REAL

MOLECULE CLASSIFICATION USING VISUALIZATION AND CONVOLUTIONAL NEURAL NETWORK

Lakatos, István and Hajdu, András and Harangi, Balázs (2021) MOLECULE CLASSIFICATION USING VISUALIZATION AND CONVOLUTIONAL NEURAL NETWORK. In: IEEE 18th International Symposium on Biomedical Imaging.

[img] Text
ISBI_2021___Molecule_classification_using_visualization_and_convolutional_neural_network.pdf - Published Version
Restricted to Registered users only

Download (653kB)

Abstract

In this paper, we propose a procedure that provides solid performance regarding molecule classification. Our solution can predict with high accuracy the toxicity and activity of different unknown molecules based on their compounds and structural information. As for the methodological contribution, our approach takes the commonly used SMILES strings and generates the three dimensional model of the investigated molecule. After that, we project this model to the two-dimensional plane from different points of view and a pre-trained convolutional neural network classifies all of these generated 2D images. The final class label is derived as an ensemble of these classification outputs. For the ensemble of class labels and the applied visualization method, we have reached 90:66% classification accuracy with ROC-AUC 0:9629.

Item Type: Conference or Workshop Item (Poster)
Subjects: T Technology / alkalmazott, műszaki tudományok > T2 Technology (General) / műszaki tudományok általában
Depositing User: Dr Balazs Harangi
Date Deposited: 28 Sep 2021 21:15
Last Modified: 28 Sep 2021 21:15
URI: http://real.mtak.hu/id/eprint/131183

Actions (login required)

Edit Item Edit Item