Artificial Intelligent (AI) and Machine Learning (ML) are developing significant advances and gaining importance information processing in a huge number of fields such as chemical, pharmaceutical, biological etc. The Perturbation Theory (PT) is commonly combined with ML in order to generate PTML models and has been used in various disciplines to predict the biological activity of drugs and nanoparticles. In addition, this powerful tool has showed promising results in the field of nanoinformatics. As a consequence of evident achievements on a wide range of predictive tasks, ML techniques are attracting significant interest across a variety of stakeholders. Therefore, In this review different type of application of machine learning in nanoparticles involve in neurological diseases will be discussed.

In addition, different startup, spin-off, Small and Medium Enterprises (SMEs), and also some BigPharman, Tech companies, Nanoform-Drug Particle Engineering, Precision Medicine, NanosticsNanotechnology-Baed Diagnostic etc. are developing AI-based nanomedicine, nanotechnology, brain diseases so on. This communication also lists some of these startup companies.

This article aims to offer an objective methodological tool that helps identify the most relevant criteria in the process of selection and evaluation of projects in business acceleration, supported by the use of Super Decisions software. The Hierarchical Analysis of Processes (AHP), defined by Tomas Saaty, was used as a methodology, taking as a framework of analysis an accelerator in operation at the time of the research. The results indicate that the AHP is reliable for selecting and evaluating initiatives and provides flexibility for defining the importance of the criteria according to expert judgment.

Since 1996 the Fojanini Foundation has been undertaking a project for the reintroduction, after eight centuries, of olive growing in Valtellina (along the Italian Alpine boundary with Switzerland), by recovering abandoned terraces so to stem forest advancement as an indirect effect. This has been made possible by the increase in temperatures recorded in the last three decades in this Alpine area. In particular, in comparison with the 1977-1981 period, all the years between 1990 and 2021 in Valtellina were found to be in a range between 0.5 and 4°C warmer.

For the rebirth of Valtellina olive growing, a preliminary phase of varietal selection according to a bibliographic study and the consultation and analysis of historical data took place. Then the molecularly characterized planted varieties have been evaluated concerning physiological performances and olive oil characteristics throughout the 22-year-long study.

The varietal comparison to evaluate agronomic success, cold resistance, olive yield, and oil quality to identify the most suitable cultivars for the lasting development of alpine olive growing, may serve as a touchstone for overcoming the olive conventional limits even in non-traditional olive-producing countries.

Brain tumor segmentation aims to distinguish between healthy and tumorous tissue. Early and accurate diagnosis of brain tumors increases the chances of people with this complication surviving. Manual tumor segmentation in three-dimensional Magnetic Resonance images (volume MRI) is a time-consuming and tedious task. Its accuracy depends heavily on the operator's experience doing it. The need for an accurate and fully automatic method for segmenting brain tumors and measuring tumor size is strongly felt. Attention to the construction and improvement of CAD systems to diagnose this complication can help experts in this field. In this project, using the ability of deep networks to learn and solve problems, we examined the methods of tumor segmentation in MRI images of the brain. The architecture used in this project is U-Net architecture, which consists of an Encoder and Decoder. An attempt has been made to comprehensively examine how different parameters in education affect the degree of accuracy of the Network in a two-dimensional version. Six different experiments with different parameters were performed on the Network, and their results were compared.

Convolution neural network is a multi-layered network that is very popular today. This network is very popular due to feature extraction from images, videos, etc. In this paper, we first apply three fundamental changes to the convolution neural network architecture and thus introduce a new convolution neural network that is very resistant to noise. Then we compare the newly introduced algorithm. We do this for the MNIST dataset in noisy and non-noisy modes. The results show that even if we add 40% noise to the original data, the output of the proposed method is the same as the none-noise mode. We then suggest using the IMCNN + KNN hybrid algorithm to increase the classification accuracy. For this purpose, we use the ABIDE[1] database related to Magnetic Resonance Imaging of Autism Spectrum Disorder (ASD). The accuracy of classifying Normal Control with autism in the proposed method, even in the presence of noise, is 98.9%, which is a significant improvement over the CNN algorithm.

The last population generated by the evolutionary algorithm contains the best solutions; however, this population may be too extensive, thus difficulting the process of selecting the final solution that the decision-maker must perform. Therefore, a preference incorporation strategy must be integrated that approximates the interests of the decision maker to facilitate the solution's final choice. Different parameters are required to model the decision maker's interests, such as the objectives' weights to use the previously mentioned preference incorporation strategies. However, these values generally cannot be defined precisely by the decision maker, so ranges or intervals can be used to cover the uncertainty of these values. The decision maker's preferences can be considered before the execution of the evolutionary algorithm, at the end of the execution, or interactively during the algorithm's execution. This last method is the least studied because the process is more complex and slower than the a priori and a posteriori incorporation due to the intervention of the decision maker. Therefore, an interactive evolutionary framework has been proposed that uses preference disaggregation analysis and a chat-like interface. Then, through this proposal, the preferences of the decision maker can be efficiently incorporated, the number of tools that integrate this type of incorporation of preferences increases, and it demonstrates that the solutions converge before other types of articulation of preferences. Furthermore, with this proposal, the decision maker can see how the search moves in the solution space thanks to incorporating their preferences, thus facilitating the final choice of the solution.

