Folding the unfoldable: using AlphaFold to explore spurious proteins

Monzon, Vivian; Haft, Daniel H.; Bateman, Alex

doi:10.1093/bioadv/vbab043

Cited by 32 publications

(37 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even in light of the recent dawn of computational structure prediction, 65,66 experimental structural and functional determination remains necessary, especially for de novo proteins. While contemporary prediction methods can certainly provide a first estimate on structure, the intrinsic nature of de novo proteins, with their short length, high disorder content and lack of homology, will demand some scepticism while analyzing such predictions 67,68 . Surprisingly, the AlphaFold prediction of Goddard (GEO12017p1, AlphaFold Protein Structure Database) 69 is in line with its partial experimental characterization 25 and its central helix is predicted with high confidence.…”

Section: Discussionmentioning

confidence: 99%

Heterologous expression of naturally evolved putative de novo proteins with chaperones

Aubel

Berk

et al. 2022

Protein Science

View full text Add to dashboard Cite

Over the past decade, evidence has accumulated that new protein‐coding genes can emerge de novo from previously non‐coding DNA. Most studies have focused on large scale computational predictions of de novo protein‐coding genes across a wide range of organisms. In contrast, experimental data concerning the folding and function of de novo proteins are scarce. This might be due to difficulties in handling de novo proteins in vitro, as most are short and predicted to be disordered. Here, we propose a guideline for the effective expression of eukaryotic de novo proteins in Escherichia coli. We used 11 sequences from Drosophila melanogaster and 10 from Homo sapiens, that are predicted de novo proteins from former studies, for heterologous expression. The candidate de novo proteins have varying secondary structure and disorder content. Using multiple combinations of purification tags, E. coli expression strains, and chaperone systems, we were able to increase the number of solubly expressed putative de novo proteins from 30% to 62%. Our findings indicate that the best combination for expressing putative de novo proteins in E. coli is a GST‐tag with T7 Express cells and co‐expressed chaperones. We found that, overall, proteins with higher predicted disorder were easier to express. Statement Today, we know that proteins do not only evolve by duplication and divergence of existing proteins but also arise from previously non‐coding DNA. These proteins are called de novo proteins. Their properties are still poorly understood and their experimental analysis faces major obstacles. Here, we aim to present a starting point for soluble expression of de novo proteins with the help of chaperones and thereby enable further characterization.

show abstract

Section: Discussionmentioning

confidence: 99%

Heterologous expression of naturally evolved putative de novo proteins with chaperones

Aubel

Berk

et al. 2022

Protein Science

View full text Add to dashboard Cite

show abstract

“…Consequently, the AlphaFold2 predictions might be biased in regions that are disordered in isolation but become rigid upon interaction. Furthermore, the mean pLDDT is trivially higher for shorter than for longer proteins (Monzon et al, 2022). Since the mean protein length for the test set CheZOD117 was only 112, this could also explain some outliers.…”

Section: Discussionmentioning

confidence: 99%

“…The resulting score, dubbed pLDDT (predicted local distance difference test), distinguishes formidably between trustworthy and less reliable predictions (Jumper et al, 2021). Low values for pLDDT have been suggested to predict IDRs rather accurately (Wilson et al, 2021;Piovesan et al, 2022) or to predict non-existing proteins (Monzon et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

SETH predicts nuances of residue disorder from protein embeddings

Ilzhoefer

Heinzinger

Rost

2022

Preprint

View full text Add to dashboard Cite

Predictions of millions of protein 3D structures are only a few clicks away since the release of AlphaFold2 results for entire data sets. However, many proteins have so-called intrinsically disordered regions (IDRs) that do not adopt unique structures in isolation. These IDRs are associated with several diseases, including Alzheimer's Disease. We showed that the absence of reliable AlphaFold2 predictions correlated only to a limited extent with IDRs. In contrast, many expert methods predict IDRs directly and reliably by combining complex machine learning models with expert-crafted input features and evolutionary information from multiple sequence alignments. Some of these input features are not always available and computationally expensive to generate, limiting their scalability. In this work, we present the novel prediction method SETH that predicts residue disorder from embeddings generated by the protein Language Model ProtT5, which explicitly only uses single sequences as input. Thereby SETH, a relatively shallow convolutional neural network, already outperformed much more complex state-of-the-art solutions while being much faster, allowing to create predictions for the human proteome in fewer than 30 minutes on a machine with one RTX A6000 GPU with 48GB RAM. Trained on a continuous disorder scale, our method captured subtle variations in disorder, thereby providing important information beyond the binary classification of other predictors. The new method is freely publicly available at: https://github.com/DagmarIlz/SETH.

show abstract

“…The largest effect was observed for the mixed secondary structure benchmark groups (~1.0 Å with outliers and ~0.5 Å without outliers), suggesting that this shortcoming is a significant problem especially when the system has flexible regions that increase the number of conformations that can be adopted by the peptide but can also cause deviations based on the extent of the secondary structures predicted for the system. A study investigating multiple aspects of protein folding with AF2 involved testing of pLDDT values for proteins of varying lengths, which showed that shorter sequences tend to have larger pLDDT values in general [32]. This may reduce the utility of this metric for small peptide structures by narrowing the gap between good and bad predicted structures.…”

Section: Discussionmentioning

confidence: 99%

Benchmarking Peptide Structure Prediction with AlphaFold2

Gulsevin

Meiler

2022

Preprint

View full text Add to dashboard Cite

AlphaFold2 (AF2) is a computational tool developed for the determination of protein structures with high accuracy. AF2 has been used for the modeling of many soluble and membrane proteins, but its performance in modeling peptide structures has not been systematically investigated so far. We benchmarked the accuracy of AF2 in predicting peptide structures between 16 – 60 amino acids using experimentally-determined peptide structures as reference. Our results show that while AF2 can predict the structures of certain peptide scaffolds with RMSD values below 3 Å, it is less successful in predicting the structures of peptides that have kinks, turns, or have extended flexible regions. Further, AF2 had several shortcomings in predicting rotamer recoveries, disulfide bonds, and the lowest RMSD structures based on pLDDT values. In summary, AF2 can be a powerful tool to determine peptide structures, but additional steps may be necessary to analyze and validate the results.

show abstract

Folding the unfoldable: using AlphaFold to explore spurious proteins

Cited by 32 publications

References 17 publications

Heterologous expression of naturally evolved putative de novo proteins with chaperones

Heterologous expression of naturally evolved putative de novo proteins with chaperones

SETH predicts nuances of residue disorder from protein embeddings

Benchmarking Peptide Structure Prediction with AlphaFold2

Contact Info

Product

Resources

About