Proceedings of the First International Conference on Artificial Intelligence, Smart Technologies and Communications (AISTC 2025)

<Previous Article In Volume
Next Article In Volume>

DualGen-GAT: A Dual-Generation Pipeline for Molecular Property Prediction

Authors
Latefa Oulladji1, *, Nor-El-Houda Bekhti2, Mouna Saadallah1, Zakaria Guelli2
1Evolutionary Engineering and Distributed Information Systems Laboratory, Department of Computer Science, Djillali Liabes University of Sidi Bel Abbes, Sidi Bel Abbès, Algeria, 22000
2Department of Computer Science, Djillali Liabes University of Sidi Bel Abbes, Sidi Bel Abbès, Algeria, 22000
*Corresponding author. Email: latifa.oulladji@univ-sba.dz
Corresponding Author
Latefa Oulladji
Available Online 5 August 2025.
DOI
10.2991/978-94-6463-805-9_12How to use a DOI?
Keywords
Drug discovery; Deep learning; LSTM; VAE; GAT
Abstract

The drug research and discovery field has heavily contributed to medicine throughout the years, providing more treatment options and a variety of new molecule combinations. However, Traditional methods are often characterized by extensive trial, error, and lengthy timelines. This led to the need to pursue more automated and advanced methodologies. The integration of deep learning techniques and different computational approaches has promised greater efficiency and accuracy in discovering new molecular drugs. Among these methodologies, Long Short-Term Memory (LSTM) networks, Variational Autoencoders (VAE), and Graph Attention Networks (GAT) have proven to be powerful tools for modeling complex biochemical interactions and predicting molecular properties. This paper explores the use of these techniques to produce new molecular structures as drug candidates and apply deep learning models on them to predict their pharmacological properties and implement visualization tools to represent these molecules along with their predicted properties. Experimental results demonstrate the strengths of the techniques used, exceeding the accuracy of 90% on test set.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the First International Conference on Artificial Intelligence, Smart Technologies and Communications (AISTC 2025)
Series
Advances in Intelligent Systems Research
Publication Date
5 August 2025
ISBN
978-94-6463-805-9
ISSN
1951-6851
DOI
10.2991/978-94-6463-805-9_12How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Latefa Oulladji
AU  - Nor-El-Houda Bekhti
AU  - Mouna Saadallah
AU  - Zakaria Guelli
PY  - 2025
DA  - 2025/08/05
TI  - DualGen-GAT: A Dual-Generation Pipeline for Molecular Property Prediction
BT  - Proceedings of the First International Conference on Artificial Intelligence, Smart Technologies and Communications (AISTC 2025)
PB  - Atlantis Press
SP  - 94
EP  - 103
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-805-9_12
DO  - 10.2991/978-94-6463-805-9_12
ID  - Oulladji2025
ER  -