CC BY
69
REVIEWS
UDC 004:591.5:612:616-006 https://doi.org/10.15407/biotech11.06.005
ELECTRONIC EXPERT SYSTEMS FOR BIOLOGY AND MEDICINE
O. M. KLYUCHKO
Kavetsky Institute of Experimental Pathology, Oncology and Radiobiology of the National
Academy of Sciences of Ukraine, Kyiv
E-mail: kelenaXX@ukr.net
Received 29.12.2017 Revised 17.11.2018 Accepted 28.12.2018
The purpose of the present work was to carry out a deep investigations of prototypes of information expert systems, their structure, functions and practical application, and to develop a new one for solving practical problems in biotechnology, laboratory practice and environmental protection. The observed prototypes were developed for the use in genetic studies, agricultural production, nature protection from pests and environmental pollutants, for works in medicine, and etc. During the work, following methods were used such as methods of comparative research of the samples of technical devices, imitation and program modeling, which were based on numerical results obtained in experiments with the recording of chemosensitive transmembrane electrical currents in neurons in voltage clamp mode. As a result, an original expert system was developed. It was coupled with a detector group, databases and interface. The developed expert system was able to distinguish automatically the certain types of chemicals at the input, to display their identification data and, if necessary, the reports about their harmfulness. Conclusions were done about the practical value of these data for the elaboration of new electronic expert systems for monitoring the presence of harmful substances in the environment. It was also discussed the possibility of developed expert system application for new methods of qualitative and quantitative analysis of some organic compounds.
Key words: biological and medical expert systems, electronic informational systems, bioinforma-tics, databases.
Electronic biomedical expert systems are powerful tools in contemporary biotechnology. In computer sciences expert systems were studied usually together with knowledge bases as models of experts' behavior using the procedures of logical conclusion and decision making in a certain field of knowledge [1]. Knowledge bases, consequently, were seen as a set of facts and rules of logical conclusion in the chosen subject area of any activity. In our previous publications we had written aready about contemporary computer information systems with expert subsystems [1-10], as well as about mathematic tools used for expert systems' construction [2-5]: methods of artificial neural networks [2, 3], methods of cluster analysis [2, 4], methods of images processing [2, 5]. Present article is dedicated
to different aspects of modern expert systems constructions and functions because of great importance of expert systems' role for biotechnology as well as for contemporary biology and medicine [1].
An expert system is a computer system capable to replace (or to replace partially) professional-expert (human) in the problem solution according to classic definition. Modern expert systems started to be developed by researchers of artificial intelligence in 1970s, and in 1980s expert systems received commercial groundings. There are some evidences exist that early prototypes of biomedical expert systems were proposed by S. N. Korsakov on 1832. He invented mechanical devices, so-called "intellectual machines" that allowed to find task solutions under some given conditions, for
example, to determine the most appropriate drugs in accordance with observed patient's symptoms of disease. The similar actions today were performed by such software tool as "search or reference (encyclopedic) system". According to user request, it provided the most suitable (relevant) chapters from the article bases (knowledge about objects from the field of knowledge, their virtual model).
While expert systems technology has now existed for more than 30 years, environmental expert systems are 15 years "younger" [11]. Nonetheless, the development has been rapid with over 68 systems in existence today [11]. All of the early systems and the bulk of the current systems are PC-based, but as the limitations of the delivery capability are reached, more and more systems are moving toward larger delivery environments such as minicomputers and dedicated workstations.
From other side, the "classic" concept of expert systems developed in the 1970th — 1980-th years, is in deep crisis today. For example, the "classic" approach to the construction of expert systems is co-excided difficultly wth the relational data model, which makes it impossible to use effectively modern industrial databases to organize knowledge bases for such systems.
Electronic expert systems as one of the important types of modern electronic information systems. In our previous publications, we have already done a large-scale review of modern electronic information systems (IS) with databases (DB) [1-10]. There was suggested our invented classification of ISs main types for biology, medicine and neurophysiology (neurophysiology is at the junction of the first two spheres). It has been shown that electronic expert systems occupy the leading positions in the list of ISs' types for each of studied spheres [1, 7, 8]. They attract attention of scientists and engineers-developers by variety of their types and technical implementations, as well as by importance of solved tasks [1]. For example, in case of medical ISs, the expert systems were placed to the second place in the list of the most important ISs types (1-st place — "Medical ISs of general purpose", 2-d place — Expert systems, 3-d place — "Electronic systems for the works with images", and so on). Placing ISs' types in the hierarchy, we adhered to the principle: the more publications contain modern scientific and technical literature on a certain type of ISs, the higher the name of this ISs' type is in our list.
Regarding to classification of ISs used in biology, biotechnology, environmental
research, the most of these ISs have been designed as 1- ISs with databases for science. Than they were followed by 2 — electronic library systems in biology, 3 — electronic databases in biology, 4 — electronic systems for the work with images. And only the next type in this classification hierarchy — 5-th place occupied expert biological systems (for example, to estimate the pests presence in the fields, to detect bees diseases and etc. Determining the position of ISs' type we placed them in decreasing order — ISs that had better representation in scientific and technical publications were placed highly in this hierarchical list [1].
We would like to overlook various examples of modern biomedical expert systems that can be successfully used in biotechnology. In addition, the experience of such systems development could be used successfully for expert systems construction specifically for biotechnology, for example, to perform specific biotechnological or research tasks. The principles of such systems structure, as well as their functioning as part of biomedical electronic network information systems (IS), will also be considered. And, finally, an example of expert system developed by the author for an IS with databases (DB) for eco-monitoring of environment polluded with harmful and/or toxic substance will be described.
Mathematic methods as well as models that we described in our previous articles and published by other authors also may be used for ISs functioning or to be simulated in result of their functioning [1-5, 10-81]. A spectrum of mathematic methods were used for the newest biomedical ISs elaboration one can find in [1-6, 11, 75, 77-80, 82-159]. Content for described in this article databases was obtained usually from the results of biological and medical observations and experiments [12-17, 24-44, 47-49, 61, 68, 71-74, 82-90, 94, 104, 106, 109, 111-113, 125-191]. All such technical information systems (tIS) are electronic databases (DB) distributed in networks today [1-11, 25-69, 90-109, 112-120, 159]. The newest parts of authors work were inventions supported by patents [162-172].
Expert systems in biotechnology. Some examples of electronic expert systems, developed for task solutions in biotechnology had been supported by patents; their descriptions are suggested in this sub-chapter.
1. Expert system "Artificial intelligence system for genetic analysis". In the patent of Glenn F. Osborne, Simon S. M. Chin, Paul
McDonald, Scott Schneider their expert system "Artificial intelligence system for genetic analysis" is described in [12]. They published that their invention provides a complete artificial intelligence system for the acquisition and analysis of nucleic acid array hybridization information. The system includes a central data processing facility and one or more user facilities, linked by encrypted connections. Each user facility may include an optical scanning system to collect hybridization signals from a nucleic acid array, an image processing system to convert the optical data into a set of hybridization parameters, a connection to a data network, and a user interface to display, manipulate, search, and analyze hybridization information. This system reads the data from a nucleic acid microarray, analyzes test results, evaluates patient risk for various ailments, and recommends methods of treatment. The automated artificial intelligence system is a real time, dynamic decision making tool that can be used in conjunction with a clinical analysis system, and with the information obtained in a research and development environment.
2. Expert system for classification and prediction of genetic analysis. Other example of expert system for biotechnology we would like to observe Roland Eils patent "Expert system for classification and prediction of genetic analysis" [13]. It was directed to methods, devices and systems for classifying genetic conditions, diseases, tumors, etc., and/ or for predicting genetic diseases, and/or for associating molecular genetic parameters with clinical parameters and/or for identifying tumors by gene expression profiles etc. The invention specifies such methods, devices and systems with the steps of providing molecular genetic data and/or clinical data, automatically classification, prediction, association and/or identification data by means of a supervising machine learning system. There were further described methods making use of these steps and respective means. This invention related to the method and system for classifying genetic conditions, diseases, tumors etc., and/ or for predicting genetic diseases, and/or for associating molecular genetic parameters with clinical parameters and/or for identifying tumors by gene expression profiles etc., with the following features: providing molecular genetic data and/or clinical data, optionally automatically generating classification, prediction, association and/or identification data by means of machine learning,
and automatically generating (further) classification, prediction, association and/ or identification data by means of supervised machine learning.
The use of the supervised machine learning according to the present invention leaded to surprisingly better and more reliable results. There was noted that preferably molecular genetic data and clinical data were provided. Used machine learning system was an artificial neural network (ANN) learning system, a decision tree/rule induction system and/or a Bayesian Belief Network. Further preferably for generating the data in the machine learning system at least one decision tree/rule induction algorithm was used. The data automatically generated is tumor identification data making use of gene expression profiles and being generated by a clustering system wherein further the clustering system makes use of one or more of the following clustering methods: Fuzzy Kohonen Networks, Growing cell structures (GCS), K- means clustering and/or Fuzzy c-means clustering. Finally, it was noted that the data automatically generated is tumor classification data being generated by Rough Set Theory and/or Boolean reasoning.
Expert systems in medicine. The Internet provides unprecedented opportunities for invention and elaboration of powerful expert medical systems. In such systems the opportunities for obtaining information (OI) can be realized rather cheaply. This is the best way for large information volumes exchange; to obtain information that is varied, even controversial; to obtain information from medical experts from different fields of medicine and remote geographic regions. Clinical decision support systems (CDSS) have increasingly become used in medical practice in recent years. The first such system, which has been widely used since 1970, has become the medical expert system MYCIN. After it the number of such ISs were elaborated and developed, they provided access to medical information, interpretation of diagnoses, and so on. When these systems were developed, the methods for efficient system construction, decision making, and data usage from databases were searched. So, 2 alternative methods were invented and used: automatic OI and receiving OI in manual mode (manual OI) [1].
1. Expert system for facilitation the presentation of knowledge and data in database and for knowledge obtaining from the Internet. Using the above described theoretical approaches, the numbers of medical expert system were elaborated; one of them was
described in [132]. The authors described their system, which was based on three databases of client-server architecture and computer system for its information management (OI), which was the invention of developers. 8-bit encoding scheme and weighting system were proposed to facilitate the presentation of knowledge and data in database and to obtain knowledge from the Internet. The system had been tested already in clinic conditions. The authors set the following goals. 1 — to construct OI medical system and management system for it to facilitate the development and maintenance of medical knowledge bases; 2 — to maximize the distribution of information and its re-use between medical institutions and practical doctors; 3 — to facilitate the decision-making process by medical expert systems. The authors described the method of OI managing from the Internet, which they used to construct the large databases of medical knowledge. The testing system was designed using Delphi 5.0 and Microsoft SQL Server 2000, and it was available online for testing during 1 year. The authors wrote that their method and developed system makes it easy to operate large volumes of medical knowledge.
