Background Gastric cancer is the third most lethal malignancy worldwide. A novel deep convolution neural network (DCNN) to perform visual tasks has been recently developed. The aim of this study was to build a system using the DCNN to detect early gastric cancer (EGC) without blind spots during esophagogastroduodenoscopy (EGD).
Methods 3170 gastric cancer and 5981 benign images were collected to train the DCNN to detect EGC. A total of 24549 images from different parts of stomach were collected to train the DCNN to monitor blind spots. Class activation maps were developed to automatically cover suspicious cancerous regions. A grid model for the stomach was used to indicate the existence of blind spots in unprocessed EGD videos.
Results The DCNN identified EGC from non-malignancy with an accuracy of 92.5 %, a sensitivity of 94.0 %, a specificity of 91.0 %, a positive predictive value of 91.3 %, and a negative predictive value of 93.8 %, outperforming all levels of endoscopists. In the task of classifying gastric locations into 10 or 26 parts, the DCNN achieved an accuracy of 90 % or 65.9 %, on a par with the performance of experts. In real-time unprocessed EGD videos, the DCNN achieved automated performance for detecting EGC and monitoring blind spots.
Conclusions We developed a system based on a DCNN to accurately detect EGC and recognize gastric locations better than endoscopists, and proactively track suspicious cancerous lesions and monitor blind spots during EGD.
3’-Azidothymidine (AZT) was the first approved antiviral for the treatment of human immunodeficiency virus (HIV). Reported efforts in clicking the 3’-azido group of AZT have not yielded 1,2,3-triazoles active against HIV or any other viruses. We report herein the first AZT-derived 1,2,3-triazoles with sub-micromolar potencies against HIV-1. The observed antiviral activities from the cytopathic effect (CPE) based assay were confirmed through a single replication cycle assay. Structure-activity-relationship (SAR) studies revealed two structural features key to antiviral activity: a bulky aromatic ring and the 1,5-substitution pattern on the triazole. Biochemical analysis of the corresponding triphosphates showed lower ATP-mediated nucleotide excision efficiency compared to AZT, which along with molecular modeling, suggests a mechanism of preferred translocation of triazoles into the P-site of HIV reverse transcriptase (RT). This mechanism is corroborated with the observed reduction of fold resistance of the triazole analogue to an AZT-resistant HIV variant (9-fold compared to 56-fold with AZT).
A new molecular scaffold featuring an N-hydroxyimide functionality and capable of inhibiting both reverse transcriptase (RT) and integrase (IN) of Human Immunodeficiency Virus (HIV) was rationally designed based on 1-[(2-hydroxyethoxy) methyl]-6-(phenylthio)-thymine (HEPT) non-nucleoside RT inhibitors (NNRTIs). The design involves a minimal 3-N hydroxylation of the pyrimidine ring of HEPT compound to yield a chelating triad which, along with the existing benzyl group, appeared to satisfy major structural requirements for IN binding. In the mean time, this chemical modification did not severely compromise the compound’s ability to inhibit RT. A preliminary structure-activity-relationship (SAR) study reveals that this N-3 OH is essential for IN inhibition and that the benzyl group on N-1 side chain is more important for IN binding than the one on C-6.
Bifunctional inhibitors were designed and synthesized based on 1-[(2-hydroxyethoxy)methyl]-6-(phenylthio)thymine (HEPT)a1 non-nucleoside reverse transcriptase (RT) inhibitors and diketoacid (DKA) integrase (IN) inhibitors. Biochemical studies revealed activity against RT and IN at low nanomolar and low micromolar concentrations, respectively. Exceptionally low IC50 values from a cell-based assay were achieved along with remarkably high therapeutic indices. Compound 7 was identified as the best compound of the series (IC50: 24 nM against RT, 4.4 microM against IN, and 10 nM against HIV-1).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.