AptaNet As a Deep Learning Approach for Aptamer-protein Interaction Prediction

Overview

Journal Sci Rep

Specialty Science

Date 2021 Mar 17

PMID 33727685

Citations 17

Authors

Neda Emami

Reza Ferdousi

Affiliations

Soon will be listed here.

Abstract

Aptamers are short oligonucleotides (DNA/RNA) or peptide molecules that can selectively bind to their specific targets with high specificity and affinity. As a powerful new class of amino acid ligands, aptamers have high potentials in biosensing, therapeutic, and diagnostic fields. Here, we present AptaNet-a new deep neural network-to predict the aptamer-protein interaction pairs by integrating features derived from both aptamers and the target proteins. Aptamers were encoded by using two different strategies, including k-mer and reverse complement k-mer frequency. Amino acid composition (AAC) and pseudo amino acid composition (PseAAC) were applied to represent target information using 24 physicochemical and conformational properties of the proteins. To handle the imbalance problem in the data, we applied a neighborhood cleaning algorithm. The predictor was constructed based on a deep neural network, and optimal features were selected using the random forest algorithm. As a result, 99.79% accuracy was achieved for the training dataset, and 91.38% accuracy was obtained for the testing dataset. AptaNet achieved high performance on our constructed aptamer-protein benchmark dataset. The results indicate that AptaNet can help identify novel aptamer-protein interacting pairs and build more-efficient insights into the relationship between aptamers and proteins. Our benchmark dataset and the source codes for AptaNet are available in: https://github.com/nedaemami/AptaNet .

Citing Articles

DeepAptamer: Advancing high-affinity aptamer discovery with a hybrid deep learning model.

Yang X, Chan C, Yao S, Chu H, Lyu M, Chen Z Mol Ther Nucleic Acids. 2025; 36(1):102436.

PMID: 39897584 PMC: 11787022. DOI: 10.1016/j.omtn.2024.102436.

AltaiR: a C toolkit for alignment-free and temporal analysis of multi-FASTA data.

Silva J, Pinho A, Pratas D Gigascience. 2024; 13.

PMID: 39589438 PMC: 11590114. DOI: 10.1093/gigascience/giae086.

AptaDiff: de novo design and optimization of aptamers based on diffusion models.

Wang Z, Liu Z, Zhang W, Li Y, Feng Y, Lv S Brief Bioinform. 2024; 25(6).

PMID: 39431516 PMC: 11491854. DOI: 10.1093/bib/bbae517.

Current developments of SELEX technologies and prospects in the aptamer selection with clinical applications.

Chinchilla-Cardenas D, Cruz-Mendez J, Petano-Duque J, Garcia R, Castro L, Lobo-Castanon M J Genet Eng Biotechnol. 2024; 22(3):100400.

PMID: 39179327 PMC: 11338109. DOI: 10.1016/j.jgeb.2024.100400.

Nucleic acid-based wearable and implantable electrochemical sensors.

Ye C, Lukas H, Wang M, Lee Y, Gao W Chem Soc Rev. 2024; 53(15):7960-7982.

PMID: 38985007 PMC: 11308452. DOI: 10.1039/d4cs00001c.

References

Ariaeenejad S, Mousivand M, Moradi Dezfouli P, Hashemi M, Kavousi K, Hosseini Salekdeh G . A computational method for prediction of xylanase enzymes activity in strains of Bacillus subtilis based on pseudo amino acid composition features. PLoS One. 2018; 13(10):e0205796. PMC: 6197662. DOI: 10.1371/journal.pone.0205796. View

Guo F, Cheng Li S, Du P, Wang L . Probabilistic models for capturing more physicochemical properties on protein-protein interface. J Chem Inf Model. 2014; 54(6):1798-809. DOI: 10.1021/ci5002372. View

Hashemifar S, Neyshabur B, Khan A, Xu J . Predicting protein-protein interactions through sequence-based deep learning. Bioinformatics. 2018; 34(17):i802-i810. PMC: 6129267. DOI: 10.1093/bioinformatics/bty573. View

Li B, Zhang Y, Huang G, Cui W, Zhang N, Cai Y . Prediction of aptamer-target interacting pairs with pseudo-amino acid composition. PLoS One. 2014; 9(1):e86729. PMC: 3899287. DOI: 10.1371/journal.pone.0086729. View