2. Expert system for the selection patients for clinical trials in oncology. Another Internet-based system was developed to select patients for clinical trials in oncology. Large-scale clinical trials are often multicentral in the modern world, which means that they are based on different geographical points of the Earth, often in different countries, for example, with purpose to study the effect of any important drug, which can then be recommended for people treatment. At the same time, for such work it is necessary to provide the highest level of standardization, the record in databases numerous test results and to fulfill a number of other specific requirements. Modern Internet technologies provide the opportunities for such work, although until the last days the selection of patients for tests was carried out manually. Developers of this system from the Moffitt Cancer Center, USA, describe their expert system for patient selection [1]. The data about each patient were recorded to it, and if there are not enough data, the system offers additional tests. The system allows the automating of selection process, the increasing the number of patient that can be selected (previously up to 60% of eligible patients were lost) with a significant reduction in cost of testing procedures. A user-friendly interface has been developed, which allows a
healthcare professional to add test data and to make new selection criteria without the help of programmer. This system has been tested in oncological hospitals; and this is extremely important because, according to statistics, only in the United States 550,000 people dies of cancer every year. It is for this sphere of medicine a large number of new medicals are developing and testing constantly. In case of successful results they come to patients immediately — thus for the newly developed medicals the shortest path from the laboratory to the patient is invented.
3. Expert system for patients' selection for clinical trials in oncology. An electronic expert system with databases for diagnostics of psychosomatic disorders based on the use of fuzzy logic neural models was described [91]. Symptoms and characteristics of diseases were done as text records of patient surveys and collected in the databases. For translation of language samples of patient surveys into electronic form, an artificial domain was elaborated for the linguistic processing of this material; and the values for a fuzzy logic model were determined. These values were input to a multilayer neuronal network with direct feedback. During the work with the network the backpropagation training algorithm was used, and the model after the training was tested using symptoms and signs of disease from new patients. In addition, a comparison of the diagnostic ability of the model with the decisions and diagnoses of the medical expert was realized. The model implementation also was compared with the stochastic model based on the network of Bayesian hopes and statistical model with the use of linear discriminant analysis.
Information system with expert possibilities named "eMAGS" for medicine is suggested on Fig. 1 [141].
Expert systems in biology. This is a special group of information systems (IS) linked with databases in biology are the systems that have both academic and applied value. Intensive industry (including agriculture) requires innovations, and the information of several examples of such systems developed for practical needs, have been published below. There were already some attempts to solve problems of species preservation, environment protection from pests, etc., using electronic expert systems with academic databases as well as attempts to make simulation basing on the data that have been output by expert systems.
Patients Mgmt. DB
Mgmt, programs-applications for patients
DB for surgeons
a
Program-application for recipes #
Applications
for surgeons
DB of recipes for
patients
#
Ontologi cal server
Ontological DB
Onto logical server 1_
Ontological libra rv
«I'M A
OS Q A
b
Fig. 1. eMAGS medical system [141]:
a — Architecture of eMAGS medical system. The essences of "agent" and "ontological" types were components of eMAGS system. Indications: # the greater number of such entities were supposed to be in medical institution; ' the essence of this type had a database and an interface for the user; b — Ontological server and its components
a
An "Overview of Environmental Expert Systems" was written by Judith M. Hushon; and this overview accumulates a great volume of information concerning modern expert systems in area of environmental studies [11]. The author wrote that the development of environmental expert systems has been rapid with over 68 systems in existence today [11]. All of the early systems and the bulk of the current systems are PC-based, but as the limitations of the delivery capability were reached, more and more systems are moving toward larger delivery environments such as minicomputers and dedicated workstations. Development was occurred both using Artificial Intelligence languages such as Prolog and LISP as well as expert system "shells". The problems being tackled are also expanding. Whereas a number of the early systems took on very limited areas of expertise, such as the operation of a sewage treatment plant, the systems are now moving out to tackle siting problems and recommendation of complex remedial technology combinations. What is even more important is that expert systems are becoming an accepted vehicle for offering advice for solving environmental problems. Over the next few years more complex systems will be developed that share databases and tackle multiple related environmental problems.
Some other examples of expert systems in different spheres of bioogical practice are given below.
1. Expert systems in forests protection from the pests. The concept of integrated protection of forests from the pests has attracted the scientists' attentions for many years. But it could not be realized until present time, when modern monitoring systems appeared with electronic tools: expert systems, decision making, early warning, and etc. [186] Promising electronic decision making tools that include models, database management systems, geographic ISs and expert systems were developed during the last decade, but still it is necessary to carry out the research on user friendly interfaces and artificial intelligence systems for such expert systems. Several projects in North America have made significant progress in the development of monitoring systems and electronic decision-making tools for the elimination of Lepidoptera pests in forests (some species of Noctuidae, and others).
2. Expert systems for beekeeping. An electronic expert system was developed for the needs of beekeeping [187]. This system
diagnosed the pest presence and determined the species of bees' pests (Apis mellifera L.); it offers also appropriate treatment. Developers proposed to use this system not only in beekeeping, but also as a training system for students of corresponding specialties. The diagnosis was performed by scanning of bees' colonies. The databases contain relevant images of normal colonies and pathological ones (with different types of pathology) that were analyzed using modern techniques. This expert system is based on EXSYS for MS Windows.
3. Expert systems for agriculture: protection of crops from pests. To solve the problem of crops' protecting from pests, the electronic ISs with databases have been elaborated, and they were used by farmers for contemporary scientifically grounded agriculture management [188]. The system for relational databases' management was described. This electronic management system was elaborated for monitoring and to provide advices to farmers about pests' species Cydia pomonella and Psila rosae. This system has been used on farms since 1988. This system was developed using INFORMIX-SQL RDBMS Version 2.10.06 and installed on personal computers IBM XT 286 model from PC-DOS Version 3.30. Farmers would be able to monitor insects, and their data of field observations and traps' inspections have been transmitted to research center. There these data were input into the IS, which determined the status of pests. This information was transmitted to agricultural experts. Experts have given the recommendatios to farmers to carry out the certain control procedures concerning the pests on the basis of received data about Cydia pomonella. In the case of Psila rosae, the individual advices via IS were mailed directly to farmers. Monitoring was carried out only during flight periods; the data were transmitted by post or fax.
4. Expert system for cotton industry. Another expert system was invented and designed in Australia for the needs of cotton industry [33]. This is the electronic decision-making system (DSS), and it is widely used today to control pests, to examine the state of feeding of cotton plantations, and to solve other tasks requiring information exchange. The system contained a part of the software called EntomoLOGIC, which is, from other side, the part of larger CottonLOGIC system. In order to use EntomoLOGIC, the farmer went to the area of his interest, and input the information about the condition of this
territory: what pests are present there at this moment, at what stage of development they are, their quantity, and etc. The program forecasted the prospects of these pests development and offered the methods for their elimination or neutralization. Due to these recommendations the farmer made decisions about his work at this territory. Used software includes several databases. Many components of EntomoLOGIC software have been developed on the basis of Palm® OS for IBM.
5. Expert system for ecological monitoring of fauna for agriculture (registration of Locustae and other flying insects migrations). Interesting example of modern IS for environmental monitoring and agricultural services was the IS, that had been developed in Australia [1, 10, 189]. This information system consisted on two remotely-spaced radars that were used for insect monitoring; they both were connected to the node computer (NC) of the basic laboratory. PC-NC communications were used to transmit observation data, to perform remote services and to conduct diagnostics. Specially organized automated systems were developed to analyze meteorological information and the data about insects' migrations, recorded by the radar. On the base of this analysis the statistical reports and their graphical representations were prepared daily according to the information received by radars. The reports and graphs provided the data on the intensity, amplitude, velocity and movement of insect migration directions, orientation, size and frequency of migrant wings, as well as weather conditions at the surface of each point of survey. Such reports were transmitted to NCs and inserted automatically into the Internet pages, which users could see since 12.00 p.m. next day. Expert systems were elaborated and used in this system for data analysis as well as for automated answers to users (biologists, ecologists, farmers, others) on their questions and requests. This system was developed to track the number of such insect pests like different Locustae and other flying insects-migrants [1, 10, 189].
Development of electronic workplaces for electronic information systems with expert capabilities. Development of electronic expert system within the IS requires the development of a user-friendly interface. The author developed several types of electronic workplaces (EWP) for scientists and other professionals, which de facto fulfilled the functions of the interface. Let's describe original version of EWP named "EWP-Z" —
"electronic workplace for zoologist", which can be used by zoologists, environmentalists and professionals of other specialties; EWP-Z can serve as interface to IS with expert capabilities (like other versions of EWP). In stationary laboratory conditions electronic ISs are usually networked and realized on the base of devices and equipments specialized for this research direction. We decided to develop "electronic work places" (EWP) for such ISs for some biological specialties on early 2000-th. EWP-Z was originally developed for insects' adaptation studies in mountain conditions of Elbrus region (Caucasus, Russia), at Elbrus Medical and Biological Station (EMBS, National Academy of Sciences of Ukraine), where the author was in staff at that time. Hence, this system could be used also by researchers who study the influence of extreme conditions on bioorganisms. Since, basing on such data, the databases for monitoring, observations are subsequently formed for environmental problems solution; the EWP-Z might be also a desirable tool for ecologists who use insects' observations for ecological analysis of the environment state. EWP-Z can be used locally and autonomously, as well as a segment of electronic monitoring system, for monitoring of bioorganisms' population state, ecological monitoring in nature preserves, in neighborhood of industrialized polluted regions, etc. Block diagram of EWP-Z is shown on Fig. 2.
The images of biological objects (insects, other bioindicators) form a necessary part of databases for EWP-Z. During this system development, in the author's version, there were images of moths Noctuidae (Lepidoptera); they were necessary for appropriate databases development. Such databases further may be used for electronic identifiers of insects, expert systems that should determine pests' species, and etc.
Newly developed biotechnical monitoring system with expert subsystem. To solve the set of tasks during the monitoring of dangerous chemical substances influence on organisms in polluted environment, Dr. Klyuchko O.M. suggested the simplest version of biotechnical monitoring system supplemented with A) sensor group ("biotechnical sub-system" — "BTS") and B) expert subsystem. The main task of sensor group was "data generation" or "data mining" for the B) expert system. As input data to expert system we suggest using the data of well-known electrophysiological experiments with registration of transmembrane chemosensitive electric
Fig. 2. The scheme of electronic work place for ecologists and zoologists (EWP-Z) as interface
in IS with expert system
PDB-Z — own databases of zoologist: 1.A — electronic versions of publications selected by the scientist (printed versions of his own articles, prepared for publication, electronic versions of necessary articles of other authors); 1.B — database with information about substances and reagents; 1.C — DB with his own experimental, working data, monitoring data; 1.G — database with images; 1.D — DB with films of observations. MLIS is a mini-library Internet system for zoologists
currents that depended on applied chemical substances; so, we tried to demonstrate direct links between chemical structure of applied chemicals (input information) and characteristics of electric responses (output information). Expert system had to do: 1 — to distinguish the approximate types of acting chemical substances by the characteristics of electrical currents' records at BTS output; 2 — to "decide" whether this substance was dangerous or no; and 3 — to output necessary information on PC screen (whether the situation is "dangerous" or "not dangerous"). This sensor group A) that in our investigations was called "biotechnical subsystem" (or unit) — "BTS" is shown on Fig. 3.
BTS output electric signals further were transmitted to B) expert subsystem as input signals to it. The purpose of the work done was to develop computer biotechnical monitoring system for monitoring and profound study of different chemical substances influence on organism in different time intervals, from the time when the substance started to influence on organism. BTS might be a complex of electrophysiological devices for the registration of transmembrane electric currents and influences of different chemical substances on them with relative methodics — patch-clamp, votage-clamp, different microelectrode methods, and/or other methods from this spectrum. Influences of chemical substances were studied on mammal nervous cells (Wistar rats) as a result of changes in the characteristics of transmembrane electrical chemosensitive currents. Generally BTS contained three parts: mechanical-hydraulic part with
biological fragment (BF — neuronal membrane, or other objects like this), electric part (electric cirquit), and computer part (Fig. 3).
