Img2Side: A Transfer Learning Based Model for Predicting Drug Side Effects Using 2D Chemical Structural Images
Drug Side Effects (DSE) are inconvenient and inadvertent retorts of the drugs. DSEs impact on public health and healthcare can prove costly. These DSEs can be an important factor in the failure/acceptance of drugs. Every approved drug should be either free from DSEs or these should be minor and repo...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10483078/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841550823000113152 |
|---|---|
| author | Muhammad Asad Arshed Muhammad Ibrahim Shahzad Mumtaz Tenvir Ali Gyu Sang Choi |
| author_facet | Muhammad Asad Arshed Muhammad Ibrahim Shahzad Mumtaz Tenvir Ali Gyu Sang Choi |
| author_sort | Muhammad Asad Arshed |
| collection | DOAJ |
| description | Drug Side Effects (DSE) are inconvenient and inadvertent retorts of the drugs. DSEs impact on public health and healthcare can prove costly. These DSEs can be an important factor in the failure/acceptance of drugs. Every approved drug should be either free from DSEs or these should be minor and reported properly. The drug discovery process should be capable of predicting and preventing these effects in advance. Previously, proposed studies for the prediction/prevention of DSEs utilized the features of 1D drug chemical structures or Natural Language Processing (NLP). Both these techniques required a complex transformation process. In this research authors have proposed a deep learning model, specifically using a transfer learning approach to predict DSEs directly from 2D chemical structure images, eliminating the need for the hefty transformation process of the NLP domain. For this study, a unique dataset is prepared that associates each image (taken from PubChem) with its specific side effects (SIDER). The results are evaluated using Accuracy, Precision, Recall and F-measure. The proposed model showed its dominance with an Accuracy of 73%, Precision of 83%, Recall of 73%, and an F1 score of 75%. The achieved results of the proposed model are compared against established transfer learning models like VGG16, DenseNet121 and some previously used traditional machine learning models like SVM and KNN. The collected results indicate a significant advancement in predicting drug side effects and offer a promising avenue for streamlining the drug development process. |
| format | Article |
| id | doaj-art-18acd846611e46b58f362f4eac196e15 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-18acd846611e46b58f362f4eac196e152025-01-10T00:00:42ZengIEEEIEEE Access2169-35362024-01-0112501845020110.1109/ACCESS.2024.338293610483078Img2Side: A Transfer Learning Based Model for Predicting Drug Side Effects Using 2D Chemical Structural ImagesMuhammad Asad Arshed0https://orcid.org/0000-0002-5583-1253Muhammad Ibrahim1https://orcid.org/0000-0001-5088-9571Shahzad Mumtaz2https://orcid.org/0000-0003-2606-2405Tenvir Ali3https://orcid.org/0000-0002-8095-5346Gyu Sang Choi4https://orcid.org/0000-0002-0854-768XFaculty of Computing, The Islamia University of Bahawalpur, Bahawalpur, PakistanFaculty of Computing, The Islamia University of Bahawalpur, Bahawalpur, PakistanFaculty of Computing, The Islamia University of Bahawalpur, Bahawalpur, PakistanFaculty of Computing, The Islamia University of Bahawalpur, Bahawalpur, PakistanSchool of Computer Science and Engineering, Yeungnam University, Gyeongsan, South KoreaDrug Side Effects (DSE) are inconvenient and inadvertent retorts of the drugs. DSEs impact on public health and healthcare can prove costly. These DSEs can be an important factor in the failure/acceptance of drugs. Every approved drug should be either free from DSEs or these should be minor and reported properly. The drug discovery process should be capable of predicting and preventing these effects in advance. Previously, proposed studies for the prediction/prevention of DSEs utilized the features of 1D drug chemical structures or Natural Language Processing (NLP). Both these techniques required a complex transformation process. In this research authors have proposed a deep learning model, specifically using a transfer learning approach to predict DSEs directly from 2D chemical structure images, eliminating the need for the hefty transformation process of the NLP domain. For this study, a unique dataset is prepared that associates each image (taken from PubChem) with its specific side effects (SIDER). The results are evaluated using Accuracy, Precision, Recall and F-measure. The proposed model showed its dominance with an Accuracy of 73%, Precision of 83%, Recall of 73%, and an F1 score of 75%. The achieved results of the proposed model are compared against established transfer learning models like VGG16, DenseNet121 and some previously used traditional machine learning models like SVM and KNN. The collected results indicate a significant advancement in predicting drug side effects and offer a promising avenue for streamlining the drug development process.https://ieeexplore.ieee.org/document/10483078/Drug side effectsdrug 2D chemical structure imagestransfer learningfine tuningpretrained modelsdeep learning |
| spellingShingle | Muhammad Asad Arshed Muhammad Ibrahim Shahzad Mumtaz Tenvir Ali Gyu Sang Choi Img2Side: A Transfer Learning Based Model for Predicting Drug Side Effects Using 2D Chemical Structural Images IEEE Access Drug side effects drug 2D chemical structure images transfer learning fine tuning pretrained models deep learning |
| title | Img2Side: A Transfer Learning Based Model for Predicting Drug Side Effects Using 2D Chemical Structural Images |
| title_full | Img2Side: A Transfer Learning Based Model for Predicting Drug Side Effects Using 2D Chemical Structural Images |
| title_fullStr | Img2Side: A Transfer Learning Based Model for Predicting Drug Side Effects Using 2D Chemical Structural Images |
| title_full_unstemmed | Img2Side: A Transfer Learning Based Model for Predicting Drug Side Effects Using 2D Chemical Structural Images |
| title_short | Img2Side: A Transfer Learning Based Model for Predicting Drug Side Effects Using 2D Chemical Structural Images |
| title_sort | img2side a transfer learning based model for predicting drug side effects using 2d chemical structural images |
| topic | Drug side effects drug 2D chemical structure images transfer learning fine tuning pretrained models deep learning |
| url | https://ieeexplore.ieee.org/document/10483078/ |
| work_keys_str_mv | AT muhammadasadarshed img2sideatransferlearningbasedmodelforpredictingdrugsideeffectsusing2dchemicalstructuralimages AT muhammadibrahim img2sideatransferlearningbasedmodelforpredictingdrugsideeffectsusing2dchemicalstructuralimages AT shahzadmumtaz img2sideatransferlearningbasedmodelforpredictingdrugsideeffectsusing2dchemicalstructuralimages AT tenvirali img2sideatransferlearningbasedmodelforpredictingdrugsideeffectsusing2dchemicalstructuralimages AT gyusangchoi img2sideatransferlearningbasedmodelforpredictingdrugsideeffectsusing2dchemicalstructuralimages |