RESUMO
In drug discovery, molecular docking methods face challenges in accurately predicting energy. Scoring functions used in molecular docking often fail to simulate complex protein-ligand interactions fully and accurately leading to biases and inaccuracies in virtual screening and target predictions. We introduce the "Docking Score ML", developed from an analysis of over 200,000 docked complexes from 155 known targets for cancer treatments. The scoring functions used are founded on bioactivity data sourced from ChEMBL and have been fine-tuned using both supervised machine learning and deep learning techniques. We validated our approach extensively using multiple data sets such as validation of selectivity mechanism, the DUDE, DUD-AD, and LIT-PCBA data sets, and performed a multitarget analysis on drugs like sunitinib. To enhance prediction accuracy, feature fusion techniques were explored. By merging the capabilities of the Graph Convolutional Network (GCN) with multiple docking functions, our results indicated a clear superiority of our methodologies over conventional approaches. These advantages demonstrate that Docking Score ML is an efficient and accurate tool for virtual screening and reverse docking.
Assuntos
Aprendizado de Máquina , Simulação de Acoplamento Molecular , Ligantes , Humanos , Descoberta de Drogas/métodos , Proteínas/química , Proteínas/metabolismo , Avaliação Pré-Clínica de Medicamentos/métodos , Antineoplásicos/química , Antineoplásicos/farmacologia , Antineoplásicos/metabolismo , Interface Usuário-ComputadorRESUMO
Myeloid cell leukemia 1 (Mcl1), a critical protein that regulates apoptosis, has been considered as a promising target for antitumor drugs. The conventional pharmacophore screening approach has limitations in conformation sampling and data mining. Here, we offered an innovative solution to identify Mcl1 inhibitors with molecular dynamics-refined pharmacophore and machine learning methods. Considering the safety and druggability of FDA-approved drugs, virtual screening of the database was performed to discover Mcl1 inhibitors, and the hit was subsequently validated via TR-FRET, cytotoxicity, and flow cytometry assays. To reveal the binding characteristics shared by the hit and a typical Mcl1 selective inhibitor, we employed quantum mechanics and molecular mechanics (QM/MM) calculations, umbrella sampling, and metadynamics in this work. The combined studies suggested that fluvastatin had promising cell inhibitory potency and was suitable for further investigation. We believe that this research will shed light on the discovery of novel Mcl1 inhibitors that can be used as a supplemental treatment against leukemia and provide a possible method to improve the accuracy of drug repurposing with limited computational resources while balancing the costs of experimentation well.
Assuntos
Antineoplásicos , Reposicionamento de Medicamentos , Aprendizado de Máquina , Simulação de Dinâmica Molecular , Proteína de Sequência 1 de Leucemia de Células Mieloides , Proteína de Sequência 1 de Leucemia de Células Mieloides/antagonistas & inibidores , Proteína de Sequência 1 de Leucemia de Células Mieloides/metabolismo , Humanos , Antineoplásicos/farmacologia , Antineoplásicos/química , Teoria Quântica , Linhagem Celular Tumoral , Fluvastatina/farmacologia , Fluvastatina/química , FarmacóforoRESUMO
Blockade of the programmed cell death-1 (PD-1)/programmed cell death ligand 1 (PD-L1) pathway is an attractive strategy for immunotherapy, but the clinical application of small molecule PD-1/PD-L1 inhibitors remains unclear. In this work, based on BMS-202 and our previous work YLW-106, a series of compounds with benzo[d]isothiazol structure as scaffold were designed and synthesized. Their inhibitory activity against PD-1/PD-L1 interaction was evaluated by a homogeneous time-resolved fluorescence (HTRF) assay. Among them, LLW-018 (27c) exhibited the most potent inhibitory activity with an IC50 value of 2.61 nM. The cellular level assays demonstrated that LLW-018 exhibited low cytotoxicity against Jurkat T and MDA-MB-231. Further cell-based PD-1/PD-L1 blockade bioassays based on PD-1 NFAT-Luc Jurkat cells and PD-L1 TCR Activator CHO cells indicated that LLW-018 could interrupt PD-1/PD-L1 interaction with an IC50 value of 0.88 µM. Multi-computational methods, including molecular docking, molecular dynamics, MM/GBSA, MM/PBSA, Metadynamics, and QM/MM MD were utilized on PD-L1 dimer complexes, which revealed the binding modes and dissociation process of LLW-018 and C2-symmetric small molecule inhibitor LCH1307. These results suggested that LLW-018 exhibited promising potency as a PD-1/PD-L1 inhibitor for further investigation.
Assuntos
Antígeno B7-H1 , Desenho de Fármacos , Receptor de Morte Celular Programada 1 , Humanos , Antígeno B7-H1/metabolismo , Antígeno B7-H1/antagonistas & inibidores , Receptor de Morte Celular Programada 1/antagonistas & inibidores , Receptor de Morte Celular Programada 1/metabolismo , Relação Estrutura-Atividade , Estrutura Molecular , Relação Dose-Resposta a Droga , Bibliotecas de Moléculas Pequenas/farmacologia , Bibliotecas de Moléculas Pequenas/química , Bibliotecas de Moléculas Pequenas/síntese química , Células Jurkat , Simulação de Acoplamento Molecular , Tiazóis/farmacologia , Tiazóis/química , Tiazóis/síntese química , Animais , Benzotiazóis/farmacologia , Benzotiazóis/química , Benzotiazóis/síntese química , Antineoplásicos/farmacologia , Antineoplásicos/síntese química , Antineoplásicos/químicaRESUMO
Virtual screening-based molecular similarity and fingerprint are crucial in drug design, target prediction, and ADMET prediction, aiding in identifying potential hits and optimizing lead compounds. However, challenges such as lack of comprehensive open-source molecular fingerprint databases and efficient search methods for virtual screening are prevalent. To address these issues, we introduce FaissMolLib, an open-source virtual screening tool that integrates 2.8 million compounds from ChEMBL and ZINC databases. Notably, FaissMolLib employs the highly efficient Faiss search algorithm, outperforming the Tanimoto algorithm in identifying similar molecules with its tighter clustering in scatter plots and lower mean, standard deviation, and variance in key molecular properties. This feature enables FaissMolLib to screen 2.8 million compounds in just 0.05â¯seconds, offering researchers an efficient, easily deployable solution for virtual screening on laptops and building unique compound databases. This significant advancement holds great potential for accelerating drug discovery efforts and enhancing chemical data analysis. FaissMolLib is freely available at http://liuhaihan.gnway.cc:80. The code and dataset of FaissMolLib are freely available at https://github.com/Superhaihan/FiassMolLib.