Identification of stress response proteins through fusion of machine learning models and statistical paradigms

Abstract

Proteins are a vital component of cells that perform physiological functions to ensure smooth operations of bodily functions. Identification of a protein's function involves a detailed understanding of the structure of proteins. Stress proteins are essential mediators of several responses to cellular stress and are categorized based on their structural characteristics. These proteins are found to be conserved across many eukaryotic and prokaryotic linkages and demonstrate varied crucial functional activities inside a cell. The in-vivo, ex vivo, and in-vitro identification of stress proteins are a time-consuming and costly task. This study is aimed at the identification of stress protein sequences with the aid of mathematical modelling and machine learning methods to supplement the aforementioned wet lab methods. The model developed using Random Forest showed remarkable results with 91.1% accuracy while models based on neural network and support vector machine showed 87.7% and 47.0% accuracy, respectively. Based on evaluation results it was concluded that random-forest based classifier surpassed all other predictors and is suitable for use in practical applications for the identification of stress proteins. Live web server is available at http://biopred.org/stressprotiens, while the webserver code available is at https://github.com/abdullah5naveed/SRP_WebServer.git

Signal Peptide Efficiency: From High-Throughput Data to Prediction and Explanation

“…Here, the common theme is that a problem is often tackled with different approaches that are then benchmarked against each other. Some of the most common and successful ML models used in peptide prediction are the support vector machines − and random forests (RFs). − Recently, deep learning-based approaches have become popular, − also for SP prediction. , A relevant aspect in predictive models is the description of a peptide or protein used to train them, which can be based on information about its physicochemical properties, ,, its sequence, and/or its structure . Such information can be further encoded and fed to the algorithm in different ways.…”

“…Such information can be further encoded and fed to the algorithm in different ways. Common encoding methods include (pseudo-)­amino acid composition ,,− and positional matrices. , However, different models and feature-encoding methods may need to be applied, as each problem requires different and tailored combinations of tools.…”

“…Some of the most common and successful ML models used in peptide prediction are the support vector machines 38 − 40 and random forests (RFs). 40 − 42 Recently, deep learning-based approaches have become popular, 43 − 46 also for SP prediction. 47 , 48 A relevant aspect in predictive models is the description of a peptide or protein used to train them, which can be based on information about its physicochemical properties, 38 , 41 , 46 its sequence, 44 and/or its structure.…”

RCCC_Pred: A Novel Method for Sequence-Based Identification of Renal Clear Cell Carcinoma Genes through DNA Mutations and a Blend of Features

“…This accuracy evaluation is based on different factors. In this proposed work, various metrics were computed such as the specificity, sensitivity, and Matthew coefficient correlation (MCC) for the stability of the model and the accuracy of the model [ 33 , 40 , 41 ]. However, all these measures can be mathematically denoted as …”

IGPred‐HDnet: Prediction of Immunoglobulin Proteins Using Graphical Features and the Hierarchal Deep Learning‐Based Approach

“…Among them, the feature extraction scheme is a challenging and essential step in formulating a biological sequence into some numerical values [39]. Conventional classifcation learning models, including K-nearest neighbour (KNN), random forest (RF) [40,41], and support vector machine (SVM) [42], are based on fxedlength statistical values and are unable to handle the variable-length protein sequence; hence, the features representation algorithm can tackle this problem by extracting the fxed-length feature vector form the variable-length sequences [43][44][45]. Several researchers have used diferent feature encoding schemes [46] as shown in Figure 2; however, none of them used the proposed method for extracting vital pattern information from the immunoglobulins.…”