AUTHOR=Ikeda Kazuyoshi , Doi Takuo , Ikeda Masami , Tomii Kentaro 

TITLE=PreBINDS: An Interactive Web Tool to Create Appropriate Datasets for Predicting Compound–Protein Interactions

JOURNAL=Frontiers in Molecular Biosciences

VOLUME=Volume 8 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/molecular-biosciences/articles/10.3389/fmolb.2021.758480

DOI=10.3389/fmolb.2021.758480

ISSN=2296-889X

ABSTRACT=Given the abundant computational resources and a huge amount of data of compound-protein interactions (CPIs), constructing appropriate datasets for training and evaluating prediction models for CPIs is not always easy. In this study, we have developed a web server, called CASPER, to facilitate the development and evaluation of prediction models by providing an appropriate dataset according to the task. Our web server provides an environment and dataset that aid model developers and evaluators in obtaining a suitable dataset for both proteins and compounds, in addition to attributes necessary for deep learning. Using the interface of web server, users can customize the CPI dataset, derived from ChEMBL, by setting positive and negative thresholds to be adjusted according to a user's definitions. These functions enable effective development and evaluation of models. Furthermore, users can prepare their task-specific datasets by selecting a set of target proteins based on various criteria, such as Pfam families, ChEMBL's classification and sequence similarities. The accuracy and efficiency of in silico screening and drug design using machine learning including deep learning can therefore be improved by facilitating access to an appropriate dataset prepared using our web server (https://binds.lifematics.work/).