Projects

Personal and professional projects (7 total)

Filter by tags & tech:
AIAlphaGenomeAlphaGenome APIBPE TokenizationCUDAComputer VisionContentlayerDeep LearningDistributed TrainingFUSION/TWASGWASGraph Neural NetworksMachine LearningNext.jsPyTorchPyTorch GeometricPythonSelf-Supervised LearningSpatial TranscriptomicsSuSiESupabaseTWASTailwind CSSTransformer ArchitectureTypeScriptatrial fibrillationbioinformaticschatgptcomputational biologycomputer visioncontrastive learningdeep learningdevelopmental biologydistributed trainingfine-mappingfull-stackgenomicsgraph neural networksllmnlprepresentation learningself-supervised learningspatial transcriptomicstransformervariant effect predictionweb development

Showing all 7 projects

Evaluating AlphaGenome's pre-computed variant effect scores against TWAS associations across 10 GTEx tissues reveals weak but real directional signal, chromatin-driven fine-mapping enrichment, and fundamental limits of sequence-based expression prediction

Tech Stack:
PythonAlphaGenome APISuSiEFUSION/TWASGWAS
Nov 2025
deep learningvariant effect predictionTWASGWASatrial fibrillationgenomicsAlphaGenomefine-mapping

A hands-on journey through the complete LLM pipeline—tokenization, pretraining, distributed training, and fine-tuning—inspired by Andrej Karpathy's nanochat. Training a 561M parameter conversational model on 11.2B tokens to understand different aspects of modern language models.

Tech Stack:
PyTorchCUDADistributed TrainingBPE TokenizationTransformer Architecture
Oct 2025
llmdeep learningnlptransformerdistributed trainingself-supervised learningchatgpt

Evaluating 8 SSL methods with 3 GNN architectures on large-scale mouse embryo spatial transcriptomics data reveals interesting performance of reconstruction-based approaches

Tech Stack:
PyTorchPyTorch GeometricPythonSelf-Supervised LearningGraph Neural NetworksSpatial Transcriptomics
Sep 2025
deep learningself-supervised learningbioinformaticsspatial transcriptomicsrepresentation learningdevelopmental biology

A systematic evaluation of 8 SSL methods with 3 GNN architectures on mouse brain spatial transcriptomics data

Tech Stack:
PyTorchPyTorch GeometricPythonSelf-Supervised LearningGraph Neural NetworksSpatial Transcriptomics
Sep 2025
deep learningself-supervised learningbioinformaticsspatial transcriptomicsrepresentation learning
Research Documentation

An exploration of modern self-supervised learning methods including SimCLR, BYOL, SimSiam, Barlow Twins, DINO, etc, with mathematical foundations and mutual information theory

Tech Stack:
Machine LearningComputer VisionDeep LearningPyTorch
Jun 2025
self-supervised learningcontrastive learningrepresentation learningcomputer visiondeep learning

A comprehensive guide to understanding and applying GNNs to spatial transcriptomics data, from foundational concepts to cutting-edge research implementations

Tech Stack:
PyTorchPyTorch GeometricPythonGraph Neural NetworksSpatial Transcriptomics
Feb 2025
deep learningbioinformaticsgraph neural networksspatial transcriptomicscomputational biology
Full-stack Developer

A modern personal website with AI-powered content search and interactive knowledge graphs

Tech Stack:
Next.jsTypeScriptTailwind CSSSupabaseContentlayer
Jan 2025- Present
web developmentAIfull-stack