC|> 1.5."}, {"asset": "source:pmid:37076536", "locator": "sections[13] \"Identification of significant DEGs\" paragraph 3", "quote": "The gene expression count data for GEO datasets were processed through DESeq217 R Bioconductor package."}, {"asset": "source:pmid:37076536", "locator": "sections[13] \"Identification of significant DEGs\" paragraph 4", "quote": "To obtain a significant list of DEGs from GEO datasets \"topconfects\"18 Bioconductor R package was employed which ranks the genes based on the confidence score bound to log fold change value."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available dataset was used analyzed which are available on the TCGA repository site (https://portal.gdc.cancer.gov/) with project name TCGA-COAD and TCGA-READ and GEO site (https://www.ncbi.nlm.nih.gov/geo/). The accession number for the GEO datasets are (a) GSE144259, (b) GSE50760, and (c) GSE87096.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37076536", "locator": "sections[20] \"Data availability\" paragraph 2", "quote": "Publicly available dataset was used analyzed which are available on the TCGA repository site (https://portal.gdc.cancer.gov/) with project name TCGA-COAD and TCGA-READ and GEO site (https://www.ncbi.nlm.nih.gov/geo/). The accession number for the GEO datasets are (a) GSE144259, (b) GSE50760, and (c) GSE87096."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A total of 170 significant common DEGs were found between 3 GEO datasets and the TCGA-CRC dataset.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37076536", "locator": "sections[4] \"Identification of significant DEGs\" paragraph 4", "quote": "A total of 170 significant common DEGs were found between 3 GEO datasets and the TCGA-CRC dataset as shown in Fig. 3."}, {"asset": "source:pmid:37076536", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "170 significant DEGs were identified after DESeq2 analysis along with the topconfects R package."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "A total of 170 significant common DEGs were found between 3 GEO datasets and the TCGA-CRC dataset.", "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:37076536"], "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:GSE144259"], "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:GSE144259"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37076536", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-023-33327-4", "sha256": "sha256:86b1b28076934dd77e358889e958c52815f1001736987dc92c1f4d0aee49ccfe", "bytes": 34030, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-023-33327-4", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10115869", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE144259", "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=GSE144259", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE144259", "version": null, "note": "Publicly available dataset was used analyzed which are available on the TCGA repository site (https://portal.gdc.cancer.gov/) with project name TCGA-COAD and TCGA-READ and GEO site (https://www.ncbi.nlm.nih.gov/geo/). The accession number for the GEO datasets are (a) GSE144259, (b) GSE50760, and (c) GSE87096.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available dataset was used analyzed which are available on the TCGA repository site (https://portal.gdc.cancer.gov/) with project name TCGA-COAD and TCGA-READ and GEO site (https://www.ncbi.nlm.nih.gov/geo/). The accession number for the GEO datasets are (a) GSE144259, (b) GSE50760, and (c) GSE87096.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4284531", "GSM4284532", "GSM4284533", "GSM4284534", "GSM4284535", "GSM4284536", "GSM4284537", "GSM4284538", "GSM4284539"], "sample_count": 9, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "RNA-seq of CRC tissues", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE50760", "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=GSE50760", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE50760", "version": null, "note": "Publicly available dataset was used analyzed which are available on the TCGA repository site (https://portal.gdc.cancer.gov/) with project name TCGA-COAD and TCGA-READ and GEO site (https://www.ncbi.nlm.nih.gov/geo/). The accession number for the GEO datasets are (a) GSE144259, (b) GSE50760, and (c) GSE87096.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available dataset was used analyzed which are available on the TCGA repository site (https://portal.gdc.cancer.gov/) with project name TCGA-COAD and TCGA-READ and GEO site (https://www.ncbi.nlm.nih.gov/geo/). The accession number for the GEO datasets are (a) GSE144259, (b) GSE50760, and (c) GSE87096.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1228184", "GSM1228185", "GSM1228186", "GSM1228187", "GSM1228188", "GSM1228189", "GSM1228190", "GSM1228191", "GSM1228192", "GSM1228193", "GSM1228194", "GSM1228195", "GSM1228196", "GSM1228197", "GSM1228198", "GSM1228199", "GSM1228200", "GSM1228201", "GSM1228202", "GSM1228203", "GSM1228204", "GSM1228205", "GSM1228206", "GSM1228207", "GSM1228208", "GSM1228209", "GSM1228210", "GSM1228211", "GSM1228212", "GSM1228213", "GSM1228214", "GSM1228215", "GSM1228216", "GSM1228217", "GSM1228218", "GSM1228219", "GSM1228220", "GSM1228221", "GSM1228222", "GSM1228223", "GSM1228224", "GSM1228225", "GSM1228226", "GSM1228227", "GSM1228228", "GSM1228229", "GSM1228230", "GSM1228231", "GSM1228232", "GSM1228233", "GSM1228234", "GSM1228235", "GSM1228236", "GSM1228237"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Gene expression profiling study by RNA-seq in colorectal cancer", "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:GSE87096", "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=GSE87096", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE87096", "version": null, "note": "Publicly available dataset was used analyzed which are available on the TCGA repository site (https://portal.gdc.cancer.gov/) with project name TCGA-COAD and TCGA-READ and GEO site (https://www.ncbi.nlm.nih.gov/geo/). The accession number for the GEO datasets are (a) GSE144259, (b) GSE50760, and (c) GSE87096.