The paper studies the ability of neural networks to identify relations between different parameters that makes it possible to express massive data more compactly, providing the data blocks are closely connected to each other. Application of bioinformatics methods allowed to predict a positive effect of different chemical compounds on plants growth which is from 87.5% to 88%.
The search for new non-invasive methods of research in medicine and physiology is an urgent task of the modern development of human sciences. One of the most attractive options for solving this problem is to recognize the use of human saliva as an object of research. The results obtained confirm that oral fluid facies is a simple, noninvasive, lowcost method for additional assessment of the human organism’s functional state, applicable to the population mass screening. The morphological picture of the oral fluid facies and the results of its computer morphometry are consistently combined with the human level of general nonspecific reactivity of an organism (LGNRO) and have a distinct circadian dynamics of the main parameters. The qualitative characteristics analysis of the facies’ peripheral zone (size and homogeneous protein deposits, the structure of the boundary between the outer and inner zones) and their quantitative equivalents (thickness and intensity of crystal formation) have been proved to be the most informative when analyzing the human oral fluid facies
The paper demonstrates the importance of neural networks, which are successfully used in various fields. Artificial neural networks demonstrate a large number of brain properties. They are trained on the basis of experience, generalize previous precedents to new cases and extract significant properties from incoming information which contains excessive data. Technically, training is to find coefficients of connections between neurons. In the process of learning, a neural network is able to detect complex dependencies between input and output data, and also perform generalization. As a result, the analysis showed that, on average, the neural network made 50% of forecasts.
A process of health-saving accompaniment individualization implies constant monitoring of the functional state. There is a universal method of instrumental evaluation and prediction of the human adaptive state, considering its individual, genetically determined structural and functional characteristics. It is a method of LGNRO assessment. LGNRO is for a level of general nonspecific reactivity of an organism, qualitatively and quantitatively characterizing a level of individual sensitivity and reactivity to various exogenous effects. The biometric analysis of the organism’s nociceptive characteristics has revealed the general biological character of the normal distribution of the thermal sensitivity threshold (TST) in human populations and laboratory animals. The possibility of a rapid assessment of LGNRO by means of TST is justified. Morphofunctional characteristics of individual brain structures and their role in the formation of LGNRO have been determined. The genetic determinancy of phenotypic manifestations of LGNRO has been proved. Based on the results of experimental studies, an algorithm and a corresponding computer program have been developed that provides system-specific personalized monitoring of human health status in real time.
Bioinformation data capturing and preprocessing for molecular modelling is exceptionally time-consuming task. Researcher forced to use inconsistent instruments, which are generate vast amounts of diverse-structured data. Here we propose an integrated instrument automating the stage of data pre-processing for molecular docking – searching of protein receptors, their spatial structures and suitable ligands. The algorithm automatically finds all the synonymic constructs of original query, requesting specified biological databases, populating the list of receptor’s and their ligands’ PDB-identifiers and converts them to AutoDock format (PDBQT). The data sources are open-access specialized biological databases – UniProtKB, Protein Data Bank (PDB) and ZINC15. The virtual screening algorithm implemented using the Python 2.7.9 programming language with several plug-in modules. The result is the data preparation tool for further use in AutoDock-family docking software. The tool has two variants of user interface – desktop application and chatbot for the Telegram messenger.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.