Integrating Protein Language Model and Molecular Dynamics Simulations to Discover Antibiofouling Peptides DOI
Ibrahim A. Imam, Sean Bailey, Duolin Wang

et al.

Langmuir, Journal Year: 2024, Volume and Issue: 41(1), P. 811 - 821

Published: Dec. 30, 2024

Antibiofouling peptide materials prevent the nonspecific adsorption of proteins on devices, enabling them to perform their designed functions as desired in complex biological environments. Due importance, research antibiofouling has been one central subjects interfacial engineering. However, only a few sequences have developed. This narrow scope limits capacity adapt broad spectrum application scenarios. To address this issue, we searched for peptides vast sequence pool microbiome library using combination deep learning-based high-throughput search and molecular dynamics (MD) simulations. A random forest-based model with an ensemble ten independent classifiers was Each classifier trained by prompt-tuning foundational protein language Evolution Scaling Modeling version 2 (ESM2) distinct training data set. We constructed databases containing same amount biofouling attenuate bias existing databases. MD simulations were conducted investigate properties six selected candidates interactions lysozyme protein. Two known peptides, (glutamic acid (E)-lysine (K))15 (EK-proline (P))10, fouling peptide, (glycine)30, used reference. The simulation results indicate that five present potential resist biofouling. Our implies learning can be integrated discover functional applications.

Language: Английский

Active learning-assisted directed evolution DOI Creative Commons
Jason Yang, Ravi Lal,

James C. Bowden

et al.

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

Published: Jan. 16, 2025

Abstract Directed evolution (DE) is a powerful tool to optimize protein fitness for specific application. However, DE can be inefficient when mutations exhibit non-additive, or epistatic, behavior. Here, we present Active Learning-assisted Evolution (ALDE), an iterative machine learning-assisted workflow that leverages uncertainty quantification explore the search space of proteins more efficiently than current methods. We apply ALDE engineering landscape challenging DE: optimization five epistatic residues in active site enzyme. In three rounds wet-lab experimentation, improve yield desired product non-native cyclopropanation reaction from 12% 93%. also perform computational simulations on existing sequence-fitness datasets support our argument effective DE. Overall, practical and broadly applicable strategy unlock improved outcomes.

Language: Английский

Citations

8
Biophysics-based protein language models for protein engineering DOI Creative Commons
Sam Gelman,

Bryce Johnson,

Chase R. Freschlin

et al.

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

Published: March 17, 2024

Protein language models trained on evolutionary data have emerged as powerful tools for predictive problems involving protein sequence, structure, and function. However, these overlook decades of research into biophysical factors governing We propose Mutational Effect Transfer Learning (METL), a model framework that unites advanced machine learning modeling. Using the METL framework, we pretrain transformer-based neural networks simulation to capture fundamental relationships between energetics. finetune experimental sequence-function harness signals apply them when predicting properties like thermostability, catalytic activity, fluorescence. excels in challenging engineering tasks generalizing from small training sets position extrapolation, although existing methods train remain many types assays. demonstrate METL's ability design functional green fluorescent variants only 64 examples, showcasing potential biophysics-based engineering.

Language: Английский

Citations

11
Foundation models in bioinformatics DOI Creative Commons
Fei Guo, Renchu Guan, Yaohang Li

et al.

National Science Review, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 25, 2025

With the adoption of foundation models (FMs), artificial intelligence (AI) has become increasingly significant in bioinformatics and successfully addressed many historical challenges, such as pre-training frameworks, model evaluation interpretability. FMs demonstrate notable proficiency managing large-scale, unlabeled datasets, because experimental procedures are costly labor intensive. In various downstream tasks, have consistently achieved noteworthy results, demonstrating high levels accuracy representing biological entities. A new era computational biology been ushered by application FMs, focusing on both general specific issues. this review, we introduce recent advancements employed a variety including genomics, transcriptomics, proteomics, drug discovery single-cell analysis. Our aim is to assist scientists selecting appropriate bioinformatics, according four types: language vision graph multimodal FMs. addition understanding molecular landscapes, AI technology can establish theoretical practical for continued innovation biology.

