RF-MaloSite and DL-Malosite: Methods based on random forest and deep learning to identify malonylation sites

Hussam Al-Barakati; Niraj Thapa; Saigo Hiroto; Kaushik Roy; Robert H Newman; Dukka Kc

doi:10.1016/j.csbj.2020.02.012

RF-MaloSite and DL-Malosite: Methods based on random forest and deep learning to identify malonylation sites

Comput Struct Biotechnol J. 2020 Mar 4:18:852-860. doi: 10.1016/j.csbj.2020.02.012. eCollection 2020.

Authors

Hussam Al-Barakati¹, Niraj Thapa¹, Saigo Hiroto², Kaushik Roy¹, Robert H Newman³, Dukka Kc⁴

Affiliations

¹ Department of computational Science and Engineering, North Carolina A&T State University, Greensboro, NC, USA.
² Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan.
³ Department of Biology, North Carolina A&T State University, Greensboro, NC, USA.
⁴ Department of Electrical Engineering and Computer Science, Wichita State University, Wichita, KS, USA.

Abstract

Malonylation, which has recently emerged as an important lysine modification, regulates diverse biological activities and has been implicated in several pervasive disorders, including cardiovascular disease and cancer. However, conventional global proteomics analysis using tandem mass spectrometry can be time-consuming, expensive and technically challenging. Therefore, to complement and extend existing experimental methods for malonylation site identification, we developed two novel computational methods for malonylation site prediction based on random forest and deep learning machine learning algorithms, RF-MaloSite and DL-MaloSite, respectively. DL-MaloSite requires the primary amino acid sequence as an input and RF-MaloSite utilizes a diverse set of biochemical, physiochemical and sequence-based features. While systematic assessment of performance metrics suggests that both 'RF-MaloSite' and 'DL-MaloSite' perform well in all metrics tested, our methods perform particularly well in the areas of accuracy, sensitivity and overall method performance (assessed by the Matthew's Correlation Coefficient). For instance, RF-MaloSite exhibited MCC scores of 0.42 and 0.40 using 10-fold cross-validation and an independent test set, respectively. Meanwhile, DL-MaloSite was characterized by MCC scores of 0.51 and 0.49 based on 10-fold cross-validation and an independent set, respectively. Importantly, both methods exhibited efficiency scores that were on par or better than those achieved by existing malonylation site prediction methods. The identification of these sites may also provide important insights into the mechanisms of crosstalk between malonylation and other lysine modifications, such as acetylation, glutarylation and succinylation. To facilitate their use, both methods have been made freely available to the research community at https://github.com/dukkakc/DL-MaloSite-and-RF-MaloSite.

Keywords: Convolutional neural network; Deep learning; Malonylation; Post-translational Modification Sites; Random forest.

Grants and funding

SC1 GM130545/GM/NIGMS NIH HHS/United States