Search for: All records

Drug screening data from massive bulk gene expression databases can be analyzed to determine the optimal clinical application of cancer drugs. The growing amount of single-cell RNA sequencing (scRNA-seq) data also provides insights into improving therapeutic effectiveness by helping to study the heterogeneity of drug responses for cancer cell subpopulations. Developing computational approaches to predict and interpret cancer drug response in single-cell data collected from clinical samples can be very useful. We propose scDEAL, a deep transfer learning framework for cancer drug response prediction at the single-cell level by integrating large-scale bulk cell-line data. The highlight in scDEAL involves harmonizing drug-related bulk RNA-seq data with scRNA-seq data and transferring the model trained on bulk RNA-seq data to predict drug responses in scRNA-seq. Another feature of scDEAL is the integrated gradient feature interpretation to infer the signature genes of drug resistance mechanisms. We benchmark scDEAL on six scRNA-seq datasets and demonstrate its model interpretability via three case studies focusing on drug response label prediction, gene signature identification, and pseudotime analysis. We believe that scDEAL could help study cell reprogramming, drug selection, and repurposing for improving therapeutic efficacy.

With increasing trend of polypharmacy, drug‐drug interaction (DDI)‐induced adverse drug events (ADEs) are considered as a major challenge for clinical practice. As premarketing clinical trials usually have stringent inclusion/exclusion criteria, limited comedication data capture and often times small sample size have limited values in study DDIs. On the other hand, ADE reports collected by spontaneous reporting system (SRS) become an important source for DDI studies. There are two major challenges in detecting DDI signals from SRS: confounding bias and false positive rate. In this article, we propose a novel approach, propensity score‐adjusted three‐component mixture model (PS‐3CMM). This model can simultaneously adjust for confounding bias and estimate false discovery rate for all drug‐drug‐ADE combinations in FDA Adverse Event Reporting System (FAERS), which is a preeminent SRS database. In simulation studies, PS‐3CMM performs better in detecting true DDIs comparing to the existing approach. It is more sensitive in selecting the DDI signals that have nonpositive individual drug relative ADE risk (NPIRR). The application of PS‐3CMM is illustrated in analyzing the FAERS database. Compared to the existing approaches, PS‐3CMM prioritizes DDI signals differently. PS‐3CMM gives high priorities to DDI signals that have NPIRR. Both simulation studies and FAERS data analysis conclude that our new PS‐3CMM is a new method that is complement to the existing DDI signal detection methods.

Pharmacoinformatics research has experienced a great deal of successes in detecting drug‐induced adverse events (AEs) using large‐scale health record databases. In the era of polypharmacy, pharmacoinformatics faces many new challenges, and two significant challenges are to detect high‐order drug interactions and to handle strongly correlated drugs. In this article, we propose a super‐combo‐drug test (SupCD‐T) to address the aforementioned two challenges. SupCD‐T detects drug interactions by identifying optimal drug combinations with increased AE risks. In addition, SupCD‐T increases the statistical powers to detect single‐drug effects by combining strongly correlated drugs. Although SupCD‐T does not distinguish single‐drug effects from their combination effects, it is noticeably more powerful in selecting an individual drug effect in the multiple regression analysis, where confounding justification between two correlated drugs reduces the power in testing the individual drug effects on AEs. Our simulation studies demonstrate that SupCD‐T has generally better power comparing with the multiple regression analysis. In addition, SupCD‐T is able to select meaningful drug combinations (eg, highly coprescribed drugs). Using electronic health record database, we illustrate the utility of SupCD‐T and discover a number of drug combinations that have increased risk in myopathy. Some novel drug combinations have not yet been investigated and reported in the pharmacology research.

This study aims to create a database for quantifying the fraction of metabolism of cytochrome P450 isozymes for cancer drugs approved by theUSFood and Drug Administration. A reproducible data collection protocol was developed to extract essential information, including both substrate‐depletion and metabolite‐formation data from publicly availablein vitroselective cytochrome P450 enzyme inhibition studies. We estimated the fraction of metabolism from the curated data. To demonstrate the utility of this database, we conducted anin vitrodrug interaction prediction for the 42 cancer drugs. In the drug–drug interaction prediction, we identified 31 drug pairs with at least one cancer drug in each pair that had predicted area under concentration ratios > 2. We further found clinical drug interaction pieces of evidence in the literature to support 20 of these 31drug–drug interactionpairs.