BTS allowed the registration of new received data, their recording in computer memory (in local and network databases). BTS also allowed visualizing obtained results, their processing performance, data output and their analysis, and their transmission with the use of network technologies. The registration process was realized as following algorithm: the chemicals were applied to neuronal membrane in the BTS; after the applying of agonist the electrical signal could be registered; the changes of electrical ion transmembrane currents were measured. The actions of substances were measured in quantitative units. Some examples of BTS output electric currents registered by the author with collaborators in Bogomoletz Institute of Physiology NASU are shown on Fig. 4. There are some recordings of glutamate-(Glu) and kainat- (KK) transmembrane electric currents and influences on them by Araneidae toxins (like JSTX-3 (Nemphila clavata) and AR (argiopine from Argiope lobata, also newly synthetized substances were used) [163-182]). Other phenol- and indol-derivatives might be studied also (including some organic environmental pollutants). Examples of BTS output electrical signals might be taken to expert system input for their further processing [178].
Biological fragments (BF) in our experiments undergo preliminary processing according to specially developed procedures, including enzyme treatment; in experiments
Sensor (detector) input signal
aW[C]„
chemical i*
electric
Sioelerrtent, mechano-hydravlic block /tec TEC-current
chemical
TE-current /te
®
Electronic registration scheme
(3) ®
Sensor (detector) output signal
'out
Computer DB, models.
Memory. control,
processing recognition
INhO
Operator
INFO Modeling, recognition
/control etairfcanlid current
Controled electronic scheme
Fig. 3. General technical scheme of BTS for the registration of transmembrane electric currents and influence of different chemical substances on them
with pyramidal neurons of rat hippocampus we used proteases from A.oryzae and/or other substances in solutions with specially developed compositions and gas environments, temperature and time modes of treatment.
Substances (antagonists) were either taken from the nature, or artificially synthetized — they could be obtained using various chemical and biochemical methods. BF could be replaced depending on processing of their molecules, the type of chemicals that were analyzed; and the BF acted as the primary link in all developed biotechnical systems — as biodetector and/ or bioanalyzer of active substances (including environmental pollutants). For different versions of our developed monitoring system the names BTSM-3, BTSM-4 were given; the general name of all family of such ISs is "Ecological Information System" (abbreviation in English is "EcolS") [176]. Expert subsystem coupled with BTS was a system linked with DBs with direct and/or remote access that contains a number of subsystems for analyzing the information coming from BTS subsystem about the chemicals' influence on organisms.
Recordings on Fig. 4 were done during electrophysiological BTS experiments where BF was influenced by various chemicals (including toxins JSTX-3 and argiopin AR). The following electrical signals were obtained by the registration of transmembrane electrical
currents using voltage-clamp method; object — rat hippocampal membranes (similar experiments were carried out on numerous objects of other types: motoneurons, rat brain neurons, and other diverse living objects).
Development of analytical expert system as a part of technical system for monitoring of different chemical pollutants in environment (with recognition of different molecular structures). Physical and program model of new technical system for environment monitoring with expert subsystem was elaborated [163-178]. The system was able to detect the presence of different chemicals — pollutants, to collect and to accumulate the data about such pollutants with recognition of different molecular structures, to transfer this information to local and networked databases (with open access or with restricted access), and to show corresponding output information on PC interface.
Algorithm and its description. An algorithm of the work of developed technical analytical system with incorporated the simplest version of expert subsystem is represented on Fig. 5. It wass supposed that units described on Fig. 3 are included into the beginning unit on Fig. 5.
Obtained BTS results were processed (their mathematical processing was carried out by a number of methods, including methods of statistical processing, etc.), and they
0 0 r-f H 0 0
AH H H 8 0 °AH H H nh3 I
o NH, 0 m2 2
/nhcnh.
)l 0
0
o Ah
0 NH.
NH. N1
r
Glu
JSTX-3
0,5 nA
100 ms
0,1 nA
100 ms
kk
jstx-3
10s
0,2 na
KK
AR
□ L
H c
0,2 nA
5s
Fig. 4. Electrical signals at the output of the BTS:
toxins: a — JSTX-3 (from Nemphila clavata); b — AR (from Argiope lobata); c — their influences on transmembrane electric currents. Toxin JSTX-3 blocked glutamate-activated (Glu, above) and kainat-activated (KK, middle) transmembrane ionic currents. After receiving the control response to KK, toxin JSTX-3 was applied by the background of
the KK-activated current. Concentrations of Glu and KK were 1 mmol/l, JSTX-3 was 10-4 mol/l.
Vhold= -50 mV [163-178].
Toxin argiopine (AR, below) blocked the open state of KK-activated ion channels. After receiving the control response to Kk, the neuron was maintained in AR during 3 min., then on the background of AR the
KK-solution was added. Concentrations: KK 1 mmol/l, AR 1,610-2 mol/l, Vhold = -100 mV. Toxin was
removed from the membrane through 15 s [163-178]. All records were done on different neurons
b
a
c
were analyzed by comparing them with the corresponding values from the databases, which are linked with expert system (the DB are located in the memory of local or remote servers). During processing of input electrical signals, the sets of characteristics like the times of electric currents' amplitude decline after the action of chemical antagonists, the
binding and dissociation constants of complex receptor-antagonist, etc., were calculated.
The results of obtained recordings analysis were displayed on the output monitors of the expert system (Fig. 6, 7). If such expert system is incorporated into the biotechnical system for monitoring BTSM-4, the results of analysis were displayed on the output
Fig. 5. An algorithm of expert system functioning with the output data recording and the work of linked
alarm subsystem:
Comments to the algorithmof expert system functioning
Unit 1) Input data mining and/or obtaining. The data were input from sensors (like described ones, or registered by bioindicators). Unit 2) Data input.
Unit 3) Input of the data with certain characteristics (information supply). Unit 4) Calculation of average values.
Units 5; 6) The heart of analytical — expert system: expertise providing. Formation of output messages depending on characteristics of revealed and studied chemical substances.
Unit 7) Display of information on the monitor with corresponding comments (alarm or no). Unit 8) Information was transmitted and recorded in local and Internet databases
monitor of BTSM-4. In case when the result of comparison by expert system determined the nature of the substance (the substance is dangerous to organism, or it is safe, or its effect is other), then an appropriate message is displayed on output interface of the expert system (BTSM-4 monitor). The presence of BTS in the network of WEB-based system BTSM-4 created the possibilities for data transfer, data spreading over the network with the further use of all opportunities and benefits of network technologies.
In such a way a number of effects might be registered. For example, let's imagine that on BF influenced the substances JSTX-3 or AR — antagonists of glutamate- and kainat-activated electrical sodium transmembrane currents — and corresponding current registrations were done (recording on Fig. 4). Before there were demonstrated that both JSTX-3 and AR stops activity of glutamatergic synapses in mammals' brains in organism; in some cases, a paralysis or a fatal end is possible. The expert system [Fig. 5] processed this information and it is displayed on monitor screen [Fig. 6, 7]. If necessary, a signal of danger (sound, flash, other signal) appeared. For the implementation of the method, both software from standard packages and specially designed original samples were used (internal databases of the expert system were not shown on Fig. 5).
Program code and its description. Corresponding original software was developed. Program code was written in Java language fot interfase in Ukraine. The program code was written for the work of technical analytical expert system that is able to distinguish environmental hazard according to a number of input variables (in); the fragment of program code is presented below.
import java.util.Arrays; import java.util.List; import java.util.Scanner; import java.sql.*; import java.util.Properties;
public class Detector{
public static void main( String[] args ) {
List<String> a = Arrays.asList(
"1", "2" );
List<String> t = Arrays.asList( "3",
"4" );
List<String> A = Arrays.asList( "A",
"A" );
Scanner sc = new Scanner( System.in );
System.out.println( "Введггь вхщш даш у такому виглядi \"Ax Tx X\" ( напри-клад 1 3 A ):" );
String inputLine = sc.nextLine();
String[] input = inputLine.split(" ");
String result = "";
Boolean detected = false;
for ( int i = 0; i < 2; i++ ) {
if ( input[ 0 ].equals( a.get( i ) ) && input[ 1 ].equals( t.get( i ) ) && input[ 2 ].equals( A.get( i ) ) ) {
result = "B" + ( i + 1 );
System.out.println( "Знайдено речовину:" + result );
saveToDB( result ); detected = true; break;
}
}
if( detected == false ) {
System.out.println( "Знайдено
шшу речовину" );
}
}
public static void saveToDB( String result ) {
String dbURL = "jdbc:mysql:// localhost:3306/detector";
String username ="root";
String password = "password";
Connection dbCon = null;
ResultSet rs = null;
try {
dbCon = DriverManager. getConnection( dbURL, username, password );
String query = "INSERT INTO substance ( substance_code ) VALUES ( ? )";
PreparedStatement stmt = dbCon.prepareStatement( query );
stmt.setString( 1, result );
stmt.executeUpdate();
dbCon.close();
} catch ( SQLException ex ) {
System.out.println( "SQLException: " + ex.getMessage() );
System.out.println( "SQLState: " + ex.getSQLState() );
System.out.println(
"VendorError: " + ex.getErrorCode() ); }
}
}
Technical results of developed expert system examination were as following. 1. An original expert analytical system was developed, which determines the quantitative and qualitative components of the presence of toxic pollutants (phenol- and indol- derivatives) in environment (industrial regions, other). 2. The use of developed electronic expert system permits to determine the presence of harmful and toxic substances in the environment and to send the signal-notification about their availability and quality. 3. It gives the possibility to monitor
the effects of a large number of different chemicals much better, more efficiently, with higher accuracy than prototypes did. 4. BTS linked with the expert system allows analysing the impact of a large number of substances of natural and artificial origin. 5. Results recordings in the form of digitized electrical signals (in local and network databases) in memory of network computers permits to visualize them, to process, to analyse, to output the data, and to transfer them using all advantages of network technologies. 6. The algorithm of expert system functioning, and corresponding software code were developed for this original expert analytical system.
Development of new methods of qualitative and quantitative analysis. Using described expert systems it became possible to develop new methods of qualitative and quantitative analysis of chemicals according to their physiological influence on registered electric currents in neurons of biological organisms. Necessary requirements for this were to make links between the expert system and enough numbers of chemicals and recordings (electrical responces of cell membrane) in the databases; and such databases had to have as more as possible experimental recordings like ones on Fig. 4. Some numbers of such recordings have to be declared as "standard" and to be recorded into separated database for comparison with newly obtained data. The
po/Desktop/Sancho$ java Detector 8вед!ть вх1дн1 дан1 у такому вид! "Ах Тх X" ( напришд 1 3 А ): 1 3 А
|знайдено речоеину;В1 -alarm
pc:-/Desktop/Sancho$ java Detector Введгть вх1дн! данг у такому вид! "Ах Тх X" ( напришд 1 3 А ):
1 4 А
Знайдена \нша речовина
_pc:~/Desktop/$ancho$ java Detector_
Введгть вхгдн1 дан! у такому вид! "Ах Тх X" ( напришд 1 3 А ):
2 4 А
Знайдено речовину:В2
;~/Desktop/Sancho$ 1
Fig. 6. Interface for operator communication with expert analytic system; view of monitor screen:
comments and instructions were written in Ukrainian for domestic use of device
phpMyAdmin
üii *« Ф
selector
¿J sutetance
¿J Create labie
tjtaanost • «lector 1 i îLDsaiiffif
¡3 Browse J<*. Structure Q мл л Search iî Imert ■<à E«port —> Import ^ Operations ¥ Tracking
✓ SHwrgTOvwO- 1|4fctoi OuefylookОООЩset)
SELECT'
ШЯГзиЬйэпсв'
LIMIT Ö. 30
jjjjWIl) 130 rtw(s) starting from row * |o In liwizorilal
т mode and repeal headers alte« ijo cells
Sort by key: Mane Options
T-> Id Jubilance code
Edit »■■ inline Ea t Ji Copy 9 delete * Edit 2 Inline Etlt U Copy 4 delete 2(|Г)
t_ LTiPCT fflrurfrea'ffltTWTjvm.igtr1- Оц^е—д BsH¿"
» Export
Show :
30 rowjs! starling Srom row í
In lionzocilel
' mode and repeal headers ad« 100 cens
Query result's operation!
