ARGs: ML-Powered Detection, Network Analysis, and Interactive Visualization

To equip participants with end-to-end computational and analytical skills for studying Antibiotic Resistance Genes (ARGs), enabling them to detect, quantify, visualize, and interpret resistance patterns in both genomic and metagenomic contexts using state-of-the-art bioinformatics tools and machine learning approaches.

• Understand mechanisms of antimicrobial resistance and the biological significance of ARGs.
• Explore and extract ARG sequences from public databases (CARD, ResFinder, ARG-ANNOT, NCBI AMR).
• Perform quality control and preprocessing of genomic and metagenomic datasets.
• Detect and annotate ARGs using BLAST, DIAMOND, HMMER, and ML-based approaches.
• Quantify ARG abundance and distribution across genomes and metagenomes.
• Predict phenotypic antibiotic resistance from ARG profiles using machine learning models.
• Construct co-occurrence networks and visualize ARG interactions using Python and Cytoscape.
• Create interactive dashboards and publication-ready figures for data interpretation and reporting.
• Design and execute a mini-project applying an end-to-end ARG workflow from sequence data to report generation.

• Antimicrobial Resistance Overview: Mechanisms, clinical and environmental relevance, One Health perspective
• ARG Fundamentals: Types, functional classes, key examples (β-lactamases, efflux pumps, aminoglycoside-modifying enzymes)
• ARG Databases: CARD, ResFinder, ARG-ANNOT, NCBI AMR database
• Metagenomic & Genomic Data Handling: Collect bacterial genomes, metagenomic datasets; FASTA/FASTQ formats
• Quality Control & Preprocessing: Read trimming, filtering, assembly basics
• Tools: Python, Biopython, FASTQC, Trimmomatic, Google Colab
• Hands-On: Explore ARG databases and extract sequences; Perform QC on sample genomes/metagenomes in Google Colab

• ARG Detection Approaches: BLAST-based, HMM-based, and ML-based approaches
• Functional Annotation: Map ARGs to resistance mechanisms, antibiotic classes, and drugs
• Sequence Alignment & Similarity Search: BLAST, DIAMOND, HMMER
• ARG Abundance & Distribution Analysis: Quantification in genomes/metagenomes
• Predictive Phenotyping: ML-based genotype → phenotype prediction
• Tools: BLAST, DIAMOND, HMMER, CARD/RGI, Python (pandas, seaborn, scikit-learn), Google Colab
• Hands-On: Detect ARGs in genome/metagenomic datasets; Generate ARG resistance profiles; Apply ML models to predict phenotypic resistance; Visualize ARG abundance with heatmaps and barplots

• ARG Characterization: Phylogenetic context, mobile genetic elements, co-occurrence networks
• Network Analysis: Build ARG co-occurrence networks using NetworkX or Cytoscape
• Advanced Visualization: Heatmaps, barplots, network diagrams, interactive dashboards (Plotly/Dash or Python notebooks)
• Reproducibility & Reporting: Workflow documentation, figures for publication, interpretation of resistance patterns
• Case Studies: Clinical isolates, immunology, environmental microbiomes
• Tools: Python, NetworkX, Plotly/Dash, matplotlib, seaborn, Cytoscape, Google Colab
• Hands-On / Mini Project: Full ARG analysis workflow: detection → ML-based prediction → network visualization → interactive dashboard; Generate publication-ready figures and a report

• Execute end-to-end ARG detection, annotation, and analysis workflows.
• Apply machine learning techniques to predict resistance phenotypes from ARG profiles.
• Perform network-based and phylogenetic characterization of ARGs.
• Generate interactive visualizations, heatmaps, barplots, and dashboards using Colab-compatible tools.
• Handle real-world genomic and metagenomic datasets efficiently.
• Produce reproducible, publication-ready reports and communicate ARG analysis findings.
• Gain hands-on expertise in current bioinformatics tools and trending computational methods in antimicrobial resistance research.

• PhD scholars, researchers, and academicians in microbiology, bioinformatics, genomics, or related life sciences.
• Industry professionals working in clinical microbiology, biotechnology, pharmaceutical research, or public health surveillance.
• Graduate and postgraduate students with foundational knowledge in molecular biology, genetics, or microbiology, who want to gain practical bioinformatics and ARG analysis skills.