DeepDSC: A Deep Learning Method to Predict Drug Sensitivity of Cancer Cell Lines

Background: Prediction of the response of cancer patients to different treatments and identification of biomarkers of drug sensitivity are two major goals of individualized medicine. In this study, we developed a deep learning framework called TINDL, completely trained on preclinical cancer cell lines, to predict the response of cancer patients to different treatments. TINDL utilizes a tissue-informed normalization to account for the tissue and cancer type of the tumours and to reduce the statistical discrepancies between cell lines and patient tumours. In addition, this model identifies a small set of genes whose mRNA expression are predictive of drug response in the trained model, enabling identification of biomarkers of drug sensitivity. Results: Using data from two large databases of cancer cell lines and cancer tumours, we showed that this model can distinguish between sensitive and resistant tumours for 10 (out of 14) drugs, outperforming various other machine learning models. In addition, our siRNA knockdown experiments on 10 genes identified by this model for one of the drugs (tamoxifen) confirmed that all of these genes significantly influence the drug sensitivity of the MCF7 cell line to this drug. In addition, genes implicated for multiple drugs pointed to shared mechanism of action among drugs and suggested several important signaling pathways. Conclusions: In summary, this study provides a powerful deep learning framework for prediction of drug response and for identification of biomarkers of drug sensitivity in cancer.

Download Full-text

Predicting tumor response to drugs based on gene-expression biomarkers of sensitivity learned from cancer cell lines

BMC Genomics ◽

10.1186/s12864-021-07581-7 ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Yuanyuan Li ◽

David M. Umbach ◽

Juno M. Krahn ◽

Igor Shats ◽

Xiaoling Li ◽

...

Keyword(s):

Gene Expression ◽

Cell Lines ◽

Cancer Cell ◽

Predictive Models ◽

Drug Sensitivity ◽

Human Cancer ◽

Cancer Cell Lines ◽

The Cancer Genome Atlas ◽

Differential Sensitivity ◽

Tumor Type

Abstract Background Human cancer cell line profiling and drug sensitivity studies provide valuable information about the therapeutic potential of drugs and their possible mechanisms of action. The goal of those studies is to translate the findings from in vitro studies of cancer cell lines into in vivo therapeutic relevance and, eventually, patients’ care. Tremendous progress has been made. Results In this work, we built predictive models for 453 drugs using data on gene expression and drug sensitivity (IC50) from cancer cell lines. We identified many known drug-gene interactions and uncovered several potentially novel drug-gene associations. Importantly, we further applied these predictive models to ~ 17,000 bulk RNA-seq samples from The Cancer Genome Atlas (TCGA) and the Genotype-Tissue Expression (GTEx) database to predict drug sensitivity for both normal and tumor tissues. We created a web site for users to visualize and download our predicted data (https://manticore.niehs.nih.gov/cancerRxTissue). Using trametinib as an example, we showed that our approach can faithfully recapitulate the known tumor specificity of the drug. Conclusions We demonstrated that our approach can predict drugs that 1) are tumor-type specific; 2) elicit higher sensitivity from tumor compared to corresponding normal tissue; 3) elicit differential sensitivity across breast cancer subtypes. If validated, our prediction could have relevance for preclinical drug testing and in phase I clinical design.

Download Full-text

A pan-cancer analysis of progression mechanisms and drug sensitivity in cancer cell lines

Molecular Omics ◽

10.1039/c9mo00119k ◽

2019 ◽

Vol 15 (6) ◽

pp. 399-405 ◽

Cited By ~ 1

Author(s):

Julia L. Fleck ◽

Ana B. Pavel ◽

Christos G. Cassandras

Keyword(s):

Cell Lines ◽

Cancer Cell ◽

Late Stage ◽

Drug Sensitivity ◽

Cancer Cell Lines ◽

Resistance Mechanisms ◽

General Effect ◽

Tumor Types ◽

Pan Cancer ◽

Genetic Events

Sequences of genetic events were identified that may help explain common patterns of oncogenesis across 22 tumor types. The general effect of late-stage mutations on drug sensitivity and resistance mechanisms in cancer cell lines was evaluated.

