Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{188493,
        author = {TIRUMALA SREE VAISHNAVI and Y. Shashidhar Reddy and T. Sai Kiran Reddy and Dr Ruqsar Zaitoon},
        title = {DEEP DTI – ( PREDICTION OF DRUG TARGET INTERACTION USING DEEP LEARNING )},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {2356-2363},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188493},
        abstract = {The key to modern drug development is to uncover, identify and prepare drug molecular targets. However, it is challenging to widely use classic experimental procedures due to the impact of throughput, precision, and cost. Traditional experiments used to deduce these possible DTIs, or drug-target interactions. Thus, the development of efficient computational techniques to verify the drug-target interaction is crucial. Techniques: We built a deep learning-based model for DTIs prediction. Position Specific Scoring Matrix (PSSM) and Legendre Moment (LM) are used to extract the evolutionary properties of proteins, which are then linked to drug molecular substructure fingerprints to create feature vectors of drug-target couples.Then we utilized the Sparse principal Component Analysis (SPCA) to compress the characteristics of medicines and proteins into a consistent vector space.
Finally, the deep long short-term memory (DeepLSTM) was designed to perform prediction. findings: A considerable improvement in DTIs prediction performance may be noticed on experimental findings, with AUC of 0.9951, 0.9705, 0.9951, 0.9206, respectively, on four classes relevant drug-target datasets. Additionally Preliminary trials demonstrate the significant benefit of the suggested characterisation approach on feature expressiveness and recognition. Additionally, we have demonstrated that the suggested approach can function effectively with tiny datasets.},
        keywords = {},
        month = {December},
        }