Language: Английский

Citations

1
FASTIA: A rapid and accessible platform for protein variant interaction analysis demonstrated with a single‐domain antibody DOI Creative Commons
Ryo Matsunaga, Kouhei Tsumoto

Protein Science, Journal Year: 2025, Volume and Issue: 34(3)

Published: Feb. 21, 2025

Abstract Antibodies are critical tools in medicine and research, their affinity for target antigens is a key determinant of efficacy. Traditional antibody maturation interaction analyses often hampered by time‐consuming steps such as cloning, expression, purification, assays. To address this, we have developed FASTIA (Fast Affinity Screening Technology Interaction Analysis), novel platform that integrates rapid gene fragment preparation, cell‐free protein synthesis, bio‐layer interferometry with non‐regenerative analysis. Using this approach, can analyze the intermolecular interactions over 20 variants 2 days, requiring only parent expression plasmid basic equipment. We demonstrated ability to discriminate between single‐domain different binding affinities using anti‐HEL VHH D2‐L29, mapped results crystal structure identify sites. provides comparable those obtained traditional methods. Our system bypasses need genetic engineering facilities be easily adopted laboratories, accelerating optimization processes. In addition, applicable other protein–protein interactions, making it versatile tool studying molecular recognition. facilitates efficient maturation, engineering, analysis interactions. This accessible route improving antibodies broader understanding

Language: Английский

Citations

1
Engineering nitrogen and carbon fixation for next-generation plants DOI
Zhengang Zhao, Alisdair R. Fernie, Youjun Zhang

et al.

Current Opinion in Plant Biology, Journal Year: 2025, Volume and Issue: 85, P. 102699 - 102699

Published: March 8, 2025

Language: Английский

Citations

1
Mechanism and engineering of endoplasmic reticulum-localized membrane protein folding in Saccharomyces cerevisiae DOI

Yuhuan Luo,

Jian‐Jiang Zhong, Han Xiao

et al.

Metabolic Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

Citations

1
Engineering highly active nuclease enzymes with machine learning and high-throughput screening DOI Creative Commons
Neil Thomas, David Belanger, Chenling Xu

et al.

Cell Systems, Journal Year: 2025, Volume and Issue: 16(3), P. 101236 - 101236

Published: March 1, 2025

Highlights•TeleProt is a method for combining evolutionary and assay data to design novel proteins•TeleProt achieved an improved hit rate diversity compared with directed evolution•TeleProt discovered nuclease enzyme 11-fold-improved specific activity•Zero-shot showed higher relative error-prone PCRSummaryOptimizing enzymes function in chemical environments central goal of synthetic biology, but optimization often hindered by rugged fitness landscape costly experiments. In this work, we present TeleProt, machine learning (ML) framework that blends experimental diverse protein libraries, employ it improve the catalytic activity degrades biofilms accumulate on chronic wounds. After multiple rounds high-throughput experiments, TeleProt found significantly better top-performing than evolution (DE), had at finding diverse, high-activity variants, was even able high-performance initial library using no prior data. We have released dataset 55,000 one most extensive genotype-phenotype landscapes date, drive further progress ML-guided design. A record paper's transparent peer review process included supplemental information.Graphical abstract

Language: Английский

Citations

1
Promising Strategies for Accelerating the Eradication of Avian Leukosis in China DOI Creative Commons
Tuofan Li, Jingwen Li, Zeming Wang

et al.

Animals and zoonoses., Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

Citations

1
Molecular connectomics reveals a glucagon-like peptide 1-sensitive neural circuit for satiety DOI

Addison N. Webster,

Jordan J. Becker,

Chia Li

et al.

Nature Metabolism, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 3, 2024

Language: Английский

Citations

7
Advances in designed bionanomolecular assemblies for biotechnological and biomedical applications DOI Creative Commons
Jaka Snoj, Weijun Zhou, Ajasja Ljubetič

et al.

Current Opinion in Biotechnology, Journal Year: 2025, Volume and Issue: 92, P. 103256 - 103256

Published: Jan. 18, 2025

Recent advances in protein engineering have revolutionized the design of bionanomolecular assemblies for functional therapeutic and biotechnological applications. This review highlights progress creating complex architectures, encompassing both finite extended assemblies. AI tools, including AlphaFold, RFDiffusion, ProteinMPNN, significantly enhanced scalability success de novo designs. Finite assemblies, like nanocages coiled-coil-based structures, enable precise molecular encapsulation or domain presentation. Extended filaments 2D/3D lattices, offer unparalleled structural versatility applications such as vaccine development, responsive biomaterials, engineered cellular scaffolds. The convergence artificial intelligence-driven experimental validation promises strong acceleration development tailored offering new opportunities synthetic biology, materials science, biotechnology, biomedicine.

Language: Английский

Citations

0