Dataset Information

CAN-Scan: a multi-omic phenotype-driven precision oncology platform identifies prognostic biomarkers of therapy response for colorectal cancer

ABSTRACT: Application of machine learning (ML) on cancer-specific pharmacogenomic datasets shows immense promise for identifying predictive response-biomarkers to enable personalized treatment. We introduce CAN-Scan, a precision oncology platform, that applies ML on next-generation pharmacogenomic datasets generated from a freeze-viable biobank of patient-derived primary cell lines (PDCs). These PDCs are screened against 84 FDA-approved drugs at clinically relevant doses (Cmax), focusing on colorectal cancer (CRC) as a model system. CAN-Scan uncovers prognostic biomarkers and alternative treatment strategies, particularly for patients unresponsive to first-line chemotherapy. Specifically, it identifies gene expression signatures linked to resistance against 5-Fluorouracil (5FU)-based drugs and a focal copy number gain on chromosome 7q, harbouring critical resistance-associated genes. CAN-Scan-derived response signatures accurately predict clinical outcomes across four independent, ethnically-diverse CRC cohorts. Notably, drug-specific ML models reveal Regorafenib and Vemurafenib as alternative treatments for BRAF-expressing, 5FU-insensitive CRC. Altogether, this approach demonstrates significant potential in improving biomarker-discovery and guiding personalized treatments.

ORGANISM(S): Homo sapiens

PROVIDER: GSE287956 | GEO | 2025/04/04

REPOSITORIES: GEO

ACCESS DATA

Dataset's files

Source:

			Action	DRS
		Other

Items per page:

1 - 1 of 1

Similar Datasets

Project description:In colorectal cancer (CRC), chromosomal instability (CIN) is typically studied using comparative-genomic hybridization (CGH) arrays. We studied paired (tumor and surrounding healthy) fresh-frozen tissue from 86 CRC patients using Illumina’s Infinium-based SNP array. This method allowed us to study CIN in CRC, with simultaneous analysis of copy number (CN) and B-allele frequency (BAF), which is a representation of allelic composition. This data helped us to detect mono-allelic and bi-allelic amplifications/deletion, copy neutral loss of heterozygosity, and levels of mosaicism for mixed cell populations, some of which can not be assessed with other methods that do not measure BAF. We identified associations between CN abnormalities and different CRC phenotypes (MSI, histological diagnosis, location, tumor grade, stage, MSI and presence of lymph node metastasis). We showed commonalities between regions of CN change observed in CRC and the regions reported in previous studies of other solid cancers (e.g., amplifications of 20q, 13q, 8q, 5p and deletions of 18q, 17p and 8p). From the Therapeutic Target Database we found relevant drugs, targeted to the genes located in these regions with CN changes, approved or in trials for other cancers and common diseases. These drugs may be considered for future therapeutic trials in CRC, based on personalized cytogenetic diagnosis. We also found many regions harboring genes which are not currently targeted by any relevant drugs that may be considered for future drug discovery studies. Our study shows the application of high-density SNP arrays for cytogenetic study in CRC and its importance for personalized treatment. DNA was extracted from colon tissue samples provided by 86 CRC patients. Each patient provided paired CRC tumor tissue and adjacent normal colon mucosa samples, which were fresh-frozen after resection. Samples were genotyped using Illumina's Infinium-based 610 Quad and CytoSNP 12 microarray chips. The genotype data from paired tumor and normal samples was used to detect tumor-specific chromosomal instabilities in copy number, including copy-neutral LOH, which cannot be assessed by many other cytogenetic methods. Supplementary file "GSE34678_raw_GPL8887.txt" includes the raw data for Samples using GPL8887 (GSM853162-GSM853239); supplementary file "GSE34678_raw_GPL13829.txt" includes the raw data for Samples using GPL13829 (GSM853240-GSM853363).

Dataset Information

CAN-Scan: a multi-omic phenotype-driven precision oncology platform identifies prognostic biomarkers of therapy response for colorectal cancer

Dataset's files

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets