San Francisco, California, United States
Current research focus: Bioelectricity and bioelectrical patterns in cells, their role in encoding cellular goals, tissue regeneration (regenerative medicine), and memory storage. Working on Generative ML models for science discovery. Interests/experience: Bio-computing, Generative AI, ML for science and neuromorphic systems for brain implants.
• Built end-to-end electrotaxis pipeline: Cellpose segmentation → trackpy tracking → optical flow, extracting trajectory features (directedness, displacement, velocity) under electric-field stimulation • Developing ML models to predict cell migration dynamics from time-lapse microscopy data
• Contributed to an IP-sensitive bioengineering capstone focused on engineered experimental systems for functional cell studies • Co-developed custom experimental workflows spanning device prototyping, biological preparation, assay design, microscopy acquisition, and data analysis • Built multimodal microscopy analysis pipelines for segmentation, motion quantification, fluorescence signal extraction, and quality control across brightfield and fluorescence datasets
• Developed computational model of bioelectric state transitions (healthy glia → glioblastoma) using membrane voltage (Vmem), gap-junction coupling (Cx43), and metabolic parameters with Hodgkin Huxley dynamics • Developed evolutionary search framework (ASAL-inspired) to identify intervention regimes that restore bioelectric gradients and normalize spatial pattern formation
• Developing software for detecting Alzheimer's and Parkinson's diseases using EEG brain datasets (data analytics, applying statistics and machine learning techniques Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN)). • EEG signal processing, including artifact removal, to support software enhancement and development. Training Large Language Models (LLMs) for medical user interface applications. • Research on energy transfer methods for brain implants, focusing on charging techniques and optimizing implant longevity/battery performance. • Research on biocompatibility of brain implants, including the use of carbon nanotubes for biocompatibility and stability in neuromorphic computing systems in implants. • Research and development in electrical engineering and design for brain implants, with a focus on optimizing implant performance and integration with neuromorphic computing architectures. • In-depth research on neuromorphic algorithms (including FPGA, electronics), specifically in the context of brain implant chips and the Brain Code Unit (BCU).
• Built CV pipeline aligning electron microscopy, light microscopy, and calcium imaging data for zebrafish olfactory circuit reconstruction • Implemented FFN-like deep learning for automated axon/dendrite segmentation from volumetric imaging data