Top-Down Proteomics of Human Saliva, Analyzed with Logistic Regression and Machine Learning Methods, Reveal Molecular Signatures of Ovarian Cancer.

Ovarian cancer (OC) is the most lethal of all gynecological cancers. Due to vague symptoms, OC is mostly detected at advanced stages, with a 5-year survival rate (SR) of only 30%; diagnosis at stage I increases the 5-year SR to 90%, suggesting that early diagnosis is essential to cure OC. Currently, the clinical need for an early, reliable diagnostic test for OC screening remains unmet; indeed, screening is not even recommended for healthy women with no familial history of OC for fear of post-screening adverse events. Salivary diagnostics is considered a major resource for diagnostics of the future. In this work, we searched for OC biomarkers (BMs) by comparing saliva samples of patients with various stages of OC, breast cancer (BC) patients, and healthy subjects using an unbiased, high-throughput proteomics approach. We analyzed the results using both logistic regression (LR) and machine learning (ML) for pattern analysis and variable selection to highlight molecular signatures for OC and BC diagnosis and possibly re-classification. Here, we show that saliva is an informative test fluid for an unbiased proteomic search of candidate BMs for identifying OC patients. Although we were not able to fully exploit the potential of ML methods due to the small sample size of our study, LR and ML provided patterns of candidate BMs that are now available for further validation analysis in the relevant population and for biochemical identification.

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.

Energy efficiency and reduction of CO2 emissions from campsites management in a protected area.

Campsites can be a pollution source, mainly due to the energy consumption. In addition, the green areas, thanks to the direct CO2 sequestration and the shading, indirectly prevent the CO2 emissions related to energy consumption. The methodology presented in this paper allowed assessing the annual CO2 emissions directly related to the campsite management and the consequent environmental impact in campsite clusters in Tuscany. The software i-Tree Canopy was exploited, enabling to evaluate in terms of "canopy" the tonnes of CO2 sequestered by the vegetation within each campsite. Energy and water consumptions from 2012 to 2015 were assessed for each campsite. As far as the distribution of sequestered CO2 is concerned, the campsites ranking was in accordance to their size. According to the indicator "T-Tree" or canopy cover, a larger area of the canopy cover allows using less outdoor areas covered by trees for the sequestration of the remaining amount of pollutants. The analysis shows that the considered campsites, that are located in a highly naturalistic Park, present significant positive aspects both in terms of CO2 emission reductions and of energy efficiency. However, significant margins of improvement are also possible and they were analysed in the paper.

Exchangeable Sodium Percentage decrease in saline sodic soil after Basic Oxygen Furnace Slag application in a lysimeter trial.

The Basic Oxygen Furnace Slag results from the conversion of hot metal into steel. Some properties of this slag, such as the high pH or calcium and magnesium content, makes it suitable for agricultural use as a soil amendment. Slag application to agricultural soils is allowed in some European countries, but to date there is no common regulation in the European Union. In Italy soils in coastal areas are often affected by excess sodium, which has several detrimental effects on the soil structure and crop production. In this study, carried out within an European project, the ability of the Basic Oxygen Furnace Slag to decrease the soil Exchangeable Sodium Percentage of a sodic soil was evaluated. A three-year lysimeter trial with wheat and tomato crops was carried out to assess the effects of two slag doses (D1, 3.5 g kg-1year-1 and D, 2, 7 g kg-1year-1) on exchangeable cations in comparison with unamended soil. In addition, the accumulation in the topsoil of vanadium and chromium, the two main trace metals present in the Basic Oxygen Furnace Slag, was assessed. After two years, the soil Exchangeable Sodium Percentage was reduced by 40% in D1 and 45% in D2 compared to the control. A concomitant increase in exchangeable bivalent cations (Ca++ and Mg++) was observed. We concluded that bivalent cations supplied with the slag competed with sodium for the sorption sites in the soil. The slag treatments also had a positive effect on tomato yields, which were higher than the control. Conversely the wheat yield was lower in the slag-amended soil, possibly because of the toxicity of vanadium added with the slag. This study showed that Basic Oxygen Furnace Slag decreased the Exchangeable Sodium Percentage, but precautions are needed to avoid the build up of toxic concentrations of trace metals in the soil, especially vanadium.

Pre-processing of data coming from a laser-EMAT system for non-destructive testing of steel slabs.

Non destructive test systems are increasingly applied in the industrial context for their strong potentialities in improving and standardizing quality control. Especially in the intermediate manufacturing stages, early detection of defects on semi-finished products allow their direction towards later production processes according to their quality, with consequent considerable savings in time, energy, materials and work. However, the raw data coming from non destructive test systems are not always immediately suitable for sophisticated defect detection algorithms, due to noise and disturbances which are unavoidable, especially in harsh operating conditions, such as the ones which are typical of the steelmaking cycle. The paper describes some pre-processing operations which are required in order to exploit the data coming from a non destructive test system. Such a system is based on the joint exploitation of Laser and Electro-Magnetic Acoustic Transducer technologies and is applied to the detection of surface and sub-surface cracks in cold and hot steel slabs.

Diagnosis of the instability of the cooling behaviour of flat steel products through parametric characterisation, neural networks and statistics.

This paper presents a mathematical model developed by means of an analytical function whose shape depends on the values of a few parameters for the run-out table cooling which is used in hot strip mills. The system relies on a first-order differential equation for describing the temperature loss along the run-out table. Neural networks have been applied in order to find correlations between the model parameters and the steel and process variables. Then, traditional statistical techniques have been applied in order to evaluate the stability of the cooling behaviour. Numerical results obtained on an industrial database are presented and discussed.