Automated machine learning to predict the co‐occurrence of isocitrate dehydrogenase mutations and O 6 ‐methylguanine‐DNA methyltransferase promoter methylation in patients with gliomas

2021 ◽  
Author(s):  
Simin Zhang ◽  
Huaiqiang Sun ◽  
Xiaorui Su ◽  
Xibiao Yang ◽  
Weina Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Promoter Methylation ◽  
Isocitrate Dehydrogenase ◽  
Dna Methyltransferase ◽  
Methylguanine Dna Methyltransferase ◽  
Automated Machine Learning

scholarly journals Alteration in the expression of MGMT and RUNX3 due to non-CpG promoter methylation and their correlation with different risk factors in esophageal cancer patients

Tumor Biology ◽  
2017 ◽  
Vol 39 (5) ◽  
pp. 101042831770163 ◽  
Author(s):  
Snigdha Saikia ◽  
Asad Ur Rehman ◽  
Prajjalendra Barooah ◽  
Preeti Sarmah ◽  
Mallika Bhattacharyya ◽  
...  
Keyword(s):  
Esophageal Cancer ◽  
Transcription Factor ◽  
Promoter Methylation ◽  
Messenger Rna ◽  
Dna Methyltransferase ◽  
Rna Expression ◽  
Betel Nut ◽  
Methylguanine Dna Methyltransferase ◽  
Related Transcription Factor ◽  
Transcription Factor 3

Promoter methylation reflects in the inactivation of different genes like O6-methylguanine-DNA methyltransferase DNA repair gene and runt-related transcription factor 3, a known tumor suppressor gene in various cancers such as esophageal cancer. The promoter methylation was evaluated for O6-methylguanine-DNA methyltransferase and runt-related transcription factor 3 in CpG, CHH, and CHG context (where H is A, T, or C) by next-generation sequencing. The methylation status was correlated with quantitative messenger RNA expression. In addition, messenger RNA expression was correlated with different risk factors like tobacco, alcohol, betel nut consumption, and smoking habit. CpG methylation of O6-methylguanine-DNA methyltransferase promoter had a positive association in the development of esophageal cancer (p < 0.05), whereas runt-related transcription factor 3 promoter methylation showed no significant association (p = 1.0) to develop esophageal cancer. However, the non-CpG methylation, CHH, and CHG were significantly correlated with O6-methylguanine-DNA methyltransferase (p < 0.05) and runt-related transcription factor 3 (p < 0.05) promoters in the development of esophageal cancer. The number of cytosine converted to thymine (C→T) in O6-methylguanine-DNA methyltransferase promoter showed a significant correlation between cases and controls (p < 0.05), but in runt-related transcription factor 3 no such significant correlation was observed. Besides, messenger RNA expression was found to be significantly correlated with promoter hypermethylation of O6-methylguanine-DNA methyltransferase and runt-related transcription factor 3 in the context of CHG and CHH (p < 0.05). The CpG hypermethylation in O6-methylguanine-DNA methyltransferase showed positive (p < 0.05) association, whereas in runt-related transcription factor 3, it showed contrasting negative association (p = 0.23) with their messenger RNA expression. Tobacco, betel nut consumption, and smoking habits were associated with altered messenger RNA expression of O6-methylguanine-DNA methyltransferase (p < 0.05) and betel nut consumption and smoking habits were associated with runt-related transcription factor 3 (p < 0.05). There was no significant association between messenger RNA expression of O6-methylguanine-DNA methyltransferase and runt-related transcription factor 3 with alcohol consumption (p = 0.32 and p = 0.15). In conclusion, our results suggest that an aberrant messenger RNA expression may be the outcome of CpG, CHG, and CHH methylation in O6-methylguanine-DNA methyltransferase, whereas outcome of CHG and CHH methylation in runt-related transcription factor 3 promoters along with risk factors such as consumption of tobacco, betel nut, and smoking habits in esophageal cancer from Northeast India.

scholarly journals In Silico Prediction of O6-Methylguanine-DNA Methyltransferase Inhibitory Potency of Base Analogs with QSAR and Machine Learning Methods

Molecules ◽  
2018 ◽  
Vol 23 (11) ◽  
pp. 2892 ◽  
Author(s):  
Guohui Sun ◽  
Tengjiao Fan ◽  
Xiaodong Sun ◽  
Yuxing Hao ◽  
Xin Cui ◽  
...  
Keyword(s):  
Machine Learning ◽  
Dna Methyltransferase ◽  
Information Gain ◽  
Alkylating Agents ◽  
External Validation ◽  
Learning Methods ◽  
Methylguanine Dna Methyltransferase ◽  
Machine Learning Methods ◽  
Dragon Descriptors ◽  
External Test

O6-methylguanine-DNA methyltransferase (MGMT), a unique DNA repair enzyme, can confer resistance to DNA anticancer alkylating agents that modify the O6-position of guanine. Thus, inhibition of MGMT activity in tumors has a great interest for cancer researchers because it can significantly improve the anticancer efficacy of such alkylating agents. In this study, we performed a quantitative structure activity relationship (QSAR) and classification study based on a total of 134 base analogs related to their ED50 values (50% inhibitory concentration) against MGMT. Molecular information of all compounds were described by quantum chemical descriptors and Dragon descriptors. Genetic algorithm (GA) and multiple linear regression (MLR) analysis were combined to develop QSAR models. Classification models were generated by seven machine-learning methods based on six types of molecular fingerprints. Performances of all developed models were assessed by internal and external validation techniques. The best QSAR model was obtained with Q2Loo = 0.83, R2 = 0.87, Q2ext = 0.67, and R2ext = 0.69 based on 84 compounds. The results from QSAR studies indicated topological charge indices, polarizability, ionization potential (IP), and number of primary aromatic amines are main contributors for MGMT inhibition of base analogs. For classification studies, the accuracies of 10-fold cross-validation ranged from 0.750 to 0.885 for top ten models. The range of accuracy for the external test set ranged from 0.800 to 0.880 except for PubChem-Tree model, suggesting a satisfactory predictive ability. Three models (Ext-SVM, Ext-Tree and Graph-RF) showed high and reliable predictive accuracy for both training and external test sets. In addition, several representative substructures for characterizing MGMT inhibitors were identified by information gain and substructure frequency analysis method. Our studies might be useful for further study to design and rapidly identify potential MGMT inhibitors.

Sign in / Sign up

Export Citation Format

Share Document