Verkhivker G, Appelt K, FREER S, Villafranca J . Empirical free energy calculations of ligand-protein crystallographic complexes. I. Knowledge-based ligand-protein interaction potentials applied to the prediction of human immunodeficiency virus 1 protease binding affinity. Protein Eng. 1995; 8(7):677-91. DOI: 10.1093/protein/8.7.677. View

Macalino S, Basith S, Clavio N, Chang H, Kang S, Choi S . Evolution of In Silico Strategies for Protein-Protein Interaction Drug Discovery. Molecules. 2018; 23(8). PMC: 6222862. DOI: 10.3390/molecules23081963. View

Beknazarov N, Jin S, Poptsova M . Deep learning approach for predicting functional Z-DNA regions using omics data. Sci Rep. 2020; 10(1):19134. PMC: 7644757. DOI: 10.1038/s41598-020-76203-1. View

Xiao X, Cheng X, Chen G, Mao Q, Chou K . pLoc_bal-mVirus: Predict Subcellular Localization of Multi-Label Virus Proteins by Chou's General PseAAC and IHTS Treatment to Balance Training Dataset. Med Chem. 2018; 15(5):496-509. DOI: 10.2174/1573406415666181217114710. View

Peng C, Han S, Zhang H, Li Y . RPITER: A Hierarchical Deep Learning Framework for ncRNA⁻Protein Interaction Prediction. Int J Mol Sci. 2019; 20(5). PMC: 6429152. DOI: 10.3390/ijms20051070. View

10.

Li J, Ma X, Li X, Gu J . PPAI: a web server for predicting protein-aptamer interactions. BMC Bioinformatics. 2020; 21(1):236. PMC: 7285591. DOI: 10.1186/s12859-020-03574-7. View

11.

Ding Y, Zhang T, Chou K . Prediction of protein structure classes with pseudo amino acid composition and fuzzy support vector machine network. Protein Pept Lett. 2007; 14(8):811-5. DOI: 10.2174/092986607781483778. View

12.

Choi J, Park S, Ahn J . RefDNN: a reference drug based neural network for more accurate prediction of anticancer drug resistance. Sci Rep. 2020; 10(1):1861. PMC: 7002431. DOI: 10.1038/s41598-020-58821-x. View

13.

Rupesh K, Smith A, Boehmer P . Ligand induced stabilization of the melting temperature of the HSV-1 single-strand DNA binding protein using the thermal shift assay. Biochem Biophys Res Commun. 2014; 454(4):604-8. PMC: 4254511. DOI: 10.1016/j.bbrc.2014.10.145. View

14.

Robertson D, Joyce G . Selection in vitro of an RNA enzyme that specifically cleaves single-stranded DNA. Nature. 1990; 344(6265):467-8. DOI: 10.1038/344467a0. View

15.

Kortemme T, Baker D . Computational design of protein-protein interactions. Curr Opin Chem Biol. 2004; 8(1):91-7. DOI: 10.1016/j.cbpa.2003.12.008. View

16.

Wen J, Liu Y, Shi Y, Huang H, Deng B, Xiao X . A classification model for lncRNA and mRNA based on k-mers and a convolutional neural network. BMC Bioinformatics. 2019; 20(1):469. PMC: 6743109. DOI: 10.1186/s12859-019-3039-3. View

17.

Wang P, Yang Y, Hong H, Zhang Y, Cai W, Fang D . Aptamers as therapeutics in cardiovascular diseases. Curr Med Chem. 2011; 18(27):4169-74. PMC: 3205281. DOI: 10.2174/092986711797189673. View

18.

Flamme M, McKenzie L, Sarac I, Hollenstein M . Chemical methods for the modification of RNA. Methods. 2019; 161:64-82. DOI: 10.1016/j.ymeth.2019.03.018. View

19.

Xiang N, Lyu Y, Zhu X, Bhunia A, Narsimhan G . Effect of physicochemical properties of peptides from soy protein on their antimicrobial activity. Peptides. 2017; 94:10-18. DOI: 10.1016/j.peptides.2017.05.010. View

20.

Mattice W, Riser J, Clark D . Conformational properties of the complexes formed by proteins and sodium dodecyl sulfate. Biochemistry. 1976; 15(19):4264-72. DOI: 10.1021/bi00664a020. View