Lighting up protein design

Kudla, Grzegorz; Plech, Marcin

doi:10.7554/elife.79310

Cited by 2 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, machine learning approaches may be used to discover the protein fitness landscape. 143 New variants of desired protein can be created using preliminary experimental data with subsequent neural network training to predict the functionality of not discovered yet protein variants. 144 Using GFP, as a model, and machine learning-driven protein design, Gonzalez Somermeyer et al discovered that understanding the protein fitness landscape heterogeneity has clear practical application for protein engineering.…”

Section: Circular Permutation For Minigenes Designmentioning

confidence: 99%

“…Rational design or directed evolution is based on genetic manipulations and sequential in vitro screening of potential candidates with desired functions. Alternatively, machine learning approaches may be used to discover the protein fitness landscape 143 . New variants of desired protein can be created using preliminary experimental data with subsequent neural network training to predict the functionality of not discovered yet protein variants 144 .…”

Section: Circular Permutation For Minigenes Designmentioning

confidence: 99%

See 1 more Smart Citation

Optimization strategies and advances in the research and development of AAV‐based gene therapy to deliver large transgenes

Kolesnik,

Nurtdinov,

Oloruntimehin

et al. 2024

Clinical & Translational Med

View full text Add to dashboard Cite

Adeno‐associated virus (AAV)‐based therapies are recognized as one of the most potent next‐generation treatments for inherited and genetic diseases. However, several biological and technological aspects of AAV vectors remain a critical issue for their widespread clinical application. Among them, the limited capacity of the AAV genome significantly hinders the development of AAV‐based gene therapy. In this context, genetically modified transgenes compatible with AAV are opening up new opportunities for unlimited gene therapies for many genetic disorders. Recent advances in de novo protein design and remodelling are paving the way for new, more efficient and targeted gene therapeutics. Using computational and genetic tools, AAV expression cassette and transgenic DNA can be split, miniaturized, shuffled or created from scratch to mediate efficient gene transfer into targeted cells. In this review, we highlight recent advances in AAV‐based gene therapy with a focus on its use in translational research. We summarize recent research and development in gene therapy, with an emphasis on large transgenes (>4.8 kb) and optimizing strategies applied by biomedical companies in the research pipeline. We critically discuss the prospects for AAV‐based treatment and some emerging challenges. We anticipate that the continued development of novel computational tools will lead to rapid advances in basic gene therapy research and translational studies.

show abstract

Section: Circular Permutation For Minigenes Designmentioning

confidence: 99%

Section: Circular Permutation For Minigenes Designmentioning

confidence: 99%

Optimization strategies and advances in the research and development of AAV‐based gene therapy to deliver large transgenes

Kolesnik,

Nurtdinov,

Oloruntimehin

et al. 2024

Clinical & Translational Med

View full text Add to dashboard Cite

show abstract

“…The model was trained using data from single-site substitutions and low-order epistatic groups and was able to accurately predict epistatic variants exhibiting a high number of mutations . According to Kudla et al, the results suggest that prior knowledge of high-order interactions between all the mutations is not necessarily needed for protein design . A deeper analysis of the data is still needed to examine whether possible higher-order epistatic interactions are at play in these variants.…”

Section: Combinatorial Challenges In Enzyme Engineering and Computati...mentioning

confidence: 99%

“…122 According to Kudla et al, the results suggest that prior knowledge of highorder interactions between all the mutations is not necessarily needed for protein design. 123 A deeper analysis of the data is still needed to examine whether possible higher-order epistatic interactions are at play in these variants. Beck et al used a machine-learning model based on a high-throughput data set of the effects of mutations in the CPEB3 self-cleaving ribozyme to predict the activity of CPEB3 variants.…”

Section: Deep-learning Modelsmentioning

confidence: 99%

Learning Epistasis and Residue Coevolution Patterns: Current Trends and Future Perspectives for Advancing Enzyme Engineering

2022

View full text Add to dashboard Cite

Engineering proteins and enzymes with the desired functionality has broad applications in molecular biology, biotechnology, biomedical sciences, health, and medicine. The vastness of protein sequence space and all the possible proteins it represents can pose a considerable barrier for enzyme engineering campaigns through directed evolution and rational design. The nonlinear effects of coevolution between amino acids in protein sequences complicate this further. Data-driven models increasingly provide scientists with the computational tools to navigate through the largely undiscovered forest of protein variants and catch a glimpse of the rules and effects underlying the topology of sequence space. In this review, we outline a complete theoretical journey through the processes of protein engineering methods such as directed evolution and rational design and reflect on these strategies and data-driven hybrid strategies in the context of sequence space. We discuss crucial phenomena of residue coevolution, such as epistasis, and review the history of models created over the past decade, aiming to infer rules of protein evolution from data and use this knowledge to improve the prediction of the structure− function relationship of proteins. Data-driven models based on deep learning algorithms are among the most promising methods that can account for the nonlinear phenomena of sequence space to some degree. We also critically discuss the available models to predict evolutionary coupling and epistatic effects (classical and deep learning) in terms of their capabilities and limitations. Finally, we present our perspective on possible future directions for developing data-driven approaches and provide key orientation points and necessities for the future of the fast-evolving field of enzyme engineering.

show abstract

Lighting up protein design

Abstract: Using a neural network to predict how green fluorescent proteins respond to genetic mutations illuminates properties that could help design new proteins.

Cited by 2 publications

References 10 publications

Optimization strategies and advances in the research and development of AAV‐based gene therapy to deliver large transgenes

Optimization strategies and advances in the research and development of AAV‐based gene therapy to deliver large transgenes

Learning Epistasis and Residue Coevolution Patterns: Current Trends and Future Perspectives for Advancing Enzyme Engineering

Contact Info

Product

Resources

About