Lung detection and severity prediction of pneumonia patients based on COVID-19 DET-PRE network.

BACKGROUND: The sudden outbreak of COVID-19 pneumonia has brought a heavy disaster to individuals globally. Facing this new virus, the clinicians have no automatic tools to assess the severity of pneumonia patients. METHODS: In the current work, a COVID-19 DET-PRE network with two pipelines was proposed. Firstly, the lungs in X-rays were detected and segmented through the improved YOLOv3 Dense network to remove redundant features. Then, the VGG16 classifier was pre-trained on the source domain, and the severity of the disease was predicted on the target domain by means of transfer learning. RESULTS: The experiment results demonstrated that the COVID-19 DET-PRE network can effectively detect the lungs from X-rays and accurately predict the severity of the disease. The mean average precisions (mAPs) of lung detection in patients with mild and severe illness were 0.976 and 0.983 respectively. Moreover, the accuracy of severity prediction of COVID-19 pneumonia can reach 86.1%. CONCLUSIONS: The proposed neural network has high accuracy, which is suitable for the clinical diagnosis of COVID-19 pneumonia.

Selective Binding and Redox-Activity on Parallel G-Quadruplexes by Pegylated Naphthalene Diimide-Copper Complexes.

G-quadruplexes (G4s) are higher-order supramolecular structures, biologically important in the regulation of many key processes. Among all, the recent discoveries relating to RNA-G4s, including their potential involvement as antiviral targets against COVID-19, have triggered the ever-increasing need to develop selective molecules able to interact with parallel G4s. Naphthalene diimides (NDIs) are widely exploited as G4 ligands, being able to induce and strongly stabilize these structures. Sometimes, a reversible NDI-G4 interaction is also associated with an irreversible one, due to the cleavage and/or modification of G4s by functional-NDIs. This is the case of NDI-Cu-DETA, a copper(II) complex able to cleave G4s in the closest proximity to the target binding site. Herein, we present two original Cu(II)-NDI complexes, inspired by NDI-Cu-DETA, differently functionalized with 2-(2-aminoethoxy)ethanol side-chains, to selectively drive redox-catalyzed activity towards parallel G4s. The selective interaction toward parallel G4 topology, controlled by the presence of 2-(2-aminoethoxy)ethanol side chains, was already firmly demonstrated by us using core-extended NDIs. In the present study, the presence of protonable moieties and the copper(II) cavity, increases the binding affinity and specificity of these two NDIs for a telomeric RNA-G4. Once defined the copper coordination relationship and binding constants by competition titrations, ability in G4 stabilization, and ROS-induced cleavage were analyzed. The propensity in the stabilization of parallel topology was highlighted for both of the new compounds HP2Cu and PE2Cu. The results obtained are particularly promising, paving the way for the development of new selective functional ligands for binding and destructuring parallel G4s.