Dataset Information

Modeling cancer drug response through drug-specific informative genes.

ABSTRACT: Recent advances in pharmacogenomics have generated a wealth of data of different types whose analysis have helped in the identification of signatures of different cellular sensitivity/resistance responses to hundreds of chemical compounds. Among the different data types, gene expression has proven to be the more successful for the inference of drug response in cancer cell lines. Although effective, the whole transcriptome can introduce noise in the predictive models, since specific mechanisms are required for different drugs and these realistically involve only part of the proteins encoded in the genome. We analyzed the pharmacogenomics data of 961 cell lines tested with 265 anti-cancer drugs and developed different machine learning approaches for dissecting the genome systematically and predict drug responses using both drug-unspecific and drug-specific genes. These methodologies reach better response predictions for the vast majority of the screened drugs using tens to few hundreds genes specific to each drug instead of the whole genome, thus allowing a better understanding and interpretation of drug-specific response mechanisms which are not necessarily restricted to the drug known targets.

SUBMITTER: Parca L

PROVIDER: S-EPMC6811538 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Modeling cancer drug response through drug-specific informative genes.

Parca Luca L Pepe Gerardo G Pietrosanto Marco M Galvan Giulio G Galli Leonardo L Palmeri Antonio A Sciandrone Marco M Ferrè Fabrizio F Ausiello Gabriele G Helmer-Citterich Manuela M

Scientific reports 20191023 1

Recent advances in pharmacogenomics have generated a wealth of data of different types whose analysis have helped in the identification of signatures of different cellular sensitivity/resistance responses to hundreds of chemical compounds. Among the different data types, gene expression has proven to be the more successful for the inference of drug response in cancer cell lines. Although effective, the whole transcriptome can introduce noise in the predictive models, since specific mechanisms ar ...[more]

PMID: 31645597

Similar Datasets

Project description:The utility of tumor-derived cell lines is dependent on their ability to recapitulate underlying genomic aberrations and primary tumor biology. Here, we sequenced the exomes of 25 bladder cancer (BCa) cell lines and compared mutations, copy number alterations (CNAs), gene expression and drug response to BCa patient profiles in The Cancer Genome Atlas (TCGA). We observed a mutation pattern associated with altered CpGs and APOBEC-family cytosine deaminases similar to mutation signatures derived from somatic alterations in muscle-invasive (MI) primary tumors, highlighting a major mechanism(s) contributing to cancer-associated alterations in the BCa cell line exomes. Non-silent sequence alterations were confirmed in 76 cancer-associated genes, including mutations that likely activate oncogenes TERT and PIK3CA, and alter chromatin-associated proteins (MLL3, ARID1A, CHD6 and KDM6A) and established BCa genes (TP53, RB1, CDKN2A and TSC1). We identified alterations in signaling pathways and proteins with related functions, including the PI3K/mTOR pathway, altered in 60% of lines; BRCA DNA repair, 44%; and SYNE1-SYNE2, 60%. Homozygous deletions of chromosome 9p21 are known to target the cell cycle regulators CDKN2A and CDKN2B. This loci was commonly lost in BCa cell lines and we show the deletions extended to the polyamine enzyme methylthioadenosine (MTA) phosphorylase (MTAP) in 36% of lines, transcription factor DMRTA1 (27%) and antiviral interferon epsilon (IFNE, 19%). Overall, the BCa cell line genomic aberrations were concordant with those found in BCa patient tumors. We used gene expression and copy number data to infer pathway activities for cell lines, then used the inferred pathway activities to build a predictive model of cisplatin response. When applied to platinum-treated patients gathered from TCGA, the model predicted treatment-specific response. Together, these data and analysis represent a valuable community resource to model basic tumor biology and to study the pharmacogenomics of BCa.

Project description:MotivationIn recent years, vast advances in biomedical technologies and comprehensive sequencing have revealed the genomic landscape of common forms of human cancer in unprecedented detail. The broad heterogeneity of the disease calls for rapid development of personalized therapies. Translating the readily available genomic data into useful knowledge that can be applied in the clinic remains a challenge. Computational methods are needed to aid these efforts by robustly analyzing genome-scale data from distinct experimental platforms for prioritization of targets and treatments.ResultsWe propose a novel, biologically motivated, Bayesian multitask approach, which explicitly models gene-centric dependencies across multiple and distinct genomic platforms. We introduce a gene-wise prior and present a fully Bayesian formulation of a group factor analysis model. In supervised prediction applications, our multitask approach leverages similarities in response profiles of groups of drugs that are more likely to be related to true biological signal, which leads to more robust performance and improved generalization ability. We evaluate the performance of our method on molecularly characterized collections of cell lines profiled against two compound panels, namely the Cancer Cell Line Encyclopedia and the Cancer Therapeutics Response Portal. We demonstrate that accounting for the gene-centric dependencies enables leveraging information from multi-omic input data and improves prediction and feature selection performance. We further demonstrate the applicability of our method in an unsupervised dimensionality reduction application by inferring genes essential to tumorigenesis in the pancreatic ductal adenocarcinoma and lung adenocarcinoma patient cohorts from The Cancer Genome Atlas.Availability and implementation: The code for this work is available at https://github.com/olganikolova/gbgfa.Contact: nikolova@ohsu.edu or margolin@ohsu.edu.Supplementary informationSupplementary data are available at Bioinformatics online.

Dataset Information

Modeling cancer drug response through drug-specific informative genes.

Publications

Modeling cancer drug response through drug-specific informative genes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets