Journal Articles

Permanent URI for this collectionhttps://mro.massey.ac.nz/handle/10179/7915

Browse

Filters

2021 - 20232

Settings

Author: search.filters.author.Zhang JSubject: search.filters.subject.Computational Biology

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    DeepCAC: a deep learning approach on DNA transcription factors classification based on multi-head self-attention and concatenate convolutional neural network
    (BioMed Central Ltd, 2023-09-18) Zhang J; Liu B; Wu J; Wang Z; Li J
    Understanding gene expression processes necessitates the accurate classification and identification of transcription factors, which is supported by high-throughput sequencing technologies. However, these techniques suffer from inherent limitations such as time consumption and high costs. To address these challenges, the field of bioinformatics has increasingly turned to deep learning technologies for analyzing gene sequences. Nevertheless, the pursuit of improved experimental results has led to the inclusion of numerous complex analysis function modules, resulting in models with a growing number of parameters. To overcome these limitations, it is proposed a novel approach for analyzing DNA transcription factor sequences, which is named as DeepCAC. This method leverages deep convolutional neural networks with a multi-head self-attention mechanism. By employing convolutional neural networks, it can effectively capture local hidden features in the sequences. Simultaneously, the multi-head self-attention mechanism enhances the identification of hidden features with long-distant dependencies. This approach reduces the overall number of parameters in the model while harnessing the computational power of sequence data from multi-head self-attention. Through training with labeled data, experiments demonstrate that this approach significantly improves performance while requiring fewer parameters compared to existing methods. Additionally, the effectiveness of our approach  is validated in accurately predicting DNA transcription factor sequences.
  • Thumbnail Image
    Item
    Whole-genome sequencing and ad hoc shared genome analysis of Staphylococcus aureus isolates from a New Zealand primary school
    (Springer Nature Limited, 2021-10-13) Scott P; Zhang J; Anderson T; Priest PC; Chambers S; Smith H; Murdoch DR; French N; Biggs PJ
    Epidemiological studies of communicable diseases increasingly use large whole-genome sequencing (WGS) datasets to explore the transmission of pathogens. It is important to obtain an initial overview of datasets and identify closely related isolates, but this can be challenging with large numbers of isolates and imperfect sequencing. We used an ad hoc whole-genome multi locus sequence typing method to summarise data from a longitudinal study of Staphylococcus aureus in a primary school in New Zealand. Each pair of isolates was compared and the number of genes where alleles differed between isolates was tallied to produce a matrix of "allelic differences". We plotted histograms of the number of allelic differences between isolates for: all isolate pairs; pairs of isolates from different individuals; and pairs of isolates from the same individual. 340 sequenced isolates were included, and the ad hoc shared genome contained 445 genes. There were between 0 and 420 allelic differences between isolate pairs and the majority of pairs had more than 260 allelic differences. We found many genetically closely related S. aureus isolates from single individuals and a smaller number of closely-related isolates from separate individuals. Multiple S. aureus isolates from the same individual were usually very closely related or identical over the ad hoc shared genome. Siblings carried genetically similar, but not identical isolates. An ad hoc shared genome approach to WGS analysis can accommodate imperfect sequencing of the included isolates, and can provide insights into relationships between isolates in epidemiological studies with large WGS datasets containing diverse isolates.