scholarly journals Deep Learning Prediction of Adverse Drug Reactions in Drug Discovery Using Open TG–GATEs and FAERS Databases

2021 ◽  
Vol 1 ◽  
Author(s):  
Attayeb Mohsen ◽  
Lokesh P. Tripathi ◽  
Kenji Mizuguchi
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Adverse Drug Reactions ◽  
Predictive Models ◽  
Prediction Models ◽  
Expression Profiles ◽  
Fine Tuning ◽  
Machine Learning Techniques ◽  
Drug Reactions ◽  
Wide Range

Machine learning techniques are being increasingly used in the analysis of clinical and omics data. This increase is primarily due to the advancements in Artificial intelligence (AI) and the build-up of health-related big data. In this paper we have aimed at estimating the likelihood of adverse drug reactions or events (ADRs) in the course of drug discovery using various machine learning methods. We have also described a novel machine learning-based framework for predicting the likelihood of ADRs. Our framework combines two distinct datasets, drug-induced gene expression profiles from Open TG–GATEs (Toxicogenomics Project–Genomics Assisted Toxicity Evaluation Systems) and ADR occurrence information from FAERS (FDA [Food and Drug Administration] Adverse Events Reporting System) database, and can be applied to many different ADRs. It incorporates data filtering and cleaning as well as feature selection and hyperparameters fine tuning. Using this framework with Deep Neural Networks (DNN), we built a total of 14 predictive models with a mean validation accuracy of 89.4%, indicating that our approach successfully and consistently predicted ADRs for a wide range of drugs. As case studies, we have investigated the performances of our prediction models in the context of Duodenal ulcer and Hepatitis fulminant, highlighting mechanistic insights into those ADRs. We have generated predictive models to help to assess the likelihood of ADRs in testing novel pharmaceutical compounds. We believe that our findings offer a promising approach for ADR prediction and will be useful for researchers in drug discovery.

scholarly journals Predicting adverse drug reaction outcomes with machine learning

2018 ◽  
Vol 5 (3) ◽  
pp. 901 ◽  
Author(s):  
Andy W. Chen
Keyword(s):  
Machine Learning ◽  
Adverse Drug Reactions ◽  
Predictive Models ◽  
Safety Issue ◽  
Adverse Event Reporting System ◽  
Patient Characteristics ◽  
Learning Models ◽  
Drug Reactions ◽  
Drug Safety Issue ◽  
Machine Learning Models

Background: Adverse drug reactions are a drug safety issue affecting more than two million people in the U.S. annually. The Food and Drug Administration (FDA) maintains a comprehensive database of adverse drug reactions reported known as FAERS (FDA adverse event reporting system), providing a valuable resource for studying factors associated with ADRs. The goal of the project is to build predictive models to predict the outcome given patient characteristics and drug usage. The results can be valuable for health care practitioners by offering new knowledge on adverse drug reactions which can be used to improve decision making related to drug prescriptions.Methods: In this paper I present and discuss results from machine learning models used to predict outcomes of ADRs. Machine learning models are a popular set of models for prediction. They have gained attention recently and have been used in a variety of fields. They can be trained on existing data and retrained when new data become available. The trained models are then used to make predictions.Results: I find that the supervised learning models are work similarly within groups, with accuracy between 65% and 75% for predicting deaths and 70% to 75% for predicting hospitalizations. Across groups the models predict hospitalizations better than deaths.Conclusions: The predictive models I built achieve good accuracy. The results can potentially be improved when more data become available in the future.

scholarly journals Proposed Improvements for Automated Chemical Safety Evaluations Using In-Silico Techniques

2020 ◽  
Author(s):  
Bryan Jordan
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Chemical Space ◽  
Machine Learning Techniques ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Chemical Safety ◽  
Adversarial Networks ◽  
Wide Range ◽  
Traditional Drug

The vastness of chemical-space constrains traditional drug-discovery methods to the organic laws that are guiding the chemistry involved in filtering through candidates. Leveraging computing with machine-learning to intelligently generate compounds that meet a wide range of objectives can bring significant gains in time and effort needed to filter through a broad range of candidates. This paper details how the use of Generative-Adversarial-Networks, novel machine learning techniques to format the training dataset and the use of quantum computing offer new ways to expedite drug-discovery.

