Near Perfect Protein Multi-Label Classification with Deep Neural\n Networks

2017/03/30 by Balázs Szalkai, Szalkai, Balazs, Vince Grolmusz +1
Biochemistry, Genetics and Molecular Biology · #Biochemical and Structural Characterization #Biomolecules (q-bio.BM) #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Bioinformatics #RNA and protein synthesis mechanisms

paper · pdf · doi:10.48550/arxiv.1703.10663

openalex publication_date 2017/03/30 · openalex created_date 2022/10/02 · openalex updated_date 2026/07/28

Abstract

Artificial neural networks (ANNs) have gained a well-deserved popularity\namong machine learning tools upon their recent successful applications in\nimage- and sound processing and classification problems. ANNs have also been\napplied for predicting the family or function of a protein, knowing its residue\nsequence. Here we present two new ANNs with multi-label classification ability,\nshowing impressive accuracy when classifying protein sequences into 698 UniProt\nfamilies (AUC=99.99%) and 983 Gene Ontology classes (AUC=99.45%).\n

Related

• SECLAF: A Webserver and Deep Neural Network Design Tool for Biological\n Sequence Classification
• A Fusion-Driven Approach of Attention-Based CNN-BiLSTM for Protein Family Classification -- ProFamNet
• An Effective GCN-based Hierarchical Multi-label classification for Protein Function Prediction
• DEEPGONET: Multi-label Prediction of GO Annotation for Protein from Sequence Using Cascaded Convolutional and Recurrent Network
• Macromolecule Classification Based on the Amino-acid Sequence