¿1 Print view Й Print view (with lull lexts) Export Д Display rttart 1] Create view
Fig. 7. Data output from expert analytical system to operator and to databases in the Internet
essence of these methods of qualitative and quantitative analysis was in the discovered regularities between the structures of chemical substances and physiological effects they occur, for example, between chemical structures of JSTX-3 and AR and differences in their blocking activity (Fig. 4). After the obtaining of output transmembrane electric currents records (for example, KK-activated) under the influences of different chemical substances (Fig. 4) it was possible to compare them with standard recordings in databases and then to identify them with defined chemical structures. With enough good and complete databases the expert system can do these procedures with good result. According to the simpliest algorithm we suggested in logical units on Fig. 5 the functions of comparison were realized. There were compared two main characteristics of activity of examined substances JSTX-3 and AR: 1) (nx) — whether antagonist decreased the amplitude of transmembrane electric current: "yes" (1) or "no"(0); 2) (px) — whether it was possible to remove of antagonist from membrane by "washing" with consequent restoring of electrical currents' amplitudes:
"yes" (1) or "no"(0). Sure, more logical subunits it is possible to use also for each individual task solution depending on processed input information. More details about such methods of qualitative and quantitative analysis of chemicals we hope to write in our following publications. Described methods of BTS using with the expert system and nowel methods of qualitative and quantitative analysis were defended by our patents [179-182].
Thus, in present publication were demonstrated that electronic biomedical expert systems might be powerful tools in contemporary biotechnology as well as in biology and medicine in general. The purpose of present article was to make profound review of such information expert systems, their structure, functions and practical applications to give ones a possibility to develop new system types for specific biotechnological or research tasks solution. We discussed the abilities of electronic expert systems, their use as one of important type of modern electronic information systems. Further the information about different prototypes of expert systems in biotechnology as well as in other biomedical
spheres was suggested (possibilities of these systems application for production in agriculture, nature protection from pests and ecological pollutants, for medical systems, and etc.). The principles of expert systems' structure, electronic workplaces, as well as their functioning in biomedical electronic network information systems were demonstrated. Actual information about bioorganisms populations monitoring using electronic information systems with databases and expert capabilities was given. Biotechnical system with expert subsystem for monitoring of substances, harmful for living objects was described.
Developed original electronic information system for ecological monitoring was called "EcoIS" ("Ecological information system"), and one of its versions described in present article was called "BTSM-4". In framework of developed electronic information system the design of user interfaces ("Electronic work places — EWP") were done. The structure and function of one of such versions "EWP-Z" was described in details in present article. All abovementioned numerous electronic systems have been described already in publications in technical scientific literature and defended by patents [173-178].
The developed the simplest version of the expert system for monitoring and profound studying of different chemical substances' influences on organism (chemical environmental pollutants) also was described in details [178]. The advantages of proposed expert system and method were achieved due to co-work of two in-built into "EcoIS" subsystems: subsystem 1 (expert) and subsystem 2 (specially developed BTS with variable BF). Due to the functional capabilities of both subsystems, it was possible to register changes in electrical transmembrane currents in neuronal membranes after the influence of chemicals
REFERENCES
1. Klyuchko O. M. Information and computer technologies in biology and medicine. Kyiv: NAU-druk. 2008, 252 p. (In Ukrainian).
2. Klyuchko O. M. On the mathematical methods in biology and medicine. Biotechnol. acta. 2017, 10 (3), 31-40. https://doi. org/10.15407/biotech10.03.031
3. Klyuchko O. M. Application of artificial neural networks method in biotechnology. Biotechnol. acta. 2017, 10 (4), 5-13. https:// doi.org/10.15407/biotech10.04.005
on them, which may indicate a possible danger to living organism; the output monitor of electronic system then receives corresponding signal. The analysis of the data obtained from BTS was carried out by comparing the data from the corresponding inner databases connected with the expert system. After such analysis by expert system the resulting report about the presence (or absence or otherwise) of danger to organism in zone with chemical substances were displayed on the monitor at the output of electronic information system BTSM-4; if necessary, an alarm signal (sound, flash-signal, others) is output also. The use of BF as a detector and/or bioanalyser allows a significant increase of chemicals number in the list of substances, and among them it is possible to register such harmful and dangerous substances for humans, as some derivatives of phenols and/or indoles. BTSM-4 can be used also as an express system.
Using described expert systems it became possible to develop new methods of qualitative and quantitative analysis. The essence of these methods was in registered regularities between the structure of chemical substances and physiological effects they occur. After the obtaining of output transmembrane electric currents records under the influences of different chemical substances (Fig. 4) it was possible to compare them with standard recordings in databases and then to identify them with defined chemical structures. With enough good and complete databases the expert system can do this procedure with satisfactory result. The described methods of BTS using with the expert system and nowel methods of qualitative and quantitative analysis were defended and supported by patents [162-182]. The work done might be implemented in such branches as biotechnology, biophysics, ecology, ecological safety, pharmacology.
4. Klyuchko O. M. Cluster analysis in biotechnology. Biotechnol. acta. 2017, 10 (5), 5-18. https://doi.org/10.15407/ biotech10.05.005
5. Klyuchko O. M. Technologies of brain images processing. Biotechnol. acta. 2017, 10 (6), 5-17. https://doi.org/10.15407/ biotech10.05.005
6. Klyuchko O. M., Onopchuk Yu. M. Some trends in mathematical modeling for biotechnology. Biotechnol. acta. 2018, 11 (1), 39-57. https:// doi.org/10.15407/biotech11.01.039
7. Klyuchko O. M. Electronic information systems in biotechnology. Biotechnol. acta. 2018, 11 (2), 5-22. https://doi.org/10.15407/ biotech11.02.005
8. Klyuchko O. M. Information computer technologies for biotechnology: electronic medical information systems. Biotechnol. acta. 2018, 11 (3), 5-26. https://doi.org/10.15407/ biotech11.03.005
9. Klyuchko O. M., Klyuchko Z. F. Electronic databases for Arthropods: methods and applications. Biotechnol.. acta. 2018, 11 (4), 28-49. https://doi. org/10.15407/biotech11.04.028
10. Klyuchko O. M., Klyuchko Z. F. Electronic information systems for monitoring of populations and migrations of insects. Biotechnol. acta. 2018, 11 (5), 5-25. https:// doi.org/10.15407/biotech11.05.005
11. Judith M. Hushon. Overview of Environmental Expert Systems. Expert Systems for Environmental Applications. Chapt.1, P. 1-24. https://doi.org/10.1021/ bk-1990-0431.ch001; ACS Symposium Series, V. 431. Publ. 05.06.1990 https://pubs.acs. org/doi/abs/10.1021/bk-1990-0431.ch001
12. Glenn F. Osborne, Simon S. M. Chin, Paul McDonald, Scott Schneider. Artificial intelligence system for genetic analysis. Patent US 8693751B2. Priority date: 199908-27, 2014-04-08 Grant. https://patents. google.com/patent/US8693751
13. Roland Eils. Expert system for classification and prediction of genetic diseases Patent US, JP, CA, WO2002047007A3. Priority date: 2000-12-07.WOApplication2002-12-12. https://patents.google.com/patent/ WO2002047007A2
14. Prasad S. Kodukula, Charles R. Stack. Water treatment monitoring system. Patent US 6845336B2. Priority date: 25-06-2002; Grant: 01-18-2005. https://patents.google. com/patent/US6845336
15. Klyuchko O. M., PashkivskyA. O., Sheremet D. Y. Computer modeling of some nanoelements for radio and television systems. Electr. Contr. Syst. 2012, 3 (33), 102-107. (In Ukrainian).
16. Klyuchko O. M., Hayrutdinov R. R. Modeling of electrical signals propagation in neurons and its nanostructures. Electr. Contr. Syst. 2011, 2 (28), 120-124. (In Ukrainian).
17. Trinus K. F., Klyuchko O. M. Mediators influence on motoneurons retrogradly marked by primulin. Physiol. J. 1984, 30 (6), 730-733. (In Russian).
18. Aralova N. I., Klyuchko O. M., Mashkin V. I., Mashkina I. V. Algorithmic and program support for optimization of interval hypoxic training modes selection of pilots. Electr. Contr. Syst. 2017, 2 (52), 85-93.
19. Aralova N. I., Klyuchko O. M., Mashkin V. I., Mashkina I. V. Mathematic and program
models for investigation of reliability of operator professional activity in "Human-Machine" systems. Electr. Contr. Syst. 2017, 1 (51), 105-113.
20. Aralova N. I., Klyuchko O. M., Mashkin V. I., Mashkina I. V. Mathematical model for research of organism restoring for operators of continuously interacted systems. Electr. Contr. Syst. 2016, 3 (49), 100-105.
21. Aralova N. I., Klyuchko O. M., Mashkin V. I., Mashkina I. V. Investigation of reliability of operators work at fluctuating temperature conditions. Electr. Contr. Syst. 2016, 2 (48), 132-139.
22. Plakhotnij S.A., Klyuchko O. M., Krotinova M. V. Information support for automatic industrial environment monitoring systems. Electr. Contr. Syst. 2016, 1 (47), 19-34.
23. Onopchuk Yu. M., Aralova N. I., Klyuchko O. M, Beloshitsky P. V. Mathematic models and integral estimation of organism systems reliability in extreme conditions. Electr. Contr. Syst. 2015, 4 (46), 109-115.
24. Onopchuk Yu. M., Aralova N. I., Klyuchko O. M., Beloshitsky P. V. Integral estimations of human reliability and working capacity in sports wrestling. J. Engin. Acad. 2015, N 3, P. 145-148.
25. Klyuchko O.M., Shutko V.N., Navrotskyi D. O, Mikolushko A. M. The set of program models for ecological monitoring technical system based on principles of biophysics. Electr. Contr. Syst. 2014, 4 (42), 135-142.
26. Klyuchko O. M., Sheremet D. Yu. Computer simulation of biological nanogenerator functions. Electr. Contr. Syst. 2014, 2 (40), 103-111.
27. Klyuchko O. M., Shutko V. N. Computer modeling of auto-oscillating phenomena in neuron complexes. Electr. Contr. Syst. 2014, 1 (39), 127-132.
28. Klyuchko O. M., Sheremet D. Yu. Computer modeling of biologic voltage-activated nanostructures. Electr. Contr. Syst. 2014, 1 (39), 133-139.