A Pharmaco-Cybernetics Approach to Patient Safety

2016 ◽  
pp. 1445-1464
Author(s):  
Kevin Yi-Lwern Yap
Keyword(s):  
Machine Learning ◽  
Patient Safety ◽  
Cancer Patients ◽  
Adverse Drug Reactions ◽  
Principal Component ◽  
Machine Learning Techniques ◽  
Drug Reactions ◽  
Internet Applications ◽  
Case Examples ◽  
Learning Techniques

Pharmaco-cybernetics is an upcoming interdisciplinary field that supports our use of medicines and drugs through the combined use of computational technologies and techniques with human-computer-environment interactions to reduce or prevent drug-related problems. The advent of pharmaco-cybernetics has led to the development of various software, tools, and Internet applications that can be used by healthcare practitioners to deliver optimum pharmaceutical care and health-related outcomes. Patients are becoming more informed through health information on the Internet, which empowers them to better participate in the management of their own conditions. Focusing on patients with cancer, this chapter describes the use of a pharmaco-cybernetics approach to identify clinically relevant predictors of two debilitating adverse drug reactions, which are a cause of patient safety – chemotherapy-induced nausea and vomiting and febrile neutropenia. The early identification of such clinical predictors enables clinicians to prevent or reduce the occurrence of adverse drug reactions in cancer patients undergoing chemotherapy through appropriate management strategies. The computational methods used in this approach involve two unsupervised machine-learning techniques – principal component and multiple correspondence analyses. Using two case examples, this chapter shows the potential of machine-learning techniques for identifying patients who are at greater risks of these adverse drug reactions, thus enhancing patient safety. This chapter also aims to increase the awareness among healthcare professionals and clinician-scientists about the usefulness of such techniques in clinical patient populations, so that these can be considered as part of clinical care pathways to enhance patient safety and effectively manage cancer patients on chemotherapy.

A Pharmaco-Cybernetics Approach to Patient Safety

2014 ◽  
pp. 179-197
Author(s):  
Kevin Yi-Lwern Yap
Keyword(s):  
Machine Learning ◽  
Patient Safety ◽  
Cancer Patients ◽  
Adverse Drug Reactions ◽  
Principal Component ◽  
Machine Learning Techniques ◽  
Drug Reactions ◽  
Internet Applications ◽  
Case Examples ◽  
Learning Techniques

Pharmaco-cybernetics is an upcoming interdisciplinary field that supports our use of medicines and drugs through the combined use of computational technologies and techniques with human-computer-environment interactions to reduce or prevent drug-related problems. The advent of pharmaco-cybernetics has led to the development of various software, tools, and Internet applications that can be used by healthcare practitioners to deliver optimum pharmaceutical care and health-related outcomes. Patients are becoming more informed through health information on the Internet, which empowers them to better participate in the management of their own conditions. Focusing on patients with cancer, this chapter describes the use of a pharmaco-cybernetics approach to identify clinically relevant predictors of two debilitating adverse drug reactions, which are a cause of patient safety – chemotherapy-induced nausea and vomiting and febrile neutropenia. The early identification of such clinical predictors enables clinicians to prevent or reduce the occurrence of adverse drug reactions in cancer patients undergoing chemotherapy through appropriate management strategies. The computational methods used in this approach involve two unsupervised machine-learning techniques – principal component and multiple correspondence analyses. Using two case examples, this chapter shows the potential of machine-learning techniques for identifying patients who are at greater risks of these adverse drug reactions, thus enhancing patient safety. This chapter also aims to increase the awareness among healthcare professionals and clinician-scientists about the usefulness of such techniques in clinical patient populations, so that these can be considered as part of clinical care pathways to enhance patient safety and effectively manage cancer patients on chemotherapy.

scholarly journals Feature Selection for Breast Cancer Detection using Machine Learning Algorithms

2019 ◽  
Vol 8 (9) ◽  
pp. 2080-2083
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Neural Networks ◽  
Cancer Detection ◽  
Predictive Models ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Cancer Type ◽  
Wide Range ◽  
Logistic Regression Algorithm

