Predicting Adverse Drug Reactions of Two-drug Combinations using Structural and Transcriptomic Drug Representations to Train a Artificial Neural Network

Shankar, Susmitha; Bhandari, Ishita; Okou, David T.; Srinivasa, Gowri; Athri, Prashanth

doi:10.1101/2020.06.30.176016

Cited by 2 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their proposed model achieved the highest precision score of 78% to predict side effects and performed the best compared to the KNN and MLP classifiers. Further, Sankar et al [106] identify side effects of drug-pair from the gene expression and chemical structure by employing an artificial neural network model. The authors collected gene expression from LINCS L1000 [70], chemical substructure from DrugBank [44], and side effects obtained from TWOSIDES [94].…”

Section: Supervised Learning Methods Used For Side Effects Predictionmentioning

confidence: 99%

An Extensive Survey on the Use of Supervised Machine Learning Techniques in the Past Two Decades for Prediction of Drug Side Effects

Das

Mazumder

2022

Preprint

View full text Add to dashboard Cite

Side Effects (SE) of drugs are one of the common reasons for drug failure that may halt the whole drug discovery pipeline. Therefore, predicting the side effects of the drug is vital in drug development, discovery, and design. Supervised machine learning-based side effects prediction task has recently received much attention since it reduces time, chemical waste, design complexity, risk of failure, and cost. The advancement of supervised learning approaches for predicting side effects have emerged as essential computational tools. Still, there are several challenges to predict drug side effects. Thus, a near-exhaustive survey is carried out in this paper on the use of supervised machine learning approaches employed in drug side effects prediction in the past two decades. In addition, this paper also summarized the drug descriptor required for the side effects prediction task, commonly utilized drug properties sources, computational models, and their performances. Finally, the research gap, open problems, and challenges for the further supervised learning-based side effects prediction task have been discussed.

show abstract

Section: Supervised Learning Methods Used For Side Effects Predictionmentioning

confidence: 99%

An Extensive Survey on the Use of Supervised Machine Learning Techniques in the Past Two Decades for Prediction of Drug Side Effects

Das

Mazumder

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Browsing or establishing multiple federated queries across the databases is often cumbersome and computationally intensive. Hence, as a single source of information, this well-connected data can be used to discover linkage across heterogeneous resources and can serve as biological knowledge graphs for multiple use cases in bioinformatics (Murali et al, 2018, Sam et al, 2019, Swathi et al, 2020, Shankar et al, 2021. In addition, this can further facilitate machine learning studies on graphs (e.g., link prediction or community detection).…”

Section: Integrated Frameworkmentioning

confidence: 99%

Predicting clinical trial outcomes using drug bioactivities through graph database integration and machine learning

Murali

Muralidhar

Königs

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The ability to estimate the probability of a drug to receive approval in clinical trials provides natural advantages to optimizing pharmaceutical research workflows. Success rates of clinical trials have deep implications to costs, duration of development, and under pressure due to stringent regulatory approval processes. We propose a machine learning approach that can predict the outcome of the trial with reliable accuracies, using biological activities, physicochemical properties of the compounds, target-related features, and NLP-based compound representation. Biological activities have never been used as a predictive feature. We have extracted the drug-disease pair from clinical trials and mapped target(s) to that pair using multiple data sources. Empirical results demonstrate that ensemble learning outperforms independently trained, small-data ML models. We report results and inferences derived from a Random forest classifier with an average accuracy of 93%, and an F1 score of 0.96 for the 'Pass' class. 'Pass' refers to one of the two classes (Pass/ Fail) of all clinical trials and the model performed well in predicting the 'Pass' category. An analysis of the features demonstrates that bioactivity plays an important role in predicting the outcome of a clinical trial. A significant effort has gone into the production of the dataset that, for the first time, integrates clinical trial information with protein targets. All code to map these entities is available through this study, and all data are from publicly available sources. While our model identifies low-lying inferences when biological activities are included, the code to integrate biological activity and target information provide researchers with access to deep curated and proprietary clinical trial databases the ability to get deeper insights, better statistical significance, and capabilities to better predict trial failures.

show abstract

Predicting Adverse Drug Reactions of Two-drug Combinations using Structural and Transcriptomic Drug Representations to Train a Artificial Neural Network

Cited by 2 publications

References 27 publications

An Extensive Survey on the Use of Supervised Machine Learning Techniques in the Past Two Decades for Prediction of Drug Side Effects

An Extensive Survey on the Use of Supervised Machine Learning Techniques in the Past Two Decades for Prediction of Drug Side Effects

Predicting clinical trial outcomes using drug bioactivities through graph database integration and machine learning

Contact Info

Product

Resources

About