No abstract

No abstract

Introduction: The application of machine learning methods involves the collection and processing of data which comes from the recording elements in the offline mode. Most models are trained on historical data and then used in forecasting, classification, search for influencing factors or impacts, and state analysis. In the long run, the data value ranges can change, affecting the quality of the classification algorithms and leading to the situation when the models should be constantly trained or readjusted taking into account the input data. Purpose: Development of a technique to improve the quality of machine learning algorithms in a dynamically changing and non-stationary environment where the data distribution can change over time. Methods: Splitting (segmentation) of multiple data based on the information about factors affecting the ranges of target variables. Results: A data segmentation technique has been proposed, based on taking into account the factors which affect the change in the data value ranges. Impact detection makes it possible to form samples based on the current and alleged situations. Using PowerSupply dataset as an example, the mass of data is split into subsets considering the effects of factors on the value ranges. The external factors and impacts are formalized based on production rules. The processing of the factors using the membership function (indicator function) is shown. The data sample is divided into a finite number of non-intersecting measurable subsets. Experimental values of the neural network loss function are shown for the proposed technique on the selected dataset. Qualitative indicators (Accuracy, AUC, F-measure) of the classification for various classifiers are presented. Practical relevance: The results can be used in the development of classification models of machine learning methods. The proposed technique can improve the classification quality in dynamically changing conditions of the functioning.

Introduction:To date 56 reciprocal microdeletion/microduplication syndromes have been described. Due to intensive application of microarray technologies new submicroscopic rearrangements are being published. The reciprocal rearrangements are particularly valuable, since they allow to determine the dosage-sensitive pathogenic genes.Objectives:To improve ID diagnostics.Aims:To identify novel candidate loci of ID.Methods:We performed the genome-wide analysis for 79 patients with idiopathic ID using CGH Microarray Kits 4×44K and 8×60K (Agilent Technologies, USA). Pathogenically significant cases were confirmed by qPCR.Results:We present two patients with microdeletion (369 kb) and microduplication (766 kb) at 3p26.3 containing the only gene - CNTN6. The microduplication was inherited from apparently healthy father. The child with microdeletion was an orphan. Recently, the microduplication in 3p26.3 (containing CNTN6) has been shown to be associated with autism spectrum disorders (ASDs). Contactin 6 is also suggested to play a neuroprotective role in ischemic injury and contribute to granule cell maturation and/or synaptic formation in the developing cerebellum.Considering the experiments with mice we found myotonic syndrome, late development of sit and walk ability in the anamnesis, current fine motor skills impairment and dysarthria in patient with dup3p26.3. His IQ is 47. Dysarthria was also observed in the patient with del3p26.3 (IQ 55).Conclusions:Obviously, CNTN6 can be a novel pathogenic gene associated with ASDs, ID, and motor functions impairment. This study was supported by EU Seventh Framework Program, CHERISH project no. 223692 and by Federal Program of Ministry of Education and Science of Russian Federation no. 8727.

Сравнительное молекулярное кариотипирование внеклеточной ДНК из внутриполостной жидкости бластоцисты, а также эмбриобласта и трофэктодермы позволило получить свидетельства в пользу наличия механизмов самокоррекции эмбрионального кариотипа на преимплантационном этапе развития человека. Comparative molecular karyotyping of cell-free DNA from the blastocoele fluid of the blastocyst and the embryoblast and trophectoderm, allowed us to obtain evidence for the presence of mechanisms of self-correction of the embryonic karyotype at the preimplantation stage of human development.