Drug-Target Interaction Prediction in Coronavirus Disease 2019 Case Using Deep Semi-Supervised Learning Model

Abstract

Coronavirus disease 2019 (COVID-19) is an infectious disease of the respiratory system that caused a pandemic in 2020. There is still not any effective special treatment to cure it. Drug repositioning is used to find an effective drug for curing new diseases by finding new efficacy of registered drug. The new efficacy can be conducted by elaborating the interactions between compounds and proteins (DTI). Deep Semi-Supervised Learning (DSSL) is used to overcome the lack of DTI information. DSSL utilizes unsupervised learning algorithms such as Stacked Auto Encoder (SAE) as pre-training for initializing weights on the Deep Neural Network (DNN). This study uses DSSL with a feature-based chemogenomics approach on the data resulted from the exploration of potential anti-coronavirus treatment. This study finds that the use of fingerprints for compound features and Dipeptide Composition (DC) for protein features gives the best results on accuracy (0.94), recall (0.83), precision (0.817), F-measure (0.822), and AUROC (0.97). From the test data predictions, 1766 and 929 positive interactions are found on the test data and herbal compounds, respectively. Keywords-coronavirus disease 2019, drug repositioning, deep semi-supervised learning, stacked autoencoder, deep neural network II. DEEP SEMI-SUPERVISED LEARNING FOR DTIResearch on drug repositioning is based on the fact that most drug compounds can activate or inhibit the biological functions of the target protein. This creates the needs to develop a DTI identification system [11]. DTI identification

Introductory Chapter: The Emerging Corner of the Omics Studies for Rational Drug Design

“…Parallelization in the Drug Biomanufacturing with incremental optimization will facilitate the pipeline of therapeutic agent development [71,72]. Such biomanufacturing efforts will be enhanced with the implementation of Artificial Intelligence (AI) for massive drug screening that could be beneficial for multicomponents drug lead such as herbal medication, and machine-learning based implementation for such pipelines has been devised accordingly in COVID-19 leads development [73][74][75][76]. The extensive utilization of the common data science methods in bioinformatics, such as machine learning, will eventually provide insight that the management of life sciences data requires more than just becoming application users [77].…”

Prediction of Drug-Target Interaction Using Random Forest in Coronavirus Disease 2019 Case

“…This dataset contains pairs of compounds and proteins that have interaction. In the model building process to predict the interaction between compounds and proteins, the model requires information on pairs of protein compounds that are known to have interactions and those whose interactions are unknown [5]. Therefore, data transformation is done by pairing all interaction pairs of unique protein IDs and compound IDs.…”

“…Drug repurposing is a process to identify new efficacy for existing drugs and is considered an efficient and economical approach to drug development [4]. Research in drug repurposing can be done by observing the interactions of drug compounds with protein related to a disease (Drug-Target Interaction or DTI), then build a model to predict the new drug-target interactions with unknown interactions previously [5].…”

Screening of Potential Indonesia Herbal Compounds Based on Multi-Label Classification for 2019 Coronavirus Disease

“…On 11 March 2020, WHO declared COVID-19 a pandemic that has affected the world's socioeconomic conditions globally. In addition, the highly contagious nature of the SARS-CoV-2 virus also worsened the impact of COVID-19 [3]. As of 9 October 2021, COVID-19 cases reached 237,995,075 cases globally, with the death toll reaching 4,857,370 people (https://www.worldometers.info/coronavirus accessed on 9 October 2021).…”

“…In drug repurposing, the drug discovery process is conducted by identifying new efficacy for approved drugs, and it is considered an efficient and economical approach [5]. Research in drug repurposing can be done by observing the interactions of drug compounds with protein related to a disease (drug-target interaction or DTI), then predicting the new drug-target interactions [3].…”