DermGemma
A multi-agent, multimodal RAG, AI dermatological assistant.
Open-source implementations, research code, and tools for the machine learning community
A multi-agent, multimodal RAG, AI dermatological assistant.
A model to predict histological, vital, and receptor status by concatenating 1,936 multi-omics features per patient node.
A Python toolkit for single-cell RNA sequencing (scRNA-seq) analysis.
FASTQ k-merization
RNA sequence data normalization.
Exon Junction Analyzer.
Single cell RNA sequencing using GenePT.
KEGG Pathway Enrichment Analysis using R and clusterProfiler.
Histopathologic CapsuleNet for cancer classification.
This Python script implements a genetic algorithm that recreates a target image (the Mona Lisa) by iteratively evolving a population of 500 semi-transparent circles through processes of selection, crossover, and mutation to minimize the visual difference between the generated art and the original.
This Jupyter Notebook implements a graph neural network (GNN) pipeline for binary survival classification (alive vs. deceased) using multi-omics breast cancer data.
Design novel protein sequences with unique binding sites using GPT-2.
DINOv2 Nuclei Segmentation.
A Gradio app for Microsoft's SOTA grounded radiology report generation model.
Fine tuned SmolLM-135M-Instruct using Group Relative Policy Optimization (with and without Flash Attenton). Made a Gradio Space for the model.
Fine tuned Llama 2 on a custom product review sentiment dataset with instructions.
A Gradio app for TotalSegmentator.
Fine-tuned the model.
A DICOM annotation tool for 3D segmentation.
Speech emotion classification with multi-head self-attention.
A Gradio app for SigLIP 2 Zero-shot image classification.