DeepSide: A Deep Learning Approach for Drug Side Effect Prediction

Date

2022-01-01

Author

Uner, Onur Can
Kuru, Halil Ibrahim
Cinbiş, Ramazan Gökberk
Tastan, Oznur
Cicek, Ercument

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

271
views

0
downloads

IEEEDrug failures due to unforeseen adverse effects at clinical trials pose health risks for the participants and lead to substantial financial losses. Side effect prediction algorithms have the potential to guide the drug design process. LINCS L1000 dataset provides a vast resource of cell line gene expression data perturbed by different drugs and creates a knowledge base for context specific features. The state-of-the-art approach that aims at using context specific information relies on only the high-quality experiments in LINCS L1000 and discards a large portion of the experiments. Here, we aim to boost the prediction performance by utilizing this data to its full extent. We experiment with 5 deep learning architectures. We find that a multi-modal architecture produces the best predictive performance when drug chemical structure (CS), and drug-perturbed gene expression profiles (GEX) are used. We observe that the CS is more informative than the GEX. A convolutional neural network-based model that uses only SMILES string representation of drugs provides 13.0% macro-AUC and 3.1% micro-AUC improvements over the state-of-the-art. We also show that the model is able to predict side effect-drug pairs that are reported in the literature but was missing in the ground truth side effect dataset.

Subject Keywords

Deep Learning, Drug Side Effect Prediction, LINCS

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85122880871&origin=inward
https://hdl.handle.net/11511/97534

Journal

IEEE/ACM Transactions on Computational Biology and Bioinformatics

DOI

https://doi.org/10.1109/tcbb.2022.3141103

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Differential gene expression analysis related to extracellular matrix components in drug-resistant RPMI-8226 cell line Mutlu, Pelin; Gündüz, Ufuk (Elsevier BV, 2012-4) Drug resistance remains a major obstacle to the successful use of chemotherapeutic drugs for many types of cancers including multiple myeloma. It is becoming increasingly apparent that tumor microenvironment could provide a shelter to malignant plasma cells that allow their survival after initial drug exposure. This study demonstrates alterations in gene expression levels of several extracellular matrix (ECM) components in prednisone, vincristine and melphalan-resistant RPMI-8226 myeloma cells. Resistant RP...
MDeePred: Novel multi-channel protein featurization for deep learning-based binding affinity prediction in drug discovery Rifaioglu, A.S.; Atalay, R. Cetin; Kahraman, Deniz Cansen; DOĞAN, TUNCA; Martin, M.; Atalay, Mehmet Volkan (2021-03-01) Motivation: Identification of interactions between bioactive small molecules and target proteins is crucial for novel drug discovery, drug repurposing and uncovering off-target effects. Due to the tremendous size of the chemical space, experimental bioactivity screening efforts require the aid of computational approaches. Although deep learning models have been successful in predicting bioactive compounds, effective and comprehensive featurization of proteins, to be given as input to deep neural networks, r...
Surface functionalization of SBA - 15 particles for amoxicillin delivery Sevimli, Filiz F; Yılmaz, Ayşen; Department of Chemistry (2011) There are several studies in order to control drug delivery, decrease the toxicity of drugs and also for novel biomedical applications. It is necessary to be able to control the release of the drug within the body by using drug delivery systems. Mesoporous silica compounds have only been discovered twenty years ago and they have already attracted many researchers to study these materials for several applications. SBA-15 particles have a highly ordered regular structure and are a good matrix for guest-host a...
Structural effects of simvastatin on liver rate tissue: Fourier transform infrared and Raman microspectroscopic studies Garip, Sebnem; Bayari, Sevgi Haman; Severcan, Mete; Abbas, Sherif; Lednev, Igor K.; Severcan, Feride (2016-02-01) Simvastatin is one of the most frequently prescribed statins because of its efficacy in the treatment of hypercholesterolemia, reducing cardiovascular risk and related mortality. Determination of its side effects on different tissues is mandatory to improve safe use of this drug. In the present study, the effects of simvastatin on molecular composition and structure of healthy rat livers were investigated by Fourier transform infrared and Raman imaging. Simvastatin-treated groups received 50 mg/kg/day simva...
Investigation of the Therapeutic Effects of Palbociclib Conjugated Magnetic Nanoparticles on Different Types of Breast Cancer Cell Lines Parsian, Maryam; MUTLU, PELİN; Taghavi Pourianazar, Negar; Yalcin Azarkan, Serap; Gündüz, Ufuk (2023-01-01) Introduction: Drug targeting and controlled drug release systems in cancer treatment have many advantages over conventional chemotherapy in terms of limiting systemic toxicity, side effects, and overcoming drug resistance. Methods and Results: In this paper, fabricating nanoscale delivery system composed of magnetic nanoparticles (MNPs) covered with poly-amidoamine (PAMAM) dendrimers and using its advantages were fully used to help the chemotherapeutic drug, Palbociclib, effectively reach tumors, specifical...

Citation Formats

O. C. Uner, H. I. Kuru, R. G. Cinbiş, O. Tastan, and E. Cicek, “DeepSide: A Deep Learning Approach for Drug Side Effect Prediction,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, pp. 0–0, 2022, Accessed: 00, 2022. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85122880871&origin=inward.