Deep learning for protein secondary structure prediction: Pre and post-AlphaFold

Ismi, Dewi Pramudi; Pulungan, Reza; Afiahayati, FNU

doi:10.1016/j.csbj.2022.11.012

Cited by 24 publications

(6 citation statements)

References 162 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Overall, the Q3 Protein SS prediction has reached 87-89% accuracy, which is close to its theoretical limit [49], [50]. However, taking current protein structure databases into account, a new study claimed that the theoretical limit of Q3 SS prediction could be extended to 90-92%.…”

Section: Related Workmentioning

confidence: 66%

See 1 more Smart Citation

Multi-S3P: Protein Secondary Structure Prediction With Specialized Multi-Network and Self-Attention-Based Deep Learning Model

et al. 2023

View full text Add to dashboard Cite

Protein structure prediction (PSP) is a vital challenge in bioinformatics, structural biology and drug discovery. Protein secondary structure (SS) prediction is critical since three-dimensional (3D) structures are primarily made up of secondary structures. With the advancement of deep learning approaches, SS classification accuracy has been significantly improved. Many existing methods use an ensemble of complex neural networks to improve SS prediction. Because of the high dimensionality of the hyperparameter space, deep neural networks with complex architectures are typically challenging to train effectively. Also, predicting secondary structures in the boundary regions between different types of SS is challenging. This study presents Multi-S3P, which employs bidirectional Long-Short-Term-Memory (BILSTM) and Convolutional Neural Networks (CNN) with a self-attention mechanism to improve the secondary structure prediction using an effective training strategy to capture the unique characteristics of each type of secondary structure and combine them more effectively. The ensemble of CNN and BILSTM can learn both contextual information and long-range interactions between the residues. In addition, using a self-attention mechanism allows the model to focus on the most important features for improving performance. We used the SPOT-1D dataset for the training and validation of our model using a set of four input features derived from amino acid sequences. Further, the model was tested on four popular independent test datasets and compared with various state-of-the-art predictors. The presented results show that Multi-S3P outperformed the other methods in terms of Q3, Q8 accuracy and other performance metrics, achieving the highest Q3 accuracy of 87.57% and a Q8 accuracy of 77.56% on the TEST2016 test set. More importantly, Multi-S3P demonstrates high performance in SS boundary regions. Our experiment also demonstrates that the combination of different input features and a multi-network-based training strategy significantly improved the performance.

show abstract

Section: Related Workmentioning

confidence: 66%

“…However, taking current protein structure databases into account, a new study claimed that the theoretical limit of Q3 SS prediction could be extended to 90-92%. The upper limit of Q8 for eight-state measurements is 84-86% [50], [51]. This indicates that there is still a gap in accuracy to be filled.…”

Section: Related Workmentioning

confidence: 99%

Multi-S3P: Protein Secondary Structure Prediction With Specialized Multi-Network and Self-Attention-Based Deep Learning Model

et al. 2023

View full text Add to dashboard Cite

show abstract

“…This work shows that for the category of therapeutic proteins above 40 amino acids, there is a weak or no correlation between the number of amino acids and their pLDDT or pTM scores. In the case of polypeptides, a reverse observation showed that a smaller number provides more complexity in prediction and less confidence in structure predictability, as applied to polypeptides [90,91]. Both tools correlate significantly positively, representing their orthogonality.…”

Section: Discussionmentioning

confidence: 97%

Limitations of Protein Structure Prediction Algorithms in Therapeutic Protein Development

Niazi,

Mariam,

Paracha

2024

BioMedInformatics

View full text Add to dashboard Cite

The three-dimensional protein structure is pivotal in comprehending biological phenomena. It directly governs protein function and hence aids in drug discovery. The development of protein prediction algorithms, such as AlphaFold2, ESMFold, and trRosetta, has given much hope in expediting protein-based therapeutic discovery. Though no study has reported a conclusive application of these algorithms, the efforts continue with much optimism. We intended to test the application of these algorithms in rank-ordering therapeutic proteins for their instability during the pre-translational modification stages, as may be predicted according to the confidence of the structure predicted by these algorithms. The selected molecules were based on a harmonized category of licensed therapeutic proteins; out of the 204 licensed products, 188 that were not conjugated were chosen for analysis, resulting in a lack of correlation between the confidence scores and structural or protein properties. It is crucial to note here that the predictive accuracy of these algorithms is contingent upon the presence of the known structure of the protein in the accessible database. Consequently, our conclusion emphasizes that these algorithms primarily replicate information derived from existing structures. While our findings caution against relying on these algorithms for drug discovery purposes, we acknowledge the need for a nuanced interpretation. Considering their limitations and recognizing that their utility may be constrained to scenarios where known structures are available is important. Hence, caution is advised when applying these algorithms to characterize various attributes of therapeutic proteins without the support of adequate structural information. It is worth noting that the two main algorithms, AlfphaFold2 and ESMFold, also showed a 72% correlation in their scores, pointing to similar limitations. While much progress has been made in computational sciences, the Levinthal paradox remains unsolved.

show abstract

“…This can be defined in several ways: using a protein's solved structure, a secondary structure predictor, or a tertiary structure predictor that predicts secondary structure. However, tools for predicting secondary structure in those proteins without solved structures (as well as IDPs) have limited accuracy [31][32][33][34]. Tertiary structure predictors such as AlphaFold do predict secondary structure, but this is not their primary function, and any potential biases in detecting secondary structure remain unclear.…”

Section: Introductionmentioning

confidence: 99%

The blobulator: a webtool for identification and visual exploration of hydrophobic modularity in protein sequences

Pitman,

Santiago-McRae,

Lohia

et al. 2024

Preprint

View full text Add to dashboard Cite

Clusters of hydrophobic residues are known to promote structured protein stability and drive protein aggregation. Recent work has shown that identifying contiguous hydrophobic residue clusters (termed 'blobs') has proven useful in both intrinsically disordered protein (IDP) simulation and human genome studies. However, a graphical interface was unavailable. Here, we present the blobulator: an interactive and intuitive web interface to detect intrinsic modularity in any protein sequence based on hydrophobicity. We demonstrate three use cases of the blobulator and show how identifying blobs with biologically relevant parameters provides useful information about a globular protein, two orthologous membrane proteins, and an IDP. Other potential applications are discussed, including: predicting protein segments with critical roles in tertiary interactions, providing a definition of local order and disorder with clear edges, and aiding in predicting protein features from sequence. The blobulator GUI can be found at www.blobulator.branniganlab.org, and the source code with pip installable command line tool can be found on GitHub at www.GitHub.com/BranniganLab/blobulator.

show abstract

Deep learning for protein secondary structure prediction: Pre and post-AlphaFold

Cited by 24 publications

References 162 publications

Multi-S3P: Protein Secondary Structure Prediction With Specialized Multi-Network and Self-Attention-Based Deep Learning Model

Multi-S3P: Protein Secondary Structure Prediction With Specialized Multi-Network and Self-Attention-Based Deep Learning Model

Limitations of Protein Structure Prediction Algorithms in Therapeutic Protein Development

The blobulator: a webtool for identification and visual exploration of hydrophobic modularity in protein sequences

Contact Info

Product

Resources

About