Cancer has been portrayed as a heterogeneous disease comprising of a wide range of subtypes. The early diagnosis of a cancer type is very important to determine the course of medical treatment required by the patient. The significance of classifying cancerous cells into benign or malignant has driven many research studies, in the biomedical and the bioinformatics field. In the past years researchers have been encouraged to use different machine learning (ML) techniques for cancer detection, as well as prediction of survivability and recurrence. What's more, ML instruments can be used to distinguish key highlights from complex datasets and uncover their significance. An assortment of these procedures, including Artificial Neural Networks (ANNs), Bayesian Networks (BNs), Random Forest Methods (RVMs) and Decision Trees (DTs) has been usually used in cancer research for the development of predictive models, resulting in successful and exact decision making. Although it is obvious that the usage of machine learning techniques can enhance our comprehension of cancer detection, progression, recurrence and survivability, a proper level of accuracy is required for these strategies to be considered in the ordinary clinical practice. The predictive models talked about here depend on different administered ML strategies and on various input features and data samples. We have used Naïve-Bayes classifier, Neural Networks method, Decision Tree and Logistic Regression algorithm to detect the type of breast cancer (Benign or Malignant) and selection of features which are more relevant for prediction. We have made a comparative study to find out the best algorithm of the above four, for prediction of cancer type. With a high level of accuracy, any of these methods can be used to predict the type of breast cancer of any particular patient

Molecular Docking for Prediction and Interpretation of Adverse Drug Reactions

2018 ◽  
Vol 21 (5) ◽  
pp. 314-322 ◽  
Author(s):  
Heng Luo ◽  
Achille Fokoue-Nkoutche ◽  
Nalini Singh ◽  
Lun Yang ◽  
Jianying Hu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Molecular Docking ◽  
Adverse Drug Reactions ◽  
Prediction Models ◽  
Structural Information ◽  
Characteristic Curve ◽  
Drug Reactions ◽  
Drug Molecules ◽  
Human Proteins ◽  
Underlying Mechanisms

Aim and Objective: Adverse drug reactions (ADRs) present a major burden for patients and the healthcare industry. Various computational methods have been developed to predict ADRs for drug molecules. However, many of these methods require experimental or surveillance data and cannot be used when only structural information is available. Materials and Methods: We collected 1,231 small molecule drugs and 600 human proteins and utilized molecular docking to generate binding features among them. We developed machine learning models that use these docking features to make predictions for 1,533 ADRs. Results: These models obtain an overall area under the receiver operating characteristic curve (AUROC) of 0.843 and an overall area under the precision-recall curve (AUPR) of 0.395, outperforming seven structural fingerprint-based prediction models. Using the method, we predicted skin striae for fluticasone propionate, dermatitis acneiform for mometasone, and decreased libido for irinotecan, as demonstrations. Furthermore, we analyzed the top binding proteins associated with some of the ADRs, which can help to understand and/or generate hypotheses for underlying mechanisms of ADRs. Conclusion: Machine learning combined with molecular docking can help to predict ADRs for drug molecules and provide possible explanations for the ADR mechanisms.

scholarly journals Application of network link prediction in drug discovery

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Khushnood Abbas ◽  
Alireza Abbasi ◽  
Shi Dong ◽  
Ling Niu ◽  
Laihang Yu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Link Prediction ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Biomedical Data ◽  
Learning Approaches ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Wide Range

Abstract Background Technological and research advances have produced large volumes of biomedical data. When represented as a network (graph), these data become useful for modeling entities and interactions in biological and similar complex systems. In the field of network biology and network medicine, there is a particular interest in predicting results from drug–drug, drug–disease, and protein–protein interactions to advance the speed of drug discovery. Existing data and modern computational methods allow to identify potentially beneficial and harmful interactions, and therefore, narrow drug trials ahead of actual clinical trials. Such automated data-driven investigation relies on machine learning techniques. However, traditional machine learning approaches require extensive preprocessing of the data that makes them impractical for large datasets. This study presents wide range of machine learning methods for predicting outcomes from biomedical interactions and evaluates the performance of the traditional methods with more recent network-based approaches. Results We applied a wide range of 32 different network-based machine learning models to five commonly available biomedical datasets, and evaluated their performance based on three important evaluations metrics namely AUROC, AUPR, and F1-score. We achieved this by converting link prediction problem as binary classification problem. In order to achieve this we have considered the existing links as positive example and randomly sampled negative examples from non-existant set. After experimental evaluation we found that Prone, ACT and $$LRW_5$$ L R W 5 are the top 3 best performers on all five datasets. Conclusions This work presents a comparative evaluation of network-based machine learning algorithms for predicting network links, with applications in the prediction of drug-target and drug–drug interactions, and applied well known network-based machine learning methods. Our work is helpful in guiding researchers in the appropriate selection of machine learning methods for pharmaceutical tasks.

