A Deep Learning-based approach for forecasting off-gas production and consumption in the blast furnace.

This article presents the application of a recent neural network topology known as the deep echo state network to the prediction and modeling of strongly nonlinear systems typical of the process industry. The article analyzes the results by introducing a comparison with one of the most common and efficient topologies, the long short-term memories, in order to highlight the strengths and weaknesses of a reservoir computing approach compared to one currently considered as a standard of recurrent neural network. As benchmark application, two specific processes common in the integrated steelworks are selected, with the purpose of forecasting the future energy exchanges and transformations. The procedures of training, validation and test are based on data analysis, outlier detection and reconciliation and variable selection starting from real field industrial data. The analysis of results shows the effectiveness of deep echo state networks and their strong forecasting capabilities with respect to standard recurrent methodologies both in terms of training procedures and accuracy. Supplementary Information: The online version contains supplementary material available at 10.1007/s00521-021-05984-x.

HCV genetic variability: from quasispecies evolution to genotype classification.

HCV is a ssRNA virus belonging to the Flaviviruses and is found worldwide worldwide in humans. Following primary infection, persistent infection develops in more than 85% of cases, which in up to 30% of cases, may progress to liver disease, cirrhosis and hepatocellular carcinoma. The virus presents a high degree of genetic variability owing to the combination of a lack of proofreading by the RNA-dependent RNA polymerase and a high level of viral replication. This genetic variability allows the classification of genotypes, subtypes, isolates and quasispecies to which epidemiological and pathogenetic significance may be associated. The features and biological implications of HCV variability and of quasispecies dynamics in infection transmission, mechanisms of chronicity and resistance to antiviral therapy are discussed.

Rare HVR1-HCV genotype 1b variants in patients with B non Hodgkin's lymphoma. Comparison with viral sequences detected in cases of lymphoproliferative disorders and B cell compartmentalisation.

We compared the E2-HVR1 region in HCV-1b positive B-NHL cases from a multicenter study with sequences from studies related to lymphoproliferative disorders and B cell compartmentalisation. We found rare and unique mutations both in B-NHL isolates and in cases with lymphoproliferative disorders and lymphocyte infection. These rare mutations could have an important effect on HVR1 region and, as a consequence, on the binding of E2 on CD81, with a possible implication for both antigenic stimulation and HCV entry. In conclusion, the HCV predominants circulating in B-NHL cases seem to be associated with clonal selection of rare variants.