SelectSmart: Autonomous Gene Panel Design

Oct 1, 2025

Training Overview

SelectSmart gene panel optimization results

SelectSmart is a reinforcement-learning framework for gene panel selection in single-cell transcriptomics.
This project was developed as part of coursework with Prof. Mykel Kochenderfer
(AA228 / CS238 – Decision Making under Uncertainty) and extended through research assistantship work with Prof. Xiaojie Qiu
(Qiu Lab, Stanford).

The method combines meta-voted candidate genes, an actor–critic architecture, and a reward balancing clustering fidelity (ARI) with panel-size regularization.

Trained on a 30k-cell kidney dataset and evaluated on an independent CZ Kidney dataset, SelectSmart produces a 500-gene panel that preserves transcriptomic geometry and outperforms classical gene panel selection methods.

Status: 🧪 Active development

Report

📄 Download the technical report (PDF)

Reinforcement Learning Single-Cell Computational Biology Clustering Deep Learning LLMs
Erwin POUSSI
Erwin POUSSI
Aeronautics & Astronautics @ Stanford | Research Assistant (MSL & Qiu Lab)

Graduate student in Aeronautics & Astronautics at Stanford, working on robot learning and autonomous systems, with a focus on sim-to-real transfer and learned control policies.