Abstract
The progesterone receptor (PR) is important therapeutic target for many malignancies and endocrine disorders due to its role in controlling ovulation and pregnancy via the reproductive cycle. Therefore, the modulation of PR activity using its agonists and antagonists is receiving increasing interest as novel treatment strategy. However, clinical trials using the PR modulators have not yet been found conclusive evidences. Recently, increasing evidence from several fields shows that the classification of chemical compounds, including agonists and antagonists, can be done with recent improvements in deep learning (DL) using deep neural network. Therefore, we recently proposed a novel DL-based quantitative structure-activity relationship (QSAR) strategy using transfer learning to build prediction models for agonists and antagonists. By employing this novel approach, referred as DeepSnap-DL method, which uses images captured from 3-dimension (3D) chemical structure with multiple angles as input data into the DL classification, we constructed prediction models of the PR antagonists in this study. Here, the DeepSnap-DL method showed a high performance prediction of the PR antagonists by optimization of some parameters and image adjustment from 3D-structures. Furthermore, comparison of the prediction models from this approach with conventional machine learnings (MLs) indicated the DeepSnap-DL method outperformed these MLs. Therefore, the models predicted by DeepSnap-DL would be powerful tool for not only QSAR field in predicting physiological and agonist/antagonist activities, toxicity, and molecular bindings; but also for identifying biological or pathological phenomena.
Highlights
The progesterone receptor (PR: NCBI Gene ID:18667) is a member of the steroid receptor superfamily and plays essential roles in female reproductive events, such as the establishment and maintenance of pregnancy, menstrual cycle regulation, sexual behavior, and development of mammary glands
In order to analyze the influence of different splits for the training, validation, and test (Tra, Val, and test datasets: Acc (Test)) datasets and the angles when capturing Jmol-generated images in the DeepSnap approach, we randomly divided the input data of a total of 7,582 chemical compounds into five ratios, namely Tra:Val:Test = 1:1:1 to 5:5:1 (Table S1)
The five angles (120, 180, 240, 300, and 360◦) produced 27, 8, 8, 8, and 1 picture(s), respectively, from the 3D structures using the DeepSnap approach. These results suggest that multiple pictures produced by the DeepSnap method outperformed single images derived from at 360◦ angle
Summary
The progesterone receptor (PR: NCBI Gene ID:18667) is a member of the steroid receptor superfamily and plays essential roles in female reproductive events, such as the establishment and maintenance of pregnancy, menstrual cycle regulation, sexual behavior, and development of mammary glands. A deep learning (DL) approach with convolutional neural networks (CNNs), Rectified Linear Unit (ReLU), and max pooling is a promising, powerful tool for the classification modeling (Date and Kikuchi, 2018; Öztürk et al, 2018; Wang et al, 2018; Agajanian et al, 2019; Idakwo et al, 2019; Jo et al, 2019), where factors affecting its prediction performance include sufficient size, suitable representation, and accurate labeling of supervised input datasets (Bello et al, 2019; Chauhan et al, 2019; Liu P. et al, 2019) To resolve these issues, the DL-based QSAR modeling approach using molecular images produced by 3D chemical structure as input data was previously developed and referred to as the DeepSnap-DL approach (Uesawa, 2018). These findings suggest that the DeepSnap-DL approach may be applied to other protein agonist and antagonist activities with high-quality and high-throughput prediction
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
