Protein secondary structure prediction using a lightweight convolutional network and label distribution aware margin loss

Yang, Wei; Hu, Zhentao; Zhou, Lin; Jin, Yong

doi:10.1016/j.knosys.2021.107771

Cited by 12 publications

(25 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MUFOLD-SS ( Fang et al, 2018 ) uses a Deep inception-inside-inception (Deep3I) network to handle local and global dependencies in sequences. ShuffleNet_SS ( Yang et al, 2022 ) uses a lightweight convolutional network and label distribution aware margin loss to improve the network’s learning ability for rare classes. For a fair comparison, we use our dataset for training in experiments, where the input is the hybrid feature PSSM + one-hot.…”

Section: Methodsmentioning

confidence: 99%

Ensemble deep learning models for protein secondary structure prediction using bidirectional temporal convolution and bidirectional long short-term memory

Yuan

Ma²,

Liu³

2023

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Protein secondary structure prediction (PSSP) is a challenging task in computational biology. However, existing models with deep architectures are not sufficient and comprehensive for deep long-range feature extraction of long sequences. This paper proposes a novel deep learning model to improve Protein secondary structure prediction. In the model, our proposed bidirectional temporal convolutional network (BTCN) can extract the bidirectional deep local dependencies in protein sequences segmented by the sliding window technique, the bidirectional long short-term memory (BLSTM) network can extract the global interactions between residues, and our proposed multi-scale bidirectional temporal convolutional network (MSBTCN) can further capture the bidirectional multi-scale long-range features of residues while preserving the hidden layer information more comprehensively. In particular, we also propose that fusing the features of 3-state and 8-state Protein secondary structure prediction can further improve the prediction accuracy. Moreover, we also propose and compare multiple novel deep models by combining bidirectional long short-term memory with temporal convolutional network (TCN), reverse temporal convolutional network (RTCN), multi-scale temporal convolutional network (multi-scale bidirectional temporal convolutional network), bidirectional temporal convolutional network and multi-scale bidirectional temporal convolutional network, respectively. Furthermore, we demonstrate that the reverse prediction of secondary structure outperforms the forward prediction, suggesting that amino acids at later positions have a greater impact on secondary structure recognition. Experimental results on benchmark datasets including CASP10, CASP11, CASP12, CASP13, CASP14, and CB513 show that our methods achieve better prediction performance compared to five state-of-the-art methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Ensemble deep learning models for protein secondary structure prediction using bidirectional temporal convolution and bidirectional long short-term memory

Yuan

Ma²,

Liu³

2023

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…In this section, we compare the proposed method with five state-of-the-art methods DCRNN, 42 CNN_BIGRU, 43 DeepACLSTM, 44 MUFOLD-SS 45 and ShuffleNet_SS 46 on seven test sets CullPDB, CASP10, CASP11, CASP12, CASP13, CASP14 and CB513. The DCRNN model utilizes a multi-scale convolutional neural network to extract local features and a bidirectional neural network composed of gated units to extract global features.…”

Section: Methodsmentioning

confidence: 99%

DLBLS_SS: protein secondary structure prediction using deep learning and broad learning system

Yuan

et al. 2022

RSC Adv.

View full text Add to dashboard Cite

show abstract

“…However, this standard practice raises an issue: the networks will change the feature vectors corresponding to the padded positions to non-zero vectors during forward propagation, affecting the prediction result of the non-padded positions. To address this issue, Yang et al [166] proposed a modified 1D batch normalization by exploiting a mask matrix, so that padding positions in the feature vectors do not participate in normalization operations. Hence, the feature vectors in these padding positions remain all-zeros.…”

Section: Pssp In Post-alphafold Publicationmentioning

confidence: 99%

“…Hence, the feature vectors in these padding positions remain all-zeros. Furthermore, they [166] also proposed a PSSP model with architecture comprised of CNNs and fully connected layers along with the implementation of masked batch normalization.…”

Section: Pssp In Post-alphafold Publicationmentioning

confidence: 99%

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

Ismi

Pulungan

Afiahayati

2022

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

Protein secondary structure prediction using a lightweight convolutional network and label distribution aware margin loss

Cited by 12 publications

References 39 publications

Ensemble deep learning models for protein secondary structure prediction using bidirectional temporal convolution and bidirectional long short-term memory

Ensemble deep learning models for protein secondary structure prediction using bidirectional temporal convolution and bidirectional long short-term memory

DLBLS_SS: protein secondary structure prediction using deep learning and broad learning system

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

Contact Info

Product

Resources

About