Mal-Light: Enhancing Lysine Malonylation Sites Prediction Problem Using Evolutionary-based Features

Abstract

Post Translational Modification (PTM) is considered an important biological process with a tremendous impact on the function of proteins in both eukaryotes, and prokaryotes cells. During the past decades, a wide range of PTMs has been identified. Among them, malonylation is a recently identified PTM which plays a vital role in a wide range of biological interactions. Notwithstanding, this modification plays a potential role in energy metabolism in different species including Homo Sapiens. The identification of PTM sites using experimental methods is time-consuming and costly. Hence, there is a demand for introducing fast and cost-effective computational methods. In this study, we propose a new machine learning method, called Mal-Light, to address this problem. To build this model, we extract local evolutionary-based information according to the interaction of neighboring amino acids using a bi-peptide based method. We then use Light Gradient Boosting (LightGBM) as our classifier to predict malonylation sites. Our results demonstrate that Mal-Light is able to significantly improve malonylation site prediction performance compared to previous studies found in the literature. Using Mal-Light we achieve Matthew's correlation coefficient (MCC) of 0.74 and 0.60, Accuracy of 86.66% and 79.51%, Sensitivity of 78.26% and 67.27%, and Specificity of 95.05% and 91.75%, for Homo Sapiens and Mus Musculus proteins, respectively. Mal-Light is implemented as an online predictor which is publicly available at: (http://brl.uiu.ac.bd/MalLight/) INDEX TERMS Cluster centroid based majority under-sampling technique, evolutionary information, light gradient boosting, lysine malonylation, machine learning, post translational modifications.

Accurately Predicting Glutarylation Sites Using Sequential Bi-Peptide-Based Evolutionary Features

“…To ensure the little variation based on the property of the dataset, we pick the maximum value of the entire feature vectors. We then multiply the positive sites to 1.0001 and 1.0005, where the new value is much closer to the original value as done in References [13,38]. Initially, we have 723 positive sites.…”

“…In this study, we have applied different kinds of classification methods. These classifiers are also widely used in the literature and demonstrated promising results for similar studies [13,39,[48][49][50]. In this case, we study several ensemble learning methods such as Extreme Gradient Boosting (XGBoost) [48], Extra Tree (ET) Classifier [49], and Random Forest (RF) [25].…”

“…In this case, we study several ensemble learning methods such as Extreme Gradient Boosting (XGBoost) [48], Extra Tree (ET) Classifier [49], and Random Forest (RF) [25]. We also investigate several meta-classifiers such as Adaptive Boosting (AdaBoost) [39] and a tree-based learning algorithm Light Gradient Boosting Machine (LightGBM) [13]. We also study several of the most popular classifiers such as the Multi-layer Perceptron (MLP) classifier, which is a popular Artificial Neural Network (ANN) model [50].…”

“…So far, more than 600 types of PTMs have been identified. Some of the most widely observed PTMs are Acetylation [7], Propionylation [8], Sumoylation [9], Succinylation [10,11], Malonylation [12], and Methylation [13,14] among the main 20 contributing amino acids to build proteins [15].…”

VoSE: An algorithm to Separate and Enhance Voices from Mixed Signals using Gradient Boosting

“…LightGBM has a maximum depth parameter, it expands like a tree but prevents overfitting. Gradient boosting, due to its tree structure, is known to be good for tabular data but recently researchers have found it useful in a various applications [55][56][57][58][59][60][61][62][63][64][65][66][67].…”