Download Full-text

Abstract 3380: Predicting the effects of small molecules on transcriptome of cancer cell lines using deep learning

10.1158/1538-7445.am2020-3380 ◽

2020 ◽

Author(s):

Junhyeok Jeon ◽

Sang Mi Lee ◽

GaRyoung Lee ◽

Hyun Uk Kim

Keyword(s):

Deep Learning ◽

Small Molecules ◽

Cell Lines ◽

Cancer Cell ◽

Cancer Cell Lines

Download Full-text

Drug sensitivity prediction for cancer cell lines based on pairwise kernels and miRNA profiles

2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) ◽

10.1109/bibm.2014.6999145 ◽

2014 ◽

Cited By ~ 1

Author(s):

Mehmet Tan

Keyword(s):

Cell Lines ◽

Cancer Cell ◽

Drug Sensitivity ◽

Cancer Cell Lines ◽

Drug Sensitivity Prediction

Download Full-text

Widespread Molecular Patterns Associated with Drug Sensitivity in Breast Cancer Cell Lines, with Implications for Human Tumors

PLoS ONE ◽

10.1371/journal.pone.0071158 ◽

2013 ◽

Vol 8 (12) ◽

pp. e71158 ◽

Cited By ~ 4

Author(s):

Chad J. Creighton

Keyword(s):

Breast Cancer ◽

Cell Lines ◽

Cancer Cell ◽

Breast Cancer Cell ◽

Drug Sensitivity ◽

Cancer Cell Lines ◽

Human Tumors ◽

Breast Cancer Cell Lines ◽

Molecular Patterns

Download Full-text

MicroRNAs related to intrinsic resistance to oxaliplatin and the irinotecan metabolite SN-38 in 10 colorectal cancer cell lines.

Journal of Clinical Oncology ◽

10.1200/jco.2012.30.4_suppl.524 ◽

2012 ◽

Vol 30 (4_suppl) ◽

pp. 524-524 ◽

Cited By ~ 2

Author(s):

Niels Frank Jensen ◽

Rolf Soekilde ◽

Jan Stenvang ◽

Birgitte Sander Nielsen ◽

Thomas Litman ◽

...

Keyword(s):

Colorectal Cancer ◽

Cell Lines ◽

Cancer Cell ◽

Drug Sensitivity ◽

Predictive Biomarkers ◽

Cancer Cell Lines ◽

Colorectal Cancer Cell ◽

Intrinsic Resistance ◽

Short Term ◽

Colorectal Cancer Cell Lines

524 Background: Chemotherapy of metastatic colorectal cancer is based on 5-flourouracil combined with either oxaliplatin or irinotecan (active metabolite: SN-38). Identification of predictive biomarkers of drug response is needed to provide a better personalized treatment. In this study we aimed to identify microRNAs related to intrinsic resistance to oxaliplatin or irinotecan in a panel of ten colorectal cancer cell lines. Methods: Drug sensitivity towards oxaliplatin and SN-38 was determined for ten colorectal cancer cell lines (Colo-205, DLD-1, HCC-2998, HCT-15, HCT-116, HT-29, KM12, LoVo, LS-174T, and SW620), using the cell viability MTT assay and the cell death LDH assay. In addition, two cell lines (DLD-1 and LoVo) were exposed to the drugs for 6, 24 or 48 hours. MicroRNA expression profiles were generated using the Exiqon miRCURY LNA microarray platform (including 840 microRNAs), and four differentially expressed microRNAs were validated by independent qRT-PCR measurements. Results: The drug sensitivities of the ten colorectal cancer cell lines varied about 50 times between the least and most sensitive cell lines. Correlation of drug sensitivity data to microRNA expression data across the ten cell lines yielded about 25 microRNA biomarker candidates, for each of the drug/assay combinations. Following short-term drug treatment 10-20 microRNAs were altered for each drug/cell line combination. Validation by qRT-PCR showed a very good correlation to the microarray data. MicroRNAs identified by correlation to drug sensitivity and by short-term treatment were compared, and less than 10% were identified by both approaches, perhaps representing the most promising candidates. These candidates are for SN-38 miR-15a, miR-22, miR-24, miR-98, miR-142-3p, miR-1290, and let-7b, and for oxaliplatin miR-23b, miR-27a, miR-192, miR-200a, miR-222, miR-886-5p, and miR-1308. Conclusions: In the present study we identified a number of microRNAs that are potentially involved in intrinsic resistance and/or could be predictive biomarkers for either irinotecan or oxaliplatin.

Download Full-text