ASTI-ALaM AI Researcher presents Cutting-Edge Anticancer Screening Approach at SPIN 2023 Int’lConference

8 May 2023 10:23 AM

Manila, PH - Department of Science and Technology-Advanced Science and Technology Institute’s (DOST-ASTI) AI Researcher Mr. Adrian S. Remigio, Science Research Specialist I of the Research Unit of  ASTI-Advanced Labeling Machine (ASTI-ALaM) Project,  presented his latest research via web conferencing at the 10th International Conference on Signal Processing and Integrated Networks (SPIN 2023) organized by the Department of Electronics and Communications Engineering at Amity University, Noida, India from 23-24 March  2023.

Mr. Adrian S. Remigio, AI Researcher and Science Research Specialist I of the Research Unit of the ASTI-Advanced Labeling Machine (ASTI-ALaM) Project presented his latest research via web conferencing at the 10th International Conference on Signal Processing and Integrated Networks (SPIN 2023) organized by the Department of Electronics and Communications Engineering at Amity University, Noida, India from March 23-24, 2023.

The paper titled “A deep hybrid GNN based on edge-conditioned and graph isomorphism network convolutions for PC-3 anticancer screening” presents an innovative screening approach using a modified deep hybrid Graph Neural Network (GNN) architecture for predicting anticancer response in prostate tumors based on the 2-D molecular structures of molecular compounds.

This study highlights ASTI-ALaM's innovative work on improving the predictive accuracy and capacity of AI models. The modified deep hybrid architecture showed acceptable and improved prediction accuracy compared to simple GNN models, which can be used to aid in the search for anticancer drugs in clinical research.

“During the initial study on the implementation of GNNs in Python, I used practice datasets to test the GNN models. One of the practice datasets that we used was the PC3 anticancer screening. Upon reading some literature on GNNs, I have decided to apply the modified architecture on the practice dataset and promising results were obtained,” Mr. Remigio explained.

Mr. Remigio is focused on studying the application of Graph Neural Networks (GNN) and hybrid Convolutional Neural Networks-Graph Neural Networks (CNN-GNN) for computer vision and finding ways to alleviate catastrophic forgetting in these network architectures. Currently, his research work in the ASTI-ALaM Project is focused on hybrid CNN-GNN models using deep hybrid architecture to develop a novel architecture, the REsNEt-deep CNN-GNN model for land-use mapping. This developed model was shown to outperform the baseline CNN model for land-use mapping applications in aerial images.

 ASTI-ALaM’s Research Unit is working to enhance the predictive accuracy and capacity of AI models and aims to publish papers and provide novel solutions that can be utilized in the repository of AI models. ASTI-ALaM Project's participation in this conference represents a significant milestone in the project’s ongoing research efforts, further solidifying DOST-ASTI’s position as an AI research powerhouse in the country.

ABOUT THE EVENT

SPIN 2023 is technically co-sponsored by the IEEE Computational Intelligence Society and presented papers are expected to be published in the IEEE Xplore journal, a digital library that provides access to scientific and technical content published by the Institute of Electrical and Electronics Engineers (IEEE) and its publishing partners. This conference aimed to bring together scientists, academicians, and industrialists working in the field of signal processing and integrated networks to discuss innovative ideas and promote research work.