End-to-End Epidemiology & Genomics Analytics Platform Built as Year-Long Thesis

CovPred integrates public health, DNA mutation, and research datasets with AI-generated official reports and epidemic-spread dashboards.

Date

May 2024

Duration

12 months

Team

Solo (Thesis)

Category

RESEARCH

PythonCDC APIsGemini APIBioinformatics
01 / 05

Epidemiology and genomics datasets exist in silos across CDC, NIH, and academic databases. Synthesis requires domain expertise, manual processing, and weeks of analysis.

CovPred automatically ingests CDC feeds, government datasets, and genomic databases, correlates DNA mutation patterns with epidemic trajectory data, and auto-generates formatted public health reports via Gemini API.

01

Multi-Source Data Fusion

Automated ETL across CDC, NIH, NCBI, and WHO datasets with normalization.

02

Genomic Mutation Tracker

Visualizes variant emergence and spread velocity alongside geographic outbreak data.

03

Epidemic Spread Dashboard

Interactive dashboard with time-series modeling and regional trend breakdowns.

04

AI Report Generator

Gemini API generates formatted epidemiological reports from raw data — no manual writing required.

Data Science

PythonPandasNumPyScikit-learn

Bioinformatics

BiopythonNCBI Entrez APICDC WONDER API

AI

Google Gemini APINLP

Visualization

PlotlyDashMatplotlib
← All Projects Back to Portfolio