Abhijit Rajkumar
Software engineer expertise in AI and Ml
Ready for work
Abhijit is ready for their next project!
🧬 Patho-Predict: AI-Powered Genetic Variant Analysis
I built Patho-Predict, a web application that helps analyze single-nucleotide variants (SNVs) by combining modern AI infrastructure with genomic data.
What it does
🧬 Analyze chromosome positions and nucleotide changes
🧪 Identify codon and amino acid substitutions
⚡ Predict whether a variant is Likely Pathogenic or Benign in seconds
🔍 Explore gene context using UCSC Genome Browser and ClinVar data
☁️ Deploy scalable inference with a serverless AI backend on Modal
Tech Stack
Next.js
Python
FastAPI
Modal
AI/ML
Genomics APIs
This project demonstrates how AI and cloud-native infrastructure can make genomic variant analysis faster, more accessible, and easier to integrate into modern research workflows.
If you're interested in AI, bioinformatics, or building scalable ML applications, I'd love to connect and hear your feedback.
#AI #Bioinformatics #Genomics #MachineLearning #Python #FastAPI #NextJS #Modal #Serverless #HealthcareAI #OpenSource
0
4
🚀 Built a Breast Cancer Prediction Web App with Flask & Scikit-learn
Early detection can save lives. To explore how Machine Learning can support healthcare, I built a Breast Cancer Prediction application using Scikit-learn and Flask.
🔧 Tech Stack
🐍 Python
🤖 Scikit-learn
🌐 Flask
📊 Pandas & NumPy
🎨 HTML/CSS
✨ Features
✅ Predicts whether a tumor is Benign or Malignant
✅ User-friendly web interface built with Flask
✅ Trained using the Breast Cancer Wisconsin dataset
✅ Fast and lightweight deployment-ready application
✅ Clean project structure for learning and extension
This project helped me gain hands-on experience in:
End-to-end Machine Learning workflows
Model serialization and deployment
Building REST-powered web applications with Flask
Integrating ML models into real-world applications
I'm continuously building AI and Full-Stack projects focused on solving practical problems and improving my production engineering skills. Feedback and contributions are always welcome!
#MachineLearning #Python #Flask #ScikitLearn #HealthcareAI #BreastCancer #AI #DataScience #WebDevelopment #OpenSource #PortfolioProject
0
8
RAG_CHAT is an AI-powered chatbot built with Retrieval-Augmented Generation (RAG) to deliver context-aware, knowledge-grounded responses.
⚙️ Tech Stack Highlights
Backend → FastAPI + LangChain/LangGraph + Qdrant (Vector DB)
Frontend → Next.js (React, Tailwind)
Infra → Docker Compose with isolated backend & frontend containers
Data Layer → SQLite-based checkpointing for persistent conversation memory
✨ Key Features
📚 Retrieval-Augmented answers using a vector database
🔄 Persistent memory with LangGraph checkpointing
🔐 Secure design: backend isolated in its own container, frontend as the only public interface
⚡ Real-time, interactive chat UI
🔗 This project reflects my journey in AI/ML, full-stack development, and scalable system design — bringing together everything from LLM orchestration to containerized deployment.
0
7
RAGnosis – AI-Powered Medical Document Analysis Platform
RAGnosis is an AI-powered healthcare application that enables users to upload medical documents and receive accurate, context-aware answers using Retrieval-Augmented Generation (RAG). The platform extracts relevant information from medical reports, prescriptions, discharge summaries, and lab results, then generates reliable responses backed by document citations, helping users understand complex medical information quickly and securely.
0
25