Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess.
Ki dataset [14] and Davis dataset [26] are used to verify the effectiveness of our method. The values of Ki dataset were selected from the BindingDB dataset [27]. The Davis dataset is a well-known benchmark dataset that contains selectivity assays of the kinase protein family and the relevant inhibitors with their respective \(K_{d}\) values. The detailed information about these two datasets is shown in Table 1.
2.2. Data Pre-Processing and Augmentation Each molecule corresponds to a unique molecular structure. Due to the ambiguity of the SMILES models, there are multiple SMILES strings that correspond to the same molecule, as shown in , which provides an efficient way to enlarge the training dataset to meet the need for DL model training. Specifically, for molecular property prediction tasks, there are two main benefits for using data augmentation.
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
