Deepenz: prediction of enzyme classification by deep learning

Hamza Chehili (University of Constantine 1)
Salah Eddine Aliouane (University of Constantine 1)
Abdelhafedh Bendahmane (University of Constantine 1)
Mohamed Abdelhafid Hamidechi (University of Constantine 1)

Indonesian Journal of Electrical Engineering and Computer Science
Vol 22, No 2: May 2021

Previously, the classification of enzymes was carried out by traditional heuritic methods, however, due to the rapid increase in the number of enzymes being discovered, new methods aimed to classify them are required. Their goal is to increase the speed of processing and to improve the accuracy of predictions. The Purpose of this work is to develop an approach that predicts the enzymes’ classification. This approach is based on two axes of artificial intelligence (AI): natural language processing (NLP) and deep learning (DL). The results obtained in the tests  show the effectiveness of this approach. The combination of these two tools give a model with a great capacity to extract knowledge from enzyme data to predict and classify them. The proposed model learns through intensive training by exploiting enzyme sequences. This work highlights the contribution of this approach to improve the precision of enzyme classification.