.png){kind=icon}
返回
StackBRAF: A Large-Scale Stacking Ensemble Learning for BRAF Affinity Prediction
.png){kind=icon}
OA
AI
DOI：10.1021/acsomega.3c01641.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The B-rapidly acceleratedfibrosarcoma (BRAF) is a proto-oncogenethat plays a vital role in cell signaling and growth regulation. Identifyinga potent BRAF inhibitor can enhance therapeutic success in high-stagecancers, particularly metastatic melanoma. In this study, we proposeda stacking ensemble learning framework for the accurate predictionof BRAF inhibitors. We obtained 3857 curated molecules with BRAF inhibitoryactivity expressed as a predicted half-maximal inhibitory concentrationvalue (pIC(50)) from the ChEMBL database. Twelve molecularfingerprints from PaDeL-Descriptor were calculated for model training.Three machine learning algorithms including extreme gradient boosting,support vector regression, and multilayer perceptron were utilizedfor constructing new predictive features (PFs). The meta-ensemblerandom forest regression, called StackBRAF, was created based on the36 PFs. The StackBRAF model achieves lower mean absolute error (MAE)and higher coefficient of determination (R (2) and Q (2)) than the individual baselinemodels. The stacking ensemble learning model provides good y-randomization results, indicating a strong correlationbetween molecular features and pIC(50). An applicabilitydomain of the model with an acceptable Tanimoto similarity score wasalso defined. Moreover, a large-scale high-throughput screening of2123 FDA-approved drugs against the BRAF protein was successfullydemonstrated using the StackBRAF algorithm. Thus, the StackBRAF modelproved beneficial as a drug design algorithm for BRAF inhibitor drugdiscovery and drug development.
Keyword:
METASTATIC MELANOMA
KINASES
MODEL
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.3
论文数:
3.4W
被引数:
9.8W
机构
引用论文
A Mek1-Mek2 heterodimer determines the strength and duration of the Erk signalMek1-Mek2异二聚体决定Erk信号的强度和持续时间
PREAI
分享收藏分享收藏Stacking ensemble learning model to predict 6-month mortality in ischemic stroke patients.png)
SCIENTIFIC REPORTSOAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏Transformer-Based Generative Model Accelerating the Development of Novel BRAF InhibitorsACS OMEGAOAAI
ACS OMEGAIF4.3
OAAI分享收藏
查看更多内容