Applications of cell free protein synthesis in protein design DOI Creative Commons
Ella Lucille Thornton,

Sarah Maria Paterson,

Michael J. Stam

et al.

Protein Science, Journal Year: 2024, Volume and Issue: 33(9)

Published: Aug. 24, 2024

Abstract In protein design, the ultimate test of success is that designs function as desired. Here, we discuss utility cell free synthesis (CFPS) a rapid, convenient and versatile method to screen for activity. We champion use CFPS in screening potential designs. Compared vivo screening, wider range different activities can be evaluated using CFPS, scale on which it easily used—screening tens hundreds designed proteins—is ideally suited current needs. Protein design physics‐based strategies tended have relatively low rate, compared with machine‐learning based methods. Screening steps (such yeast display) were often used identify proteins displayed desired activity from many highly ranked computationally. also describe how well‐suited reasons fail, may include problems transcription, translation, solubility, addition not achieving structure function.

Language: Английский

Machine learning for functional protein design DOI
Pascal Notin, Nathan Rollins, Yarin Gal

et al.

Nature Biotechnology, Journal Year: 2024, Volume and Issue: 42(2), P. 216 - 228

Published: Feb. 1, 2024

Language: Английский

Citations

94

Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering DOI Creative Commons
Jason Yang, Francesca-Zhoufan Li, Frances H. Arnold

et al.

ACS Central Science, Journal Year: 2024, Volume and Issue: 10(2), P. 226 - 241

Published: Feb. 5, 2024

Enzymes can be engineered at the level of their amino acid sequences to optimize key properties such as expression, stability, substrate range, and catalytic efficiency-or even unlock new activities not found in nature. Because search space possible proteins is vast, enzyme engineering usually involves discovering an starting point that has some desired activity followed by directed evolution improve its "fitness" for a application. Recently, machine learning (ML) emerged powerful tool complement this empirical process. ML models contribute (1) discovery functional annotation known protein or generating novel with functions (2) navigating fitness landscapes optimization mappings between associated values. In Outlook, we explain how complements discuss future potential improved outcomes.

Language: Английский

Citations

76

Unsupervised evolution of protein and antibody complexes with a structure-informed language model DOI
Varun R. Shanker, Theodora U. J. Bruun, Brian Hie

et al.

Science, Journal Year: 2024, Volume and Issue: 385(6704), P. 46 - 53

Published: July 4, 2024

Large language models trained on sequence information alone can learn high-level principles of protein design. However, beyond sequence, the three-dimensional structures proteins determine their specific function, activity, and evolvability. Here, we show that a general model augmented with structure backbone coordinates guide evolution for diverse without need to individual functional tasks. We also demonstrate ESM-IF1, which was only single-chain structures, be extended engineer complexes. Using this approach, screened about 30 variants two therapeutic clinical antibodies used treat severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. achieved up 25-fold improvement in neutralization 37-fold affinity against antibody-escaped viral concern BQ.1.1 XBB.1.5, respectively. These findings highlight advantage integrating structural identify efficient trajectories requiring any task-specific training data.

Language: Английский

Citations

35

Sparks of function by de novo protein design DOI
Alexander E. Chu, Tianyu Lu, Po‐Ssu Huang

et al.

Nature Biotechnology, Journal Year: 2024, Volume and Issue: 42(2), P. 203 - 215

Published: Feb. 1, 2024

Language: Английский

Citations

33

Noncanonical Amino Acids in Biocatalysis DOI Creative Commons
Zachary Birch-Price, Florence J. Hardy,

Thomas M. Lister

et al.

Chemical Reviews, Journal Year: 2024, Volume and Issue: 124(14), P. 8740 - 8786

Published: July 3, 2024

In recent years, powerful genetic code reprogramming methods have emerged that allow new functional components to be embedded into proteins as noncanonical amino acid (ncAA) side chains. this review, we will illustrate how the availability of an expanded set building blocks has opened a wealth opportunities in enzymology and biocatalysis research. Genetic provided insights enzyme mechanisms by allowing introduction spectroscopic probes targeted replacement individual atoms or groups. NcAAs also been used develop engineered biocatalysts with improved activity, selectivity, stability, well enzymes artificial regulatory elements are responsive external stimuli. Perhaps most ambitiously, combination laboratory evolution given rise classes use ncAAs key catalytic elements. With framework for developing ncAA-containing now firmly established, optimistic become progressively more tool armory designers engineers coming years.

Language: Английский

Citations

23

DPFunc: accurately predicting protein function via deep learning with domain-guided structure information DOI Creative Commons
Wenkang Wang,

Yunyan Shuai,

Min Zeng

et al.

