Computational biology, AI, oncology, wearables, writing

Computational biology, AI systems, and writing.

Hanson Wen is a Molecular and Cell Biology + Computer Science student at UC Berkeley building across computational biology, AI systems, oncology, wearable technology, and writing.

Current work spans research, side projects, and writing: multimodal biology, wearable sensing, evaluation for agent systems, and hacker-built prototypes that make technical questions tangible sooner.

  • Incoming Computational Biology Intern at Regeneron
  • Student Researcher at UC Berkeley Sky Computing Lab
  • Student Researcher at Berkeley RDI
  • Writer behind The Quixotic Method

Three active threads

A simple way to browse the work.

This page is a short overview. More detail lives on the projects, writing, about, and resume pages.

Oncology

Multimodal patient models

Work on systems that combine histopathology, transcriptomics, EHR context, and model infrastructure in a form clinicians can inspect.

Agents

Scientific tooling and agent evaluation

Research on agent benchmarks, biological workflows, and the interface choices that make a system more reliable in practice.

Writing

Writing as part of the process

Essays and notes that help explain how I am thinking about the technical work and the questions around it.

Wearables

Hacker-built interfaces and sensing

An interest in wearable technology and fast experimental builds that make biology, behavior, and decision-making easier to inspect in the real world.

Selected projects

Selected projects and experiments.

Pathology AI

Enso Atlas

2026

A fully local pathology AI system for treatment-response prediction, evidence retrieval, and reporting on whole-slide images.

Top 10 in Google MedGemma Impact Challenge

Clinical trials

TrialScope AI

2025

An agentic workflow for extracting decision-useful insight from clinical trial protocols and trial documents.

CalHacks 12.0 Regeneron Track Winner

Personal bioinformatics

Personal Genome Analysis

2025

Processed 131GB of whole-genome sequencing data, identified 4.99 million variants, and built a full pipeline for ancestry and pharmacogenomics analysis.

Full-stack genome pipeline

Agent evaluation

AgentHLE

2026

Humanity's Last Exam for computer-use agents, spanning 63 high-GDP domains and a much tougher standard for useful agent performance.

Benchmark design at Berkeley RDI

Photography

Another practice in attention.

Photography is where I practice composition, patience, and noticing details outside the usual research loop.

Writing

Writing alongside the technical work.

Essays and notes that add context to the projects and research.

The Quixotic Method

Between the windmill and the brick.

Essays on AI, computational biology, philosophy, and the practical questions around building things that might last.

Resume summary

A concise summary.

Current experience, education, projects, and awards pulled from the resume.

  • Regeneron Pharmaceuticals — Incoming Computational Biology Intern
  • UC Berkeley Sky Computing Lab — Student Researcher
  • Berkeley RDI — Student Researcher
  • Stealth Biotech — Co-founder