DeepFrag-k: a fragment-based deep learning approach for protein fold recognition

Elhefnawy, Wessam; Li, Min; Wang, Jianxin; Li, Yaohang

doi:10.1186/s12859-020-3504-z

Cited by 8 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second task is direct fold classification (DFC), in which the protein sequences are directly mapped into a pre-defined group of fold classes [46]. Most of the proposed methods [47][48][49][50][51][52][53][54][55][56] had used evolutionary information and machine learning to classify only a small portion of all possible SCOP folds (i.e.…”

Section: Introductionmentioning

confidence: 99%

An analysis of protein language model embeddings for fold prediction

Villegas-Morcillo

Gómez

Sánchez

2022

Briefings in Bioinformatics

View full text Add to dashboard Cite

The identification of the protein fold class is a challenging problem in structural biology. Recent computational methods for fold prediction leverage deep learning techniques to extract protein fold-representative embeddings mainly using evolutionary information in the form of multiple sequence alignment (MSA) as input source. In contrast, protein language models (LM) have reshaped the field thanks to their ability to learn efficient protein representations (protein-LM embeddings) from purely sequential information in a self-supervised manner. In this paper, we analyze a framework for protein fold prediction using pre-trained protein-LM embeddings as input to several fine-tuning neural network models, which are supervisedly trained with fold labels. In particular, we compare the performance of six protein-LM embeddings: the long short-term memory-based UniRep and SeqVec, and the transformer-based ESM-1b, ESM-MSA, ProtBERT and ProtT5; as well as three neural networks: Multi-Layer Perceptron, ResCNN-BGRU (RBG) and Light-Attention (LAT). We separately evaluated the pairwise fold recognition (PFR) and direct fold classification (DFC) tasks on well-known benchmark datasets. The results indicate that the combination of transformer-based embeddings, particularly those obtained at amino acid level, with the RBG and LAT fine-tuning models performs remarkably well in both tasks. To further increase prediction accuracy, we propose several ensemble strategies for PFR and DFC, which provide a significant performance boost over the current state-of-the-art results. All this suggests that moving from traditional protein representations to protein-LM embeddings is a very promising approach to protein fold-related tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

An analysis of protein language model embeddings for fold prediction

Villegas-Morcillo

Gómez

Sánchez

2022

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…Prediction based on co-evolutionary information by using deep learning has considerably advanced protein structure prediction [2][3][4]. However, current deep learning methods, including the end-to-end structure prediction methods [5,6], have limited effectiveness in the exploration and understanding of the protein-folding mechanism that is one of the central problems in biochemistry and essential for the study of protein misfolding diseases [7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Construct a variable-length fragment library for de novo protein structure prediction

Feng

Hou

Liu

et al. 2022

Briefings in Bioinformatics

View full text Add to dashboard Cite

Although remarkable achievements, such as AlphaFold2, have been made in end-to-end structure prediction, fragment libraries remain essential for de novo protein structure prediction, which can help explore and understand the protein-folding mechanism. In this work, we developed a variable-length fragment library (VFlib). In VFlib, a master structure database was first constructed from the Protein Data Bank through sequence clustering. The hidden Markov model (HMM) profile of each protein in the master structure database was generated by HHsuite, and the secondary structure of each protein was calculated by DSSP. For the query sequence, the HMM-profile was first constructed. Then, variable-length fragments were retrieved from the master structure database through dynamically variable-length profile–profile comparison. A complete method for chopping the query HMM-profile during this process was proposed to obtain fragments with increased diversity. Finally, secondary structure information was used to further screen the retrieved fragments to generate the final fragment library of specific query sequence. The experimental results obtained with a set of 120 nonredundant proteins show that the global precision and coverage of the fragment library generated by VFlib were 55.04% and 94.95% at the RMSD cutoff of 1.5 Å, respectively. Compared with the benchmark method of NNMake, the global precision of our fragment library had increased by 62.89% with equivalent coverage. Furthermore, the fragments generated by VFlib and NNMake were used to predict structure models through fragment assembly. Controlled experimental results demonstrate that the average TM-score of VFlib was 16.00% higher than that of NNMake.

show abstract

Section: Introductionmentioning

confidence: 99%

An Analysis of Protein Language Model Embeddings for Fold Prediction

Villegas-Morcillo

Gómez

Sánchez

2022

Preprint

View full text Add to dashboard Cite

The identification of the protein fold class is a challenging problem in structural biology. Recent computational methods for fold prediction leverage deep learning techniques to extract protein fold-representative embeddings mainly using evolutionary information in the form of multiple sequence alignment (MSA) as input source. In contrast, protein language models (LM) have reshaped the field thanks to their ability to learn efficient protein representations (protein-LM embeddings) from purely sequential information in a self-supervised manner. In this paper, we analyze a framework for protein fold prediction using pre-trained protein-LM embeddings as input to several fine-tuning neural network models which are supervisedly trained with fold labels. In particular, we compare the performance of six protein-LM embeddings: the LSTM-based UniRep and SeqVec, and the transformer-based ESM-1b, ESM-MSA, ProtBERT, and ProtT5; as well as three neural networks: Multi-Layer Perceptron (MLP), ResCNN-BGRU (RBG), and Light-Attention (LAT). We separately evaluated the pairwise fold recognition (PFR) and direct fold classification (DFC) tasks on well-known benchmark datasets. The results indicate that the combination of transformer-based embeddings, particularly those obtained at amino acid-level, with the RBG and LAT fine-tuning models performs remarkably well in both tasks. To further increase prediction accuracy, we propose several ensemble strategies for PFR and DFC, which provide a significant performance boost over the current state-of-the-art results. All this suggests that moving from traditional protein representations to protein-LM embeddings is a very promising approach to protein fold-related tasks.

show abstract

DeepFrag-k: a fragment-based deep learning approach for protein fold recognition

Cited by 8 publications

References 30 publications

An analysis of protein language model embeddings for fold prediction

An analysis of protein language model embeddings for fold prediction

Construct a variable-length fragment library for de novo protein structure prediction

An Analysis of Protein Language Model Embeddings for Fold Prediction

Contact Info

Product

Resources

About