Dataset Information

Comparing Multiple Machine Learning Algorithms and Metrics for Estrogen Receptor Binding Prediction.

ABSTRACT: Many chemicals that disrupt endocrine function have been linked to a variety of adverse biological outcomes. However, screening for endocrine disruption using in vitro or in vivo approaches is costly and time-consuming. Computational methods, e.g., quantitative structure-activity relationship models, have become more reliable due to bigger training sets, increased computing power, and advanced machine learning algorithms, such as multilayered artificial neural networks. Machine learning models can be used to predict compounds for endocrine disrupting capabilities, such as binding to the estrogen receptor (ER), and allow for prioritization and further testing. In this work, an exhaustive comparison of multiple machine learning algorithms, chemical spaces, and evaluation metrics for ER binding was performed on public data sets curated using in-house cheminformatics software (Assay Central). Chemical features utilized in modeling consisted of binary fingerprints (ECFP6, FCFP6, ToxPrint, or MACCS keys) and continuous molecular descriptors from RDKit. Each feature set was subjected to classic machine learning algorithms (Bernoulli Naive Bayes, AdaBoost Decision Tree, Random Forest, Support Vector Machine) and Deep Neural Networks (DNN). Models were evaluated using a variety of metrics: recall, precision, F1-score, accuracy, area under the receiver operating characteristic curve, Cohen's Kappa, and Matthews correlation coefficient. For predicting compounds within the training set, DNN has an accuracy higher than that of other methods; however, in 5-fold cross validation and external test set predictions, DNN and most classic machine learning models perform similarly regardless of the data set or molecular descriptors used. We have also used the rank normalized scores as a performance-criteria for each machine learning method, and Random Forest performed best on the validation set when ranked by metric or by data sets. These results suggest classic machine learning algorithms may be sufficient to develop high quality predictive models of ER activity.

SUBMITTER: Russo DP

PROVIDER: S-EPMC6181119 | biostudies-literature | 2018 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparing Multiple Machine Learning Algorithms and Metrics for Estrogen Receptor Binding Prediction.

Russo Daniel P DP Zorn Kimberley M KM Clark Alex M AM Zhu Hao H Ekins Sean S

Molecular pharmaceutics 20180828 10

Many chemicals that disrupt endocrine function have been linked to a variety of adverse biological outcomes. However, screening for endocrine disruption using in vitro or in vivo approaches is costly and time-consuming. Computational methods, e.g., quantitative structure-activity relationship models, have become more reliable due to bigger training sets, increased computing power, and advanced machine learning algorithms, such as multilayered artificial neural networks. Machine learning models c ...[more]

PMID: 30114914

Similar Datasets

Project description:BackgroundTrauma is one of the most critical public health issues worldwide, leading to death and disability and influencing all age groups. Therefore, there is great interest in models for predicting mortality in trauma patients admitted to the ICU. The main objective of the present study is to develop and evaluate SMOTE-based machine-learning tools for predicting hospital mortality in trauma patients with imbalanced data.MethodsThis retrospective cohort study was conducted on 126 trauma patients admitted to an intensive care unit at Besat hospital in Hamadan Province, western Iran, from March 2020 to March 2021. Data were extracted from the medical information records of patients. According to the imbalanced property of the data, SMOTE techniques, namely SMOTE, Borderline-SMOTE1, Borderline-SMOTE2, SMOTE-NC, and SVM-SMOTE, were used for primary preprocessing. Then, the Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost) methods were used to predict patients' hospital mortality with traumatic injuries. The performance of the methods used was evaluated by sensitivity, specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), accuracy, Area Under the Curve (AUC), Geometric Mean (G-means), F1 score, and P-value of McNemar's test.ResultsOf the 126 patients admitted to an ICU, 117 (92.9%) survived and 9 (7.1%) died. The mean follow-up time from the date of trauma to the date of outcome was 3.98 ± 4.65 days. The performance of ML algorithms is not good with imbalanced data, whereas the performance of SMOTE-based ML algorithms is significantly improved. The mean area under the ROC curve (AUC) of all SMOTE-based models was more than 91%. F1-score and G-means before balancing the dataset were below 70% for all ML models except ANN. In contrast, F1-score and G-means for the balanced datasets reached more than 90% for all SMOTE-based models. Among all SMOTE-based ML methods, RF and ANN based on SMOTE and XGBoost based on SMOTE-NC achieved the highest value for all evaluation criteria.ConclusionsThis study has shown that SMOTE-based ML algorithms better predict outcomes in traumatic injuries than ML algorithms. They have the potential to assist ICU physicians in making clinical decisions.

Project description:Background: Long non-coding RNAs (lncRNAs) play an important role in the immune regulation of gastric cancer (GC). However, the clinical application value of immune-related lncRNAs has not been fully developed. It is of great significance to overcome the challenges of prognostic prediction and classification of gastric cancer patients based on the current study. Methods: In this study, the R package ImmLnc was used to obtain immune-related lncRNAs of The Cancer Genome Atlas Stomach Adenocarcinoma (TCGA-STAD) project, and univariate Cox regression analysis was performed to find prognostic immune-related lncRNAs. A total of 117 combinations based on 10 algorithms were integrated to determine the immune-related lncRNA prognostic model (ILPM). According to the ILPM, the least absolute shrinkage and selection operator (LASSO) regression was employed to find the major lncRNAs and develop the risk model. ssGSEA, CIBERSORT algorithm, the R package maftools, pRRophetic, and clusterProfiler were employed for measuring the proportion of immune cells among risk groups, genomic mutation difference, drug sensitivity analysis, and pathway enrichment score. Results: A total of 321 immune-related lncRNAs were found, and there were 26 prognostic immune-related lncRNAs. According to the ILPM, 18 of 26 lncRNAs were selected and the risk score (RS) developed by the 18-lncRNA signature had good strength in the TCGA training set and Gene Expression Omnibus (GEO) validation datasets. Patients were divided into high- and low-risk groups according to the median RS, and the low-risk group had a better prognosis, tumor immune microenvironment, and tumor signature enrichment score and a higher metabolism, frequency of genomic mutations, proportion of immune cell infiltration, and antitumor drug resistance. Furthermore, 86 differentially expressed genes (DEGs) between high- and low-risk groups were mainly enriched in immune-related pathways. Conclusion: The ILPM developed based on 26 prognostic immune-related lncRNAs can help in predicting the prognosis of patients suffering from gastric cancer. Precision medicine can be effectively carried out by dividing patients into high- and low-risk groups according to the RS.

Dataset Information

Comparing Multiple Machine Learning Algorithms and Metrics for Estrogen Receptor Binding Prediction.

Publications

Comparing Multiple Machine Learning Algorithms and Metrics for Estrogen Receptor Binding Prediction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets