RESUMO
In the past few decades, chronic hepatitis B caused by hepatitis B virus (HBV) has been one of the most serious diseases to human health. The development of innovative systems is essential for preventing the complex pathogenesis of hepatitis B and reducing side effects caused by drugs. HBV inhibitory drugs have been developed through various compounds, and they are often limited by routine experimental screening and delay drug development. More recently, virtual screening of compounds has gradually been used in drug research with strong computational capability and is further applied in anti-HBV drug screening, thus facilitating a reliable drug screening process. However, the lack of structural information in traditional compound analysis is an important hurdle for unsatisfactory efficiency in drug screening. Here, a natural language processing technique was adopted to analyze compound simplified molecular input line entry system strings. By using the targeted optimized word2vec model for pretraining, we can accurately represent the relationship between the compound and its substructure. The machine learning model based on training results can effectively predict the inhibitory effect of compounds on HBV and liver toxicity. The reliability of the model is verified by the results of wet-lab experiments. In addition, a tool has been published to predict potential compounds. Hence, this article provides a new perspective on the prediction of compound properties for anti-HBV drugs that can help improve hepatitis B diagnosis and further develop human health in the future.
Assuntos
Vírus da Hepatite B , Hepatite B , Antivirais/farmacologia , Antivirais/uso terapêutico , Descoberta de Drogas/métodos , Hepatite B/tratamento farmacológico , Humanos , Reprodutibilidade dos TestesRESUMO
Existing formats based on the simplified molecular input line entry system (SMILES) encoding and molecular graph structure are designed to encode the complete semantic and structural information of molecules. However, the physicochemical properties of molecules are complex, and a single encoding of molecular features from SMILES sequences or molecular graph structures cannot adequately represent molecular information. Aiming to address this problem, this study proposes a sequence graph cross-attention (SG-ATT) representation architecture for a molecular property prediction model to efficiently use domain knowledge to enhance molecular graph feature encoding and combine the features of molecular SMILES sequences. The SG-ATT fuses the two-dimensional molecular features so that the current model input molecular information contains molecular structure information and semantic information. The SG-ATT was tested on nine molecular property prediction tasks. Among them, the biggest SG-ATT model performance improvement was 4.5% on the BACE dataset, and the average model performance improvement was 1.83% on the full dataset. Additionally, specific model interpretability studies were conducted to showcase the performance of the SG-ATT model on different datasets. In-depth analysis was provided through case studies of in vitro validation. Finally, network tools for molecular property prediction were developed for the use of researchers.
RESUMO
Latest studies confirmed that abnormal function of histone deacetylase (HDAC) plays a pivotal role in formation of tumors and is a potential therapeutic target for treating breast cancer. In this research, in-silico drug discovery approaches via quantitative structure activity relationship (QSAR) and molecular docking simulations were adapted to 43 compounds of indazole derivatives with HDAC inhibition for anticancer activity against breast cancer. The QSAR models were built from multiple linear regression (MLR), and models predictability was cross-validated by leave-one-out (LOO) method. Based on these results, compounds C32, C26 and C31 from model 3 showed superior inhibitory activity with pIC50 of 9.30103, 9.1549 and 9.1549. We designed 10 novel compounds with molecular docking scores ranging from -7.9 to -9.3â¯kcal/mol. The molecular docking simulation results reveal that amino acid residues ILE1122 and PRO1123 play a significant role in bonding with 6CE6 protein. Furthermore, newly designed compounds P5, P2 and P7 with high docking scores of -9.3â¯kcal/mol, -8.9â¯kcal/mol and -8.8â¯kcal/mol than FDA-approved drug Raloxifene (-8.5â¯kcal/mol) and aid in establishment of potential drug candidate for HDAC inhibitors. The in-silico ADME functionality is used in the final phase to evaluate newly designed inhibitors as potential drug candidates. The results suggest that newly designed compounds P5, P2 and P7 can be used as a potential anti-breast cancer drug candidate.
