Our Research

Tackling antimicrobial resistance through innovative combination therapies, artificial intelligence, and next-generation biological strategies.

Research Area 01

Combination Therapy Against Priority Pathogens

Harnessing the synergistic power of phytochemicals and conventional antibiotics to combat WHO-priority pathogens. We screen plant-derived bioactive compounds for their ability to potentiate antibiotic efficacy, reverse resistance mechanisms, and reduce minimum inhibitory concentrations against critical drug-resistant bacteria.

  • Synergy screening of phytochemical–antibiotic combinations
  • Mechanistic studies on resistance reversal
  • In vitro and in vivo efficacy evaluation against ESKAPE pathogens
Research Area 02

AI-Based Drug Discovery & Repurposing

Leveraging artificial intelligence and machine learning to accelerate the discovery and repurposing of drugs against WHO-priority pathogens. Our computational pipelines integrate molecular docking, deep learning, and network pharmacology to identify novel therapeutic candidates from existing drug libraries.

  • Virtual screening and molecular docking against resistance targets
  • Deep learning models for drug–target interaction prediction
  • Repurposing FDA-approved drugs for antimicrobial applications
Research Area 03

Heavy Metal Impact on Bacterial Antibiotic Resistance

Investigating the co-selection pressure of heavy metals on the emergence and propagation of antibiotic resistance in environmental and clinical bacterial isolates. We explore how metal contamination in soil and water ecosystems drives cross-resistance and co-resistance through shared genetic determinants.

  • Co-selection of metal and antibiotic resistance genes
  • Environmental surveillance of metal-contaminated sites
  • Plasmid-mediated co-transfer of resistance determinants
Research Area 04

AI-Based AMR Prediction Using Morphology

Developing AI-powered image analysis pipelines that predict antimicrobial resistance directly from bacterial morphology. By training deep learning models on microscopy images, we aim to enable rapid, culture-free resistance profiling that can dramatically shorten diagnostic turnaround times in clinical settings.

  • Convolutional neural networks for morphological classification
  • Rapid phenotypic resistance prediction from microscopy
  • Integration with clinical diagnostic workflows
Research Area 05

Phage Therapy Against Priority Pathogens

Exploring bacteriophages as a targeted biological weapon against multi-drug-resistant priority pathogens. We isolate, characterize, and engineer lytic phages with high specificity to combat infections where conventional antibiotics have failed, offering a precision alternative for the post-antibiotic era.

  • Isolation and characterization of lytic bacteriophages
  • Phage–antibiotic synergy studies
  • Phage cocktail design for clinical applications