Nature Communications, Journal Year: 2025, Volume and Issue: 16(1)

Published: Jan. 2, 2025

Computational methods for predicting protein function are of great significance in understanding biological mechanisms and treating complex diseases. However, existing computational approaches prediction lack interpretability, making it difficult to understand the relations between structures functions. In this study, we propose a deep learning-based solution, named DPFunc, accurate with domain-guided structure information. DPFunc can detect significant regions accurately predict corresponding functions under guidance domain It outperforms current state-of-the-art achieves improvement over structure-based methods. Detailed analyses demonstrate that information contributes prediction, enabling our method key residues or structures, which closely related their summary, serves as an effective tool large-scale pushes border systems. deep-learning-based tool, uses structures. prediction.

Language: Английский

Citations

2

Engineering of highly active and diverse nuclease enzymes by combining machine learning and ultra-high-throughput screening DOI Creative Commons
Neil Thomas, David Belanger, Chenling Xu

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: March 24, 2024

Abstract Optimizing enzymes to function in novel chemical environments is a central goal of synthetic biology, but optimization often hindered by rugged, expansive protein search space and costly experiments. In this work, we present TeleProt, an ML framework that blends evolutionary experimental data design diverse variant libraries, employ it improve the catalytic activity nuclease enzyme degrades biofilms accumulate on chronic wounds. After multiple rounds high-throughput experiments using both TeleProt standard directed evolution (DE) approaches parallel, find our approach found significantly better top-performing than DE, had hit rate at finding diverse, high-activity variants, was even able high-performance initial library no prior data. We have released dataset 55K one most extensive genotype-phenotype landscapes date, drive further progress ML-guided design.

Language: Английский

Citations

13

A Top-Down Design Approach for Generating a Peptide PROTAC Drug Targeting Androgen Receptor for Androgenetic Alopecia Therapy DOI
Bohan Ma,

Donghua Liu,

Zhe Wang

et al.

Journal of Medicinal Chemistry, Journal Year: 2024, Volume and Issue: 67(12), P. 10336 - 10349

Published: June 5, 2024

While large-scale artificial intelligence (AI) models for protein structure prediction and design are advancing rapidly, the translation of deep learning practical macromolecular drug development remains limited. This investigation aims to bridge this gap by combining cutting-edge methodologies create a novel peptide-based PROTAC paradigm. Using ProteinMPNN RFdiffusion, we identified binding peptides androgen receptor (AR) Von Hippel-Lindau (VHL), followed computational modeling with Alphafold2-multimer ZDOCK predict spatial interrelationships. Experimental validation confirmed designed peptide's ability AR VHL. Transdermal microneedle patching technology was seamlessly integrated peptide delivery in androgenic alopecia treatment. In summary, our approach provides generic method generating PROTACs offers application designing potential therapeutic drugs androgenetic alopecia. showcases interdisciplinary approaches personalized medicine.

Language: Английский

Citations

10

Simultaneous enhancement of multiple functional properties using evolution-informed protein design DOI Creative Commons
Benjamin Fram, Yang Su,

Ian Truebridge

et al.

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: June 20, 2024

Abstract A major challenge in protein design is to augment existing functional proteins with multiple property enhancements. Altering several properties likely necessitates numerous primary sequence changes, and novel methods are needed accurately predict combinations of mutations that maintain or enhance function. Models co-variation (e.g., EVcouplings), which leverage extensive information about various activities from homologous sequences, have proven effective for many applications including structure determination mutation effect prediction. We apply EVcouplings computationally variants the model TEM-1 β -lactamase. Nearly all 14 experimentally characterized designs were functional, one 84 nearest natural homolog. The also had large increases thermostability, increased activity on substrates, nearly identical wild type enzyme. This study highlights efficacy evolutionary models guiding alterations generate diversity applications.

Language: Английский

Citations

10

Responsible AI in biotechnology: balancing discovery, innovation and biosecurity risks DOI Creative Commons
Nicole E. Wheeler

Frontiers in Bioengineering and Biotechnology, Journal Year: 2025, Volume and Issue: 13

Published: Feb. 5, 2025

The integration of artificial intelligence (AI) in protein design presents unparalleled opportunities for innovation bioengineering and biotechnology. However, it also raises significant biosecurity concerns. This review examines the changing landscape bioweapon risks, dual-use potential AI-driven tools, necessary safeguards to prevent misuse while fostering innovation. It highlights emerging policy frameworks, technical safeguards, community responses aimed at mitigating risks enabling responsible development application AI design.

Language: Английский

Citations

1