Machine Learning Prediction of Cancer Cell Sensitivity to Drugs Based on Genomic and Chemical Properties

Predicting the response of a specific cancer to a therapy is a major goal in modern oncology that should ultimately lead to a personalised treatment. High-throughput screenings of potentially active compounds against a panel of genomically heterogeneous cancer cell lines have unveiled multiple relat...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:PloS one Ročník 8; číslo 4; s. e61318
Hlavní autoři: Menden, Michael P., Iorio, Francesco, Garnett, Mathew, McDermott, Ultan, Benes, Cyril H., Ballester, Pedro J., Saez-Rodriguez, Julio
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States Public Library of Science 30.04.2013
Public Library of Science (PLoS)
Témata:
Analysis of Variance
Antineoplastic Agents - pharmacology
Antineoplastic Agents - therapeutic use
Artificial Intelligence
Bioinformatics
Biology
Biomarkers
Biotechnology
Cancer
Chemical properties
Computation
Computer applications
Computer Science
Computer Simulation
Design optimization
Drug development
Drug Resistance, Neoplasm - genetics
Drug screening
Drugs
Experimental design
Gene amplification
Gene expression
Genomes
Genomics
Genomics - methods
Humans
Inhibitory Concentration 50
Learning algorithms
Machine learning
Mathematical models
Medical screening
Medicine
Multivariate analysis
Mutation
Neoplasms - drug therapy
Neoplasms - genetics
Pharmacogenetics - methods
Precision medicine
Predictions
Sensitivity
Tumor cell lines
Tumors
Workflow
United States > US
Massachusetts
ISSN:1932-6203, 1932-6203
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Predicting the response of a specific cancer to a therapy is a major goal in modern oncology that should ultimately lead to a personalised treatment. High-throughput screenings of potentially active compounds against a panel of genomically heterogeneous cancer cell lines have unveiled multiple relationships between genomic alterations and drug responses. Various computational approaches have been proposed to predict sensitivity based on genomic features, while others have used the chemical properties of the drugs to ascertain their effect. In an effort to integrate these complementary approaches, we developed machine learning models to predict the response of cancer cell lines to drug treatment, quantified through IC₅₀ values, based on both the genomic features of the cell lines and the chemical properties of the considered drugs. Models predicted IC₅₀ values in a 8-fold cross-validation and an independent blind test with coefficient of determination R² of 0.72 and 0.64 respectively. Furthermore, models were able to predict with comparable accuracy (R² of 0.61) IC50s of cell lines from a tissue not used in the training stage. Our in silico models can be used to optimise the experimental design of drug-cell screenings by estimating a large proportion of missing IC₅₀ values rather than experimentally measuring them. The implications of our results go beyond virtual drug screening design: potentially thousands of drugs could be probed in silico to systematically test their potential efficacy as anti-tumour agents based on their structure, thus providing a computational framework to identify new drug repositioning opportunities as well as ultimately be useful for personalized medicine by linking the genomic traits of patients to drug sensitivity.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Designed the software and implementation of different approaches: MPM FI PJB. Conceived and designed the experiments: MPM PJB JSR. Performed the experiments: MPM FI PJB. Analyzed the data: MPM FI MG UM CHB PJB JSR. Contributed reagents/materials/analysis tools: MPM FI MG UM CHB PJB. Wrote the paper: MPM CHB PJB JSR.
Competing Interests: The authors have declared that no competing interests exist.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0061318