A Data-Driven Machine Learning Approach to Predict the Natural Gas Density of Pure and Mixed Hydrocarbons

2021 ◽  
pp. 1-27
Author(s):  
Zeeshan Tariq ◽  
Amjed Hassan ◽  
Umair Bin Waheed ◽  
Mohamed Mahmoud ◽  
Dhafer Al-Shehri ◽  
...  
Keyword(s):  
Machine Learning ◽  
Natural Gas ◽  
Prediction Models ◽  
Estimation Error ◽  
Machine Learning Techniques ◽  
Coefficient Of Determination ◽  
Reduced Pressure ◽  
Gas Density ◽  
Wide Range ◽  
Input Parameters

Abstract Natural gas is one of the main fossil energy resources and its density is an effective thermodynamic property, which is required in almost every pressure-volume-temperature (PVT) calculation. Conventionally, the density of natural gas is determined from the gas deviation (Z-) factor using an equation of states (EOS). Several models have been developed to estimate the Z-factor utilizing the EOS approach, however, most of these models involve complex calculations and require many input parameters. In this study, an improved natural gas density prediction model is presented using robust machine learning techniques such as artificial neural networks and functional networks. A total of 3800 data points were collected from different published sources covering a wide range of input parameters. Moreover, explicit empirical correlations are also derived that can be used explicitly without the need for any machine learning-based software. The proposed correlations are a function of molecular weight (Mw) of natural gas, pseudo reduced pressure (p_pr), and pseudo reduced temperature (T_pr). The proposed correlations can be applied for the gases having Mw between 16 – 129.7 grams, p_pr range 0.02 – 29.3, and T_pr range 0.5 – 2.7. The prediction of the new correlation was compared against the most common methods for determining the natural gas density. The developed correlation showed better estimation than the common prediction models. The estimation error was reduced by 2% on average using the new correlations, the coefficient of determination (R2) was 0.98 using the developed correlation.

scholarly journals Using machine learning techniques to develop risk prediction models to predict graft failure following kidney transplantation: protocol for a retrospective cohort study

F1000Research ◽  
2020 ◽  
Vol 8 ◽  
pp. 1810
Author(s):  
Sameera Senanayake ◽  
Adrian Barnett ◽  
Nicholas Graves ◽  
Helen Healy ◽  
Keshwar Baboolal ◽  
...  
Keyword(s):  
Machine Learning ◽  
Kidney Transplant ◽  
Predictive Models ◽  
Graft Failure ◽  
Prediction Models ◽  
Deceased Donor ◽  
Machine Learning Techniques ◽  
Kidney Graft ◽  
Learning Techniques ◽  
Deceased Donor Kidney Transplant

Background: A mechanism to predict graft failure before the actual kidney transplantation occurs is crucial to clinical management of chronic kidney disease patients.  Several kidney graft outcome prediction models, developed using machine learning methods, are available in the literature.  However, most of those models used small datasets and none of the machine learning-based prediction models available in the medical literature modelled time-to-event (survival) information, but instead used the binary outcome of failure or not. The objective of this study is to develop two separate machine learning-based predictive models to predict graft failure following live and deceased donor kidney transplant, using time-to-event data in a large national dataset from Australia.   Methods: The dataset provided by the Australia and New Zealand Dialysis and Transplant Registry will be used for the analysis. This retrospective dataset contains the cohort of patients who underwent a kidney transplant in Australia from January 1 st, 2007, to December 31 st, 2017. This included 3,758 live donor transplants and 7,365 deceased donor transplants. Three machine learning methods (survival tree, random survival forest and survival support vector machine) and one traditional regression method, Cox proportional regression, will be used to develop the two predictive models (for live donor and deceased donor transplants). The best predictive model will be selected based on the model’s performance. Discussion: This protocol describes the development of two separate machine learning-based predictive models to predict graft failure following live and deceased donor kidney transplant, using a large national dataset from Australia. Furthermore, these two models will be the most comprehensive kidney graft failure predictive models that have used survival data to model using machine learning techniques. Thus, these models are expected to provide valuable insight into the complex interactions between graft failure and donor and recipient characteristics.

Sign in / Sign up

Export Citation Format

Share Document