Hello, welcome to my GitHub Account 👋 I work at the intersection of biology, bioinformatics, data science, machine learning, and scientific software. My focus is on building practical computational tools that help turn biological questions into transparent and reproducible workflows. Here, you will find projects spanning phage biology, CRISPR, microbial genomics, structural bioinformatics, bioprocess modelling, and AI/ML for biotechnology.

I am an M.Sc. Biotechnology student specialization in Industrial Biotechnology at Gujarat Biotechnology University working at the intersection of biology, data science, bioinformatics, and research software.

My work focuses on turning biological questions into transparent, reproducible, and practical computational workflows. I am especially interested in microbial genomics, phage biology, antimicrobial research, genome engineering, structural bioinformatics, and machine-learning applications in biotechnology.

Current direction: using data and biology together to build tools that are scientifically useful, interpretable, and reproducible.

• 🦠 Phage & microbial bioinformatics - phage annotation, endolysin discovery, sequence analysis, protein representations, and host prediction
• 🧬 Genome engineering - CRISPR guide design, multi-gene targeting, validation, and sequence provenance
• 🧫 Bioprocess data science - soft sensors, fault-inclusive modelling, uncertainty, and out-of-distribution analysis
• 🔬 Structural bioinformatics - protein structure analysis, molecular docking, and computational modelling
• 🛠️ Scientific software - Python-based tools, Streamlit applications, reproducible pipelines, and research dashboards

Developing an end-to-end computational workflow for phage-host analysis:

Metagenomic data
      ↓
Viral / phage sequence detection
      ↓
Genome annotation
      ↓
Endolysin identification
      ↓
Protein sequence representations / embeddings
      ↓
Bacterial host prediction

The objective is to combine biologically meaningful sequence information with interpretable AI/ML methods for phage-bacteria association analysis.

I aim to keep research tools:

• Biologically grounded - scientific assumptions and limitations are stated clearly
• Reproducible - versions, provenance, benchmark inputs, and tests are retained
• Interpretable - model or heuristic outputs are presented with appropriate context
• Usable - researchers can run workflows through practical interfaces and export results
• Open to validation - computational predictions are treated as evidence to investigate, not substitutes for experimental confirmation

• 🐍 AMS Venom Diagnostic Dashboard - interactive simulation and visualization of antigen-scFv diagnostic signals

I am interested in research collaborations where biotechnology, computational biology, bioinformatics, machine learning, and practical scientific software come together.

Thank you for visiting my profile
_{Biotechnology × AI/ML for Biological Systems × Computational Biology × Bioinformatics}