1 Assistant Professor, Department of Computer Science and Engineering, Sri Padmavati mahila Vishwavidyalayam( Women's University), Tirupati, Andhra Pradesh -517502
2*(corresponding author) Assistant professor, Department of Computer Science and Engineering, Sri Padmavati mahila Vishwavidyalayam( Women's University), Tirupati, Andhra Pradesh -517502
3 Sr.Assistant Professor, New Horizon College, Marathahalli, Bengaluru, Karnataka-560130, India
4 Assistant Professor, Department of computer science and engineering, Aditya University, Surampalem-533437, Andhra Pradesh, India.
5 Assistant Professor, Department of Computer Science, Government Arts and Science College, Veerapandi, Theni, Tamilnadu, India.
6 Assistant Professor, Department of Mathematics, Erode sengunthar Engineering College, Thudupathi, perundurai(TK)-638057, Erode, Tamilnadu, India.
7 Assistant Professor (Sl.G), Department of Mathematics, Kongu Engineering College, Perundurai
8 Assistant professor of Chemistry, Department of chemistry, V.S.B Engineering college Autonomous, Karudayampalayam po, Karur 639111
9 Assistant Professor, Dept.of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, GreenFields, Vaddeswaram, Guntur Dist-522302, Andhra Pradesh, India.
10 Assistant Professor, Department of Computer Science, Government Arts and Science College, Veerapandi, Theni, Tamilnadu, India.
The integration of artificial intelligence into pharmaceutical research has ushered in a transformative era for drug discovery and development. Among various deep learning architectures, Convolutional Neural Networks (CNNs) have emerged as particularly powerful tools for modeling complex biological and chemical data. This paper provides a comprehensive review of CNN-based approaches in drug discovery, examining their applications in drug-target interaction prediction, adverse drug reaction forecasting, and de novo drug design. Through a systematic analysis of recent literature and experimental studies, we demonstrate that CNN architectures achieve superior performance across multiple pharmaceutical applications, with drug-target interaction prediction accuracies reaching 93-95% and adverse drug reaction detection rates of 78%. The review synthesizes findings from 2018-2025, highlighting how CNNs effectively extract spatial patterns from molecular representations, identify critical features from protein sequences, and integrate with complementary architectures such as graph neural networks and long short-term memory networks. We also address key challenges including data quality limitations, model interpretability concerns, and regulatory integration pathways. This paper concludes by outlining future research directions, emphasizing the potential of hybrid architectures, multi-modal learning, and explainable AI in advancing CNN-driven drug discovery toward clinical implementation.
Keywords: Convolutional Neural Networks, drug discovery, drug-target interaction, deep learning, pharmaceutical AI, adverse drug reaction prediction
How to cite this article: Anusha D, Uma B, Deviprasad S, Nagalakshmidevi J, Vengatesh T, Kasthuri C, Yamuna V, Brindha G, Cheekati V, Anbuselvan B, Convolutional Neural Networks For Advanced Drug Discovery And Development. Int J Drug Deliv Technol. 2026;16(5s): 883-894. DOI: 10.25258/ijddt.16.5s.107
Source of support: Nil.
Conflict of interest: None