FP-GNN: a versatile deep learning architecture for enhanced molecular property prediction.

Accurate prediction of molecular properties, such as physicochemical and bioactive properties, as well as ADME/T (absorption, distribution, metabolism, excretion and toxicity) properties, remains a fundamental challenge for molecular design, especially for drug design and discovery. In this study, we advanced a novel deep learning architecture, termed FP-GNN (fingerprints and graph neural networks), which combined and simultaneously learned information from molecular graphs and fingerprints for molecular property prediction. To evaluate the FP-GNN model, we conducted experiments on 13 public datasets, an unbiased LIT-PCBA dataset and 14 phenotypic screening datasets for breast cell lines. Extensive evaluation results showed that compared to advanced deep learning and conventional machine learning algorithms, the FP-GNN algorithm achieved state-of-the-art performance on these datasets. In addition, we analyzed the influence of different molecular fingerprints, and the effects of molecular graphs and molecular fingerprints on the performance of the FP-GNN model. Analysis of the anti-noise ability and interpretation ability also indicated that FP-GNN was competitive in real-world situations. Collectively, FP-GNN algorithm can assist chemists, biologists and pharmacists in predicting and discovering better molecules with desired functions or properties.

Highly Accurate and Explainable Predictions of Small-Molecule Antioxidants for Eight In Vitro Assays Simultaneously through an Alternating Multitask Learning Strategy.

Small molecule antioxidants can inhibit or retard oxidation reactions and protect against free radical damage to cells, thus playing a key role in food, cosmetics, pharmaceuticals, the environment, as well as materials. Experimentally driven antioxidant discovery is a major paradigm, and computationally assisted antioxidants are rarely reported. In this study, a functional-group-based alternating multitask self-supervised molecular representation learning method is proposed to simultaneously predict the antioxidant activities of small molecules for eight commonly used in vitro antioxidant assays. Extensive evaluation results reveal that compared with the baseline models, the multitask FG-BERT model achieves the best overall predictive performance, with the highest average F1, BA, ROC-AUC, and PRC-AUC values of 0.860, 0.880, 0.954, and 0.937 for the test sets, respectively. The Y-scrambling testing results further demonstrate that such a deep learning model was not constructed by accident and that it has reliable predictive capabilities. Additionally, the excellent interpretability of the multitask FG-BERT model makes it easy to identify key structural fragments/groups that contribute significantly to the antioxidant effect of a given molecule. Finally, an online antioxidant activity prediction platform called AOP (freely available at https://aop.idruglab.cn/) and its local version were developed based on the high-quality multitask FG-BERT model for experts and nonexperts in the field. We anticipate that it will contribute to the discovery of novel small-molecule antioxidants.

HiGNN: A Hierarchical Informative Graph Neural Network for Molecular Property Prediction Equipped with Feature-Wise Attention.

Elucidating and accurately predicting the druggability and bioactivities of molecules plays a pivotal role in drug design and discovery and remains an open challenge. Recently, graph neural networks (GNNs) have made remarkable advancements in graph-based molecular property prediction. However, current graph-based deep learning methods neglect the hierarchical information of molecules and the relationships between feature channels. In this study, we propose a well-designed hierarchical informative graph neural network (termed HiGNN) framework for predicting molecular property by utilizing a corepresentation learning of molecular graphs and chemically synthesizable breaking of retrosynthetically interesting chemical substructure (BRICS) fragments. Furthermore, a plug-and-play feature-wise attention block is first designed in HiGNN architecture to adaptively recalibrate atomic features after the message passing phase. Extensive experiments demonstrate that HiGNN achieves state-of-the-art predictive performance on many challenging drug discovery-associated benchmark data sets. In addition, we devise a molecule-fragment similarity mechanism to comprehensively investigate the interpretability of the HiGNN model at the subgraph level, indicating that HiGNN as a powerful deep learning tool can help chemists and pharmacists identify the key components of molecules for designing better molecules with desired properties or functions. The source code is publicly available at https://github.com/idruglab/hignn.

Large-scale comparison of machine learning methods for profiling prediction of kinase inhibitors.

Conventional machine learning (ML) and deep learning (DL) play a key role in the selectivity prediction of kinase inhibitors. A number of models based on available datasets can be used to predict the kinase profile of compounds, but there is still controversy about the advantages and disadvantages of ML and DL for such tasks. In this study, we constructed a comprehensive benchmark dataset of kinase inhibitors, involving in 141,086 unique compounds and 216,823 well-defined bioassay data points for 354 kinases. We then systematically compared the performance of 12 ML and DL methods on the kinase profiling prediction task. Extensive experimental results reveal that (1) Descriptor-based ML models generally slightly outperform fingerprint-based ML models in terms of predictive performance. RF as an ensemble learning approach displays the overall best predictive performance. (2) Single-task graph-based DL models are generally inferior to conventional descriptor- and fingerprint-based ML models, however, the corresponding multi-task models generally improves the average accuracy of kinase profile prediction. For example, the multi-task FP-GNN model outperforms the conventional descriptor- and fingerprint-based ML models with an average AUC of 0.807. (3) Fusion models based on voting and stacking methods can further improve the performance of the kinase profiling prediction task, specifically, RF::AtomPairs + FP2 + RDKitDes fusion model performs best with the highest average AUC value of 0.825 on the test sets. These findings provide useful information for guiding choices of the ML and DL methods for the kinase profiling prediction tasks. Finally, an online platform called KIPP ( https://kipp.idruglab.cn ) and python software are developed based on the best models to support the kinase profiling prediction, as well as various kinase inhibitor identification tasks including virtual screening, compound repositioning and target fishing.

DEEPCYPs: A deep learning platform for enhanced cytochrome P450 activity prediction.

