Methods In Computational Genomics

Antimicrobial peptides are present ubiquitously in intra- and extra-biological environments and display considerable antibacterial and antifungal activities. Clinically, it has shown good antibacterial effect in the treatment of diabetic foot and its complications. However, the discovery and screening of antimicrobial peptides primarily rely on wet lab experiments, which are inefficient. This study endeavors to create a precise and efficient method of predicting antimicrobial peptides by incorporating novel machine learning technologies. We proposed a deep learning strategy named AMP-EBiLSTM to accurately predict them, and compared its performance with ensemble learning and baseline models. We utilized Binary Profile Feature (BPF) and Pseudo Amino Acid Composition (PSEAAC) for effective local sequence capture and amino acid information extraction, respectively, in deep learning and ensemble learning. Each model was cross-validated and externally tested independently. The results demonstrate that the Enhanced Bi-directional Long Short-Term Memory (EBiLSTM) deep learning model outperformed others with an accuracy of 92.39% and AUC value of 0.9771 on the test set. On the other hand, the ensemble learning models demonstrated cost-effectiveness in terms of training time on a T4 server equipped with 16 GB of GPU memory and 8 vCPUs, with training durations varying from 0 to 30 s. Therefore, the strategy we propose is expected to predict antimicrobial peptides more accurately in the future.

The ongoing SARS-CoV-2 pandemic demonstrates the utility of real-time sequence analysis in monitoring and surveillance of pathogens. However, cost-effective sequencing requires that samples be PCR amplified and multiplexed via barcoding onto a single flow cell, resulting in challenges with maximising and balancing coverage for each sample. To address this, we developed a real-time analysis pipeline to maximise flow cell performance and optimise sequencing time and costs for any amplicon based sequencing. We extended our nanopore analysis platform MinoTour to incorporate ARTIC network bioinformatics analysis pipelines. MinoTour predicts which samples will reach sufficient coverage for downstream analysis and runs the ARTIC networks Medaka pipeline once sufficient coverage has been reached. We show that stopping a viral sequencing run earlier, at the point that sufficient data has become available, has no negative effect on subsequent down-stream analysis. A separate tool, SwordFish, is used to automate adaptive sampling on Nanopore sequencers during the sequencing run. This enables normalisation of coverage both within (amplicons) and between samples (barcodes) on barcoded sequencing runs. We show that this process enriches under-represented samples and amplicons in a library as well as reducing the time taken to obtain complete genomes without affecting the consensus sequence.