Biology subjects

Gilvary, C.

Publications and source records attributed to Gilvary, C..

3 recordsLinked to original sources

bioRxiv2019

A machine learning and network framework to discover new indications for small molecules

Drug repurposing, identifying novel indications for drugs, bypasses common drug development pitfalls to ultimately deliver therapies to patients faster. However, most repurposing discoveries have been led by anecdotal observations (e.g. Viagra) or experimental-based repurposing screens, which are costly, time-consuming, and imprecise. Recently, more systematic computational approaches have been proposed, however these rely on utilizing the information from the diseases a drug is already approved to treat. This inherently limits the algorithms, making them unusable for investigational molecules. Here, we present a computational approach to drug repurposing, CATNIP, that requires only biological and chemical information of a molecule. CATNIP is trained with 2,576 diverse small molecules and uses 16 different drug similarity features, such as structural, target, or pathway based similarity. This model obtains significant predictive power (AUC = 0.841). Using our model, we created a repurposing network to identify broad scale repurposing opportunities between drug types. By exploiting this network, we identified literature-supported repurposing candidates, such as the use of systemic hormonal preparations for the treatment of respiratory illnesses. Furthermore, we demonstrated that we can use our approach to identify novel uses for defined drug classes. We found that adrenergic uptake inhibitors, specifically amitriptyline and trimipramine, could be potential therapies for Parkinsons disease. Additionally, using CATNIP, we predicted the kinase inhibitor, vandetanib, as a possible treatment for Type 2 Diabetes. Overall, this systematic approach to drug repurposing lays the groundwork to streamline future drug development efforts.

pharmacology and toxicology↗

bioRxiv2019

A machine learning approach predicts essential genes and pharmacological targets in cancer

Loss-of-function (LoF) screenings have the potential to reveal novel cancer-specific vulnerabilities, prioritize drug treatments, and inform precision medicine therapeutics. These screenings were traditionally done using shRNAs, but with the recent emergence of CRISPR technology there has been a shift in methodology. However, recent analyses have found large inconsistencies between CRISPR and shRNA essentiality results. Here, we examined the DepMap project, the largest cancer LoF effort undertaken to date, and find a lack of correlation between CRISPR and shRNA LoF results; we further characterized differences between genes found to be essential by either platform. We then introduce ECLIPSE, a machine learning approach, which combines genomic, cell line, and experimental design features to predict essential genes and platform specific essential genes in specific cancer cell lines. We applied ECLIPSE to known drug targets and found that our approach strongly differentiated drugs approved for cancer versus those that have not, and can thus be leveraged to identify potential cancer repurposing opportunities. Overall, ECLIPSE allows for a more comprehensive analysis of gene essentiality and drug development; which neither platform can achieve alone.

cancer biology↗

bioRxiv2018

A Machine Learning Approach Predicts Tissue-Specific Drug Adverse Events

One of the main causes for failure in the drug development pipeline or withdrawal post approval is the unexpected occurrence of severe drug adverse events. Even though such events should be detected by in vitro, in vivo, and human trials, they continue to unexpectedly arise at different stages of drug development causing costly clinical trial failures and market withdrawal. Inspired by the \"moneyball\" approach used in baseball to integrate diverse features to predict player success, we hypothesized that a similar approach could leverage existing adverse event and tissue-specific toxicity data to learn how to predict adverse events. We introduce MAESTER, a data-driven machine learning approach that integrates information on a compounds structure, targets, and phenotypic effects with tissue-wide genomic profiling and our toxic target database to predict the probability of a compound presenting with different types of tissue-specific adverse events. When tested on 6 different types of adverse events MAESTER maintains a high accuracy, sensitivity, and specificity across both the training data and new test sets. Additionally, MAESTER scores could flag a number of drugs that were approved, but later withdrawn due to unknown adverse events - highlighting its potential to identify events missed by traditional methods. MAESTER can also be used to identify toxic targets for each tissue type. Overall MAESTER provides a broadly applicable framework to identify toxic targets and predict specific adverse events and can accelerate the drug development pipeline and drive the design of new safer compounds.

pharmacology and toxicology↗