MFPS_CNN: Multi‐filter Pattern Scanning from Position‐specific Scoring Matrix with Convolutional Neural Network for Efficient Prediction of Ion Transporters

Abstract

In cellular transportation mechanisms, the movement of ions across the cell membrane and its proper control are important for cells, especially for life processes. Ion transporters/pumps and ion channel proteins work as border guards controlling the incessant traffic of ions across cell membranes. We revisited the study of classification of transporters and ion channels from membrane proteins with a more efficient deep learning approach. Specifically, we applied multi‐window scanning filters of convolutional neural networks on almost full‐length position‐specific scoring matrices for extracting useful information. In this way, we were able to retain important evolutionary information of the proteins. Our experiment results show that a convolutional neural network with a minimum number of convolutional layers can be enough to extract the conserved information of proteins which leads to higher performance. Our best prediction models were obtained after examining different data imbalanced handling techniques, and different protein encoding methods. We also showed that our models were superior to traditional deep learning approaches on the same datasets as well as other machine learning classification algorithms.

Identifying SNARE Proteins Using an Alignment-Free Method Based on Multiscan Convolutional Neural Network and PSSM Profiles

“…Based on the principle of multitask learning and following the architecture of DeepFam, the design of our model architecture was constructed on multiscan CNN including various convolutional layers. Inspired by the performance of DeepFam, this multiscan CNN has been also applied in the later sequence-based studies such as electron transporters or ion transporters …”

“…Inspired by the performance of DeepFam, this multiscan CNN has been also applied in the later sequencebased studies such as electron transporters 31 or ion transporters. 43 The layers were designed with different window sizes L of (16,24,32) to recognize the patterns better for the prediction task. We input the sequences of the (20 × 20) matrix into the convolution layer, which scanned those sequences across 20 channels.…”

“…Inspired by the performance of DeepFam, this multiscan CNN has been also applied in the later sequence-based studies such as electron transporters 31 or ion transporters. 43 …”

Discriminating Ion Channels from Non-Ion Channel Membrane Proteins Using Machine Learning and Deep Learning Classifiers with Protein Language Model Representations

“…There has been a significant amount of research on predicting ion channel proteins in the past, with an emphasis on developing computational methods that can accurately differentiate ion channels from non-ion channels [8][9][10][11][12][13][14]. These methods have often utilized traditional machine learning techniques, such as support vector machines (SVM) and random forests (RF), which classify protein sequences based on features derived from their primary, secondary, and tertiary structures.…”

“…The use of these features for ion channel prediction is thoroughly explained in Menke et al [9] and Ashrafuzzaman [8]. However, the emergence of deep learning has provided new opportunities for ion channel prediction, with recent studies demonstrating the potential of these techniques to generate rich representations of protein sequences and enhance the performance of ion channel predictors [13,14]. These models are able to learn complex patterns in protein sequences and use this information to improve prediction performance, potentially overcoming limitations of traditional machine learning approaches.…”