AlphaFold encodes the principles to identify high affinity peptide binders

Chang, Liwei; Pérez, Alberto

doi:10.1101/2022.03.18.484931

Cited by 21 publications

(25 citation statements)

References 21 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent study reported that competitive binding can be simulated in protein–peptide docking using ColabFold [ 48 ]. In other words, competition binding experiments of peptides can be performed virtually.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Solubility-Aware Protein Binding Peptide Design Using AlphaFold

Kosugi

Ohue

2022

Biomedicines

View full text Add to dashboard Cite

New protein–protein interactions (PPIs) are identified, but PPIs have different physicochemical properties compared with conventional targets, making it difficult to use small molecules. Peptides offer a new modality to target PPIs, but designing appropriate peptide sequences by computation is challenging. Recently, AlphaFold and RoseTTAFold have made it possible to predict protein structures from amino acid sequences with ultra-high accuracy, enabling de novo protein design. We designed peptides likely to have PPI as the target protein using the “binder hallucination” protocol of AfDesign, a de novo protein design method using AlphaFold. However, the solubility of the peptides tended to be low. Therefore, we designed a solubility loss function using solubility indices for amino acids and developed a solubility-aware AfDesign binder hallucination protocol. The peptide solubility in sequences designed using the new protocol increased with the weight of the solubility loss function; moreover, they captured the characteristics of the solubility indices. Moreover, the new protocol sequences tended to have higher affinity than random or single residue substitution sequences when evaluated by docking binding affinity. Our approach shows that it is possible to design peptide sequences that can bind to the interface of PPI while controlling solubility.

show abstract

Section: Discussionmentioning

confidence: 99%

“…This method was based on previously published paper [48]. Modeling was performed in the publicly available localcolabfold (https://github.com/YoshitakaMo/localcolabfold (accessed on 29 June 2022)).…”

Section: Competitive Peptide Binding Predictions Using Alphafoldmentioning

confidence: 99%

Solubility-Aware Protein Binding Peptide Design Using AlphaFold

Kosugi

Ohue

2022

Biomedicines

View full text Add to dashboard Cite

show abstract

“…Recently, it was reported that competitive binding can be simulated in protein–peptide docking using ColabFold [53]. In other words, it is possible to perform virtual competition binding experiments of peptides.…”

Section: Discussionmentioning

confidence: 99%

“…However, the ability to design sequences with high solubility and high binding affinity that could be candidates for PPI inhibition from among a large number of candidate sequences is meaningful from both the drug discovery and industrial perspectives. Recently, it was reported that competitive binding can be simulated in protein-peptide docking using ColabFold [53]. In other words, it is possible to perform virtual competition binding experiments of peptides.…”

Section: Discussionmentioning

confidence: 99%

Solubility-aware protein binding peptide design using AlphaFold

Kosugi

Ohue

2022

Preprint

View full text Add to dashboard Cite

New protein–protein interactions (PPIs) are being identified, but PPIs have different physicochemical properties compared with conventional targets, making it difficult to use small molecules. Peptides offer a new modality to target PPIs, but designing appropriate peptide sequences by computation is challenging. Recently, AlphaFold and RosettaFold have made it possible to predict protein structures from amino acid sequences with ultra-high accuracy, enabling de novo protein design. We designed peptides likely to have PPI as the target protein using the “binder hallucination” protocol of AfDesign, a de novo protein design method using AlphaFold. However, the solubility of the peptides tended to be low. Therefore, we designed a solubility loss function using solubility indices for amino acids and developed a solubility-aware AfDesign binder hallucination protocol. The peptide solubility in sequences designed using the new protocol increased with the weight of the solubility loss function; moreover, they captured the characteristics of the solubility indices. Moreover, the new protocol sequences tended to have higher affinity than random or single residue substitution sequences when evaluated by docking binding affinity. Our approach shows that it is possible to design peptide sequences that can bind to the interface of PPI while controlling solubility.

show abstract

“…We reasoned that the recent advances in protein structure prediction could help overcome both limitations: that of structure based methods in utilizing large amounts of known binding data, and sequence-based methods, in using structural information. AlphaFold (9) and RoseTTAFold (10) predict highly accurate structures (11) and structure quality confidence metrics that have been used to distinguish pairs of proteins which bind from those that don’t with some success (12, 13). However, while these methods can be readily trained with structural data, in their current form it is not straightforward to train on binding data.…”

Section: Main Textmentioning

confidence: 99%

Peptide binding specificity prediction using fine-tuned protein structure prediction networks

Motmaen

Dauparas

Baek

et al. 2022

Preprint

View full text Add to dashboard Cite

Peptide binding proteins play key roles in biology, and predicting their binding specificity is a long-standing challenge. While considerable protein structural information is available, the most successful current methods use sequence information alone, in part because it has been a challenge to model the subtle structural changes accompanying sequence substitutions. Protein structure prediction networks such as AlphaFold model sequence-structure relationships very accurately, and we reasoned that if it were possible to specifically train such networks on binding data, more generalizable models could be created. We show that placing a classifier on top of the AlphaFold network and fine-tuning the combined network parameters for both classification and structure prediction accuracy leads to a model with strong generalizable performance on a wide range of Class I and Class II peptide-MHC interactions that approaches the overall performance of the state-of-the-art NetMHCpan sequence-based method. The peptide-MHC optimized model shows excellent performance in distinguishing binding and non-binding peptides to SH3 and PDZ domains. This ability to generalize well beyond the training set far exceeds that of sequence only models, and should be particularly powerful for systems where less experimental data is available.

show abstract

AlphaFold encodes the principles to identify high affinity peptide binders

Cited by 21 publications

References 21 publications

Solubility-Aware Protein Binding Peptide Design Using AlphaFold

Solubility-Aware Protein Binding Peptide Design Using AlphaFold

Solubility-aware protein binding peptide design using AlphaFold

Peptide binding specificity prediction using fine-tuned protein structure prediction networks

Contact Info

Product

Resources

About