Ligand- and structure-based identification of novel CDK9 inhibitors for the potential treatment of leukemia

Meta Learning with Attention Based FP-GNNs for Few-Shot Molecular Property Prediction

Molecular property prediction holds significant importance in drug discovery, enabling the identification of biologically active compounds with favorable drug-like properties. However, the low data problem, arising from the scarcity of labeled data in drug discovery, poses a substantial obstacle for accurate predictions. To address this challenge, we introduce a novel architecture, AttFPGNN-MAML, for few-shot molecular property prediction. The proposed approach incorporates a hybrid feature representation to enrich molecular representations and model intermolecular relationships specific to the task. By leveraging ProtoMAML, a meta-learning strategy, our model is trained and adapted to new tasks. Evaluation on two few-shot data sets, MoleculeNet and FS-Mol, demonstrates our method's superior performance in three out of four tasks and across various support set sizes. These results convincingly validate the effectiveness of our method in the realm of few-shot molecular property prediction. The source code is publicly available at https://github.com/sanomics-lab/AttFPGNN-MAML.

Orally Administered Drugs and Their Complicated Relationship with Our Gastrointestinal Tract

Orally administered compounds represent the great majority of all pharmaceutical compounds produced for human use and are the most popular among patients since they are practical and easy to self-administer. Following ingestion, orally administered drugs begin a "perilous" journey down the gastrointestinal tract and their bioavailability is modulated by numerous factors. The gastrointestinal (GI) tract anatomy can modulate drug bioavailability and accounts for interpatient drug response heterogeneity. Furthermore, host genetics is a contributor to drug bioavailability modulation. Importantly, a component of the GI tract that has been gaining notoriety with regard to drug treatment interactions is the gut microbiota, which shares a two-way interaction with pharmaceutical compounds in that they can be influenced by and are able to influence administered drugs. Overall, orally administered drugs are a patient-friendly treatment option. However, during their journey down the GI tract, there are numerous host factors that can modulate drug bioavailability in a patient-specific manner.

Machine learning in onco-pharmacogenomics: a path to precision medicine with many challenges

Over the past two decades, Next-Generation Sequencing (NGS) has revolutionized the approach to cancer research. Applications of NGS include the identification of tumor specific alterations that can influence tumor pathobiology and also impact diagnosis, prognosis and therapeutic options. Pharmacogenomics (PGx) studies the role of inheritance of individual genetic patterns in drug response and has taken advantage of NGS technology as it provides access to high-throughput data that can, however, be difficult to manage. Machine learning (ML) has recently been used in the life sciences to discover hidden patterns from complex NGS data and to solve various PGx problems. In this review, we provide a comprehensive overview of the NGS approaches that can be employed and the different PGx studies implicating the use of NGS data. We also provide an excursus of the ML algorithms that can exert a role as fundamental strategies in the PGx field to improve personalized medicine in cancer.

Identification of thrombopoiesis inducer based on a hybrid deep neural network model

Thrombocytopenia is a common haematological problem worldwide. Currently, there are no relatively safe and effective agents for the treatment of thrombocytopenia. To address this challenge, we propose a computational method that enables the discovery of novel drug candidates with haematopoietic activities. Based on different types of molecular representations, three deep learning (DL) algorithms, namely recurrent neural networks (RNNs), deep neural networks (DNNs), and hybrid neural networks (RNNs+DNNs), were used to develop classification models to distinguish between active and inactive compounds. The evaluation results illustrated that the hybrid DL model exhibited the best prediction performance, with an accuracy of 97.8 % and Matthews correlation coefficient of 0.958 on the test dataset. Subsequently, we performed drug discovery screening based on the hybrid DL model and identified a compound from the FDA-approved drug library that was structurally divergent from conventional drugs and showed a potential therapeutic action against thrombocytopenia. The novel drug candidate wedelolactone significantly promoted megakaryocyte differentiation in vitro and increased platelet levels and megakaryocyte differentiation in irradiated mice with no systemic toxicity. Overall, our work demonstrates how artificial intelligence can be used to discover novel drugs against thrombocytopenia.

