Loading...

Developing a Deep Neural Network for Bio-sequence Classification Capable of Optical Computing

Mohammadi, Amir Hossein | 2023

88 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 55769 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Koohi, Somayyeh
  7. Abstract:
  8. 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. On the other side We presented a new encoding method, named PC-mer, based on the k-mer and physicochemical properties of nucleotides, which minimizes the size of encoded data by around 2k times, compared to the classical k-mer based profiling method. Moreover, using PC-mer, we designed a Machine-Learning-based classification tool for biological sequences with the ability to get input sequences from NCBI database. PC-mer achieves 100% accuracy despite the use of very simple classification algorithms based on ML (Machine Learning). This outperformance of PC-mer implies that it can replace the alignment-based approaches for the goal of sequence comparison and phylogenetic analysis.
  9. Keywords:
  10. Convolutional Neural Network ; Machine Learning ; Coding ; Optical Computing ; Data Classification ; Bioloical Data ; Genome Sequencing ; Feature Vector ; Data Encoding

 Digital Object List

 Bookmark

No TOC