@article{Uhl_Tran_Heyl-RNAPr_effic_and-2021,
author = {Uhl, Michael and Tran, Van Dinh and Heyl, Florian and 
          Backofen, Rolf},
title = {{RNAProt}: an efficient and feature-rich {RNA} binding 
         protein binding site predictor},
journal = {Gigascience},
year = {2021},
doi = {10.1093/gigascience/giab054},
volume = {10},
user = {backofen},
pmid = {34406415},
pages = {},
number = {8},
issn = {2047-217X},
abstract = {BACKGROUND: Cross-linking and immunoprecipitation followed 
            by next-generation sequencing (CLIP-seq) is the 
            state-of-the-art technique used to experimentally determine 
            transcriptome-wide binding sites of RNA-binding proteins 
            (RBPs). However, it relies on gene expression, which can be 
            highly variable between conditions and thus cannot provide a 
            complete picture of the RBP binding landscape. This creates 
            a demand for computational methods to predict missing 
            binding sites. Although there exist various methods using 
            traditional machine learning and lately also deep learning, 
            we encountered several problems: many of these are not well 
            documented or maintained, making them difficult to install 
            and use, or are not even available. In addition, there can 
            be efficiency issues, as well as little flexibility 
            regarding options or supported features. RESULTS: Here, we 
            present RNAProt, an efficient and feature-rich computational 
            RBP binding site prediction framework based on recurrent 
            neural networks. We compare RNAProt with 1 traditional 
            machine learning approach and 2 deep-learning methods, 
            demonstrating its state-of-the-art predictive performance 
            and better run time efficiency. We further show that its 
            implemented visualizations capture known binding preferences 
            and thus can help to understand what is learned. Since 
            RNAProt supports various additional features (including 
            user-defined features, which no other tool offers), we also 
            present their influence on benchmark set performance. 
            Finally, we show the benefits of incorporating additional 
            features, specifically structure information, when learning 
            the binding sites of an hairpin loop binding RBP. 
            CONCLUSIONS: RNAProt provides a complete framework for RBP 
            binding site predictions, from data set generation over 
            model training to the evaluation of binding preferences and 
            prediction. It offers state-of-the-art predictive 
            performance, as well as superior run time efficiency, while 
            at the same time supporting more features and input types 
            than any other tool available so far. RNAProt is easy to 
            install and use, comes with comprehensive documentation, and 
            is accompanied by informative statistics and visualizations. 
            All this makes RNAProt a valuable tool to apply in future 
            RBP binding site research.}
}