29. Beloshitsky P. V., Klyuchko O. M,, Onopchuk Yu. M. Radiation damage of organism and its correction in conditions of adaptation to high-mountain meteorological factors. Bull. Nat.Acad. Sci. Ukr. 2010, N 1, P. 224-231. (In Ukrainian).
30. Beloshitsky P. V., Klyuchko O. M., Onopchuk Yu., Makarenko M. V. Estimation of psycho-physiological functions of a person and operator work in extreme conditions. Bull. Nat. Acad. Sci. Ukr. 2009, N 3, P. 96-104. (In Ukrainian).
31. Beloshitsky P. V., Klyuchko O. M., Onopchuk Yu., Kolchinska A. Z. Results of research of higher nervous activity problems by Ukrainian scientists in Prielbrussie. Bull. Nat. Acad. Sci. Ukr. 2009, N 2, P. 105-112. (In Ukrainian).
32. Beloshitsky P. V., Klyuchko O. M., Onopchuk Yu. Results of research of structural and
functional interdependences by Ukrainian scientists in Prielbrussie. Bull. Nat. Acad. Sci. Ukr. 2009, N 1, P. 61-67. (In Ukrainian).
33. Beloshitsky P. V., Klyuchko O. M., Onopchuk Yu. Results of research of highlands factors influence on health and longevity by Ukrainian scientists in Prielbrussie. Bull. Nat. Acad. Sci. Ukr. 2008, N 4, P. 108-117. (In Ukrainian).
34. Onopchuk Yu. M., Klyuchko O. M., Beloshitsky P. V. Development of mathematical models basing on researches of Ukrainian scientists at Elbrus. Bull. Nat. Acad. Sci. Ukr. 2008, N 3, P. 146-155. (In Ukrainian).
35. Beloshitsky P. V., Klyuchko O. M., Onopchuk Yu. Results of research of adaptation problems by Ukrainian scientists in Prielbrussie. Bull. Nat. Acad. Sci. Ukr. 2008, N 1, P. 102-108. (In Ukrainian).
36. Beloshitsky P. V., Klyuchko O. M., Onopchuk Yu. Results of research of hypoxia problems by Ukrainian scientists in Elbrus region. Bull. Nat. Acad. Sci. Ukr. 2007, N 3-4, P. 44-50. (In Ukrainian).
37. Beloshitsky P. V., Klyuchko O. M., Onopchuk Yu. Results of medical and biological research of Ukrainian scientists at Elbrus. Bull. Nat. Acad. Sci. Ukr. 2007, N 2, P. 10-16. (In Ukrainian).
38. Belan P., Gerasimenko O., Petersen O. H,, Tepikin A. Localization of Ca2+ extrusion sites in pancreatic acinar cells. J. Biol. Chem. 1996, V.271, P.7615-7619.
39. Belan P. V, Gerasimenko O. V, Tepikin A. V, Petersen O. H. Extracellular Ca2+ spikes due to secretory events in salivary gland cells. J. Biol. Chem. 1998, V. 273, P. 4106-4111.
40. Jabs R., Pivneva T., Huttmann K. Synaptic transmission onto hyppocampal glial cells with hGFAP promoter activity. J. Cell Sci. 2005, V.118, P.3791-3803.
41. Gavrilovich M. Spectra image processing and application in biotechnology and pathology. Dissertation for Ph.D. Acta Universitatis Upsaliensis. Upsala. 2011, 63 p.
42. Perner P., Salvetti O. Advances in Mass Data Analysis of Images and Signals in Medicine, Biotechnology, Chemistry and Food Industry. Third International Conference, Leipzig, (Germany): Springer, 2008, Proceedings. 2008, 173 p.
43. Baert P., Meesen G., De Schynkel S., PoffijnA., Oostveldt P. V. Simultaneous in situ profiling of DNA lesion endpoints based on image cytometry and a single cell database approach. Micron. 2005, 36 (4), 321-330. https://doi. org/ 10.1016/j.micron.2005.01.005
44. Berks G., Ghassemi A., von Keyserlingk D. G. Spatial registration of digital brain atlases based on fuzzy set theory. Comp. Med. Imag. Graph. 2001, 25 (1), 1-10. https://doi. org/10.1016/S0895-6111(00)00038-0
45. Nowinski W. L., Belov D. The Cerefy Neuroradiology Atlas: a Talairach-Tournoux atlas-based tool for analysis of neuroimages available over the internet. Neurolmage. 2003, 20 (1), 50-57. https:// doi.org/10.1016/S1053-8119(03)00252-0
46. Chaplot S., Patnaik L. M., Jagannathan N. R. Classification of magnetic resonance brain images using wavelets as input to support vector machine and neural network. Biomed. Sign. Proc. Contr. 2006, 1 (1), 86-92. https:// doi.org/10.1016/j.bspc.2006.05.002
47. Kovalev V. A., Petrou M., Suckling J. Detection of structural differences between the brains of schizophrenic patients and controls. Psychiatry Research: Neuroimaging. 2003, 124 (3), 177-189. https://doi.org/10.1016/ S0925-4927(03) 00070-2
48. Araujo T. et al. Classification of breast cancer histology images using Convolutional Neural Networks. PloS One. 2017, 12 (6), e0177544.
49. Vecht-Lifshitz S. E., Ison A. P. Biotechnolo-gical applications of image analysis: present and future prospects. J. Biotechnol. 1992, 23 (1), 1-18.
50. Toga A. W., Thompson P. M. The role of image registration in brain mapping. Image Vis. Comp. 2001, 19 (1-2), 3-24.
51. Shu-HsienLiao. Expert system methodologies and applications — a decade review from 1995 to 2004. Expert Systems with Applications. 2005, 28 (1), 93-103. https:// doi.org/10.1016/j.eswa.2004.08.003
52. Weiskopf N., Scharnowski F., Veit R., Goebel R., Birbaumer N, Mathiak K. Self-regulation of local brain activity using real-time functional magnetic resonance imaging (fMRI). J. Physiol. Paris. 2004, 98 (4-6), 357-373. https://doi. org/10.1016/j.jphysparis.2005.09.019
53. Y an H., Y. Jiang, J.Zheng, Fu B., Xiao S., Peng C. The internet-based knowledge acquisition and management method to construct large-scale distributed medical expert systems. - Computer methods and programs in biomedicine. 2004, 74 (1), 1-10. https://doi. org/10.1016/S0169-2607(03)00076-2
54. Yi M. Y., J. D. Jackson, J. S. Park, Probst J. C. Understanding information technology acceptance by individual professionals: Toward an integrative view. Information & Management. 2006, 43 (3), 350-363. https://doi.Org/10.1016/j.im.2005.08.006
55. Young R. Genetic toxicology: web resources. Toxicology. 2002, 173 (1-2), 103-121.
56. Yu C. Methods in biomedical ontology. J. Biomed. Inform. 2006, 39 (3), 252-266. https://doi.org/10.1016/j.jbi.2005.11.006
57. Zhang J., Sun J., Yang Y., Chen X., Meng L., Lian P. Web-based electronic patient records for collaborative medical applications. Computerized Medical Imaging and Graphics.
2005, 29 (2-3), 115-124. https://doi. org/10.1016/j.compmedimag.2004.09.005
58. Zhoua X., Weib J., Xub C.-Z. Quality-of-service differentiation on the Internet: A taxonomy. Journal of Network and Computer Applications. 2007, 30 (1), 354-383. https:// doi.org/10.1016/j.jnca.2005.07.001
59. Zimowska G. J., Handler A M.. Highly conserved piggyBac elements in Noctuidae species of Lepidoptera. Insect Biochemistry and Molecular Biology. 2006, 36 (5). 421-428. https:/doi.org/10.1016/j.ibmb.2006.03.001
60. Carro S. A., Scharcanski J. A framework for medical visual information exchange on the WEB. Computers in Biology and Medicine.
2006, 36 (4), 327-338.
61. Chakravarty M. M., Bertrand G., Hodge C. P., Sadikot A F., Collins D. L. The creation of a brain atlas for image guided neurosurgery using serial histological data. Neurolmage. 2006, 30 (2), 359-376. https://doi. org/10.1016/ j.neuroimage.2005.09.041
62. Dikshit A., Wu D., Wu C., Zhao W. An online interactive simulation system for medical imaging education. Comp. Med. Imag. Graph. 2005, 29 (6), 395-404. https://doi. org/10.1016/j.compmedimag.2005.02.001
63. Singh R., Schwarz N., Taesombut N., Lee D., Jeong B., Renambot L., Lin A. W., West R., Otsuka H., Naitof S., Peltier S. T, Martone M. E., Nozaki K., Leigh J., Ellisman M. H. Real-time multi-scale brain data acquisition, assembly, and analysis using an end-to-end. OptlPuter Fut. Gener. Comp. Syst. 2006.
64. Stefanescu R., Pennec X., Ayache N. Grid powered nonlinear image registration with locally adaptive regularization. Med. Image Anal. 2004, 8 (3), 325-342.
65. Ma Y., Hof P. R., Grant S. C., Blackband S. J., Bennett R., Slatest L., McGuigan M. D, Benveniste H. A three-dimensional digital atlas database of the adult C57BL/6J mouse brain by magnetic resonance microscopy. Neuroscience. 2005, 135 (4), 1203-1215. https://doi.org/10.1016/j. neuroscience.2005.07.014
66. Yu-Len Huang. Computer-aided Diagnosis Using Neural Networks and Support Vector Machines for Breast Ultrasonography. J. Med. Ultrasound. 2009, 17 (1), 17-24.
67. Prachi Damodhar Shahare, Ram Nivas Giri. Comparative Analysis of Artificial Neural Network and Support Vector Machine Classification for Breast Cancer Detection. Int. Res. J. Engin. Technol. (IRJET). 2015, V. 2, Is. 9.
68. Natrajan R., Sailem H., Mardakheh F. K., Garcia M. F., Tape C. G., Dowsett M., Bakal C., Yuan Y. Microenvironmental heterogeneity parallels breast cancer progression: a histology-genomic integration analysis.
PLoS Med. 2016. 13 (2), e1001961. https:// doi.org/10.1371/journal.pmed.1001961
69. Klyuchko O. M. Brain images in information systems for neurosurgery and neurophysiology. Electr. Contr. Syst. 2009, 3 (21), 152-156. (In Ukrainian).
70. Klyuchko O. M. Using of images' databases for diagnostics of pathological changes in organism tissues. Electr. Contr. Syst. 2009, 2 (20), 62-68. (In Ukrainian).
71. Klyuchko O. M. Elements of different level organization of the brain as material for electronic databases with images. Electr. Contr. Syst. 2009, 1 (19), 69-75. (In Ukrainian).
72. Klyuchko O.M,, Shutko V.N., MikolushkoA.M., Navrotskyi D. A. Possibility of images recognition by artificial biotechnical system. 2014 IEEE 3d Intl Conference: MSNMC Proceedings. 2014, P. 165-169.
73. Klyuchko O. M., Managadze Yu. L., Pashkivsky A. O. Program models of 2D neuronal matrix for ecological monitoring and images' coding. Bull. Engin. Acad. 2013, N 3-4, P. 77-82. (In Ukrainian).
74. Klyuchko O.M., Piatchanina T. V., MazurM. G. Combined use of relation databases of images for diagnostics, therapy and prognosis of oncology diseases. "Integrated robototechnic complexes". X IIRTC-2017 Conference Proceedings. P. 275-276. (In Ukrainian).
