Hematotoxicity has been becoming a serious but overlooked toxicity in drug discovery. However, only a few in silico models have been reported for the prediction of hematotoxicity. In this study, we constructed a high-quality dataset comprising 759 hematotoxic compounds and 1623 nonhematotoxic compounds and then established a series of classification models based on a combination of seven machine learning (ML) algorithms and nine molecular representations. The results based on two data partitioning strategies and applicability domain (AD) analysis illustrate that the best prediction model based on Attentive FP yielded a balanced accuracy (BA) of 72.6%, an area under the receiver operating characteristic curve (AUC) value of 76.8% for the validation set, and a BA of 69.2%, an AUC of 75.9% for the test set. In addition, compared with existing filtering rules and models, our model achieved the highest BA value of 67.5% for the external validation set. Additionally, the shapley additive explanation (SHAP) and atom heatmap approaches were utilized to discover the important features and structural fragments related to hematotoxicity, which could offer helpful tips to detect undesired positive substances. Furthermore, matched molecular pair analysis (MMPA) and representative substructure derivation technique were employed to further characterize and investigate the transformation principles and distinctive structural features of hematotoxic chemicals. We believe that the novel graph-based deep learning algorithms and insightful interpretation presented in this study can be used as a trustworthy and effective tool to assess hematotoxicity in the development of new drugs.

Machine learning-based scoring functions (MLSFs) have become a very favorable alternative to classical scoring functions because of their potential superior screening performance. However, the information of negative data used to construct MLSFs was rarely reported in the literature, and meanwhile the putative inactive molecules recorded in existing databases usually have obvious bias from active molecules. Here we proposed an easy-to-use method named AMLSF that combines active learning using negative molecular selection strategies with MLSF, which can iteratively improve the quality of inactive sets and thus reduce the false positive rate of virtual screening. We chose energy auxiliary terms learning as the MLSF and validated our method on eight targets in the diverse subset of DUD-E. For each target, we screened the IterBioScreen database by AMLSF and compared the screening results with those of the four control models. The results illustrate that the number of active molecules in the top 1000 molecules identified by AMLSF was significantly higher than those identified by the control models. In addition, the free energy calculation results for the top 10 molecules screened out by the AMLSF, null model and control models based on DUD-E also proved that more active molecules can be identified, and the false positive rate can be reduced by AMLSF.

Traditional Chinese Medicine (TCM) has been widely used in the treatment of various diseases for millennia. In the modernization process of TCM, TCM ingredient databases are playing more and more important roles. However, most of the existing TCM ingredient databases do not provide simplification function for extracting key ingredients in each herb or formula, which hinders the research on the mechanism of actions of the ingredients in TCM databases. The lack of quality control and standardization of the data in most of these existing databases is also a prominent disadvantage. Therefore, we developed a Traditional Chinese Medicine Simplified Integrated Database (TCMSID) with high storage, high quality and standardization. The database includes 499 herbs registered in the Chinese pharmacopeia with 20,015 ingredients, 3270 targets as well as corresponding detailed information. TCMSID is not only a database of herbal ingredients, but also a TCM simplification platform. Key ingredients from TCM herbs are available to be screened out and regarded as representatives to explore the mechanism of TCM herbs by implementing multi-tool target prediction and multilevel network construction. TCMSID provides abundant data sources and analysis platforms for TCM simplification and drug discovery, which is expected to promote modernization and internationalization of TCM and enhance its international status in the future. TCMSID is freely available at https://tcm.scbdd.com.