Predicting the secondary, i.e. base-pairing structure of a folded RNA strand is an important problem in synthetic and computational biology. First-principle algorithmic approaches to this task are challenging because existing models of the folding process are inaccurate, and even if a perfect model existed, finding an optimal solution would be in general NP-complete. In this paper, we propose a simple, yet extremely effective data-driven approach. We represent RNA sequences in the form of three-dimensional tensors in which we encode possible relations between all pairs of bases in a given sequence. We then use a convolutional neural network to predict a two-dimensional map which represents the correct pairings between the bases. Our model achieves significant accuracy improvements over existing methods on two standard datasets. Our experiments show excellent performance of the model across a wide range of sequence lengths and RNA families. We also observe considerable improvements in predicting complex pseudoknotted RNA structures, as compared to previous approaches.
The impaired adaptation is a dynamic condition, structurally comprising the combination of independent components: the syndrome of professional-psychological disadaptation (SPPD) (psychological component), morbidity (somatic component), and psychosomatics, including the interaction of the above components. Thus, a psychological compo-nent is the initial phase, and a somatic one, to a more marked degree, leading to further disruptions in the increase of psychological disorders and morbidity, i.e. disadaptation. The study found that the highest rates of the syndrome of professional psychological disadaptatiion are noted in the group with work experience of 0–5 years. The cause is a long period of not working in their specialty, which leads to a decrease in self-regulation, psychological defenses, general theoretical and practical professional level.Preventive work in the organization should focus on psychological trainings, refresher courses or the introduction of mentoring.
Федеральное государственное бюджетное научное учреждение «Дальневосточный научный центр физиологии и патологии дыхания», 675000, г. Благовещенск, ул. Калинина, 22РЕЗЮМЕ В данной работе использовались результаты наших собственных исследований, в подавляющем большинстве выполненных в амбулаторных усло-виях -в консультативной поликлинике ДНЦ ФПД. Стандартное МСКТ (мультиспиральная компью-терная томография) исследование включало в себя проведение топографической разметки во фрон-тальной и сагиттальной проекциях, нативное (без внутривенного контрастирования) исследование органов грудной клетки в мягкотканном и легоч-ном режимах. Полученные данные сопоставлялись с результатами традиционной рентгенографии, ли-нейной томографии и патоморфологическими на-ходками. Максимальное и адекватное использование постпроцессинговой обработки изоб-ражений позволило впервые, без внутривенного контрастного усиления, получить четкие, удобные для практической работы рентгеноморфологиче-ские структурные изображения (артерии, вены и бронхиальное дерево) корней легких. Трехмерная реконструкция позволяет так же вращать объемное изображение за экраном монитора во всех плоско-стях, более детально изучать строение и топогра-фию структурных элементов корня легкого. Разработанные технологии лучевой диагностики, успешное применение их на протяжении многих лет собственной практики, позволяют рекомендовать данные разработки практическому здравоохране-нию и, особенно, что очень важно -амбулаторно-по-ликлиническому звену. Данный краткий атлас может быть полезен не только лучевому диагносту, но и многим специалистам: пульмонологам, врачам общего профиля, торакальным хирургам, и даже анатомам и патологоанатомам. Ведь недаром суще-ствует такое определение, как: «рентгенолог -это патологоанатом на живом».Ключевые слова: патология корней легких, техно-логии лучевой диагностики, мультиспиральная ком-пьютерная томография, постпроцессинговая обработка изображений, трехмерная реконструкция изображений. SUMMARY NORM AND PATHOLOGY OF LUNGS ROOTS. SHORT ATLAS OF ROENTGENOLOGIC IMAGES A.V.Lenshin, A.V.Il'in Far Eastern Scientific Center of Physiology andPathology of Respiration, 22 Kalinina Str., Blagoveshchensk, 675000, Russian Federation The results of our own researches conducted in the out-patient advisory clinic of FEC PPR are presented in this work. Standard multispiral computed tomography (MSCT) research included topographic marking in frontal and sagittal projections, native (without intravenous contrast) study of the chest in soft-tissue and pulmonary regimes. The obtained data was compared with the results of traditional roentgenography, linear tomography and pathomorphological findings. Maximal and adequate use of image postprocessing allowed for the first time without intravenous contrast strength-
Restriction of access to data of forest inventory leads to difficulties in the implementation of scientific developments in the field of forestry, as a significant part of them until the business implementation passes a way of testing and improvements carried out actually on the enthusiasm of developers. Taking into account difficulty in obtaining forest inventory data for research in the article there is an example of the definition of information on forest plantations on the basis of the decryption freeware remote sensing data from Landsat 8 (OLI). One advantage of the processing of these data is their accessibility to any territory of Russia, as well as the presence of a significant number of spectral channels, which allows using different methods of analysis of satellite imagery to determine the characteristics of forest stands. Based on the information assignment of forestry activities for the care of forests is made and the proportion of various activities in the overall system of care for forests is assessed. The results show the possibility of using modern methods of processing of satellite data for a preliminary analysis of forest resources in a certain area in order to obtain information on forest plantations. When working to verify the results reference areas were used laid down in the stands of different composition. When conducting field experiments we focused on the naturally-formed plantings in place of clearcuts. Data of test plots were associated with automatic classification standards that are being implemented in the program Envi. In areas with a lack of data on test plots verification was carried out using partially materials of forest inventory, as well as of remote shooting of high-resolution 1.2 m placed in the public domain on Google and Yandex services. The results show the possibility of a preliminary analysis of the potential destination of different activities of forest care based on freely available data of Earth remote sensing (ERS).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.