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

Machine learning prediction of cancer cell sensitivity to drugs based on genomic and chemical properties.

PLoS One. 2013; 8(4): e61318
Menden MP, Iorio F, Garnett M, McDermott U, Benes CH, Ballester PJ, Saez-Rodriguez J

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 R(2) of 0.72 and 0.64 respectively. Furthermore, models were able to predict with comparable accuracy (R(2) 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. HubMed – drug

Reactions, beliefs and concerns associated with providing hair specimens for medical research among a South African sample: a qualitative approach.

Future Virol. 2012 Nov 1; 7(11): 1135-1142
Coetzee B, Kagee A, Tomlinson M, Warnich L, Ikediobi O

In order to optimize treatment outcome among antiretroviral therapy users, there is a strong imperative to engage in continued monitoring and maintenance of therapeutic drug levels in patients. The aim of this study was to document the perspectives, beliefs, and concerns of South African antiretroviral therapy users providing hair specimens to determine antiretroviral drug levels. Twenty-one women living with HIV were recruited from a community health center in the Western Cape. Interviews were recorded and transcribed, and analyzed using Atlas.ti version 6. Although participants identified several cultural beliefs influencing their decision to provide hair specimens for drug level measurement, nearly all agreed that they would be willing to do so if provided with enough information by the researcher. HubMed – drug

Zebrafish based small molecule screens for novel DMD drugs.

Drug Discov Today Technol. 2013; 10(1): e91-e96
Kawahara G, Kunkel LM

Recently, a number of chemical and drug screens using zebrafish embryos have been published. Using zebrafish dystrophin mutants, we screened a chemical library for small molecules that modulate the muscle phenotype and identified seven small molecules that influence muscle pathology in dystrophin-null zebrafish. One chemical, aminophylline, which is known to be a non-selective phosphodiesterase (PDE) inhibitor, had the greatest ability to restore normal muscle structure and to up-regulate cAMP-dependent protein kinase (PKA) in treated dystrophin deficient fish. Our methodologies, which combine drug screening with assessment of the chemical effects by genotyping and staining with anti-dystrophin, provide a powerful means to identify template structures potentially relevant to the development of novel human muscular dystrophies therapeutics. HubMed – drug

Alzheimer’s Disease Drug Discovery: In-vivo screening using C. elegans as a model for ?-amyloid peptide-induced toxicity.

Drug Discov Today Technol. 2013; 10(1): e115-e119
Lublin A, Link C

Alzheimer’s disease (AD) is a complex human neurodegenerative disease. Currently the therapeutics for AD only treat the symptoms. While numbers of excellent studies have used mammalian models to discover new compounds, the time and effort involved with screening large numbers of candidates is prohibitive. Cultured mammalian neurons are of often used to perform high through-put screens (HTS) however, cell culture lacks the organismal complexity involved in AD. To address these issues a number of researchers are turning to the round worm, C. elegans. C. elegans has numerous models of both Tau and A? induced toxicity; the two prime components observed to correlate with AD pathology. These models have lead to the discovery of numerous AD modulating candidates. Further, the ease of performing RNAi for any gene in the C. elegans genome allows for identification of proteins involved in the mechanism of drug action. These attributes make C. elegans well positioned to aid in the discovery of new AD therapies. HubMed – drug