Assuntos
Antineoplásicos , Neoplasias da Mama , Desenho de Fármacos , Inibidores de Histona Desacetilases , Indazóis , Simulação de Acoplamento Molecular , Relação Quantitativa Estrutura-Atividade , Indazóis/química , Indazóis/farmacologia , Inibidores de Histona Desacetilases/química , Inibidores de Histona Desacetilases/farmacologia , Humanos , Neoplasias da Mama/tratamento farmacológico , Neoplasias da Mama/patologia , Antineoplásicos/química , Antineoplásicos/farmacologia , Feminino , Estrutura Molecular , Ensaios de Seleção de Medicamentos Antitumorais , Histona Desacetilases/metabolismo , Proliferação de Células/efeitos dos fármacosRESUMO
Compound-protein interaction (CPI) affinity prediction plays an important role in reducing the cost and time of drug discovery. However, the interpretability of how fragments function in CPI is impacted by the fact that current methods ignore the affinity relationships between fragments of compounds and fragments of proteins in CPI modeling. This article introduces an improved Transformer called FOTF-CPI (a Fusion of Optimal Transport Fragments compound-protein interaction prediction model). We use an optimal transport-based fragmentation approach to improve the model's understanding of compound and protein sequences. Additionally, a fused attention mechanism is employed, which combines the features of fragments to capture full affinity information. This fused attention redistributes higher attention scores to fragments with higher affinity. Experimental results show FOTF-CPI achieves an average 2% higher performance than other models on all three datasets. Furthermore, the visualization confirms the potential of FOTF-CPI for drug discovery applications.
RESUMO
Through the revolutionization of artificial intelligence (AI) technologies in clinical research, significant improvement is observed in diagnosis of cancer. Utilization of these AI technologies, such as machine and deep learning, is imperative for the discovery of novel anticancer drugs and improves existing/ongoing cancer therapeutics. However, building a model for complicated cancers and their types remains a challenge due to lack of effective therapeutics that hinder the establishment of effective computational tools. In this review, we exploit recent approaches and state-of-the-art in implementing AI methods for anticancer drug discovery, and discussed how advances in these applications need to be considered in the current cancer therapeutics. Considering the immense potential of AI, we explore molecular docking and their interactions to recognize metabolic activities that support drug design. Finally, we highlight corresponding strategies in applying machine and deep learning methods to various types of cancer with their pros and cons.
Assuntos
Antineoplásicos , Neoplasias , Humanos , Inteligência Artificial , Aprendizado de Máquina , Simulação de Acoplamento Molecular , Descoberta de Drogas/métodos , Neoplasias/tratamento farmacológico , Antineoplásicos/uso terapêuticoRESUMO
Drought is the primary and dominant natural cause of stress on vegetation, and thus, it needs our full attention. Current understanding of drought across extensive spatial measures, around the world, is considerably limited. As case studies to evaluate the feasibility of utilizing space-based solar-induced chlorophyll fluorescence (SIF) across extensive spatial measures, here, we have used data from 2007 to 2017 in Heilongjiang and Jiangsu provinces of China. The onset of the 2015 drought was accompanied by a substantial response of SIF from vegetation in both the provinces; these data were associated with changes in soil moisture, standardized precipitation evapotranspiration index, and emissivity. Our findings suggest that SIF can effectively provide the spatial and temporal progress of drought, as inferred through substantial associations with SIF normalized by absorbed photosynthetically active radiation (related to ΦF) and by photosynthetically active radiation (SIFpar). For the depiction of onset to drought, SIF, ΦF, and SIFpar provide a significant association and a quicker response than the leaf area index and the normalized difference vegetation index. Furthermore, we found that the correlation between gross primary productivity and SIF is highly substantial in both Heilongjiang (R2 = 0.85, p < 0.001) and Jiangsu (R2 = 0.75, p < 0.001) during the drought period. Our results indicate that continuing evaluation from space-based SIF can indeed provide an understanding of the seasonal differences in vegetation for evaluating the impact of drought across extensive spatial measures.