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available dataset was used analyzed which are available on the TCGA repository site (https://portal.gdc.cancer.gov/) with project name TCGA-COAD and TCGA-READ and GEO site (https://www.ncbi.nlm.nih.gov/geo/). The accession number for the GEO datasets are (a) GSE144259, (b) GSE50760, and (c) GSE87096.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2322214", "GSM2322215", "GSM2322216", "GSM2322217", "GSM2322218", "GSM2322219", "GSM2322220", "GSM2322221", "GSM2322222", "GSM2322223", "GSM2322224", "GSM2322225", "GSM2322226", "GSM2322227", "GSM2322228", "GSM2322229", "GSM2322230", "GSM2322231", "GSM2322232", "GSM2322233", "GSM2322234", "GSM2322235", "GSM2322236", "GSM2322237", "GSM2322238", "GSM2322239", "GSM2322240", "GSM2322241", "GSM2322242", "GSM2322243", "GSM2322244", "GSM2322245", "GSM2322246", "GSM2322247", "GSM2322248", "GSM2322249"], "sample_count": 36, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Methylome, hydroxymethylome, and integrative transcriptome profiling in human CRC tissue and paired normal tissues", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE144259 not downloaded", "asset:data:geo:GSE144259 licence not read", "asset:data:geo:GSE50760 not downloaded", "asset:data:geo:GSE50760 licence not read", "asset:data:geo:GSE87096 not downloaded", "asset:data:geo:GSE87096 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "reordered", "quote": "Thereafter, the threshold implemented to identify the DEGs between normal and CRC tumor samples using the edgeR by glmRT method was FDR cut-off of 0.01 and |log 2‐FC|> 1.5. The gene expression count data for GEO datasets were processed through DESeq217 R Bioconductor package. To obtain a significant list of DEGs from GEO datasets \"topconfects\"18 Bioconductor R package was employed which ranks the genes based on the confidence score bound to log fold change value."}}, {"id": "method-2", "family": "differential_expression", "specific": "edger", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {"fdr_threshold": "geR by glmRT method was FDR cut-off of 0"}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.8, "band": "high", "quote": "edgeR"}}], "targets": [], "gaps": []}, "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: deseq2."}, "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": ["GSE144259", "GSE50760", "GSE87096"], "resolved_accessions": ["GSE144259", "GSE50760", "GSE87096"], "statements": ["Publicly available dataset was used analyzed which are available on the TCGA repository site (https://portal.gdc.cancer.gov/) with project name TCGA-COAD and TCGA-READ and GEO site (https://www.ncbi.nlm.nih.gov/geo/). The accession number for the GEO datasets are (a) GSE144259, (b) GSE50760, and (c) GSE87096."], "basis": "The paper names GSE144259, GSE50760, GSE87096 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:37076536", "data:geo:GSE144259"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE144259"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:36:57Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 10585, "completion_tokens": 2082, "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:37076536", "type": "paper", "label": "pmid:37076536"}, {"id": "source:pmid:37076536", "type": "manuscript", "label": "PMID 37076536 full text"}, {"id": "data:geo:GSE144259", "type": "dataset", "label": "GEO GSE144259"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37076536", "type": "paper", "label": "pmid:37076536"}, {"id": "source:pmid:37076536", "type": "manuscript", "label": "PMID 37076536 full text"}, {"id": "data:geo:GSE144259", "type": "dataset", "label": "GEO GSE144259"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37076536", "type": "extraction", "used": ["source:pmid:37076536"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE144259", "type": "accession_resolution", "used": ["data:geo:GSE144259"], "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:37076536", "parent_hash": "sha256:34d75f774ac4e3a7ebc81b270aee0b0e8e2f12ebef09af8e700e272f782c58ab", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE144259 licence not read", "asset:data:geo:GSE144259 not downloaded", "asset:data:geo:GSE50760 licence not read", "asset:data:geo:GSE50760 not downloaded", "asset:data:geo:GSE87096 licence not read", "asset:data:geo:GSE87096 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Thereafter, the threshold implemented to identify the DEGs between normal and CRC tumor samples using the edgeR by glmRT method was FDR cut-off of 0.01 and |log 2‐FC|> 1.5. The gene expression count data for GEO datasets were processed through DESeq217 R Bioconductor package. To obtain a significant list of DEGs from GEO datasets \"topconfects\"18 Bioconductor R package was employed which ranks the genes based on the confidence score bound to log fold change value."], "order_basis": "analysis_only", "id": "assay:1"}]}