HormoNet: a Deep Learning Approach for Hormone-drug Interaction Prediction

Overview

Journal BMC Bioinformatics

Publisher Biomed Central

Specialty Biology

Date 2024 Feb 28

PMID 38418979

Authors

Neda Emami

Reza Ferdousi

Affiliations

Soon will be listed here.

Abstract

Several experimental evidences have shown that the human endogenous hormones can interact with drugs in many ways and affect drug efficacy. The hormone drug interactions (HDI) are essential for drug treatment and precision medicine; therefore, it is essential to understand the hormone-drug associations. Here, we present HormoNet to predict the HDI pairs and their risk level by integrating features derived from hormone and drug target proteins. To the best of our knowledge, this is one of the first attempts to employ deep learning approach for prediction of HDI prediction. Amino acid composition and pseudo amino acid composition were applied to represent target information using 30 physicochemical and conformational properties of the proteins. To handle the imbalance problem in the data, we applied synthetic minority over-sampling technique technique. Additionally, we constructed novel datasets for HDI prediction and the risk level of their interaction. HormoNet achieved high performance on our constructed hormone-drug benchmark datasets. The results provide insights into the understanding of the relationship between hormone and a drug, and indicate the potential benefit of reducing risk levels of interactions in designing more effective therapies for patients in drug treatments. Our benchmark datasets and the source codes for HormoNet are available in: https://github.com/EmamiNeda/HormoNet .

References

Lakkis J, Schroeder A, Su K, Lee M, Bashore A, Reilly M . A multi-use deep learning method for CITE-seq and single-cell RNA-seq data integration with cell surface protein prediction and imputation. Nat Mach Intell. 2023; 4(11):940-952. PMC: 9979929. DOI: 10.1038/s42256-022-00545-w. View

Bakhtiarizadeh M, Rahimi M, Mohammadi-Sangcheshmeh A, Shariati J V, Salami S . PrESOgenesis: A two-layer multi-label predictor for identifying fertility-related proteins using support vector machine and pseudo amino acid composition approach. Sci Rep. 2018; 8(1):9025. PMC: 5998058. DOI: 10.1038/s41598-018-27338-9. View

Ju Z, Wang S . Prediction of citrullination sites by incorporating k-spaced amino acid pairs into Chou's general pseudo amino acid composition. Gene. 2018; 664:78-83. DOI: 10.1016/j.gene.2018.04.055. View

Chowdhury S, Shatabda S, Dehzangi A . iDNAProt-ES: Identification of DNA-binding Proteins Using Evolutionary and Structural Features. Sci Rep. 2017; 7(1):14938. PMC: 5668250. DOI: 10.1038/s41598-017-14945-1. View

Xiong G, Yang Z, Yi J, Wang N, Wang L, Zhu H . DDInter: an online drug-drug interaction database towards improving clinical decision-making and patient safety. Nucleic Acids Res. 2021; 50(D1):D1200-D1207. PMC: 8728114. DOI: 10.1093/nar/gkab880. View

Ahmed S, Muhammod R, Khan Z, Adilina S, Sharma A, Shatabda S . ACP-MHCNN: an accurate multi-headed deep-convolutional neural network to predict anticancer peptides. Sci Rep. 2021; 11(1):23676. PMC: 8654959. DOI: 10.1038/s41598-021-02703-3. 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

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

Reeder A, Attar M, Nazario L, Bathula C, Zhang A, Hochbaum D . Stress hormones reduce the efficacy of paclitaxel in triple negative breast cancer through induction of DNA damage. Br J Cancer. 2015; 112(9):1461-70. PMC: 4453678. DOI: 10.1038/bjc.2015.133. View

10.

Llinares-Lopez F, Berthet Q, Blondel M, Teboul O, Vert J . Deep embedding and alignment of protein sequences. Nat Methods. 2022; 20(1):104-111. DOI: 10.1038/s41592-022-01700-2. View

11.

Hu H, Feng Z, Lin H, Zhao J, Zhang Y, Xu F . Modeling and analyzing single-cell multimodal data with deep parametric inference. Brief Bioinform. 2023; 24(1). DOI: 10.1093/bib/bbad005. View

12.

Liu Z, Dong W, Jiang W, He Z . csDMA: an improved bioinformatics tool for identifying DNA 6 mA modifications via Chou's 5-step rule. Sci Rep. 2019; 9(1):13109. PMC: 6739324. DOI: 10.1038/s41598-019-49430-4. View

13.

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

14.

Zeng W, Zhou X, Willems S, Ammar C, Wahle M, Bludau I . AlphaPeptDeep: a modular deep learning framework to predict peptide properties for proteomics. Nat Commun. 2022; 13(1):7238. PMC: 9700817. DOI: 10.1038/s41467-022-34904-3. View

15.

Wang T, Sun J, Zhao Q . Investigating cardiotoxicity related with hERG channel blockers using molecular fingerprints and graph attention mechanism. Comput Biol Med. 2022; 153:106464. DOI: 10.1016/j.compbiomed.2022.106464. View

16.

Bhadra P, Yan J, Li J, Fong S, Siu S . AmPEP: Sequence-based prediction of antimicrobial peptides using distribution patterns of amino acid properties and random forest. Sci Rep. 2018; 8(1):1697. PMC: 5785966. DOI: 10.1038/s41598-018-19752-w. View

17.

Zheng J, Zhang X, Zhao X, Tong X, Hong X, Xie J . Deep-RBPPred: Predicting RNA binding proteins in the proteome scale based on deep learning. Sci Rep. 2018; 8(1):15264. PMC: 6189057. DOI: 10.1038/s41598-018-33654-x. View

18.

Flint M, Kim G, Hood B, Bateman N, Stewart N, Conrads T . Stress hormones mediate drug resistance to paclitaxel in human breast cancer cells through a CDK-1-dependent pathway. Psychoneuroendocrinology. 2009; 34(10):1533-41. DOI: 10.1016/j.psyneuen.2009.05.008. View

19.

Li X, Zhong C, Wu R, Xu X, Yang Z, Cai S . RIP1-dependent linear and nonlinear recruitments of caspase-8 and RIP3 respectively to necrosome specify distinct cell death outcomes. Protein Cell. 2021; 12(11):858-876. PMC: 8563874. DOI: 10.1007/s13238-020-00810-x. View

20.

Tubiana J, Schneidman-Duhovny D, Wolfson H . ScanNet: an interpretable geometric deep learning model for structure-based protein binding site prediction. Nat Methods. 2022; 19(6):730-739. DOI: 10.1038/s41592-022-01490-7. View