A CNN2D-EXTENDED GRAPH FRAMEWORK FOR ACCURATE DETECTION OF DRUG–DRUG INTERACTION SIDE EFFECTS

Chintapalli Prasanna, Dr.R. Srinivas

Abstract


Adverse Drug Reactions (ADRs) caused by drug-drug interactions remain a major challenge in modern healthcare. The proposed study introduces an advanced method using Graph Neural Networks (GNNs) and Self-Supervised Learning to predict side effects before a drug reaches the market. In this model, each drug’s molecular structure is represented as a graph of atoms and bonds, allowing accurate analysis of chemical interactions. To further enhance performance, an extension model using CNN2D is applied, which extracts two-dimensional features from drug data to improve accuracy and reduce overfitting. The proposed system was tested on the TwoSides and DrugBank datasets, achieving remarkable accuracy of up to 99.87%. This hybrid approach not only improves predictive efficiency but also provides a scientific method for early detection of ADRs, reducing patient risks and healthcare costs. The model lays a foundation for future research combining graph and convolutional neural techniques in pharmacology.

References


M. W. Al Nabki, E. Fidalgo, E. Alegre, and I. de Paz, ‘‘Classifying illegal activities on tor network based on Web textual contents,’’ in Proc. 15th Conf. Eur. Chapter Assoc. Comput. Linguistics, vol. 4, 2017, pp. 35–43, doi: 10.18653/v1/E17-1004.

G. Cascavilla, D. A. Tamburri, and W.-J. Van Den Heuvel, ‘‘Cybercrime threat intelligence: A systematic multi-vocal literature review,’’ Comput. Secur., vol. 105, Jun. 2021, Art. no. 102258, doi: 10.1016/j.cose.2021.102258.

J. Saleem, R. Islam, and M. A. Kabir, ‘‘The anonymity of the dark Web: A survey,’’ IEEE Access, vol. 10, pp. 33628–33660, 2022, doi: 10.1109/ACCESS.2022.3161547.

M. Balduzzi and V. Ciancaglini, ‘‘Cybercrime in the deep web,’’ Black Hat, Amsterdam, The Netherlands, Tech. Rep., 2015.

S. RahamatBasha and J. K. Rani, ‘‘A comparative approach of dimensionality reduction techniques in text classification,’’ Eng., Technol. Appl. Sci. Res., vol. 9, no. 6, pp. 4974–4979, Dec. 2019, doi: 10.48084/etasr.3146.

K. N. Singh, S. D. Devi, H. M. Devi, and A. K. Mahanta, ‘‘A novel approach for dimension reduction using word embedding: An enhanced text classification approach,’’ Int. J. Inf. Manage. Data Insights, vol. 2, no. 1, Apr. 2022, Art.no. 100061, doi: 10.1016/j.jjimei.2022.100061.

W. Alkhatib, C. Rensing, and J. Silberbauer, ‘‘Multi-label text classification using semantic features and dimensionality reduction with autoencoders,’’ in Proc. 1st Int. Conf. Lang., Data, Knowl., 2017, pp. 380–394, doi: 10.1007/978-3-319-59888-8_32.

M. Umer, Z. Imtiaz, S. Ullah, A. Mehmood, G. S. Choi, and B.-W. On, ‘‘Fake news stance detection using deep learning architecture (CNN-LSTM),’’ IEEE Access, vol. 8, pp. 156695–156706, 2020, doi: 10.1109/ACCESS.2020.3019735.

R. Basheer and B. Alkhatib, ‘‘Threats from the dark: A review over dark Web investigation research for cyber threat intelligence,’’ J. Comput. Netw.Commun., vol. 2021, pp. 1–21, Dec. 2021, doi: 10.1155/2021/1302999.

A. Alharbi, M. Faizan, W. Alosaimi, H. Alyami, A. Agrawal, R. Kumar, and R. A. Khan, ‘‘Exploring the topological properties of the tor dark Web,’’ IEEE Access, vol. 9, pp. 21746–21758, 2021, doi: 10.1109/ACCESS.2021.3055532.

L. Ouyang and Y. Zhang, ‘‘Phishing Web page detection with HTMLlevel graph neural network,’’ in Proc. IEEE 20th Int. Conf. Trust, Secur.Privacy Comput.Commun. (TrustCom), Oct. 2021, pp. 952–958, doi: 10.1109/TrustCom53373.2021.00133.

H. Alnabulsi and R. Islam, ‘‘Identification of illegal forum activities inside the dark net,’’ in Proc. Int. Conf. Mach. Learn.Data Eng. (iCMLDE), Dec. 2018, pp. 22–29.

D. Hayes, F. Cappa, and J. Cardon, ‘‘A framework for more effective dark Web marketplace investigations,’’ Information, vol. 9, no. 8, p. 186, Jul. 2018, doi: 10.3390/info9080186.

M. W. Al-Nabki, E. Fidalgo, E. Alegre, and L. Fernández-Robles, ‘‘ToRank: Identifying the most influential suspicious domains in the tor network,’’ Expert Syst. Appl., vol. 123, pp. 212–226, Jun. 2019, doi: 10.1016/j.eswa.2019.01.029.

M. W. Al Nabki, E. Fidalgo, E. Alegre, and D. Chaves, ‘‘Supervised ranking approach to identify infLuential websites in the darknet,’’ Int. J. Speech Technol., vol. 53, no. 19, pp. 22952–22968, Oct. 2023, doi: 10.1007/s10489-023-04671-9.

T. Sabbah, A. Selamat, M. H. Selamat, R. Ibrahim, and H. Fujita, ‘‘Hybridized term-weighting method for dark Web classification,’’ Neurocomputing, vol. 173, pp. 1908–1926, Jan. 2016, doi: 10.1016/j.neucom.2015.09.063.

S. He, Y. He, and M. Li, ‘‘Classification of illegal activities on the dark Web,’’ in Proc. 2nd Int. Conf. Inf. Sci. Syst., Mar. 2019, pp. 73–78, doi: 10.1145/3322645.3322691.

S. Nazah, S. Huda, J. H. Abawajy, and M. M. Hassan, ‘‘An unsupervised model for identifying and characterizing dark Web forums,’’ IEEE Access, vol. 9, pp. 112871–112892, 2021, doi: 10.1109/ACCESS.2021.3103319.

R. Li, S. Chen, J. Yang, and E. Luo, ‘‘Edge-based detection and classification of malicious contents in tor darknet using machine learning,’’ Mobile Inf. Syst., vol. 2021, pp. 1–13, Nov. 2021, doi: 10.1155/2021/8072779.

G. Cascavilla, G. Catolino, F. Ebert, D. A. Tamburri, and W. J. van den Heuvel, ‘‘‘When the code becomes a crime scene’ towards dark threat intelligence with software quality metrics,’’ in Proc. IEEE Int. Conf. Softw.Maintenance Evol. (ICSME), Oct. 2022, pp. 439–443, doi: 10.1109/ICSME55016.2022.00055.


Full Text: PDF [Full Text]

Refbacks

  • There are currently no refbacks.


Copyright © 2013, All rights reserved.| ijseat.com

Creative Commons License
International Journal of Science Engineering and Advance Technology is licensed under a Creative Commons Attribution 3.0 Unported License.Based on a work at IJSEat , Permissions beyond the scope of this license may be available at http://creativecommons.org/licenses/by/3.0/deed.en_GB.

Â