Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Self-driving laboratories to autonomously navigate the protein fitness landscape

Journal Article · · Nature Chemical Engineering
Abstract

Protein engineering has nearly limitless applications across chemistry, energy and medicine, but creating new proteins with improved or novel functions remains slow, labor-intensive and inefficient. Here we present the Self-driving Autonomous Machines for Protein Landscape Exploration (SAMPLE) platform for fully autonomous protein engineering. SAMPLE is driven by an intelligent agent that learns protein sequence–function relationships, designs new proteins and sends designs to a fully automated robotic system that experimentally tests the designed proteins and provides feedback to improve the agent’s understanding of the system. We deploy four SAMPLE agents with the goal of engineering glycoside hydrolase enzymes with enhanced thermal tolerance. Despite showing individual differences in their search behavior, all four agents quickly converge on thermostable enzymes. Self-driving laboratories automate and accelerate the scientific discovery process and hold great potential for the fields of protein engineering and synthetic biology.

Sponsoring Organization:
USDOE
Grant/Contract Number:
SC0018409
OSTI ID:
2281045
Journal Information:
Nature Chemical Engineering, Journal Name: Nature Chemical Engineering Journal Issue: 1 Vol. 1; ISSN 2948-1198
Publisher:
Nature Publishing GroupCopyright Statement
Country of Publication:
United States
Language:
English

References (36)

Beyond Ternary OPV: High‐Throughput Experimentation and Self‐Driving Laboratories Optimize Multicomponent Systems journal April 2020
Minding the gaps: The importance of navigating holes in protein fitness landscapes journal November 2021
Perspectives for self-driving labs in synthetic biology journal February 2023
Adaptive machine learning for protein engineering journal February 2022
The Rosetta All-Atom Energy Function for Macromolecular Modeling and Design journal May 2017
Discovering New Chemistry with an Autonomous Robotic Platform Driven by a Reactivity-Seeking Neural Network journal November 2021
Opportunities at the Intersection of Synthetic Biology, Machine Learning, and Automation journal July 2019
Cloud labs: where robots do the research journal June 2022
Functional genomic hypothesis generation and experimentation by a robot scientist journal January 2004
A diverse family of thermostable cytochrome P450s created by recombination of stabilizing fragments journal August 2007
Exploring protein fitness landscapes by directed evolution journal December 2009
Towards a fully automated algorithm driven platform for biosystems design journal November 2019
Machine learning-guided acyl-ACP reductase engineering for improved in vivo fatty alcohol production journal October 2021
AlphaFlow: autonomous discovery and optimization of multi-step chemistry using a self-driven fluidic lab guided by reinforcement learning journal March 2023
A mobile robotic chemist journal July 2020
Deep diversification of an AAV capsid protein by machine learning journal February 2021
Machine learning-guided channelrhodopsin engineering enables minimally invasive optogenetics journal October 2019
An automated Design-Build-Test-Learn pipeline for enhanced microbial production of fine chemicals journal June 2018
The rise of self-driving labs in chemical and materials sciences journal January 2023
A self-driving laboratory designed to accelerate the discovery of adhesive materials journal January 2022
Navigating the protein fitness landscape with Gaussian processes journal December 2012
Dissecting enzyme function with microfluidic-based deep mutational scanning journal May 2015
Closed-loop cycles of experiment design, execution, and learning accelerate systems biology model development in yeast journal August 2019
nhmmer: DNA homology search with profile HMMs journal July 2013
Site-directed protein recombination as a shortest-path problem journal August 2004
Consensus protein design journal June 2016
Taking the Human Out of the Loop: A Review of Bayesian Optimization journal January 2016
A beta-glucosidase gene (bgl3) from Streptomyces sp. strain QM-B814. Molecular cloning, nucleotide sequence, purification and characterization of the encoded enzyme, a new member of family 1 glycosyl hydrolases journal July 1994
Self-driving laboratory for accelerated discovery of thin-film materials journal May 2020
The Automation of Science journal April 2009
Robust deep learning–based protein sequence design using ProteinMPNN journal October 2022
Combinatorial assembly and design of enzymes journal January 2023
Structure-Guided Recombination Creates an Artificial Family of Cytochromes P450 journal April 2006
A One Pot, One Step, Precision Cloning Method with High Throughput Capability journal November 2008
Thermal stability and kinetic constants for 129 variants of a family 1 glycoside hydrolase reveal that enzyme activity and stability can be separately designed journal May 2017
Levels of autonomy in synthetic biology engineering journal December 2020

Similar Records

A generalized platform for artificial intelligence-powered autonomous enzyme engineering
Journal Article · Mon Jun 30 20:00:00 EDT 2025 · Nature Communications · OSTI ID:2574786

Engineering PHL7 for Improved Poly(Ethylene Terephthalate) Depolymerization via Rational Design and Directed Evolution
Journal Article · Mon May 26 00:00:00 EDT 2025 · Chem Catalysis · OSTI ID:2574707

Related Subjects