Prediction of disease-associated nsSNPs by integrating multi-scale ResNet models with deep feature fusion

Abstract

More than 6000 human diseases have been recorded to be caused by non-synonymous single nucleotide polymorphisms (nsSNPs). Rapid and accurate prediction of pathogenic nsSNPs can improve our understanding of the principle and design of new drugs, which remains an unresolved challenge. In the present work, a new computational approach, termed MSRes-MutP, is proposed based on ResNet blocks with multi-scale kernel size to predict disease-associated nsSNPs. By feeding the serial concatenation of the extracted four types of features, the performance of MSRes-MutP does not obviously improve. To address this, a second model FFMSRes-MutP is developed, which utilizes deep feature fusion strategy and multi-scale 2D-ResNet and 1D-ResNet blocks to extract relevant two-dimensional features and physicochemical properties. FFMSRes-MutP with the concatenated features achieves a better performance than that with individual features. The performance of FFMSRes-MutP is benchmarked on five different datasets. It achieves the Matthew’s correlation coefficient (MCC) of 0.593 and 0.618 on the PredictSNP and MMP datasets, which are 0.101 and 0.210 higher than that of the existing best method PredictSNP1. When tested on the HumDiv and HumVar datasets, it achieves MCC of 0.9605 and 0.9507, and area under curve (AUC) of 0.9796 and 0.9748, which are 0.1747 and 0.2669, 0.0853 and 0.1335, respectively, higher than the existing best methods PolyPhen-2 and FATHMM (weighted). In addition, on blind test using a third-party dataset, FFMSRes-MutP performs as the second-best predictor (with MCC and AUC of 0.5215 and 0.7633, respectively), when compared with the other four predictors. Extensive benchmarking experiments demonstrate that FFMSRes-MutP achieves effective feature fusion and can be explored as a useful approach for predicting disease-associated nsSNPs. The webserver is freely available at http://csbio.njust.edu.cn/bioinf/ffmsresmutp/ for academic use.

Accurate few-shot object counting with Hough matching feature enhancement

“…It contains 6,135 images from 147 classes, and each image has randomly selected three exemplars annotated by the bounding box to show the target objects. There are different cross-validation methods, such as k-fold cross-validation and jackknife test, which are generally used to develop deep learning model (Arif et al, 2018 , 2020 , 2021 ; Ge et al, 2021 , 2022a , b ; Sikander et al, 2022 ). According to the division method of the original dataset (Ranjan et al, 2021 ), we divide the dataset into training set, validation set, and test set.…”

An initial prediction and fine-tuning model based on improving GCN for 3D human motion prediction

“…There are different cross-validation methods, such as k-fold cross-validation and jack-knife test, which have been generally used to train the model (Arif et al, 2021 ; Ge et al, 2021 , 2022a , b ; Sikander et al, 2022 ). We trained our proposed model using a 10-fold cross-validation method.…”

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.…”