PhaseXplorer Creates High-Dimensional Phase Diagrams with Closed-Loop Active Learning

TL;DR

PhaseXplorer is a new platform that uses microfluidics and machine learning to create detailed phase diagrams much faster and with less material than traditional methods.

Contribution

PhaseXplorer introduces a closed-loop active learning system for high-dimensional phase diagram creation with minimal sampling and real-time analysis.

Findings

PhaseXplorer creates four-dimensional phase diagrams 100 times faster than traditional methods.

The system uses less than 1/10,000th the material required by conventional approaches.

A convolutional neural network identifies phase separation in droplets in under 1 ms.

Abstract

Phase separation fundamentally governs material properties
and
cellular function on multiple organizational scales. Conventional
approaches to studying this nonlinear phenomenon necessitate resource-intensive
experiments. As such, investigations were limited to low-dimensional
space. We present PhaseXplorer, a platform that combines microfluidics,
microscopy, and machine learning to efficiently study phase separation
systems. PhaseXplorer autonomously designs, generates, and analyzes
samples in a closed-loop active learning workflow until an accurate
phase diagram is obtained. Using an acquisition function that balances
exploration and exploitation, all the phase boundaries are located
with minimal sampling. A convolutional neural network executes real-time
image recognition to identify microfluidic droplets and phase separation
within them in less than 1 ms per droplet. PhaseXplorer standardizes
analysis across experiments and does not require calibration nor extensive
postexperiment analysis. We demonstrate PhaseXplorer’s capabilities
using a poly rA model system by creating a four-dimensional phase
diagram 100 times faster than traditional methods while simultaneously
consuming 10,000 times less material.

Figures