👤 P.J. Hergenrother

The task of drug-target interaction prediction holds significant importance in pharmacology and therapeutic drug design. In this paper, we present FRnet-DTI, an auto-encoder based feature manipulation and a convolutional neural network based classifier for drug target interaction prediction. Two convolutional neural networks are proposed: FRnet-Encode and FRnet-Predict. Here, one model is used for feature manipulation and the other one for classification. Using the first method FRnet-Encode, we generate 4096 features for each of the instances in each of the datasets and use the second method, FRnet-Predict, to identify interaction probability employing those features. We have tested our method on four gold standard datasets extensively used by other researchers. Experimental results shows that our method significantly improves over the state-of-the-art method on three out of four drug-target interaction gold standard datasets on both area under curve for Receiver Operating Characteristic (auROC) and area under Precision Recall curve (auPR) metric. We also introduce twenty new potential drug-target pairs for interaction based on high prediction scores. The source codes and implementation details of our methods are available from https://github.com/farshidrayhanuiu/FRnet-DTI/ and also readily available to use as an web application from http://farshidrayhan.pythonanywhere.com/FRnet-DTI/ . Show less

In this chapter several aspects of Pt(II) are highlighted that focus on the properties of Pt(II)-RNA adducts and the possibility that they influence RNA-based processes in cells. Cellular distribution of Pt(II) complexes results in significant platination of RNA, and localization studies find Pt(II) in the nucleus, nucleolus, and a distribution of other sites in cells. Treatment with Pt(II) compounds disrupts RNA-based processes including enzymatic processing, splicing, and translation, and this disruption may be indicative of structural changes to RNA or RNA-protein complexes. Several RNA-Pt(II) adducts have been characterized in vitro by biochemical and other methods. Evidence for Pt(II) binding in non-helical regions and for Pt(II) cross-linking of internal loops has been found. Although platinated sites have been identified, there currently exists very little in the way of detailed structural characterization of RNA-Pt(II) adducts. Some insight into the details of Pt(II) coordination to RNA, especially RNA helices, can be gained from DNA model systems. Many RNA structures, however, contain complex tertiary folds and common, purine-rich structural elements that present suitable Pt(II) nucleophiles in unique arrangements which may hold the potential for novel types of platinum-RNA adducts. Future research aimed at structural characterization of platinum-RNA adducts may provide further insights into platinum-nucleic acid binding motifs, and perhaps provide a rationale for the observed inhibition by Pt(II) complexes of splicing, translation, and enzymatic processing. Show less