Xiangxiang Zeng

TL;DR: ADMETlab 2.0 as discussed by the authors is a completely redesigned version of the widely used AMDETlab web server for the predictions of pharmacokinetics and toxicity properties of chemicals, of which the supported ADMET-related endpoints are approximately twice the number of the endpoints in the previous version, including 17 physicochemical properties, 13 medicinal chemistry properties, 23 ADME properties, 27 toxicity endpoints and 8 toxicophore rules.

TL;DR: A network-based deep-learning approach for in silico drug repurposing by integrating 10 networks, termed deepDR, which learns high-level features of drugs from the heterogeneous networks by a multimodal deep autoencoder and infer candidates for approved drugs for which they were not originally approved.

TL;DR: The existing computational approaches for predicting potential disease-related miRNA based on networks are summarized and the confronted difficulties that help understand the research status are presented.

TL;DR: An improved and easy-to-use circRNA read simulator that can produce mimicking backsplicing reads supporting circRNAs deposited in CircBase is provided and the performance of 11 circRNA detection tools on both simulated and real datasets is compared.

TL;DR: Case studies further demonstrated the feasibility of the method to discover potential miRNA-disease associations and highlighted three limitations commonly associated with previous computational methods.