scholarly journals Predicting JNK1 Inhibitors Regulating Autophagy in Cancer using Random Forest Classifier

2018 ◽  
Author(s):  
Chetna Kumari ◽  
Naidu Subbarao ◽  
Muhammad Abulaish
Keyword(s):  
Machine Learning ◽  
Protein Kinase ◽  
Random Forest ◽  
Protein Kinases ◽  
Variable Importance ◽  
Random Forest Classifier ◽  
Selective Inhibitors ◽  
Molecular Features ◽  
Variable Importance Measures

AbstractAutophagy (in Greek: self-eating) is the cellular process for delivery of heterogenic intracellular material to lysosomal digestion. Protein kinases are integral to the autophagy process, and when dysregulated or mutated cause several human diseases. Atg1, the first autophagy-related protein identified is a serine/threonine protein kinases (STPKs). mTOR (mammalian Target of Rapamycin), AMPK (AMP-activated protein kinase), Akt, MAPK (mitogen-activated protein kinase) and PKC (protein kinase C) are other STPKs which regulate various components/steps of autophagy, and are often deregulated in cancer. MAPK have three subfamilies – ERKs, p38, and JNKs. JNKs (c-Jun N-terminal Kinases) have three isoforms in mammals – JNK1, JNK2, and JNK3, each with distinct cellular locations and functions. JNK1 plays role in starvation induced activation of autophagy, and the context-specific role of autophagy in tumorigenesis establish JNK1 a challenging anticancer drug target. Since JNKs are closely related to other members of MAPK family (p38, MAP kinase and the ERKs), it is difficult to design JNK-selective inhibitors. Designing JNK isoform-selective inhibitors are even more challenging as the ATP-binding sites among all JNKs are highly conserved. Although limited informations are available to explore computational approaches to predict JNK1 inhibitors, it seems diificult to find literature exploring machine learning techniques to predict JNKs inhibitors. This study aims to apply machine learning to predict JNK1 inhibitors regulating autophagy in cancer using Random Forest (RF). Here, RF algorithm is used for two purposes‐ to select and rank the molecular descriptors calculated using PaDEL descriptor software and as clasifier. The descriptors are prioritized by calculating Variable Importance Measures (VIMs) using functions based on mean square error (IncMSE) and node purity (IncNodePurity) of RF. The classification models based on a set of 22 prioritized descriptors shows accuracy 86.36%, precision 88.27% and AUC (Area Under ROC curve) 0.8914. We conclude that machine learning-based compound classification using Random Forest is one of the ligand-based approach that can be opted for virtual screening of large compound library of JNK1 bioactives.Author SummaryOut of the three isoforms of JNKs (cJun N-terminal Kinases) in human (each with distinct cellular locations and functions), JNK1 plays role in starvation induced activation of autophagy. The role of JNK1 in autophagy modulation and dual role of autophagy in tumor cells makes JNK1 a promising anticancer drug target. Since JNKs are closely related to other members of MAPK (Mitogen-Activated Protein Kinases) family, it is difficult to design JNK selective inhibitors. Designing JNK isoformselective inhibitors are even more challenging as the ATP binding sites among all JNKs are highly conserved. Random forest classifier usually outperforms several other machine learning algorithms for classification and prediction tasks in diverse areas of research. In this work, we have used Random Forest algorithm for two purposes: (i) calculating variable importance measures to rank and select molecular features, and (ii) predicting JNK1 inhibitors regulating autophagy in cancer. We have used paDEL calculated molecular features of JNK1 bioactivity dataset from ChEMBL database to build classification models using random forest classifier. Our results show that by optimally selecting features from top 10% based on variable importance measure the classification accuracy is high, and the classification model proposed in this study can be integrated with drug design pipeline to virtually screen compound libraries for predicting JNK1 inhibitors.

scholarly journals Addressing Measurement Error in Random Forests using Quantitative Bias Analysis

2021 ◽  
Author(s):  
Tammy Jiang ◽  
Jaimie L Gradus ◽  
Timothy L Lash ◽  
Matthew P Fox
Keyword(s):  
Machine Learning ◽  
Measurement Error ◽  
Random Forest ◽  
Random Forests ◽  
Model Performance ◽  
Variable Importance ◽  
Bias Analysis ◽  
Variable Importance Measures ◽  
Quantitative Bias Analysis ◽  
The Impact

