RESUMO
OBJECTIVE: The aim of this study was to build a convolutional neural network (CNN)-based prediction model of glioblastoma (GBM) molecular subtype diagnosis and prognosis with multimodal features. METHODS: In total, 222 GBM patients were included in the training set from Sun Yat-sen University Cancer Center (SYSUCC) and 107 GBM patients were included in the validation set from SYSUCC, Xuanwu Hospital Capital Medical University, and the First Hospital of Jilin University. The multimodal model was trained with MR images (pre- and postcontrast T1-weighted images and T2-weighted images), corresponding MRI impression, and clinical patient information. First, the original images were segmented using the Multimodal Brain Tumor Image Segmentation Benchmark toolkit. Convolutional features were extracted using 3D residual deep neural network (ResNet50) and convolutional 3D (C3D). Radiomic features were extracted using pyradiomics. Report texts were converted to word embedding using word2vec. These three types of features were then integrated to train neural networks. Accuracy, precision, recall, and F1-score were used to evaluate the model performance. RESULTS: The C3D-based model yielded the highest accuracy of 91.11% in the prediction of IDH1 mutation status. Importantly, the addition of semantics improved precision by 11.21% and recall in MGMT promoter methylation status prediction by 14.28%. The areas under the receiver operating characteristic curves of the C3D-based model in the IDH1, ATRX, MGMT, and 1-year prognosis groups were 0.976, 0.953, 0.955, and 0.976, respectively. In external validation, the C3D-based model showed significant improvement in accuracy in the IDH1, ATRX, MGMT, and 1-year prognosis groups, which were 88.30%, 76.67%, 85.71%, and 85.71%, respectively (compared with 3D ResNet50: 83.51%, 66.67%, 82.14%, and 70.79%, respectively). CONCLUSIONS: The authors propose a novel multimodal model integrating C3D, radiomics, and semantics, which had a great performance in predicting IDH1, ATRX, and MGMT molecular subtypes and the 1-year prognosis of GBM.
RESUMO
Dopamine receptor, a polypeptide chain composed of 7 hydrophobic transmembrane regions, is a new and vital drug target, especially Dopamine receptor 2(D2). Targeting dopamine receptors, Dopamine receptor agonists are a class of drugs similar in function and structure to dopamine and can directly act on dopamine receptors and activate it. Clinically, Dopamine receptor agonist drugs have achieved significant therapeutic effects on prolactinoma and Parkinson's Disease. In the study, we virtually screened a series of potential effective agonists of Dopamine receptor by computer techniques. Firstly, we used the Molecular Docking (LibDock) step to screen out some molecules that can dock well with the protein. Then, analysis of toxicity prediction and ADME (adsorption, distribution, metabolism and excretion) were carried out. More precise molecular docking (CDOCKER) and 3-Dimensional Quantitative Structure-Activity Relationship Modeling Study(3D-QSAR) pharmacophore generation were implemented to research and explore these compounds' binding mechanism with Dopamine receptor. Last but not least, to assess compound's binding stabilities, we carried out a molecular dynamic analysis. As the results show, two compounds (ZINC000008860530 and ZINC000004096987) from the small molecule database (ZINC database) were potential effective agonists of Dopamine receptor. These two compounds can combine with Dopamine receptor with higher affinity and proved to be no toxic. The cell experiment showed that two compounds could inhibit the proliferation and PRL secretion of MMQ cells (pituitary tumor cells). Thus, this study provided valuable information about Dopamine receptor agonist-based drug discovery. So, this study will benefit patients with prolactinoma and Parkinson's disease a lot.