Exploring the cytotoxic effect and CDK-9 inhibition potential of novel sulfaguanidine-based azopyrazolidine-3,5-diones and 3,5-diaminoazopyrazoles

Regarding the structural analysis of variable effective CDK-9 suppressors, we record the design and synthesis of two new sets of sulfaguanidine-based azopyrazolidine-3,5-diones and 3,5-diaminoazopyrazoles with expected anticancer and CDK-9 inhibiting activity. In the designed molecules, the pyrazole ring and sulphaguanidine fragment were linked together for the first time through diazo linkers as they are expected to enhance the anticancer activity and CDK degrading interaction. All derivatives have been estimated regarding their cytotoxic activity toward three tumor cells where CDK overexpression has been reported (HePG2, HCT-116, and MCF-7). Among these, four derivatives VII, VIII, X, and XIII exerted potent cytotoxicity against the chosen tumor cells presenting IC₅₀ range equal to 2.86-25.89 µM. As well cytotoxicity on non-cancer cells and CDK-9 inhibition assay have been also assessed for these candidates to evaluate their selectivity indices and enzyme inhibition. The 3,5-diaminopyrazole-1-carboxamide derivative XIII showed a superior combined profile as cytotoxic with high selectivity toward cancer cells (HePG2: IC₅₀ = 6.57 µM, SI = 13.31; HCT-116: IC₅₀ = 9.54 µM, SI = 9.16; MCF-7: IC₅₀ = 7.97 µM, SI = 10.97). Accordingly, it has been chosen to evaluate its probable mechanistic effect both in vitro (via enzyme assay, apoptosis induction, and cell cycle study) as well as in silico (through molecular docking). Overall, this work introduces the 3,5-diaminopyrazole-1-carboxamide derivative XIII as a potent CDK-9 inhibitor candidate (IC₅₀ = 0.16 µM) that merits further investigations for the management of breast, colorectal, and hepatic malignancies.

Development of the "hidden" multi-target-directed ligands by AChE/BuChE for the treatment of Alzheimer's disease

Accumulation of evidences suggested that excessive amounts of AChE and BuChE in the brain of AD patients at the different stage of AD, which could hydrolyze ACh and accelerated Aβ aggregation. To develop new "hidden" multifunctional agents through AChE/BuChE would be a promising strategy to treat AD. To this end, firstly, a series of chalcone derivatives with chelating property was designed and synthesized. The in vitro results showed that compound 3f indicated significant selective MAO-B inhibitory activity (IC₅₀ = 0.67 μM) and remarkable anti-inflammatory property. It also significantly inhibited self-induced Aβ_1-42 aggregation and showed remarkable neuroprotective effects on Aβ_25-35-induced PC12 cell injury. Furthermore, compound 3f was a selective metal chelator and could inhibit Cu²⁺-induced Aβ_1-42 aggregation. Based on this, the carbamate fragment was introduced to compound 3f to obtain carbamate derivatives. The biological activity results exhibited that compound 4b showed good BBB permeability, good AChE inhibitory potency (IC₅₀ = 5.3 μM), moderate BuChE inhibitory potency (IC₅₀ = 12.4 μM), significant MAO-B inhibitory potency, anti-inflammation potency on LPS-induced BV-2 cells and neuroprotective effects on Aβ_25-35-induced PC12 cell injury. Compared with 3f, compound 4b did not show obvious chelation property. Significantly, compound 4b could be activated by AChE/BuChE following inhibition of AChE/BuChE to liberate an active multifunctional chelator 3f, which was consistent with our original intention. More importantly, compounds 3f and 4b presented favorable ADME properties and good stability in artificial gastrointestinal fluid, blood plasma and rat liver microsomes. The in vivo results suggested that compound 4b (0.0195 μg/mL) could significantly improve dyskinesia and reaction capacity of the AlCl₃-induced zebrafish AD model by increasing the level of ACh. Together our data suggest that compound 4b was a promising "hidden" multifunctional agent by AChE/BuChE, and this strategy deserved further development for the treatment of AD.

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.

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.