×

Deep neural learning based protein function prediction. (English) Zbl 1489.92052

Summary: It is vital for the annotation of uncharacterized proteins by protein function prediction. At present, deep neural network based protein function prediction is mainly carried out for dataset of small scale proteins or gene ontology, and usually explore the relationships between single protein feature and function tags. The practical methods for large-scale multi-features protein prediction still need to be studied in depth. This paper proposes a DNN based protein function prediction approach IGP-DNN. This method uses grasshopper optimization algorithm (GOA) and intuitionistic fuzzy c-means clustering (IFCM) based protein function modules extracting algorithm to extract the features of protein modules, utilizing kernel principal component analysis (KPCA) method to reduce the dimensionality of the protein attribute information, and integrating module features and attribute features. Inputting integrated data into DNN through multiple hidden layers to classify proteins and predict protein functions. In the experiments, the F-measure value of IGP-DNN on the DIP dataset reaches 0.4436, which shows better performance.

MSC:

92C40 Biochemistry, molecular biology
68T07 Artificial neural networks and deep learning
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] L, Module overlapping structure detection in PPI using an improved link similarity-based Markov clustering algorithm, Neural. Comput. Appl., 31, 1481-1490 (2019) · doi:10.1007/s00521-018-3508-z
[2] R, ProLanGO: protein function prediction using neural machine translation based on a recurrent neural network, Molecules, 22, 1732 (2017) · doi:10.3390/molecules22101732
[3] B, SECLAF: a webserver and deep neural network design tool for hierarchical biological sequence classification, Bioinformatics, 34, 2487-2489 (2018) · doi:10.1093/bioinformatics/bty116
[4] A. Tavanaei, A.S. Maida, A. Kaniymattam, R. Loganantharaj, Towards recognition of protein function based on its structure using deep convolutional networks, In <i>2016 IEEE Int. Conf. Bioinform. Biomed.</i> (<i>BIBM</i>). <i>IEEE</i>, 2016,145-149. <a href=“https://doi.org/10.1109/BIBM.2016.7822509” target=“_blank”>https://doi.org/10.1109/BIBM.2016.7822509</a>
[5] V, deepNF: deep network fusion for protein function prediction, Bioinformatics, 34, 3873-3881 (2018) · doi:10.1093/bioinformatics/bty440
[6] R, Predicting human protein function with multi-task deep neural networks, PloS one, 13, e0198216 (2018) · doi:10.1371/journal.pone.0198216
[7] X, Protein function prediction using deep restricted Boltzmann machines, BioMed Res. Int., 2017, 1729301 (2017) · doi:10.1371/journal.pone.0198216
[8] A, DEEPred: automated protein function prediction with multi-task feed-forward deep neural networks, Sci. Rep., 9, 1-16 (2019) · doi:10.1038/s41598-019-43708-3
[9] C, iOri-Human: identify human origin of replication by incorporating dinucleotide physicochemical properties into pseudo nucleotide composition, Oncotarget, 7, 69783 (2016) · doi:10.18632/oncotarget.11975
[10] Y, Accurate prediction of functional effects for variants by combining gradient tree boosting with optimal neighborhood properties, PloS one, 12, e0179314 (2017) · doi:10.1371/journal.pone.0179314
[11] Y, An overview of protein function prediction methods, Chin. J. Bioinform., 11, 33-38 (2013)
[12] S, Gapped BLAST and PSI-BLAST: a new generation of protein database search programs, Nucleic Acids Res., 25, 3389-3402 (1997) · doi:10.1093/nar/25.17.3389
[13] J, Effusion: prediction of protein function from sequence similarity networks, Bioinformatics, 35, 442-451 (2019) · doi:10.1093/bioinformatics/bty672
[14] S, Protein function prediction from dynamic protein interaction network using gene expression data, J. Bioinform. Comput. Biol., 17, 1950025 (2019) · doi:10.1142/S0219720019500252
[15] B, A new protein binding pocket similarity measure based on comparison of clouds of atoms in 3D: application to ligand prediction, BMC bioinform., 11, 99 (2010) · doi:10.1186/1471-2105-11-99
[16] A, A novel method for protein function prediction based on sequence numerical features, Match-Commun. Math. Comput. Chem., 67, 833 (2012)
[17] L, New types of deep neural network learning for speech recognition and related applications: An overview, 2013 IEEE Int. Conf. Acoust. Speech Signal Process., 8599-8603 (2013) · doi:10.1109/ICASSP.2013.6639344
[18] C, Deep learning for computational biology, Mol. Syst. Boil., 12, 878 (2016) · doi:10.15252/msb.20156651
[19] S, Deep learning in bioinformatics, Briefings Bioinform., 18, 851-869 (2017) · doi:10.1093/bib/bbw068
[20] R, QAcon: single model quality assessment using protein structural and contact information with machine learning techniques, Bioinformatics, 33, 586-588 (2017) · doi:10.1093/bioinformatics/btw694
[21] M, DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier, Bioinformatics, 34, 660-668 (2018) · doi:10.1093/bioinformatics/btx624
[22] R, NetGO: improving large-scale protein function prediction with massive network information, Nucleic Acids Res., 47, W379-W387 (2019) · doi:10.1093/nar/gkz388
[23] S, NetGO 2.0: improving large-scale protein function prediction with massive sequence. text, domain, family and network information, Nucleic Acids Res. (2021) · doi:10.1093/nar/gkab398
[24] I, DIP, the Database of Interacting Proteins: a research tool for studying cellular networks of protein interactions, Nucleic Acids Res., 30, 303-305 (2002) · doi:10.1093/nar/30.1.303
[25] UniProt Consortium; The universal protein resource (UniProt) in 2010; <i>Nucleic Acids Res, The universal protein resource (UniProt) in 2010, Nucleic Acids Res., 38, D142-D148 (2010) · doi:10.1093/nar/gkp846
[26] M, Gene ontology: tool for the unification of biology, Nat. Genet., 25, 25-29 (2000) · doi:10.1038/75556
[27] S, Up-to-date catalogues of yeast protein complexes, Nucleic Acids Res., 37, 825-831 (2009) · doi:10.1093/nar/gkn1005
[28] A, Functional organization of the yeast proteome by systematic analysis of protein complexes, Nature, 415, 141-147 (2002) · doi:10.1038/415141a
[29] J, Protein function prediction method based on PPI network and machine learning, J. Comput. Appl., 38, 722-727 (2018)
[30] A, FFPred: an integrated feature-based function prediction server for vertebrate proteomes, Nucleic Acids Res., 36, W297-W302 (2008) · doi:10.1093/nar/gkn193
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.