75. Shutko V. M., Shutko O. M., Kolganova O. O. Methods and means of compression of information. Kyiv: Nauk. dumka. 2012, 168 p. (In Ukrainian).
76. Jecheva V., Nikolova E. Some clustering-based methodology applications to anomaly intrusion detection systems. Int. J. Secur. Appl. 2016, 10 (1), 215-228. http://dx.doi. org/10.14257/ijsia.2016.10.1.20
77. Iakovidis D. K., Maroulis D. E., Karkanis S. A. Texture multichannel measurements for cancer precursors' identification using support vector machines. Measurement. 2004, V. 36, P. 297-313. https://doi. org/10.1016/j.measurement. 2004.09.010
78. Nguyen H. Q., Carrieri-Kohlman V., Rankin S. H., Slaughter R., Stulbarg M. S. Internet-based patient education and support interventions: a review of evaluation studies and directions for future research. Comp. Biol. Med. 2004, 34 (2), 95-112. https://doi.org/10.1016/ S0010-4825(03)00046-5
79. Jezequel P., Loussouarn L., Guerin-Charbonnel C., Campion L., Vanier A., Gouraud W., Lasla H., Guette C., Valo I., Verriele V., Campone M. Gene-expression molecular subtyping of triple-negative breast cancer tumours: importance of immune response. Breast Cancer Res. 2015, 17 (1), 43. https://doi. org/10.1186/s13058-015-0550-y
80. Bozhenko V. K. Multivariable analysis of laboratory blood parameters for obtaining diagnostic information in experimental and clinical oncology. The dissertation author's abstract on scientific degree editions. Dc. Med. Study. Moscow. 2004. (In Russian).
81. Ko J. H, Ko E. A., Gu W., Lim I., Bang H, Zhou T. Expression profiling of ion channel genes predicts clinical outcome in breast cancer. Mol. Cancer. 2013, 12 (1), 106. https://doi.org/10.1186/1476-4598-12-106
82. KawaiM,NakashimaA.,KamadaS,Kikkawa U. Midostaurin preferentially attenuates proliferation of triple-negative breast cancer cell lines through inhibition of Aurora kinase family. J. Biomed. Sci. 2015, 22 (1), 48. https://doi.org/10.1186/s12929-015-0150-2
83. Uhr K., Wendy J. C., Prager-van der Smissen, Anouk A. J. Heine, Bahar Ozturk, Marcel Smid, Hinrich W. H. Göhlmann, Agnes Jager, John A. Foekens, John W. M. Martens. Understanding drugs in breast cancer through drug sensitivity screening. SpringerPlus. 2015, 4 (1), 611. https://doi. org/10.1186/s40064-015-1406-8
84. Onopchuk Yu. M., Biloshitsky P. V., Klyuchko O. M. Development of mathematical models based on the results of researches of Ukrainian scientists at Elbrus. Visnyk Nat. Acad. Sci. Ukr. 2008, N 3, P. 146-155. (In Ukrainian).
85.Ankur Poudel, Dhruba Bahadur Thapa, Manoj Sapkota. Cluster Analysis of Wheat (Triticum aestivum L.) Genotypes Based Upon Response to Terminal Heat Stress. Int. J.Appl. Sci. Biotechnol. 2017, 5 (2), 188193. https://dx.doi.org/10.3126/ijasbt. v5i2.17614
86. Zaslavsky L., Ciufo S., Fedorov B., Tatusova T. Clustering analysis of proteins from microbial genomes at multiple levels of resolution. BMC Bioinform. 2016, 17 (8), 276. Published online 2016 Aug 31. https:// doi.org/10.1186/s12859-016-1112-8
87. Zhou J., Richardson A. J., Rudd K. E. EcoGene-RefSeq: EcoGene tools applied to the RefSeq prokaryotic genomes. Bioinformatics. 2013, 29 (15), 1917-1918. Published: 04 June 2013. https://doi.org/10.1093/ bioinformatics/btt302
88. Zhang J., Wu G., Hu X., Li S., Hao S. A Parallel Clustering Algorithm with MPI — MKmeans. J. Comput. 2013, 8 (1), 10-17. https://doi.org/10.1109/PAAP. 2011.17
89. Tatusova T., Zaslavsky L., Fedorov B., Had-dad D., Vatsan A., Ako-adjei D., Blinkova O., Ghazal H. Protein Clusters. The NCBI Handbook [Internet]. 2nd edition. Available at https:// www.ncbi.nlm.nih.gov/books/NBK242632
90. Anderson J. G. Evaluation in health informatics: computer simulation. Comp.
Biol. Med. 2002, 32 (3), 151-164. https:// doi.org/10.1016/S0010-4825(02)00012-4
91. Aruna P., Puviarasan N., Palaniappan B. An investigation of neuro-fuzzy systems in psychosomatic disorders. Exp. Syst. Appl. 2005, 28 (4), 673-679. https://doi. org/10.1016/j.eswa.2004.12.024
92. Bange M. P., Deutscher S. A., Larsen D., Linsley D., Whiteside S. A handheld decision support system to facilitate improved insect pest management in Australian cotton systems. Comp. Electron. Agricult. 2004, 43 (2), 131-147. https://doi.org/10.1016/j. compag.2003.12.003
93. Beaulieu A. From brainbank to database: the informational turn in the study of the brain. Stud. Hist. Phil. Biol. Biomed. Sci. 2004, V. 35, P. 367-390. https://doi. org/10.1016/j.shpsc.2004.03.011
94. Bedathur S. J., Haritsa J. R., Sen U. S. The building of BODHI, a bio-diversity database system. Inform. Syst. 2003, 28 (4), 347367. https://doi.org/ 10.1016/S0306-4379(02)00073-X
95. Brake I. Unifying revisionary taxonomy: insect exemplar groups. Abstr. XV SEL Congr. Berlin (Germany). 2007.
96. Braxton S. M., Onstad D. W., Dockter D. E., Giordano R., Larsson R., Humber R. A. Description and analysis of two internet-based databases of insect pathogens: EDWIP and VIDIL. J. Invertebr. Pathol. 2003, 83 (3), 185-195. https://doi.org/10.1016/S0022-2011(03)00089-2
97. Breaux A., Cochrane S., Evens J., Martindaled M., Pavlike B., Suera L., Benner D. Wetland ecological and compliance assessments in the San Francisco Bay Region, California, USA. J. Environm. Manag. 2005, 74 (3), 217-237.
98. Budura A., hilippeCudre-Mauroux P., Aberer K. From bioinformatic web portals to semantically integrated Data Grid networks. Fut. Gener. Comp. Syst. 2007, 23 (3), 281-522. https://doi.org/10.1016/j. jenvman.2004.08.017
99. Burns G., Stephan K. E., Ludäscher B., Gupta A., Kötter R. Towards a federated neuroscientific knowledge management system using brain atlases. Neurocomputing. 2001, V. 3840, P. 1633-1641. https://doi. org/10.1016/S0925-2312(01)00520-3
100. Butenko S., Wilhelm W. E. Clique-detection models in computational biochemistry and genomics. Eur. J. Oper. Res. 2006, 173 (1), 117. https://doi.org/ 10.1016/j. ejor.2005.05.026
101. Carro S. A., Scharcanski J. Framework for medical visual information exchange on the WEB. Comp. Biol. Med. 2006, 36 (4), 327-338. https://doi.org/10.1016/ j.compbiomed.2004.10.004
102. Chau M., Huang Z., Qin J., Zhou Y., Chen H. Building a scientific knowledge web portal: The NanoPort experience. Decisi. Supp. Syst. 2006. https://doi.org/10.1016/j. dss.2006.01.004
103. Chen M., Hofestadt R. A medical bioinformatics approach for metabolic disorders: Biomedical data prediction, modeling, and systematic analysis. J. Biomed. Inform. 2006, 39 (2), 147-159. https://doi.org/10.1016Zj.jbi.2005.05.005
104. Chli M., De Wilde P. Internet search: Subdivision-based interactive query expansion and the soft semantic web Applied Soft Computing. 2006. https://doi. org/10.1016/j.asoc.2005.11.003
105. Despont-Gros C., Mueller H., Lovis C. Evaluating user interactions with clinical information systems: A model based on human-computer interaction models. J. Biomed. Inform. 2005, 38 (3), 244-255. https://doi.org/10.1016/ j.jbi.2004.12.004
106. Despont-Gros C., Mueller H., Lovis C. Evaluating user interactions with clinical information systems: a model based on human-computer interaction models. J. Biomed. Inform. 2005, 38 (3), 244-255. https://doi.org/10.1016/j.jbi.2004.12.004
107. Marios D, Dikaiakos M. D. Intermediary infrastructures for the World Wide Web. Comp. Networks. 2004, V. 45, P. 421-447. https:// doi.org/ 10.1016/j.comnet.2004.02.008
108. Dimitrov S. D., Mekenyan O. G., Sinks G. D., Schultz T. W. Global modeling of narcotic chemicals: ciliate and fish toxicity. J. Mol. Struct: Theochem. 2003, 622 (12), 63-70. https://doi. org/10.1016/S0166-1280(02)00618-8
109. Dong Y., Zhuang Y., Chen K., Tai X. A hierarchical clustering algorithm based on fuzzy graph connectedness. Fuzzy Sets. Syst. 2006, V. 157, P. 1760-1774. https:// doi.org/10.1016/j.fss.2006.01.001
110. Duan Y., Edwards J. S., Xu M. X. Web-based expert systems: benefits and challenges. Inf. Manag. 2005, 42 (6), 799-811. https://doi. org/10.1016/j.im.2004. 08.005
111. Essen van D. C. Windows on the brain: the emerging role of atlases and databases in neuroscience. Curr. Opin. Neurobiol. 2002, 12 (5), 574-579. https://doi.org/10.1016/ S0959-4388(02)00361-6
112. Fellbaum C., Hahn U., Smith B. Towards new information resources for public health From Word Net to Medical Word Net. J. Biomed. Inform. 2006, 39 (3), 321-332. https://doi.org/10.1016/j.jbi.2005.09.004
113. Ferraris M., Frixione P., Squarcia S. Network oriented radiological and medical archive. Comp. Physics Commun. 2001, V. 140, P. 226-232. https://doi.org/10.1016/ S0010-4655(01)00273-9
114. Flower D. R., Attwood T. K. Integrative bioinformatics for functional genome annotation: trawling for G protein-coupled receptors. Semin. Cell. Dev. Biol. 2004, 15 (6), 693-701. https://doi.org/10.1016/jj. semcdb.2004.09.008
115. Fink E., Kokku P. K., Nikiforou S., Hall L. O., Goldgof D. B., Krischer J. P. Selection of patients for clinical trials: an interactive web-based system. Art. Intell. Med. 2004, 31 (3), 241-254. https://doi.org/10.1016/jj. artmed.2004.01.017
116. Fitzpatrick M. J., Ben-Shahar Y., Smid H. M., Vet L. E., Robinson G. E., Sokolowski M. B. Candidate genes for behavioural ecology. Trend Ecol. Evol. 2005, 20 (2), 96-104. https://doi.org/10.1016/jj.tree.2004.11.017
117. Fox J., Alabassi A., Patkar V., Rose T., Black E. An ontological approach to modelling tasks and goals. Comp. Biol. Med. 2006, V. 36, P. 837-856. https://doi.org/10.1016/jj. compbiomed.2005.04.011
118. Fu Zetian, Xu Feng, Zhou Yun, Shuan X. Z. Pig-vet: a web-based expert system for pig disease diagnosis. 2006. https://doi. org/10.1016/j.eswa.2005.01.011
119. Gaulton A., Attwood T. K. Bioinformatics approaches for the classification of G-protein-coupled receptors. Curr. Opin. Pharmacol. 2003, 3 (2), 114-120. https:// doi.org/10.1016/S1471-4892(03)00005-5
120. Gevrey M., Worner S., Kasabov N., Pitt J., Giraudel J. L. Estimating risk of events using SOM models: A case study on invasive species establishment. Ecol. Modell. 2006, 197 (34), 361-372. https://doi. org/10.1016/j.ecolmodel. 2006.03.032
121. Glenisson P., Glänzel W., Janssens F., MoorB. D. Combining full text and bibliometric information in mapping scientific disciplines. Inf. Proc. Manag. 2005, 41 (6), 1548-1572. https://doi.org/10.1016Zj.ipm.2005.03.021
