flowchart TD
A[Genomic Data]
B[Database Layer]
C[AI Engine LLM]
D[ARG Prediction & Classification]
E[Research Insights & Reports]
A -->|Data Flow| B
B -->|Query Processing| C
C -->|Analysis| D
D -->|Output| E
style A fill:#FF6B9D,stroke:#fff,stroke-width:3px,color:#fff
style B fill:#00D9FF,stroke:#fff,stroke-width:3px,color:#fff
style C fill:#FFD700,stroke:#fff,stroke-width:3px,color:#000
style D fill:#00FF88,stroke:#fff,stroke-width:3px,color:#000
style E fill:#9D4EDD,stroke:#fff,stroke-width:3px,color:#fff
This final-year research project integrates AI and genomic data to analyze antibiotic resistance genes (ARGs). The framework enables ARG detection, classification, and interpretation, providing actionable insights for researchers and students.
Organization: Genomic AI Research Lab (GARL)
Abdullah Al Noman 0112230367 
|
Kazi Neyamul Hasan 0112230359 
|
Mahathir Mohammad 0112230889 
|
Md. Habibulla Misbah 011221373 
|
Rakibul Hassan 0112230362 
|
┌────────────────────────────────────────────────────────────────┐
│ "Transforming genetic data into actionable research insights" │
│ Making science accessible through AI │
└────────────────────────────────────────────────────────────────┘
This project addresses genomic data accessibility challenges in Bangladesh and pioneers novel approaches to ARG analysis using AI.
|
Infrastructure Development AI Integration |
Analysis & Reporting Knowledge Transfer |
| Challenge | Our Solution |
|---|---|
| Localized Data Gap | Region-specific genomic database for Bangladesh |
| Accessibility Barriers | AI-powered interpretation for researchers and students |
| Complexity | Automated ARG detection and classification |
| Engagement | Interactive reports and visualizations for genomic data |
Genomic databases are fundamental to modern biological research, yet significant barriers persist. Our framework addresses these challenges through intelligent automation and creative engagement strategies, making cutting-edge genetic research accessible to everyone.
┌──────────────────────────────────────────────────────────────┐
│ │
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
│ │ Database │───▶│ AI Engine │───▶│Visualization│ │
│ │ Layer │ │ (LLM) │ │& Reporting │ │
│ └─────────────┘ └─────────────┘ └─────────────┘ │
│ │ │ │ │
│ └───────────────────┴───────────────────┘ │
│ │ │
│ ┌─────────────┐ │
│ │ API Layer │ │
│ └─────────────┘ │
│ │
└──────────────────────────────────────────────────────────────┘
| Component | Description |
|---|---|
| Database Layer | Region-specific genomic repository storing sequences and ARG annotations |
| AI Engine | LLM for ARG prediction, classification, and interpretation |
| Visualization & Reporting | Interactive dashboards, tables, and natural language summaries |
| API Infrastructure | RESTful services for programmatic access and queries |
graph TD
A[Literature Review] --> B[Genomic Database Construction]
B --> C[ARG Annotation & Labeling]
C --> D[AI Model Selection & Training]
D --> E[ARG Prediction Module Development]
E --> F[Testing Validation & Iteration]
F --> G[Documentation & Reporting]
style A fill:#FF6B9D,stroke:#fff,stroke-width:2px,color:#fff
style B fill:#00D9FF,stroke:#fff,stroke-width:2px,color:#fff
style C fill:#FFD700,stroke:#fff,stroke-width:2px,color:#fff
style D fill:#00FF88,stroke:#fff,stroke-width:2px,color:#fff
style E fill:#9D4EDD,stroke:#fff,stroke-width:2px,color:#fff
style F fill:#FF6B9D,stroke:#fff,stroke-width:2px,color:#fff
style G fill:#00D9FF,stroke:#fff,stroke-width:2px,color:#fff
Our development process follows rigorous academic standards, combining theoretical research with practical implementation and continuous refinement based on expert feedback and user testing.
| Phase | Focus Area | Status |
|---|---|---|
| Phase 1 | Database Architecture & Data Acquisition |  |
| Phase 2 | LLM Integration & Query System |  |
| Phase 3 | ARG Prediction & Reporting Module | |
| Phase 4 | Testing & Refinement | |
| Phase 5 | Final Documentation & Presentation | |
|
Provides local researchers with tailored genomic resources Offers an engaging platform for genetics education |
Demonstrates practical AI applications in scientific contexts Supports public health initiatives through accessible genetic information |
We extend our gratitude to our academic advisors, the Computer Science department, and the Genomic AI Research Lab for their guidance and support throughout this endeavor.