Background: Autism spectrum disorder (ASD) is a neurodevelopmental disorder whose precise etiologic seems to be as heterogeneous as its severity levels. Nevertheless, accumulating evidence suggests that oxidative stress could be a common feature in autism, which may be further exacerbated by inflammatory phenomena, immune deregulation, and certain autoimmune risk factors, that may also contribute to the development and pathogenesis of autism. Following our research line linked to the tripeptide glutathione (GSH) as a key mechanism underlying symptoms of ASD, arise the hypothesis of GSH metabolism imbalance correlates with impairments on the domains of autism quotient (AQ).

Objetives: To study the correlation of glutathione (one of the major antioxidants) to the Autism Quotient (AQ) domains for adults using 1H-MRS in vivo.

Methods: We quantified glutathione reduced (GSH), creatine (Cr), and N-acetyl aspartate (NAA) signal in anterior (ACC) and posterior (PCC) cingulated cortices separately by magnetic resonance spectroscopy (MRS) on a 3.0 Tesla MR scanner, to assessed 22 adult patients with ASD and compared with 44 healthy subjects, matched for age, gender. AQ tests were applied where the subgroup algorithm, which combines the scores on the five AQ domains (social skills, attention switching/tolerance to change, attention to detail, communication, and imagination) derived the cut-off threshold to yield reliable autism subgroups as follows: AQ1 (0–10 points) = below average; AQ2 (11–21 points) = average values of the normal population; AQ3 (22–31 points) = above average; AQ4 (32–50points) = very high index of autistic characteristics (Asperger’s syndrome or high functioning autism has an average score of 35). Statistic one-way ANOVA was applied. Pearson´s correlation hallmarks our goal.

Results: The Pearson correlation coefficient represented graphically, showed a positive significant correlation between AQ domain ‘Communication’ to GSH (r = 0.51, p = 0.01); to GSH/Cr ratio (r = 0.51, p = 0.01); and GSH/NAA ratio (r = 0.56, p = 0.004) in AQ2 group (see Fig.1; Fig.2); in AQ3 to GSH negative significant correlation (r = -0.69, p = 0.05) in the PCC. Contrary in AQ4 to GSH/NAA positive significant correlation (r = -0.54, p = 0.05) in ACC.

Notably, in AQ1 group is a significant negative correlation between GSH/Cr ratio to the ´Attention switching/tolerance to change´ domain (r = -0.57, p = 0.03); and a significative positive correlation between GSH/NAA ratio to the ´Attention to details´ domain (r = 0.52, p = 0.05) in PCC; indicating the intervention of creatine, responsible of the cell damage caused by lack of oxygen and protector by preventing the depletion of energy ATP, and N-Acetyl aspartate (a marker of density neuronal). AQ2, AQ3, and AQ4 groups maintain a pattern correlation to AQ domains different than the AQ1 group (considered a group of healthy subjects) and highlight the differences in the autistic characteristics within ASD, and as the hallmark of the ´Communication´ deficit (Bjørklund, G., 2021).

Conclusions: The opportunity to measure the concentration of GSH in cingulated cortices creates a new and promising approach for intensified diagnosis and the effects of a new venue clinical trial in ASD.

The application of multicriteria analysis methods to the creation of models that allow evaluation of the smoker's pleasure, and optimizing the integral quality of the tobacco leaf, ensuring the degree of sensory satisfaction and the harmfulness of the habit, is presented. The quality model was verified in practice, comparing it with the opinion of a representative group of expert tasters. A decision support system (DSS), capable of simulating and increasing quality with high computational efficiency, is briefly described

The blood-brain barrier (BBB) is a highly selective permeability barrier that separates circulating blood from brain extracellular fluid in the central nervous system (CNS). This barrier allows the passage of water, some gases, and lipid-soluble molecules by passive diffusion, as well as the selective transport of molecules such as glucose and amino acids that are crucial for neuronal function. In this research, we present an exploratory study, where several machine learning techniques are applied to predict blood-brain barrier passage by applying molecular descriptors based on atomic vectors, obtained by MD-LOVIs software. Several techniques such as KNN-AWV(ACC= 0.712), AVNNET-AWV(ACC=0.768), Random Forest-AWV(ACC=0.776) and GBM-AWV(ACC=0.784) obtained good prediction performance. The results show that machine learning techniques are powerful tools for the prediction of this activity.

Project portfolio selection is very complex. Often the multiple criteria used to assess projects are hierarchically structured and show interaction. Most of these criteria are also used at portfolio level to assess the supported projects as a whole; however, additional criteria must be considered to define the conformity of the decision maker with the portfolios. Here, we present a novel method to comprehensively address all these characteristics of the problem. The method uses a generalization of the outranking approach and value functions to aggregate the criteria scores, and evolutionary algorithms to define the most preferred portfolio.