AI-Powered Antibiotic Discovery: Microbial Genome Mining, Biosynthetic Gene Clusters & Natural Product Prioritization

To equip researchers and industry professionals with practical knowledge and computational skills in microbial genome mining, biosynthetic gene cluster analysis, and AI-assisted prioritization of promising natural product candidates for antibiotic discovery.

• Understand the role of microbial natural products and biosynthetic gene clusters in antibiotic discovery.
• Explore microbial genome databases and retrieve genomic information for computational analysis.
• Identify and characterize PKS, NRPS, and RiPP biosynthetic gene clusters using genome-mining tools.
• Investigate microbial secondary metabolite pathways and assess biosynthetic diversity.
• Perform comparative BGC analysis using antiSMASH and MIBiG reference data.
• Understand applications of machine learning and AI in natural product discovery.
• Apply data-driven approaches to prioritize promising antibiotic-associated biosynthetic gene clusters.
• Develop reproducible bioinformatics workflows using Google Colab and Python.

📅 Day 1: Microbial Genome Mining & Biosynthetic Gene Cluster Discovery

• Introduction to AI-powered antibiotic discovery and antimicrobial resistance (AMR)
• Microbial natural products and secondary metabolites as sources of new antibiotics
• Antibiotic-producing microorganisms: Streptomyces, Bacillus, and other promising microbial taxa
• Microbial genome retrieval using NCBI Genome and RefSeq
• Fundamentals of biosynthetic gene clusters (BGCs) and secondary metabolite pathways
• Identification of PKS, NRPS, and RiPP biosynthetic gene clusters
• Genome mining and functional annotation using antiSMASH and GECCO

🧪 Hands-On: Identification of Antibiotic Biosynthetic Gene Clusters

• Analyze a microbial genome using prepared antiSMASH results and Google Colab to identify, classify, and visualize potential antibiotic-associated BGCs.
• Microbial Genome → BGC Identification → Functional Annotation → Annotated BGC Dataset

🧰 Tools: Google Colab | NCBI Genome | antiSMASH | GECCO | Python | pandas

🎯 Expected Outcome: Annotated microbial BGC dataset highlighting potential antibiotic biosynthetic pathways.

📅 Day 2: Natural Product Discovery, BGC Annotation & Novelty Assessment

• Microbial biosynthetic pathways involved in natural product and antibiotic production
• Identification of antibiotic-associated BGCs and specialized metabolite families
• Genome-based discovery of bacteriocins and antimicrobial peptides
• Reference-based BGC annotation using the MIBiG database
• Comparative biosynthetic gene cluster analysis and gene cluster families
• Introduction to BiG-SCAPE for BGC similarity networking and comparative analysis
• Assessing biosynthetic novelty through reference similarity, cluster diversity, and genomic context
• Linking microbial biosynthetic potential with known natural product classes

🧪 Hands-On: Comparative Analysis of Antibiotic Biosynthetic Gene Clusters

• Compare selected BGCs with MIBiG reference clusters, assess biosynthetic similarity, and identify potentially distinct natural product pathways using Google Colab.
• BGC Annotation → MIBiG Comparison → Similarity Analysis → Novelty Assessment

🧰 Tools: Google Colab | antiSMASH | MIBiG | BiG-SCAPE Reference Outputs | pandas | matplotlib

🎯 Expected Outcome: Comparative BGC analysis report identifying known and potentially novel biosynthetic pathways.

📅 Day 3: AI-Assisted Antibiotic Candidate Prioritization & Predictive Analysis

• Role of artificial intelligence and machine learning in genome-guided antibiotic discovery
• Integrating BGC annotations, biosynthetic classes, and reference similarity data
• Introduction to machine learning approaches for natural product discovery
• Applications of Random Forest and XGBoost in biological data analysis
• Feature engineering from BGC characteristics and genomic annotations
• Multi-parameter prioritization of promising antibiotic-associated BGCs
• Data visualization and interpretable candidate ranking
• Experimental validation strategies: metabolomics, antimicrobial activity screening, and compound characterization

🧪 Hands-On: AI-Assisted Prioritization of Antibiotic-Producing Gene Clusters

• Integrate BGC features and reference annotations in Google Colab, apply a multi-criteria prioritization model, and visualize ranked BGCs for further investigation.
• BGC Features → Data Integration → Candidate Scoring → Ranked BGCs

🧰 Tools: Google Colab | Python | pandas | NumPy | scikit-learn | matplotlib

🎯 Expected Outcome: Ranked candidate BGCs, comparative visualizations, and a reproducible computational screening workflow.

This workshop is designed for researchers, academicians, and industry professionals interested in microbial natural products, genomics, and computational antibiotic discovery.

• • Researchers & PhD Scholars: Working in Microbiology, Biotechnology, Microbial Genomics, Natural Products, and Antibiotic Discovery.
  • Academicians & Faculty Members: Specializing in Molecular Biology, Bioinformatics, Microbial Biotechnology, and Pharmaceutical Sciences.
  • Postdoctoral Researchers: Investigating microbial secondary metabolites, biosynthetic pathways, and antimicrobial compounds.
  • Pharmaceutical & Biotechnology Professionals: Involved in antimicrobial drug discovery, natural product research, and computational R&D.
  • Bioinformatics & Computational Biology Researchers: Interested in genome mining, biosynthetic gene cluster analysis, and AI-assisted molecular discovery.
  • Natural Product & Medicinal Chemistry Researchers: Exploring microbial metabolites and potential bioactive compounds for therapeutic development.

• Upon successful completion of the workshop, participants will be able to:

  • Perform Microbial Genome Mining: Retrieve and analyze microbial genomic data to explore antibiotic biosynthetic potential.
  • Identify Biosynthetic Gene Clusters: Detect and classify BGCs associated with microbial secondary metabolite production.
  • Analyze Natural Product Pathways: Investigate biosynthetic diversity and compare gene clusters with characterized references.
  • Evaluate Potential Novelty: Identify potentially distinct biosynthetic pathways using comparative genomic analysis.
  • Apply AI-Assisted Prioritization: Integrate genomic features and computational screening parameters to rank promising BGC candidates.
  • Develop Practical Bioinformatics Skills: Use Google Colab, Python, antiSMASH, and MIBiG for reproducible research workflows.
  • Support Future Antibiotic Research: Generate computational findings that can guide subsequent experimental screening and natural product characterization.