Assessing and enhancing foldability in designed proteins

Listov, Dina; Lipsh‐Sokolik, Rosalie; Rosset, Stéphane; Yang, Che; Correia, Bruno E.; Fleishman, Sarel J.

doi:10.1002/pro.4400

Cited by 13 publications

(12 citation statements)

References 57 publications

(139 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When inspecting the per residue pLDDT of protein G and ubiquitin-like fold designs, we found regions of the designs with low confidence (ubiquitin) or noticeable lower on the unfolded designs compared to the folded ones (protein G, Figure 5d ). This observation is consistent with the findings reported by Listov et al, where per residue pLDDT scores were also utilized as an indicator of problematic areas in designed proteins (Listov et al, 2022). In conclusion, we obtained eight soluble and well-folded proteins out of 39 designs.…”

Section: Resultssupporting

confidence: 92%

De novo protein design by inversion of the AlphaFold structure prediction network

Goverde

Wolf

Khakzad

et al. 2022

Preprint

View full text Add to dashboard Cite

De novo protein design enhances our understanding of the principles that govern protein folding and interactions, and has the potential to revolutionize biotechnology through the engineering of novel protein functionalities. Despite recent progress in computational design strategies, de novo design of protein structures remains challenging, given the vast size of the sequence-structure space. AlphaFold2 (AF2), a state-of-the-art neural network architecture, achieved remarkable accuracy in predicting protein structures from amino acid sequences. This raises the question whether AF2 has learned the principles of protein folding sufficiently for de novo design. Here, we sought to answer this question by inverting the AF2 network, using the prediction weight set and a loss function to bias the generated sequences to adopt a target fold. Initial design trials resulted in de novo designs with an overrepresentation of hydrophobic residues on the protein surface compared to their natural protein family, requiring additional surface optimization. In silico validation of the designs showed protein structures with the correct fold, a hydrophilic surface and a densely packed hydrophobic core. In vitro validation showed that several designs were folded and stable in solution with high melting temperatures. In summary, our design workflow solely based on AF2 does not seem to fully capture basic principles of de novo protein design, as observed in the protein surface's hydrophobic vs. hydrophilic patterning. However, with minimal post-design intervention, these pipelines generated viable sequences as assessed experimental characterization. Thus such pipelines show the potential to contribute to solving outstanding challenges in de novo protein design.

show abstract

Section: Resultssupporting

confidence: 92%

De novo protein design by inversion of the AlphaFold structure prediction network

Goverde

Wolf

Khakzad

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…When inspecting the per residue pLDDT of protein G and ubiquitin-like fold designs, we found regions of the designs with low confidence (ubiquitin) or noticeable lower on the unfolded designs compared to the folded ones (protein G, Figure 5d). This observation is consistent with the findings reported by Listov et al, where per residue pLDDT scores were also utilized as an indicator of problematic areas in designed proteins (Listov et al 2022). In conclusion, we obtained seven soluble and well-folded proteins out of 39 designs.…”

Section: In Vitro Characterization Of Designed Sequencessupporting

confidence: 93%

De novo protein design by inversion of the AlphaFold structure prediction network

et al. 2023

Self Cite

View full text Add to dashboard Cite

De novo protein design enhances our understanding of the principles that govern protein folding and interactions, and has the potential to revolutionize biotechnology through the engineering of novel protein functionalities. Despite recent progress in computational design strategies, de novo design of protein structures remains challenging, given the vast size of the sequence-structure space. AlphaFold2 (AF2), a state-of-the-art neural network architecture, achieved remarkable accuracy in predicting protein structures from amino acid sequences. This raises the question whether AF2 has learned the principles of protein folding sufficiently for de novo design. Here, we sought to answer this question by inverting the AF2 network, using the prediction weight set and a loss function to bias the generated sequences to adopt a target fold. Initial design trials resulted in de novo designs with an overrepresentation of hydrophobic residues on the protein surface compared to their natural protein family, requiring additional surface optimization. In silico validation of the designs showed protein structures with the correct fold, a hydrophilic surface and a densely packed hydrophobic core. In vitro validation showed that 7 out of 39 designs were folded and stable in solution with high melting temperatures. In summary, our design workflow solely based on AF2 does not seem to fully capture basic principles of de novo protein design, as observed in the protein surface's hydrophobic vs. hydrophilic patterning. However, with minimal post-design intervention, these pipelines generated viable sequences as assessed experimental characterization. Thus, such pipelines show the potential to contribute to solving outstanding challenges in de novo protein design.

show abstract

“…We used pSUFER( 68 ) to detect poorly designed positions, flagging positions with more than four alternative amino acids with ΔΔ G < 0, located outside the active site. Those positions were designed by FuncLib ( 31 ), using mutations with PSSM > −2 and ΔΔ G < 6 R.e.u.…”

Section: Methodsmentioning

confidence: 99%

Combinatorial assembly and design of enzymes

Lipsh‐Sokolik

Khersonsky

Schröder

et al. 2022

Preprint

View full text Add to dashboard Cite

Functional diversity in enzymes often requires significant backbone changes, but even subtle mutations in an enzyme may negatively impact its activity. We introduce CADENZ, an atomistic and machine-learning strategy to design modular enzyme fragments that combine all-against-all to generate diverse, low-energy structures with stable catalytic constellations. Applied to endoxylanases, CADENZ designed nearly a million unique proteins, and activity-based protein profiling with an endoxylanase-specific probe rapidly recovered 3,114 active enzymes that adopt 756 distinct backbones. Functional designs exhibit higher active-site preorganization than nonfunctional ones and more stable and compact packing outside the active site. Implementing these lessons into CADENZ led to a tenfold improved hit rate. This design-test-learn loop can be applied, in principle, to any modular enzyme or binding protein family, yielding huge diversity and general lessons on protein design principles.

show abstract

Assessing and enhancing foldability in designed proteins

Cited by 13 publications

References 57 publications

De novo protein design by inversion of the AlphaFold structure prediction network

De novo protein design by inversion of the AlphaFold structure prediction network

De novo protein design by inversion of the AlphaFold structure prediction network

Combinatorial assembly and design of enzymes

Contact Info

Product

Resources

About