122. Goldys E. M. Fluorescence Applications in Biotechnology and the Life Sciences. USA: John Wiley & Sons. 2009, 367 p.
123. Graham C. H., Ferrier S., Huettman F., Moritz C., Peterson A. T. New developments in museum-based informatics and applications in biodiversity analysis. Trend. Ecol. Evol. 2004, 19 (9), 497-503. https:// doi.org/10.1016/ j.tree.2004.07.006
124. Gruber T. R. A translation approach to portable ontologies. Knowl. Acquisition. 1993, 5 (2), 199-220. https://doi. org/10.1006/knac.1993.1008
125. Hirano S., Sun X., Tsumoto S. Comparison of clustering methods for clinical databases. Inform. Sci. 2004, 159 (34), 155-165. https://doi.org/10.1016/j.ins.2003.03.011
126. Hong Yu., Hatzivassiloglou V., Rzhetsky A., Wilbur W. J. Automatically identifying
gene/protein terms in MEDLINE abstracts. J. Biomed. Inform. 2002, 35 (56), 322330. https://doi.org/10.1016/S1532-0464(03)00032-7
127. Horn W. AI in medicine on its way from knowledge-intensive to data-intensive systems. Artificial Intelligence in Medicine. Elsevier. 2001, 23 (1), 512. https://doi. org/10.1016/S0933-3657(01)00072-0
128. Hsi-Chieh Lee, Szu-Wei Huang, Li E. Y. Mining protein-protein interaction information on the internet. Exp. Syst. Appl. Elsevier. 2006, 30 (1), 142-148. https:// doi.org/10.1016/j.eswa.2005.09.083
129. Jabs R., Pivneva T., Huttmann K., Wyczynski A., Nolte C., Kettenmann H., Steinhäuser C. Synaptic transmission onto hyppocampal glial cells with hGFAP promoter activity. J. Cell Sci. 2005, V. 118, P. 3791-3803. https://doi.org/10.1242/jcs.02515
130. Johnson S. B., Friedman R. Bridging the gap between biological and clinical informatics in a graduate training program. J. Biomed. Inform. 2007, 40 (1), 59-66. Epub. 2006 Mar 15. https://doi.org/10.1016/j. jbi.2006.02.011
131. Kaiser M., Hilgetag C. C. Modelling the development of cortical systems networks. Neurocomputing. 2004, V. 5860, P. 297-302. https://doi.org/ 10.1016/j. neucom.2004.01.059
132. Yan H., Jiang Y., Zheng J. The internet-based knowledge acquisition and management method to construct large-scale distributed medical expert system. Comp. Meth. Progr. Biomed. 2004, 74 (1), 1-10.
133. Kannathal N., Acharya U. R., Lim C. M., Sadasivan P. K. Characterization of EEG. A comparative study. Comp. Meth. Progr. Biomed. 2005, 80 (1), 17-23. https://doi. org/10.1016/j.cmpb.2005.06.005
134. Koh W., McCormick B. H. Brain microstructure database system: an exoskeleton to 3D reconstruction and modelling. Neurocomputing.
2002, V. 4446, P. 1099-1105. https://doi. org/10.1016/S0925-2312(02)00426-5
135. Koh W., McCormick B. H. Registration of a 3D mouse brain atlas with brain microstructure data. Neurocomputing.
2003, V. 5254, P. 307-312. https://doi. org/10.1016/S0925-2312(02)00793-2
136. Kulish V., Sourin A., Sourina O. Human electro encephalograms seen as fractal time series: Mathematical analysis and visualization. Comp. Biol. Med. 2006, 36 (3), 291-302. https://doi.org/10.1016/j. compbiomed.2004.12.003
137. Lubitz von D., Wickramasinghe N. Networkcentric healthcare and bioinformatics: Unified operations within three domains of knowledge. Exp. Syst.
Appl. 2006, 30 (1), 11-23. https://doi. org/10.1016/j.eswa.2005.09.069
138. Martin-Sanchez F., Iakovidis I., Norager S., Maojo V., de Groen P., Van der Lei J., Jones T., Abraham-Fuchs K., Apweiler R., Babic A., Baud R., Breton V., Cinquin P., Doupi P., Dugas M., Eils R., Engelbrecht R., Ghazal P., Jehenson P., Kulikowski C., Lampe K., De Moor G., Orphanoudakis S., Rossing N., Sarachan B., Sousa A., Spekowius G., Thireos G., Zahlmann G., Zvárová J., Hermosilla I., Vicente F. J. Synergy between medical informatics and bioinformatics: facilitating genomic medicine for future health care. J. Biomed. Inform. 2004, 37 (1), 30-42. https://doi.org/10.1016/j. jbi.2003.09.003
139. Masseroli M., Visconti A., Bano S. G., Pinciroli F. He@lthCo-op: a web-based system to support distributed healthcare co-operative work. Comp. Biol. Med. 2006, 36 (2), 109-127. https://doi.org/10.1016/j. compbiomed.2004.09.005
140. Moon S., Byun Y., Han K. FSDB: A frameshift signal database. — Comp. Biol. Chem. 2007, 31 (4), 298-302. https://doi. org/10.1016/j.compbiolchem.2007.05.004
141. Orgun B., Vu J. HL7 ontology and mobile agents for interoperability in heterogeneous medical information systems. Comp. Biol. Med. 2006, 36 (78), 817-836. https://doi. org/10.1016/j.compbiomed.2005.04.010
142. Pérez-Rey D., Maojo V., García-Remesal M., Alonso-Calvo R., Billhardt H., Martin-Sánchez F., Sousa A. Ontofusion: Ontology-based integration of genomic and clinical databases. Comp. Biol. Med. 2006, 36 (78), 712-730. https://doi.org/10.1016/j. compbiomed.2005.02.004
143. Krishtal O. A., Kiskin N. I., Tsyndrenko A Ya., Klyuchko E. M. Pharmacological properties of amino acid receptors in isolated hippocampal neurons. Receptors and ion channels. Ed. by Ovchinnikov Y. A., Hucho F. Berlin-New York: Walter de Gruyter. 1987, P. 127-137.
144. Klyuchko E. M, Klyuchko Z. F., Beloshits-ky P. V. Some adaptation characteristics of insects in mountains of Prielbrussie. Nalchik (Russia), "Hypoxia: automatic analysis of hypoxic states of healthy people and sick ones. 2005, V. 1, P. 137-140. (In Russian).
145. Klyuchko O. M., Development of ecological databases of part of algorithm of ecological monitoring. Electr. Contrl. Syst. 2008,
2 (16), 42-50. (In Ukrainian).
146. Klyuchko O. M., Development of electronic information systems for monitoring of insect fauna. Electr. Contrl. Syst. 2008,
3 (17), 57-63. (In Ukrainian).
147. Gonchar O., Klyuchko E., Mankovskaya I. Role of complex nucleosides in the reversal of oxidative stress and metabolic disorders induced by acute nitrite poisoning. Indian J. Pharmacol. 2006, 38 (6), 414-418. http:// www.ijp-online.com/article.asp?issn=0253-7613;year=2006;volume=38;issue=6;spage =414;epage=418;aulast=Gonchar
148. Gonchar O., Klyuchko E., Seredenko M., Oliynik S. Corrections of prooxidant — antioxidant homeostasis of organism under hypoxia of different genesis by yackton, new pharmacological preparation. Sofia (Bulgaria), Acta Physiol. Pharmacol. Bulg. 2003, V. 27, P. 53-58.
149. Klyuchko O., Klyuchko Z., Lizunova A. Electronic Noctuidae database: some problems and solutions. Proceed. 16th European Congress of Lepidopterology. Cluj (Romania). 2009, P. 31-32.
150. Klyuchko O., Klyuchko Z., Lizunova A. Noctuidae fauna of Ukrainian Karpathy: results of monitoring (1956-2008). Proceed. 16th European Congress of Lepidopterology. Cluj (Romania). 2009, P. 31.
151. Klyuchko O. M., Klyuchko Z. F., Lizunova A G. Development Of Database For Noctuidae Species In Ukraine. 5-th International Conference On the Biology Of Butterflies, Roma. 2007.
152. Klyuchko Z. F., Klyuchko O. M. Diversity and biogeography Of Noctuidae Species In Ukraine. 5-th International Conference On the Biology Of Butterflies, Roma. 2007.
153. Klyuchko O. M., Beloshitsky P. V. Investigation of insect adaptation characteristics in Prielbrussie in 2004-2005. Mater. VIII World Congress of International Society for Adaptive Medicine (ISAM). Moscow (Russia). 2006, P. 165-166.
154. Beloshitsky P. V., Klyuchko O. M. Contribution of Sirotinin's school into adaptation medicine. Mater. VIII World Congress of International Society for Adaptive Medicine (ISAM). Moscow (Russia). 2006, P. 158.
155. Klyuchko O. M., Klyuchko Z. F. Ukrainian Noctuidae Database. Mater. Of XIV SEL Congress. Roma (Italy). 2005, P. 49.
156. Klyuchko Z.F., Klyuchko O.M. Noctuidae (Lepidoptera) of Donbass, Ukraine. Mater. Of XIVSEL Congress. Roma (Italy). 2005, P. 41-2.
157. Beloshitsky P., Klyuchko O., Onopchuck Yu., Onopchuck G. Mathematic model for hypoxic states development for healthy people and ones with ischemic heart disease. High altitude medicine and biology: Mater. ISMM Congress.Beijing (China). 2004, V. 5, P. 251.
158. Beloshitsky P., Klyuchko O., Kostyuk O., Beloshitsky S. Peculiarities of high mountain factors influence on organism. High altitude
medicine and biology: Mater. ISMM Congress. Beijing (China). 2004, V. 5, P. 250.
159. Gonchar O., Klyuchko O., Beloshitsky P. Ways of myocardial metabolic disorders correction at hypoxia by new pharmacological preparations. High altitude medicine and biology: Mater. ISMM Congress. Beijing (China). 2004, V. 5, P. 249.
160. Gonchar O., Klyuchko O., Seredenko M., Oliynyk B. Correction of metabolic disorders at hypoxia by new pharmacological preparations. Mater. 3 FEPS Congress. Nice (France). 2003, P. 228.
161. Troyan V., Klyuchko O., Taran N. About some ways to change gender standards. Standard: abweichung: Mater. Intl. Kongress in Natur wissenschaft und Technik. Berlin (Germany). 2003, P. 208.
