scholarly journals Identification of Estrogen Receptor α Antagonists from Natural Products via In Vitro and In Silico Approaches

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Xiaocong Pang ◽  
Weiqi Fu ◽  
Jinhua Wang ◽  
De Kang ◽  
Lvjie Xu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Estrogen Receptor ◽  
Natural Products ◽  
Molecular Docking ◽  
Luciferase Reporter ◽  
Luciferase Reporter Gene ◽  
Learning Methods ◽  
Test Set ◽  
Machine Learning Methods ◽  
Gene Assay

Estrogen receptor α (ERα) is a successful target for ER-positive breast cancer and also reported to be relevant in many other diseases. Selective estrogen receptor modulators (SERMs) make a good therapeutic effect in clinic. Because of the drug resistance and side effects of current SERMs, the discovery of new SERMs is given more and more attention. Virtual screening is a validated method to high effectively to identify novel bioactive small molecules. Ligand-based machine learning methods and structure-based molecular docking were first performed for identification of ERα antagonist from in-house natural product library. Naive Bayesian and recursive partitioning models with two kinds of descriptors were built and validated based on training set, test set, and external test set and then were utilized for distinction of active and inactive compounds. Totally, 162 compounds were predicted as ER antagonists and were further evaluated by molecular docking. According to docking score, we selected 8 representative compounds for both ERα competitor assay and luciferase reporter gene assay. Genistein, daidzein, phloretin, ellagic acid, ursolic acid, (−)-epigallocatechin-3-gallate, kaempferol, and naringenin exhibited different levels for antagonistic activity against ERα. These studies validated the feasibility of machine learning methods for predicting bioactivities of ligands and provided better insight into the natural products acting as estrogen receptor modulator, which are important lead compounds for future new drug design.

scholarly journals Machine Learning Models for the Classification of CK2 Natural Products Inhibitors with Molecular Fingerprint Descriptors

Processes ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 2074
Author(s):  
Yuting Liu ◽  
Mengzhou Bi ◽  
Xuewen Zhang ◽  
Na Zhang ◽  
Guohui Sun ◽  
...  
Keyword(s):  
Machine Learning ◽  
Natural Products ◽  
Inhibitory Activity ◽  
Predictive Accuracy ◽  
Information Gain ◽  
High Reliability ◽  
Learning Methods ◽  
Test Set ◽  
Machine Learning Methods ◽  
Ck2 Inhibitors

Casein kinase 2 (CK2) is considered an important target for anti-cancer drugs. Given the structural diversity and broad spectrum of pharmaceutical activities of natural products, numerous studies have been performed to prove them as valuable sources of drugs. However, there has been little study relevant to identifying structural factors responsible for their inhibitory activity against CK2 with machine learning methods. In this study, classification studies were conducted on 115 natural products as CK2 inhibitors. Seven machine learning methods along with six molecular fingerprints were employed to develop qualitative classification models. The performances of all models were evaluated by cross-validation and test set. By taking predictive accuracy(CA), the area under receiver operating characteristic (AUC), and (MCC)as three performance indicators, the optimal models with high reliability and predictive ability were obtained, including the Extended Fingerprint-Logistic Regression model (CA = 0.859, AUC = 0.826, MCC = 0.520) for training test andPubChem fingerprint along with the artificial neural model (CA = 0.826, AUC = 0.933, MCC = 0.628) for test set. Meanwhile, the privileged substructures responsible for their inhibitory activity against CK2 were also identified through a combination of frequency analysis and information gain. The results are expected to provide useful information for the further utilization of natural products and the discovery of novel CK2 inhibitors.

scholarly journals Deep learning accurately predicts estrogen receptor status in breast cancer metabolomics data

2017 ◽  
Author(s):  
Fadhl M Alakwaa ◽  
Kumardeep Chaudhary ◽  
Lana X Garmire
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Estrogen Receptor ◽  
Deep Learning ◽  
Support Vector ◽  
Integrated Analysis ◽  
Learning Method ◽  
Learning Methods ◽  
Metabolomics Data ◽  
Machine Learning Methods

ABSTRACTMetabolomics holds the promise as a new technology to diagnose highly heterogeneous diseases. Conventionally, metabolomics data analysis for diagnosis is done using various statistical and machine learning based classification methods. However, it remains unknown if deep neural network, a class of increasingly popular machine learning methods, is suitable to classify metabolomics data. Here we use a cohort of 271 breast cancer tissues, 204 positive estrogen receptor (ER+) and 67 negative estrogen receptor (ER-), to test the accuracies of autoencoder, a deep learning (DL) framework, as well as six widely used machine learning models, namely Random Forest (RF), Support Vector Machines (SVM), Recursive Partitioning and Regression Trees (RPART), Linear Discriminant Analysis (LDA), Prediction Analysis for Microarrays (PAM), and Generalized Boosted Models (GBM). DL framework has the highest area under the curve (AUC) of 0.93 in classifying ER+/ER-patients, compared to the other six machine learning algorithms. Furthermore, the biological interpretation of the first hidden layer reveals eight commonly enriched significant metabolomics pathways (adjusted P-value<0.05) that cannot be discovered by other machine learning methods. Among them, protein digestion & absorption and ATP-binding cassette (ABC) transporters pathways are also confirmed in integrated analysis between metabolomics and gene expression data in these samples. In summary, deep learning method shows advantages for metabolomics based breast cancer ER status classification, with both the highest prediction accurcy (AUC=0.93) and better revelation of disease biology. We encourage the adoption of autoencoder based deep learning method in the metabolomics research community for classification.

