Scholarlink

<p>A growing global health concern is Antimicrobial Resistance (AMR), especially in livestock such as ruminants, where overuse of antibiotics leads to resistance. Predicting AMR in these hosts accurately is crucial for enhancing treatment plans and reducing hazards to the public’s health. Machine Learning (ML) and Deep Learning (DL) based framework for predicting AMR in ruminant-associated bacterial pathogens is presented in this study. The sequences of 190 strains of <i>Staphylococcus aureus</i>, <i>Escherichia coli</i> and <i>Enterococcus faecalis</i> were collected from different international bioprojects based on how the strains responded to five widely used antibiotics—Methicillin, Penicillin, Ampicillin, Ciprofloxacin, and Gentamicin. Features like GC content, <i>k-mer</i> frequencies, and open reading frame (ORF) statistics were extracted from genomic sequence data of susceptible and resistant strains to train a number of DL and ML models. Further, a transformer-based architecture called DNABERT was fine-tuned on DNA sequences using 6-mer tokenization in order to capture contextual nucleotide patterns. Furthermore, a web-based application have been developed to make it easier for users to upload genomic sequences and receive real-time resistance/susceptibility forecasts. Compared to existing alignment-based and database-dependent AMR prediction methods, the proposed models DNABERT and XGBoost were found to be the best with the precision 86.7% and 84.8% respectively, while maintaining robustness to novel and unannotated genomic sequences. Thus paper presents a new and intuitive AMR prediction system for ruminant specific microorganisms, which is not bound to specific database methods, and achieves the detection of AMR through recognition of alignment-free inherent genomic sequence features and transformer-based sequence learning.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Artificial intelligence based approaches for prediction of antimicrobial resistance in ruminant host pathogens

  • 期刊论文

  • 发表日期：

    2026年3月9日

查看全文
  • Ragini Kushwaha,
  • Anu Sharma,
  • Bhavesh Kumar Choubisa,
  • Dwijesh Chandra Mishra,
  • Mohammad Samir Farooqi,
  • Sudhir Srivastava,
  • Priyanka Balley,
  • Shashi Bhusan Lal

摘要

A growing global health concern is Antimicrobial Resistance (AMR), especially in livestock such as ruminants, where overuse of antibiotics leads to resistance. Predicting AMR in these hosts accurately is crucial for enhancing treatment plans and reducing hazards to the public’s health. Machine Learning (ML) and Deep Learning (DL) based framework for predicting AMR in ruminant-associated bacterial pathogens is presented in this study. The sequences of 190 strains of Staphylococcus aureus, Escherichia coli and Enterococcus faecalis were collected from different international bioprojects based on how the strains responded to five widely used antibiotics—Methicillin, Penicillin, Ampicillin, Ciprofloxacin, and Gentamicin. Features like GC content, k-mer frequencies, and open reading frame (ORF) statistics were extracted from genomic sequence data of susceptible and resistant strains to train a number of DL and ML models. Further, a transformer-based architecture called DNABERT was fine-tuned on DNA sequences using 6-mer tokenization in order to capture contextual nucleotide patterns. Furthermore, a web-based application have been developed to make it easier for users to upload genomic sequences and receive real-time resistance/susceptibility forecasts. Compared to existing alignment-based and database-dependent AMR prediction methods, the proposed models DNABERT and XGBoost were found to be the best with the precision 86.7% and 84.8% respectively, while maintaining robustness to novel and unannotated genomic sequences. Thus paper presents a new and intuitive AMR prediction system for ruminant specific microorganisms, which is not bound to specific database methods, and achieves the detection of AMR through recognition of alignment-free inherent genomic sequence features and transformer-based sequence learning.