162. Seredenko M., Gonchar O., Klyuchko O., Oliynyk S. Peculiarities of prooxidant — antioxidant balance of organism under hypoxia of different genesis and its corrections by new pharmacological preparations. Acta Physiologica Hungarica. Budapest (Hungary). 2002, 89 (1-3), 292.
163. Klyuchko O. M., Kiskin N. I., Krishtal O. A., Tsyndrenko A. Ya. Araneidae toxins as antagonists of excitatory amino acid responses in isolated hippocampal neurons. X School on biophysics of membrane transport. Szczyrk (Poland). 1990, V. 2, P. 271.
164. Akaike N., Kawai N., Kiskin N. I., Krishtal O. A., Tsyndrenko A. Ya., Klyuchko O. M. Spider toxin blocks excitatory amino acid responses in isolated hippocampal pyramidal neurons. Neurosci. Lett. 1987, V. 79, P. 326-330.
165. Aralova N. I., Klyuchko O. M. Mathematic modeling of functional self-organization of pilots' respiratory systems. "Integrated intellectual robototechnical complexes" — "IIRTC-2018". Mat. XI Intl. Scient. Tech. Conference. 2018, P. 268-269. (In Ukrainian).
166. Klyuchko Z. F., Klyuchko O. M. Moths (Lepidoptera: Noctuidae s. l.) of Cherkasska Region of Ukraine according to results of long-term monitoring. Eversmannia. 2014, V. 37, P. 32-49. (In Russian).
167. Klyuchko Z. F., Klyuchko O. M. Analysis of moth fauna taxonomic structure (Lepidoptera: Noctuidae s. l.) of Ukraine according to monitoring data. Eversmannia. 2014, 33 (3), 41-45. (In Russian).
168. Klyuchko Z. F. Noctuidae of Ukraine. Kyiv: Raevsky Publishing. 2006. (In Ukrainian).
169. Klyuchko Z. F., Klyuchko O. M. Monitoring of the diversity of Noctuidae (Lepidoptera) fauna in Ukrainian Polissia. "Nature of Polissia: investigation and protection": Mat. Intl. Sci. Conf. 2014, P. 498-502. (In Ukrainian).
170. Klyuchko Z. F., Klyuchko O. M., Lizunova A G. Monitoring of Noctuidae fauna of Ukraine
using electronic information systems. "Nature of Polissia: investigation and protection": Mat. Intl. Sci. Conf. 2014, P. 261-265. (In Ukrainian).
171. Klyuchko O. M., Pyatchanina T. V., Mazur M. G. Methods of mathematics and bioinformatics in contemporary oncology. Mat. World Congr. "Aviation in the XXI c.", 10-12 Oct 2018, Kyiv. P. 6.2.10-6.2.14. http:// conference.nau.edu.ua/index.php/Congress/ Congress2018/paper/viewFile/5014/4327
172. Klyuchko E. M., Tzyndrenko A. Ya. The method for dissociation of hippocampal cells. Patent 1370136 USSR, MEM C12N 5/00. Priority: 31.01.1986; Issued: 30.01.1988, Bull. N 4. — 3 p. http://www. findpatent.ru/patent/137/1370136.html http: / / www.findpatent.ru/img_ show/6580725.html
173. Klyuchko O. M., Biletsky A. Ya., Navrots-kyi D. O. Method of bio-sensor test system application. Patent UA129923 U, G01N33/50. Priority: 22. 03. 2018, u201802896, issued: 26. 11. 2018, Bull. 22. (In Ukrainian).
174. Klyuchko O. M., Biletsky A. Ya., Navrots-kyi D. O. Method of application of biotechnical monitoring system with biosensor (biosensor test system). Patent UA; G01N33/00, C12Q 1/02. Priority: 22. 03. 2018 u201802893. (In Ukrainian).
175. Klyuchko O. M., Biletsky A. Ya., Navrotskyi D. O. Method of application of biotechnical monitoring system with biosensor and subsystem for optical registration. Patent UA 129922 U, G01N33/50. Priority: 22.03.2018, u201802894, issued: 26.11.2018, Bull. 22. (In Ukrainian).
176. Klyuchko O. M. Method of application of biotechnical monitoring system for bioindicators' accounting with biosensor and sub-system for optical registration. Patent UA 129987 U, G01N33/00, C12Q 1/02, C12N 15/00. Priority: 27. 04. 2018, u201804662, issued: 26. 11. 2018, Bull. 22. (In Ukrainian).
177. Klyuchko O. M. Method for cells' dissociation. Patent UA 130672 U, G01N33/00, C12Q 1/02, C12N 15/00. Priority: 27.04.18, u201804668, issued 26.12.2018, Bull. 24. (In Ukrainian).
178. Klyuchko O. M., Biletsky A. Ya., Navrotskyi D. Method of application of biotechnical monitoring system with expert subsystem and biosensor. Patent UA 131016 U, G01N33/50, C12Q 1/02, C12N15/00. Priority: 27. 04. 18, u201804663. (In Ukrainian).
179. Klyuchko O. M. Method of qualitative analysis of chemical substances. Patent UA 131016 U, G01N33/50, G01N21/78, C12Q 1/60. Priority: 11.05.2018, u201805174, issued 10.01.2019, Bull. 1. (In Ukrainian).
180. Klyuchko O. M., Biletsky A. Ya., Navrots-kyi D. A. Method of quantitative analysis of chemical substances. Patent UA; G01N33/50, G01N21/78, C12Q1/60. Priority: May 2018, u201805175. (In Ukrainian).
181. Klyuchko O. M., Biletsky A. Ya. Method of qualitative analysis of chemical substances for the influence on electrical currents in bioobjects. Patent UA; G01N 33/50, G01N 21/78, C12Q 1/60. Priority: May 2018, u201806345. (In Ukrainian).
182. Klyuchko O. M., Biletsky A. Ya. Method of qualitative analysis of hydrocarbons with a high and toxic effect on bioobjects. Patent UA; G01N 33/50, G01N 21/78, C12Q 1/60. Priority: May 2018, u201806342. (In Ukrainian).
183. Schnase J. L., Cushing J., Frame M. Information technology challenges of biodiversity and ecosystems informatics. Inform. Syst. 2003, 28 (4), 339-345.
184. Hardy P. B., Sparks T. H., Isaak N. J. Specialism for larval and adult consumer resources among Brittish butterflies: implications for conservation. Biol. Conserv. 2007, 138 (3-4), 440-452.
185. Dennis R. L. H., Shreeve T. G., Sparks T. H. A comparison of geographical and neighbourhood models for improving atlas databases. The case of the French butterfly atlas. Biol. Conserv. 2002, 108 (2), 143-159.
186. Ravlin F. W. Development of monitoring and decision-support systems for integrated pest management of forest defoliators in North America. Forest Ecol. Manag. 1991, V. 39, P. 3-13.
187. Mahaman B. D., Harizanis P., Filis I, Antonopouloua E.,. YialourisC.. P. aSid-eridis A.V. aA diagnostic expert system for honeybee pests. Comp. Electron. Agricult. 2002, 36 (1), 17-31.
188. Murali N. S., Percy-Smith A. Databasemanagement system for monitoring and warning of codling moth (Cydia pomonella) and carrot fly (Psila rosae). Comp. Electron. Agricult. 1991, 6 (3), 267-272.
189. Drake V. A., Wang H. K., Harman I. T. Insect - monitoring radar: remote and network operation. Comp. Electron. Agricult. 2002, 35 (2-3), 77-94.
190. Nikolov N., Visone R., Nesteruk I., Rasponi M., Redaelly A. A new algorithm to analyze the video data of cell contractions in microfluidic platforms. Innov Biosyst Bioeng. 2018, 2(2), 74-83. https://doi. org/10.20535/ibb.2018.2.2.128477
191. Umanets V. S., Voinyk B. A., Pavlov V. A., Nas tenko I. A. Estimation of algorithms efficiency in the task of biological objects clustering. Innov Biosyst Bioeng. 2018, 2(2), 84-9. https://doi.org/10.20535/ ibb.2018.2.2.133466
ЕЛЕКТРОНН1 ЕКСПЕРТН1 СИСТЕМИ ДЛЯ Б1ОЛОГП ТА МЕДИЦИНИ
О. М. Ключко
1нститут експериментально! патологи, онкологи та радмб^логп iM. Р. С. Кавецького НАН Укра!ни, Ки!в
E-mail: kelenaXX@ukr.net
Метою роботи було дослщження прототи-niB iнформацiйних експертних систем, 1хньо! структури, функцiй, практичного використан-ня та розроблення ново! системи для виршен-ня завдань у галузi бмтехнологи, в лаборатор-нш практицi й захистi довкiлля. Розглянут прототипи розроблено для застосування в гене-тичних дослiдженнях, у сiльському господар-ствi, охоронi природи вiд шкщнишв та еколо-гiчних забруднювачiв, у медицин тощо. Пiд час виконання роботи використовували методи компаративних дослщжень зразкiв технiчних пристро!в, iмiтацiйного та програмного моде-лювання, якi базувалися на числових результатах, отриманих у експериментах з реестращею хемочутливих трансмембранних електричних струмiв у нейронах у режимi фшсацй потен-цiалу. У результатi було розроблено оригшаль-ну експертну систему, поеднану з детекторною групою, базами даних та штерфейсом. Розро-блена експертна система здатна автоматично розрiзняти деяш типи хiмiчних речовин на входi й виводити данi !х щентифшаци та за потребою — повщомлення щодо 1хьно! шкщливо-сть Зроблено висновки про практичну щншсть наведених даних для створення нових електро-нних експертних систем для мониторингу наяв-ностi шкiдливих речовин у довшлль У заключ-нш частинi також обговорюеться можливiсть застосування розроблено1 експертно1 системи для нових методiв якiсного та шльшсного ана-лiзу деяких органiчних сполук.
Ключовi слова: б^лопчш та медичш експертш системи, електроннi iнформацiйнi системи, бмшформатика, бази даних.
ЭЛЕКТРОННЫЕ ЭКСПЕРТНЫЕ СИСТЕМЫ ДЛЯ БИОЛОГИИ И МЕДИЦИНЫ
Е. М. Ключко
Институт экспериментальной патологии, онкологии и радиобиологии им. Р. Е. Кавецкого НАН Украины, Киев
E-mail: kelenaXX@ukr.net
Целью работы было исследование прототипов информационных экспертных систем, их структуры, функций и практического применения, а также разработка новой системы для решения задач в области биотехнологии, в лабораторной практике и защите окружающей среды. Рассмотренные прототипы разработаны для применения в генетических исследованиях, в сельском хозяйстве, охране природы от вредителей и экологических загрязнителей, в медицине и т. д. При выполнении работы использовали методы компаративных исследований образцов технических устройств, имитационного и программного моделирования, базирующиеся на численных результатах, полученных в экспериментах с регистрацией хе-мочувствительных трансмембранных электрических токов в нейронах в режиме фиксации потенциала. В результате была разработана оригинальная экспертная система, соединенная с детекторной группой, базами данных и интерфейсом. Разработанная экспертная система способна автоматически различать некоторые типы химических веществ на входе, выводить данные их идентификации и при необходимости — сообщения об их вредности. Сделаны выводы о практической ценности приведенных данных для создания новых электронных экспертных систем для мониторинга наличия вредных веществ в окружающей среде. В заключении также обсуждается и возможность применения разработанной экспертной системы для новых методов качественного и количественного анализа некоторых органических соединений.
Ключевые слова: биологические и медицинские экспертные системы, электронные информационные системы, биоинформатика, базы данных.