Abstract Although variables are often measured with error, the impact of measurement error on machine learning predictions is seldom quantified. The purpose of this study was to assess the impact of measurement error on random forest model performance and variable importance. First, we assessed the impact of misclassification (i.e., measurement error of categorical variables) of predictors on random forest model performance (e.g., accuracy, sensitivity) and variable importance (mean decrease in accuracy) using data from the United States National Comorbidity Survey Replication (2001 - 2003). Second, we simulated datasets in which we know the true model performance and variable importance measures and could verify that quantitative bias analysis was recovering the truth in misclassified versions of the datasets. Our findings show that measurement error in the data used to construct random forests can distort model performance and variable importance measures, and that bias analysis can recover the correct results. This study highlights the utility of applying quantitative bias analysis in machine learning to quantify the impact of measurement error on study results.

scholarly journals Amide proton transfer weighted (APTw) imaging based radiomics allows for the differentiation of gliomas from metastases

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Elisabeth Sartoretti ◽  
Thomas Sartoretti ◽  
Michael Wyss ◽  
Carolin Reischauer ◽  
Luuk van Smoorenburg ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Brain Tumors ◽  
Proton Transfer ◽  
Multilayer Perceptron ◽  
Random Forest Classifier ◽  
Amide Proton ◽  
Low Grade ◽  
Who Grade ◽  
Amide Proton Transfer

AbstractWe sought to evaluate the utility of radiomics for Amide Proton Transfer weighted (APTw) imaging by assessing its value in differentiating brain metastases from high- and low grade glial brain tumors. We retrospectively identified 48 treatment-naïve patients (10 WHO grade 2, 1 WHO grade 3, 10 WHO grade 4 primary glial brain tumors and 27 metastases) with either primary glial brain tumors or metastases who had undergone APTw MR imaging. After image analysis with radiomics feature extraction and post-processing, machine learning algorithms (multilayer perceptron machine learning algorithm; random forest classifier) with stratified tenfold cross validation were trained on features and were used to differentiate the brain neoplasms. The multilayer perceptron achieved an AUC of 0.836 (receiver operating characteristic curve) in differentiating primary glial brain tumors from metastases. The random forest classifier achieved an AUC of 0.868 in differentiating WHO grade 4 from WHO grade 2/3 primary glial brain tumors. For the differentiation of WHO grade 4 tumors from grade 2/3 tumors and metastases an average AUC of 0.797 was achieved. Our results indicate that the use of radiomics for APTw imaging is feasible and the differentiation of primary glial brain tumors from metastases is achievable with a high degree of accuracy.

scholarly journals Ca2+ Microdomains, Calcineurin and the Regulation of Gene Transcription

Cells ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 875
Author(s):  
Gerald Thiel ◽  
Tobias Schmidt ◽  
Oliver G. Rössler
Keyword(s):  
Transcription Factors ◽  
Protein Kinase ◽  
Protein Kinases ◽  
Gene Transcription ◽  
Intracellular Signaling ◽  
Second Messengers ◽  
Major Function ◽  
Surface Receptors ◽  
Dependent Protein

Ca2+ ions function as second messengers regulating many intracellular events, including neurotransmitter release, exocytosis, muscle contraction, metabolism and gene transcription. Cells of a multicellular organism express a variety of cell-surface receptors and channels that trigger an increase of the intracellular Ca2+ concentration upon stimulation. The elevated Ca2+ concentration is not uniformly distributed within the cytoplasm but is organized in subcellular microdomains with high and low concentrations of Ca2+ at different locations in the cell. Ca2+ ions are stored and released by intracellular organelles that change the concentration and distribution of Ca2+ ions. A major function of the rise in intracellular Ca2+ is the change of the genetic expression pattern of the cell via the activation of Ca2+-responsive transcription factors. It has been proposed that Ca2+-responsive transcription factors are differently affected by a rise in cytoplasmic versus nuclear Ca2+. Moreover, it has been suggested that the mode of entry determines whether an influx of Ca2+ leads to the stimulation of gene transcription. A rise in cytoplasmic Ca2+ induces an intracellular signaling cascade, involving the activation of the Ca2+/calmodulin-dependent protein phosphatase calcineurin and various protein kinases (protein kinase C, extracellular signal-regulated protein kinase, Ca2+/calmodulin-dependent protein kinases). In this review article, we discuss the concept of gene regulation via elevated Ca2+ concentration in the cytoplasm and the nucleus, the role of Ca2+ entry and the role of enzymes as signal transducers. We give particular emphasis to the regulation of gene transcription by calcineurin, linking protein dephosphorylation with Ca2+ signaling and gene expression.