Cytochrome P450 (CYP) is a superfamily of heme-containing oxidizing enzymes involved in the metabolism of a wide range of medicines, xenobiotics, and endogenous compounds. Five of the CYPs (1A2, 2C9, 2C19, 2D6, and 3A4) are responsible for metabolizing the vast majority of approved drugs. Adverse drug-drug interactions, many of which are mediated by CYPs, are one of the important causes for the premature termination of drug development and drug withdrawal from the market. In this work, we reported in silicon classification models to predict the inhibitory activity of molecules against these five CYP isoforms using our recently developed FP-GNN deep learning method. The evaluation results showed that, to the best of our knowledge, the multi-task FP-GNN model achieved the best predictive performance with the highest average AUC (0.905), F1 (0.779), BA (0.819), and MCC (0.647) values for the test sets, even compared to advanced machine learning, deep learning, and existing models. Y-scrambling testing confirmed that the results of the multi-task FP-GNN model were not attributed to chance correlation. Furthermore, the interpretability of the multi-task FP-GNN model enables the discovery of critical structural fragments associated with CYPs inhibition. Finally, an online webserver called DEEPCYPs and its local version software were created based on the optimal multi-task FP-GNN model to detect whether compounds bear potential inhibitory activity against CYPs, thereby promoting the prediction of drug-drug interactions in clinical practice and could be used to rule out inappropriate compounds in the early stages of drug discovery and/or identify new CYPs inhibitors.

DeepCancerMap: A versatile deep learning platform for target- and cell-based anticancer drug discovery.

Discovering new anticancer drugs has been widely concerned and remains an open challenge. Target- and phenotypic-based experimental screening represent two mainstream anticancer drug discovery methods, which suffer from time-consuming, labor-intensive, and high experimental costs. In this study, we collected 485,900 compounds involving in 3,919,974 bioactivity records against 426 anticancer targets and 346 cancer cell lines from academic literature, as well as 60 tumor cell lines from NCI-60 panel. A total of 832 classification models (426 target- and 406 cell-based predictive models) were then constructed to predict the inhibitory activity of compounds against targets and tumor cell lines using FP-GNN deep learning method. Compared to the classical machine learning and deep learning methods, the FP-GNN models achieve considerable overall predictive performance, with the highest AUC values of 0.91, 0.88, 0.91 for the test sets of targets, academia-sourced and NCI-60 cancer cell lines, respectively. A user-friendly webserver called DeepCancerMap and its local version were developed based on these high-quality models, enabling users to perform anticancer drug discovery-related tasks including large-scale virtual screening, profiling prediction of anticancer agents, target fishing, and drug repositioning. We anticipate this platform to accelerate the discovery of anticancer drugs in the field. DeepCancerMap is freely available at https://deepcancermap.idruglab.cn.

Corrigendum: Machine Learning Enables Accurate and Rapid Prediction of Active Molecules Against Breast Cancer Cells.

[This corrects the article DOI: 10.3389/fphar.2021.796534.].

A multi-task FP-GNN framework enables accurate prediction of selective PARP inhibitors.

PARP (poly ADP-ribose polymerase) family is a crucial DNA repair enzyme that responds to DNA damage, regulates apoptosis, and maintains genome stability; therefore, PARP inhibitors represent a promising therapeutic strategy for the treatment of various human diseases including COVID-19. In this study, a multi-task FP-GNN (Fingerprint and Graph Neural Networks) deep learning framework was proposed to predict the inhibitory activity of molecules against four PARP isoforms (PARP-1, PARP-2, PARP-5A, and PARP-5B). Compared with baseline predictive models based on four conventional machine learning methods such as RF, SVM, XGBoost, and LR as well as six deep learning algorithms such as DNN, Attentive FP, MPNN, GAT, GCN, and D-MPNN, the evaluation results indicate that the multi-task FP-GNN method achieves the best performance with the highest average BA, F1, and AUC values of 0.753 ± 0.033, 0.910 ± 0.045, and 0.888 ± 0.016 for the test set. In addition, Y-scrambling testing successfully verified that the model was not results of chance correlation. More importantly, the interpretability of the multi-task FP-GNN model enabled the identification of key structural fragments associated with the inhibition of each PARP isoform. To facilitate the use of the multi-task FP-GNN model in the field, an online webserver called PARPi-Predict and its local version software were created to predict whether compounds bear potential inhibitory activity against PARPs, thereby contributing to design and discover better selective PARP inhibitors.

Machine Learning Enables Accurate and Rapid Prediction of Active Molecules Against Breast Cancer Cells.

Breast cancer (BC) has surpassed lung cancer as the most frequently occurring cancer, and it is the leading cause of cancer-related death in women. Therefore, there is an urgent need to discover or design new drug candidates for BC treatment. In this study, we first collected a series of structurally diverse datasets consisting of 33,757 active and 21,152 inactive compounds for 13 breast cancer cell lines and one normal breast cell line commonly used in in vitro antiproliferative assays. Predictive models were then developed using five conventional machine learning algorithms, including naïve Bayesian, support vector machine, k-Nearest Neighbors, random forest, and extreme gradient boosting, as well as five deep learning algorithms, including deep neural networks, graph convolutional networks, graph attention network, message passing neural networks, and Attentive FP. A total of 476 single models and 112 fusion models were constructed based on three types of molecular representations including molecular descriptors, fingerprints, and graphs. The evaluation results demonstrate that the best model for each BC cell subtype can achieve high predictive accuracy for the test sets with AUC values of 0.689-0.993. Moreover, important structural fragments related to BC cell inhibition were identified and interpreted. To facilitate the use of the model, an online webserver called ChemBC (http://chembc.idruglab.cn/) and its local version software (https://github.com/idruglab/ChemBC) were developed to predict whether compounds have potential inhibitory activity against BC cells.