DEEPre: sequence-based enzyme EC number prediction by deep learning

By Yu Li, Sheng Wang, Ramzan Umarov, Bingqing Xie, Ming Fan, Lihua Li, Xin Gao. 2017

268 citations recorded by the source corpus.

Motivation Annotation of enzyme function has a broad range of applications, such as metagenomics, industrial biotechnology, and diagnosis of enzyme deficiency‐caused diseases. However, the time and resource required make it prohibitively expensive to experimentally determine the function of every enzyme. Therefore, computational enzyme function prediction has become increasingly important. In this paper, we develop such an approach, determining the enzyme function by predicting the Enzyme Commission number. Results We propose an end‐to‐end feature selection and classification model training approach, as well as an automatic and robust feature dimensionality uniformization method, DEEPre, in the field of enzyme function prediction. Instead of extracting manually crafted features from enzyme sequences, our model takes the raw sequence encoding as inputs, extracting convolutional and sequential features from the raw encoding based on the classification result to directly improve the prediction performance. The thorough cross‐fold validation experiments conducted on two large‐scale datasets show that DEEPre improves the prediction performance over the previous state‐of‐the‐art methods. In addition, our server outperforms five other servers in determining the main class of enzymes on a separate low‐homology dataset. Two case studies demonstrate DEEPre's ability to capture the functional difference of enzyme isoforms. Availability and implementation The server could be accessed freely at http://www.cbrc.kaust.edu.sa/DEEPre. Contact xin.gao@kaust.edu.sa Supplementary information Supplementary data are available at Bioinformatics online.

Subfields: 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 Molecular Biology

1. Xin Gao
2. Yu Li
3. Mathias Lietaert
4. Ramzan Umarov
5. Le Song
6. Chao Huang
7. Celine Vens
8. Felipe Kenji Nakano

Citations in the corpus

• RNA Secondary Structure Prediction By Learning Unrolled Algorithms (2020, background): “A hand-tuned weight is needed to balance them while using `2 or crossentropy losses, but F1 loss handles this issue automatically, which can be useful for a number of problems (Wang et al., 2016; Li et al., 2017).”
• SupportNet: solving catastrophic forgetting in class incremental learning with support data (2018, methodology): “This dataset 1 is from our previous work (Li et al. , 2018a), which predicts the function of enzymes from their sequences through a novel deep learning architecture.”
• Machine learning for discovering missing or wrong protein function annotations (2019, background): “Li [34] proposed to use this strategy with deep neural networks to predict the commission number of enzymes.”
• Deep learning in bioinformatics: introduction, application, and perspective in big data era (2019, methodology): “The common ways of encoding a protein sequences are discussed in [85].”
• mlDEEPre: Multi-Functional Enzyme Function Prediction With Hierarchical Multi-Label Deep Learning (2019, methodology): “For the mono-functional enzyme data, we use the dataset from Li et al. (2018d).”