Diagnosing asthma and chronic obstructive pulmonary disease with machine learning

2017 ◽  
Vol 25 (3) ◽  
pp. 811-827 ◽  
Author(s):  
Dimitris Spathis ◽  
Panayiotis Vlamos
Keyword(s):  
Machine Learning ◽  
Chronic Obstructive Pulmonary Disease ◽  
Random Forest ◽  
Pulmonary Disease ◽  
Clinical Decision Support Systems ◽  
Clinical Decision ◽  
Forced Expiratory Volume ◽  
Random Forest Classifier ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease

This study examines the clinical decision support systems in healthcare, in particular about the prevention, diagnosis and treatment of respiratory diseases, such as Asthma and chronic obstructive pulmonary disease. The empirical pulmonology study of a representative sample (n = 132) attempts to identify the major factors that contribute to the diagnosis of these diseases. Machine learning results show that in chronic obstructive pulmonary disease’s case, Random Forest classifier outperforms other techniques with 97.7 per cent precision, while the most prominent attributes for diagnosis are smoking, forced expiratory volume 1, age and forced vital capacity. In asthma’s case, the best precision, 80.3 per cent, is achieved again with the Random Forest classifier, while the most prominent attribute is MEF2575.

scholarly journals Machine learning approaches to the determinants of women’s vasomotor symptoms using general hospital data

2020 ◽  
Author(s):  
Ki-Jin Ryu ◽  
Kyong Wook Yi ◽  
Yong Jin Kim ◽  
Jung Ho Shin ◽  
Jun Young Hur ◽  
...  
Keyword(s):  
Machine Learning ◽  
Insulin Resistance ◽  
Random Forest ◽  
Variable Importance ◽  
Vasomotor Symptoms ◽  
Model Assessment ◽  
Cancer Antigen ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Glutamyl Transferase

Abstract Background To analyze the determinants of women’s vasomotor symptoms (VMS) using machine learning. Methods Data came from Korea University Anam Hospital in Seoul, Korea, with 3298 women, aged 40–80 years, who attended their general health check from January 2010 to December 2012. Five machine learning methods were applied and compared for the prediction of VMS, measured by a Menopause Rating Scale. Variable importance, the effect of a variable on model performance, was used for identifying major determinants of VMS. Results In terms of the mean squared error, the random forest (0.9326) was much better than linear regression (12.4856) and artificial neural networks with one, two and three hidden layers (1.5576, 1.5184 and 1.5833, respectively). Based on variable importance from the random forest, the most important determinants of VMS were age, menopause age, thyroid stimulating hormone, monocyte and triglyceride, as well as gamma glutamyl transferase, blood urea nitrogen, cancer antigen 19 − 9, C-reactive protein and low-density-lipoprotein cholesterol. Indeed, the following determinants ranked within the top 20 in terms of variable importance: cancer antigen 125, total cholesterol, insulin, free thyroxine, forced vital capacity, alanine aminotransferase, forced expired volume in one second, height, homeostatic model assessment for insulin resistance and carcinoembryonic antigen. Conclusions Machine learning provides an invaluable decision support system for the prediction of VMS. For preventing VMS, preventive measures would be needed regarding the thyroid function, the lipid profile, the liver function, inflammation markers, insulin resistance, the monocyte, cancer antigens and the lung function.

A Machine Learning Approach to Detect Student Dropout at University

2021 ◽  
Vol 10 (6) ◽  
pp. 3101-3107
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Dropout Rate ◽  
Random Forest Classifier ◽  
Drop Out ◽  
Dropout Rates ◽  
Learning Technology ◽  
Student Dropout ◽  
High Dropout Rate ◽  
Academic Plan

In universities, student dropout is a major concern that reflects the university's quality. Some characteristics cause students to drop out of university. A high dropout rate of students affects the university's reputation and the student's careers in the future. Therefore, there's a requirement for student dropout analysis to enhance academic plan and management to scale back student's drop out from the university also on enhancing the standard of the upper education system. The machine learning technique provides powerful methods for the analysis and therefore the prediction of the dropout. This study uses a dataset from a university representative to develop a model for predicting student dropout. In this work, machine- learning models were used to detect dropout rates. Machine learning is being more widely used in the field of knowledge mining diagnostics. Following an examination of certain studies, we observed that dropout detection may be done using several methods. We've even used five dropout detection models. These models are Decision tree, Naïve bayes, Random Forest Classifier, SVM and KNN. We used machine-learning technology to analyze the data, and we discovered that the Random Forest classifier is highly promising for predicting dropout rates, with a training accuracy of 94% and a testing accuracy of 86%.

scholarly journals Activation of Extracellular Signal-Related Protein Kinases 1 and 2 of the Mitogen-Activated Protein Kinase Family by Lipopolysaccharide Requires Plasma in Neutrophils from Adults and Newborns

2001 ◽  
Vol 69 (5) ◽  
pp. 3143-3149 ◽  
Author(s):  
S. Bonner ◽  
S. R. Yan ◽  
D. M. Byers ◽  
R. Bortolussi
Keyword(s):  
Protein Kinase ◽  
Protein Kinases ◽  
Oxidative Burst ◽  
Mitogen Activated Protein Kinase ◽  
Related Protein ◽  
Extracellular Signal ◽  
Oxidative Response ◽  
Mitogen Activated Protein ◽  
Mediated Priming

