WalkIm: Compact image-based encoding for high-performance classification of biological sequences using simple tuning-free CNNs

Abstract

The classification of biological sequences is an open issue for a variety of data sets, such as viral and metagenomics sequences. Therefore, many studies utilize neural network tools, as the well-known methods in this field, and focus on designing customized network structures. However, a few works focus on more effective factors, such as input encoding method or implementation technology, to address accuracy and efficiency issues in this area. Therefore, in this work, we propose an image-based encoding method, called as WalkIm, whose adoption, even in a simple neural network, provides competitive accuracy and superior efficiency, compared to the existing classification methods (e.g. VGDC, CASTOR, and DLM-CNN) for a variety of biological sequences. Using WalkIm for classifying various data sets (i.e. viruses whole-genome data, metagenomics read data, and metabarcoding data), it achieves the same performance as the existing methods, with no enforcement of parameter initialization or network architecture adjustment for each data set. It is worth noting that even in the case of classifying high-mutant data sets, such as Coronaviruses, it achieves almost 100% accuracy for classifying its various types. In addition, WalkIm achieves high-speed convergence during network training, as well as reduction of network complexity. Therefore WalkIm method enables us to execute the classifying neural networks on a normal desktop system in a short time interval. Moreover, we addressed the compatibility of WalkIm encoding method with free-space optical processing technology. Taking advantages of optical implementation of convolutional layers, we illustrated that the training time can be reduced by up to 500 time. In addition to all aforementioned advantages, this encoding method preserves the structure of generated images in various modes of sequence transformation, such as reverse complement, complement, and reverse modes.

PC-mer: An Ultra-fast memory-efficient tool for metagenomics profiling and classification

“…These datasets are also chosen from various taxonomy levels and identities to evaluate the capability of PC-mer method against the state-of-art encoding methods, i.e. FCGR [ 11 , 12 , 20 – 22 ] and WalkIm [ 23 ]. These datasets, alongside HLT_datasets, have also been used for the second assessment.…”

“…First of all, we examine the accuracy of various architectures of machine learning-based classifiers employing the PC-mer feature extraction approach to build their input vectors for classifying various levels of metagenomics data. We then compared our best results to the best classification performances provided by the RDP classifier [ 7 ], the reference classifier for bacteria identification, WalkIm [ 23 ], and finally, CNN-DBN classifier [ 11 ]. It should be noted that all simulation results for various classifier methods have been reported in S1 File in details.…”

High-Speed Multi-Layer Convolutional Neural Network Based on Free-Space Optics

“…To emphasize the importance of optical implementation of the forward inference in CNNs, optical processing of the large biological data sequences is explored as follows. As discussed in [45], classification of virus sequences (e.g., Coronaviruses, Dengue, HIV, Hepatitis B and C, and Influenza A), metagenomics data, and metabarcoding data can be performed by CNNs taking advantages of an appropriate image-based encoding method. It should be noted that single training procedure is carried out for each biological dataset while many test procedures are required to classify the input [44].…”

Heterogeneous Ensemble for Medical Data Classification

“…The problem of how to transform 2D data into 1D data or whether to do so at all is of interest in many different areas, such as in the prediction of molecular properties on the bases of molecular structures [5] or in the case of automated methods for detecting viral subtypes using genomic data [6]. The choice often depends on the selected transformers and classifiers.…”