RESUMO
Hepatitis C, a particularly dangerous form of viral hepatitis caused by hepatitis C virus (HCV) infection, is a major socio-economic and public health problem. Due to the rapid development of deep learning, it has become a common practice to apply deep learning to the healthcare industry to improve the effectiveness and accuracy of disease identification. In order to improve the effectiveness and accuracy of hepatitis C detection, this study proposes an improved denoising autoencoder (IDAE) and applies it to hepatitis C disease detection. Conventional denoising autoencoder introduces random noise at the input layer of the encoder. However, due to the presence of these features, encoders that directly add random noise may mask certain intrinsic properties of the data, making it challenging to learn deeper features. In this study, the problem of data information loss in traditional denoising autoencoding is addressed by incorporating the concept of residual neural networks into an enhanced denoising autoencoder. In our experimental study, we applied this enhanced denoising autoencoder to the open-source Hepatitis C dataset and the results showed significant results in feature extraction. While existing baseline machine learning methods have less than 90% accuracy and integrated algorithms and traditional autoencoders have only 95% correctness, the improved IDAE achieves 99% accuracy in the downstream hepatitis C classification task, which is a 9% improvement over a single algorithm, and a nearly 4% improvement over integrated algorithms and other autoencoders. The above results demonstrate that IDAE can effectively capture key disease features and improve the accuracy of disease prediction in hepatitis C data. This indicates that IDAE has the potential to be widely used in the detection and management of hepatitis C and similar diseases, especially in the development of early warning systems, progression prediction and personalised treatment strategies.
Assuntos
Aprendizado Profundo , Hepatite C , Redes Neurais de Computação , Humanos , Hepatite C/virologia , Hepatite C/diagnóstico , Hepacivirus/isolamento & purificação , Hepacivirus/genética , AlgoritmosRESUMO
The drug-drug interaction (DDI) between amiodarone (AMIO) and sofosbuvir (SOF), a direct-acting hepatitis-C NS5B nucleotide polymerase inhibitor, has been associated with severe bradyarrhythmia in patients. Recent cryo-EM data has revealed that this DDI occurs at the α-subunit of L-type Cav channels, with AMIO binding at the fenestration site and SOF [or MSD nucleotide inhibitor #1 (MNI-1): analog of SOF] binding at the central cavity of the conductance pathway. In this study, we investigated the DDI between 21 AMIO analogs, including dronedarone (DRON) and MNI-1 (or SOF) in human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) and hCav1.2 models. Our findings indicate that among the tested AMIO analogs in hiPSC-CMs at clinically relevant concentrations, only three analogs (AA-9, AA-10, and AA-17) were able to effectively substitute for AMIO in this DDI with 1 µM MNI-1. This highlights the importance of the diethyl amino group of AMIO for interacting with MNI-1. In the hCav1.2 model, desethylamiodarone (AA-12) demonstrated synergy with 90 µM MNI-1, while three other analogs with modifications to the position of the diethyl amino group or removal of iodo groups showed weaker synergy with 90 µM MNI-1. Interestingly, DRON did not exhibit any interaction with 270 µM SOF or 90 µM MNI-1, suggesting that it could safely replace AMIO in patients requiring SOF treatment, other clinically relevant differences considered. Overall, our functional data align with the cryo-EM data, highlighting that this DDI is dependent on the structure of AMIO and cardiomyocyte resting membrane potential. SIGNIFICANCE STATEMENT: Our findings point to specific residues in the AMIO molecule playing a critical role in the DDI between AMIO and MNI-1 (SOF analog), confirming cryo-EM results. Applied at clinically relevant AMIO's concentrations or projected MNI-1's concentrations at the resting potentials mimicking the sinoatrial node, this DDI significantly slowed down or completely inhibited the beating of hiPSC-CMs. Finally, these in vitro results support the safe replacement of AMIO (Cordarone) with DRON (Multaq) for patients requiring SOF treatment, other clinical caveats considered.
Assuntos
Amiodarona , Células-Tronco Pluripotentes Induzidas , Humanos , Amiodarona/farmacologia , Amiodarona/metabolismo , Nucleotídeos/farmacologia , Células-Tronco Pluripotentes Induzidas/metabolismo , Interações Medicamentosas , Relação Estrutura-AtividadeRESUMO
Homogenous molecular photocatalysts for CO2 reduction, especially metal complex-based photosensitizerâcatalyst assemblages, have been attracting extensive research interests due to their efficiency and customizability. However, their low durability and recyclability limit practical applications. In this work, we immobilized the catalysts of metal terpyridyl complexes and the photosensitizer of [Ru(bpy)3]Cl2 onto the surface of carbon nanotubes through covalent bonds and electrostatic interactions, respectively, transforming the homogeneous system into a heterogeneous one. Our characterizations prove that these metal complexes are well dispersed on CNTs with a high loading (ca. 12 wt.%). Photocatalytic measurements reveal that catalytic activity is remarkably enhanced when the molecular catalysts are anchored, which is three times higher than that of homogeneous molecular catalysts. Moreover, when the photosensitizer of [Ru(bpy)3]Cl2 is immobilized, the side reaction of hydrogen evolution is completely suppressed and the selectivity for CO production reaches 100%, with its durability also significantly improved. This work provides an effective pathway for constructing heterogeneous photocatalysts based on rational assembly of efficient molecular photosensitizers and catalysts.