ABSTRACT Neutrophils exposed to low concentrations of gram-negative lipopolysaccharide (LPS) become primed and have an increased oxidative response to a second stimulus (e.g., formyl-methionyl-leucyl-phenylalanine [fMLP]). In studies aimed at understanding newborn sepsis, we have shown that neutrophils of newborns are not primed in response to LPS. To further understand the processes involved in LPS-mediated priming of neutrophils, we explored the role of extracellular signal-related protein kinases (ERK 1 and 2) of the mitogen-activated protein kinase family. We found that LPS activated ERK 1 and 2 in cells of both adults and newborns and that activation was plasma dependent (maximal at ≥5%) through LPS-binding protein. Although fibronectin in plasma is required for LPS-mediated priming of neutrophils of adults assessed by fMLP-triggered oxidative burst, it was not required for LPS-mediated activation of ERK 1 and 2. LPS-mediated activation was dose and time dependent; maximal activation occurred with approximately 5 ng of LPS per ml and at 10 to 40 min. We used the inhibitor PD 98059 to study the role of ERK 1 and 2 in the LPS-primed fMLP-triggered oxidative burst. While Western blotting showed that 100 μM PD 98059 completely inhibited LPS-mediated ERK activation, oxidative response to fMLP by a chemiluminescence assay revealed that the same concentration inhibited the LPS-primed oxidative burst by only 40%. We conclude that in neutrophils, LPS-mediated activation of ERK 1 and 2 requires plasma and that this activation is not dependent on fibronectin. In addition, we found that the ERK pathway is not responsible for the lack of LPS priming in neutrophils of newborns but may be required for 40% of the LPS-primed fMLP-triggered oxidative burst in cells of adults.

Sweet Taste Transduction in Hamster: Role of Protein Kinases

2000 ◽  
Vol 83 (5) ◽  
pp. 2526-2532 ◽  
Author(s):  
Brian Varkevisser ◽  
Sue C. Kinnamon
Keyword(s):  
Protein Kinase ◽  
Protein Kinases ◽  
Sweet Taste ◽  
Taste Buds ◽  
Regulatory Proteins ◽  
Camp Phosphodiesterase ◽  
Kinase C ◽  
Taste Transduction ◽  
Second Messenger Pathways

Two different second-messenger pathways have been implicated in sweet taste transduction: sugars produce cyclic AMP (cAMP), whereas synthetic sweeteners stimulate production of inositol 1,4,5-tris-phosphate (IP3) and diacylglycerol (DAG). Both sugars and sweeteners depolarize taste cells by blocking the same resting K+conductance, but the intermediate steps in the transduction pathways have not been examined. In this study, the loose-patch recording technique was used to examine the role of protein kinases and other downstream regulatory proteins in the two sweet transduction pathways. Bursts of action currents were elicited from ∼35% of fungiform taste buds in response to sucrose (200 mM) or NC-00274–01 (NC-01, 200 μM), a synthetic sweetener. To determine whether protein kinase C (PKC) plays a role in sweet transduction, taste buds were stimulated with the PKC activator PDBu (10 μM). In all sweet-responsive taste buds tested ( n = 11), PDBu elicited burst of action currents. In contrast, PDBu elicited responses in only 4 of 19 sweet-unresponsive taste buds. Inhibition of PKC by bisindolylmaleimide I (0.15 μM) resulted in inhibition of the NC-01 response by ∼75%, whereas the response to sucrose either increased or remained unchanged. These data suggest that activation of PKC is required for the transduction of synthetic sweeteners. To determine whether protein kinase A (PKA) is required for the transduction of sugars, sweet responses were examined in the presence of the membrane-permeant PKA inhibitor H-89 (10 and 19 μM). Surprisingly, H-89 did not decrease responses to either sucrose or NC-01. Instead, responses to both compounds were increased in the presence of the inhibitor. These data suggest that PKA is not required for the transduction of sugars, but may play a modulatory role in both pathways, such as adaptation of the response. We also examined whether Ca2+-calmodulin dependent cAMP phosphodiesterase (CaM-PDE) plays a role in sweet taste transduction, by examining responses to sucrose and synthetic sweeteners in the presence of the CaM-PDE inhibitor W-7 (100 μM). Inhibition resulted in an increase in the response to sucrose, whereas the response to NC-01 remained unchanged. These data suggest that the pathways for sugars and sweeteners are negatively coupled; the Ca2+ that is released from intracellular stores during stimulation with synthetic sweeteners may inhibit the response to sucrose by activation of CaM-PDE.

Sign in / Sign up

Export Citation Format

Share Document