Capturing non‐local interactions by long short‐term memory bidirectional recurrent neural networks for improving prediction of protein secondary structure, backbone angles, contact numbers and…

By Rhys Heffernan, Yuedong Yang, Kuldip K. Paliwal, Yaoqi Zhou. 2017

329 citations recorded by the source corpus.

Subfields: Materials Chemistry, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Materials Chemistry

1. Jinbo Xu
2. Sheng Wang
3. Yaoqi Zhou
4. Yuedong Yang
5. Kuldip K. Paliwal
6. Jack Hanson
7. David T. Jones
8. Shaun M. Kandathil

In Molecular Biology

1. Jinbo Xu
2. David T. Jones
3. Sheng Wang
4. Yang Zhang
5. Joe G. Greener
6. Jianlin Cheng
7. Yaoqi Zhou
8. Shaun M. Kandathil

Citations in the corpus

• Modeling aspects of the language of life through transfer-learning protein sequences (2019, methodology): “Performance values for the same data set exist also for other recent methods such as Spider3 [62], RaptorX [63, 64] and JPred4 [65].”
• NetSurfP-2.0: improved prediction of protein structural features by integrated deep learning (2018, methodology): “We have compared the performance of the old and updated version of our tool, and compared to that of Spider3, a recent tool with a similar architecture that only predicts the ASA.”
• ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised Deep Learning and High Performance Computing (2020, neutral): “0 [15], and Jpred4 [70], RaptorX [71], [72], Spider3 [73].”
• Deep learning methods in protein structure prediction (2020, methodology): “Sphere exposures, torsion angles and secondary structure [61].”
• A Survey of Deep Learning for Scientific Discovery (2020, methodology): “…benchmark in natural language, and also for capturing sequence dependencies in scientific applications, such as protein function prediction [77, 80], and using the hidden representations as part of a larger pipeline for protein structure prediction in AlphaFold [205] (with opensourced code…”
• Deep learning extends de novo protein modelling coverage of genomes using iteratively predicted structural constraints (2018, methodology): “The accuracy of torsion angle prediction was observed to be comparable with the current state-of-the-art [36,37], with an average MAE (mean absolute error) of 18.”
• Modeling the language of life – Deep Learning Protein Sequences (2019, methodology): “17 Performance values for the same data set exist also for other recent methods such as Spider3 18 [57], RaptorX [58, 59] and JPred4 [60].”
• Accurate prediction of protein contact maps by coupling residual two-dimensional bidirectional long short-term memory with convolutional neural networks (2018, methodology): “The predicted values obtained from SPIDER3 were: 1 relative solvent-Accessible Surface Area, 2 Half-Sphere Exposures based on the Ca atom, the 8 sine/cosines of the backbone torsion angles (theta, tau, phi and psi) and the three probabilities of the predicted secondary structure.”
• RaptorX-Angle: real-value prediction of protein backbone dihedral angles through a hybrid method of clustering and deep learning (2018, methodology): “Heffernan et al. has developed more accurate SPIDER3 employing Long Short-Term Memory (LSTM) Bidirectional Recurrent Neural Networks (BRNNs), which are capable of capturing long range interactions [53].”