Deploying synthetic coevolution and machine learning to engineer protein-protein interactions

Science, Год журнала: 2023, Номер 381(6656)

Опубликована: Июль 27, 2023

Fine-tuning of protein-protein interactions occurs naturally through coevolution, but this process is difficult to recapitulate in the laboratory. We describe a platform for synthetic coevolution that can isolate matched pairs interacting muteins from complex libraries. This large dataset coevolved complexes drove systems-level analysis molecular recognition between Z domain–affibody spanning wide range structures, affinities, cross-reactivities, and orthogonalities, captured broad spectrum coevolutionary networks. Furthermore, we harnessed pretrained protein language models expand, silico, amino acid diversity our screen, predicting remodeled interfaces beyond reach experimental library. The integration these approaches provides means simulating generating with diverse properties biotechnology biology.

Язык: Английский

---

Advancing Antibody Engineering through Synthetic Evolution and Machine Learning

The Journal of Immunology, Год журнала: 2024, Номер 212(2), С. 235 - 243

Опубликована: Янв. 2, 2024

Abstract Abs are versatile molecules with the potential to achieve exceptional binding target Ags, while also possessing biophysical properties suitable for therapeutic drug development. Protein display and directed evolution systems have transformed synthetic Ab discovery, engineering, optimization, vastly expanding number of clones able be experimentally screened binding. Moreover, burgeoning integration high-throughput screening, deep sequencing, machine learning has further augmented in vitro promising accelerate design process massively expand sequence space interrogated. In this Brief Review, we discuss experimental computational tools employed engineering optimization. We explore challenges posed by developing infectious diseases, prospects leveraging learning–guided protein prospectively resistant viral escape.

Язык: Английский

---

Best practices for machine learning in antibody discovery and development

Drug Discovery Today, Год журнала: 2024, Номер 29(7), С. 104025 - 104025

Опубликована: Май 17, 2024

In the past 40 years, therapeutic antibody discovery and development have advanced considerably, with machine learning (ML) offering a promising way to speed up process by reducing costs number of experiments required. Recent progress in ML-guided design (D&D) has been hindered diversity data sets evaluation methods, which makes it difficult conduct comparisons assess utility. Establishing standards guidelines will be crucial for wider adoption ML advancement field. This perspective critically reviews current practices, highlights common pitfalls proposes method various ML-based techniques D&D. Addressing challenges across process, best practices are recommended each stage enhance reproducibility progress.

Язык: Английский

---

Yeast-based screening platforms to understand and improve human health

Trends in biotechnology, Год журнала: 2024, Номер 42(10), С. 1258 - 1272

Опубликована: Апрель 26, 2024

Язык: Английский

---

Addressing epistasis in the design of protein function

Proceedings of the National Academy of Sciences, Год журнала: 2024, Номер 121(34)

Опубликована: Авг. 12, 2024

Mutations in protein active sites can dramatically improve function. The site, however, is densely packed and extremely sensitive to mutations. Therefore, some mutations may only be tolerated combination with others a phenomenon known as epistasis. Epistasis reduces the likelihood of obtaining improved functional variants slows natural lab evolutionary processes. Research has shed light on molecular origins epistasis its role shaping trajectories outcomes. In addition, sequence- AI-based strategies that infer epistatic relationships from mutational patterns or experimental evolution data have been used design variants. recent years, combinations such approaches atomistic calculations successfully predicted highly combinatorial sites. These were thousands active-site variants, demonstrating that, while our understanding remains incomplete, determinants are critical for accurate now sufficiently understood. We conclude space explored by expanded enhance activities discover new ones. Furthermore, opens way systematically exploring sequence structure impacts function, deepening control over activity.

Язык: Английский

---

Reactive Oxygen Species Mechanisms That Regulate Protein-Protein Interactions in Cancer

Опубликована: Авг. 20, 2024

Reactive oxygen species (ROS) are produced during cellular metabolism and in response to environmental stress. While low levels of ROS play essential physiological roles, excess can damage components, leading cell death or transformation. also regulate protein interactions cancer cells, thereby affecting processes such as growth, migration, angiogenesis. Dysregulated occur via various mechanisms, including amino acid modifications, conformational changes, alterations complex stability. Understanding ROS-mediated changes is crucial for targeted therapies. In this review, we examine the role that mechanisms regulating pathways through protein-protein interactions.

Язык: Английский

---

Computational tools for plant genomics and breeding

Science China Life Sciences, Год журнала: 2024, Номер 67(8), С. 1579 - 1590

Опубликована: Апрель 23, 2024

Язык: Английский

---

Combining Directed Evolution with Machine Learning Enables Accurate Genotype-to-Phenotype Predictions

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2025, Номер unknown

Опубликована: Янв. 29, 2025

Abstract Linking sequence variation to phenotypic effects is critical for efficient exploitation of large genomic datasets. Here we present a novel approach combining directed evolution with protein language modeling characterize naturally-evolved variants rice immune receptor. Using high-throughput evolution, engineered the receptor Pik-1 bind and recognize fungal proteins Avr-PikC Avr-PikF, which evade detection by currently characterized alleles. A model was fine-tuned on this data correlate ligand binding behavior. This then used found in 3,000 Rice Genomes Project dataset. Two scored highly against Avr-PikC, vitro analyses confirmed their improved over wild-type Overall, machine learning identified promising sources disease resistance shows potential utility exploring other interest.

Язык: Английский

---

Evolutionary paths that link orthogonal pairs of binding proteins

Cell Systems, Год журнала: 2025, Номер unknown, С. 101262 - 101262

Опубликована: Апрель 1, 2025

Язык: Английский

---

Highly Efficient Display of Oligomeric Enzymes on Yeast Surface for Enhanced Glycyrrhizin Hydrolysis and Cellulosic Ethanol Production

ACS Synthetic Biology, Год журнала: 2025, Номер unknown

Опубликована: Апрель 15, 2025

The subunit dissociation of oligomeric enzymes is a major challenge that limits their practical applications. In this study, yeast-surface-displayed tetrameric β-glucuronidase with C-terminal anchor protein fusion was found partially dissociated into dimers. coexpression free and anchored subunits significantly improved the display efficiency catalytic activity. Given may adopt non-native conformation on cell surface, interfaces surface-displayed were in situ characterized using Förster resonance energy transfer (FRET) strategy, structure well maintained coexpressed β-glucuronidases. Finally, strategy applied to cellulases, enhancing activities endoglucanase dimeric β-glucosidase concentration cellulosic ethanol for two-enzyme codisplaying strain. This work provides insights structure-activity relationship efficient utilization enzymes.

Язык: Английский

---