Boron clusters for medicinal drug design: Selective estrogen receptor modulators bearing carborane

2003 ◽  
Vol 75 (9) ◽  
pp. 1197-1205 ◽  
Author(s):  
Yasuyuki Endo ◽  
Tomohiro Yoshimi ◽  
Chisato Miyaura
Keyword(s):  
Estrogen Receptor ◽  
Estrogenic Activity ◽  
Medical Application ◽  
Molecular Shape ◽  
Biologically Active ◽  
Luciferase Reporter ◽  
Luciferase Reporter Gene ◽  
Estrogen Receptor Modulators ◽  
Gene Assay

The molecular shape and hydrophobicity of dicarba-closo -dodecaboranes may allow a new medical application as biologically active molecules. Recently, we have developed potent estrogen receptor (ER) agonists bearing carborane cage. The most potent compound (BE120) exhibited activity at least several times greater than that of 17 beta-estradiol in luciferase reporter gene assay and ER alpha binding. We also designed and synthesized estrogen antagonists on the basis of the structure of BE120, and we noticed the characteristic features of compound (BE360) having carborane cage and two phenols. The ER binding affinity of BE360 is comparable to that of estradiol. To examine in vivo estrogenic activity of the compound in bone, ovariectomized (OVX) mice were given BE360 or estradiol subcutaneously for 4 weeks. Treatment with BE360 at 1–30 µg/day dose-dependently restored bone loss in OVX mice to sham level without estrogenic action in uterus. These results suggest its possible application to osteoporosis as a new type of selective ER modulator.

scholarly journals Application of AI Modeling Technology Based on Fluid Biopsy to Diagnose AD

2021 ◽  
Author(s):  
Yuan Sh ◽  
Benliang Liu ◽  
Jianhu Zhang ◽  
Ying Zhou ◽  
Zhiyuan Hu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Mrna Expression ◽  
Feature Engineering ◽  
Expression Data ◽  
Blood Biomarkers ◽  
Learning Methods ◽  
Test Set ◽  
Mrna Expression Data ◽  
Machine Learning Methods

Abstract BackgroundThere are no obvious clinical symptoms in the early stages of Alzheimer's disease (AD). Therefore, the diagnosis of AD directly leads to serious lag. Studies have shown that most patients usually have mild cognitive impairment (MCI) before diagnosis. Therefore, the actual time of diagnosis of AD is much later than the time of onset. This brings great difficulties to the late treatment and management of patients. Therefore, early diagnosis of AD is very important. This paper mainly discusses the blood biomarkers of AD patients and uses machine learning methods to find the changes of blood transcriptome during the development of AD, and to search for potential blood biomarkers.MethodIndividualized blood mRNA expression data were downloaded from the GEO database in 711 patients, including control group (CON) (238 patients), MCI (189 patients), and AD (284 patients). Firstly, we analyzed the subcellular localization, protein types and enrichment pathways of the differentially expressed mRNAs in each group, and established an artificial intelligence individualized diagnostic model. Furthermore, Xcell tool was used to analyze the blood mRNA expression data to obtain the composition and quantitative data of blood cells. Ratio characteristics were established for mRNA and Xcell data respectively. Feature engineering operations such as collinearity and importance analysis are performed on all features to obtain the best feature solicitation. Finally, four machine learning algorithms, including linear support vector machine (SVM), Adaboost, random forest and artificial neural network, were used to model the optimal feature combinations and evaluate their classification performance in the test set.ResultA total of 5625 differential mRNAs were obtained by differential analysis of blood mRNAs. Through feature engineering screening, the best feature collection was obtained, and the artificial intelligence individualized diagnosis model established based on this method achieved a classification accuracy of 91.59% in the test set. The AUC of CON, MCI and AD were 0.9746, 0.9536 and 0.9807, respectively. ConclusionThe 181 features are composed of four dimensions, which can accurately classify CON, MCI and AD groups, suggesting that machine learning methods can capture changes in blood biomarkers in Alzheimer's patients. The results of cell homeostasis analysis suggested that the homeostasis of NTK cells might be related to AD, and the homeostasis of GMP might be one of the reasons for AD.

Machine-learning methods for ligand–protein molecular docking

2021 ◽  
Author(s):  
Kevin Crampon ◽  
Alexis Giorkallos ◽  
Myrtille Deldossi ◽  
Stéphanie Baud ◽  
Luiz Angelo Steffenel
Keyword(s):  
Machine Learning ◽  
Molecular Docking ◽  
Learning Methods ◽  
Machine Learning Methods
Sign in / Sign up

Export Citation Format

Share Document