scholarly journals QSAR-АНАЛІЗ БІБЛІОТЕК 4-ТІАЗОЛІДИНОН-СПОРІДНЕНИХ ГЕТЕРОЦИКЛІВ ДЛЯ ПРОГНОЗУВАННЯ ПРОТИТРИПАНОСОМНИХ ВЛАСТИВОСТЕЙ НОВИХ ПОХІДНИХ

2021 ◽  
pp. 39-46
Author(s):  
A. P. Kryshchyshyn-Dylevych
Keyword(s):  
Neural Networks ◽  
Random Forest ◽  
Trypanosoma Brucei ◽  
Trypanosoma Brucei Brucei ◽  
Random Forest Regression ◽  
Trypanosoma Brucei Gambiense ◽  
Chemical Database

Вступ. Похідні тіазолідинону та споріднених гетероциклів є джерелом нових протипаразитарних агентів, у тому числі молекул із протитрипаносомними властивостями. В актуальних наукових джерелах знайдено ряд досліджень про кількісний взаємозв’язок структура – протитрипаносомна активність, що включає різні підходи комп’ютерної хімії. Більшість досліджень належить до так званих мультитаргетних, коли до вибірки включають результати інших видів протипаразитарних активностей. Розробка нових QSAR-моделей похідних тіазолідинону з протитрипаносомними властивостями дозволить окреслити напрямки спрямованого дизайну нових протипаразитарних агентів на основі циклів тіазолу та тіазолідинону. Мета дослідження – встановити кількісний взаємозв’язок структура – протитрипаносомна активність у межах бібліотек тіазолідинонів та споріднених гетероциклів. Методи дослідження. Побудову математичних моделей на основі QSAR-аналізу здійснювали за допомогою онлайн-платформи Online Chemical Database. Результати й обговорення. Аналіз кількісного взаємозв’язку структура – протитрипаносомна активність проводили із застосуванням математичної моделі асоціативних нейронних мереж (ASNN: Associative Neural Networks) та методу регресії Random Forest (RFR: Random Forest regression) на основі вибірок, що включали похідні ізотіокумарин-3-карбонових кислот, тіопіранотіазолів і 4-тіазолідинон-імідазотіадіазолів із встановленою трипаноцидною активністю щодо Trypanosoma brucei brucei та Trypanosoma brucei gambiense. Кращу прогнозувальну здатність для групи ізотіокумарин-3-карбонових кислот і тіопірано[2,3-d][1,3]тіазол-2-онів обчислено за допомогою алгоритму Random Forest. Модель, обчислена на основі алгоритму Random Forest для групи імідазотіадіазолів, володіє найвищою прогнозувальною здатністю зі значенням R2=0,96. Висновок. На основі методів асоціативних нейронних мереж та регресії Random Forest розроблено прогностичні моделі для прогнозування протипаразитарної активності диверсифікованих похідних ­4-тіазолідинонів і подальшого фокусування напрямків оптимізації нових біологічно активних молекул із трипаноцидними властивостями.

Differential Effects of Trypanosoma brucei gambiense and Trypanosoma brucei brucei on Rat Macrophages

2011 ◽  
Vol 97 (1) ◽  
pp. 48-54 ◽  
Author(s):  
Kazuhiko Nishimura ◽  
Haruna Nakaya ◽  
Hiroshi Nakagawa ◽  
Saburo Matsuo ◽  
Yoshihiro Ohnishi ◽  
...  
Keyword(s):  
Trypanosoma Brucei ◽  
Trypanosoma Brucei Brucei ◽  
Differential Effects ◽  
Trypanosoma Brucei Gambiense

scholarly journals Seasonal forecasting of hydrological drought in the Limpopo basin: A comparison of statistical methods.

2016 ◽  
Author(s):  
Mathias Seibert ◽  
Bruno Merz ◽  
Heiko Apel
Keyword(s):  
Neural Networks ◽  
Random Forest ◽  
Early Warning ◽  
Linear Models ◽  
Regression Trees ◽  
Forecast Skill ◽  
Sea Surface ◽  
Coefficient Of Determination ◽  
Operating Characteristics ◽  
Random Forest Regression

Abstract. The Limpopo basin in southern Africa is prone to droughts, which affect the livelihoods of millions of people in South Africa, Botswana, Zimbabwe, and Mozambique. Seasonal drought early warning is thus vital for the whole region. In this study, the predictability of hydrological droughts during the main runoff period from December to May is assessed with statistical approaches. Three methods (Multiple Linear Models, Artifical Neural Networks, Random Forest Regression Trees) are compared in terms of their ability to forecast streamflow with up to 12 months lead time. The following four main findings result from the study. 1) There are stations in the basin at which standardised streamflow is predictable with lead times up to 12 months. The results show high interstation differences of forecast skill but reach a coefficient of determination as high as 0.73 (cross validated). 2) A large range of potential predictors is considered in this study, comprising well established climate indices, customised teleconnection indices derived from sea surface temperatures, and antecedent streamflow as proxy of catchment conditions. El-Niño and customised indices, representing sea surface temperature in the Atlantic and Indian Ocean, prove to be important teleconnection predictors for the region. Antecedent streamflow is a strong predictor in small catchments (with median 42 % explained variance), whereas teleconnections exert a stronger influence in large catchments. 3) Multiple linear models show the best forecast skill in this study and the greatest robustness compared to artificial neural networks and Random Forest regression trees, despite their capabilities to represent non-linear relationships. 4) Employed in early warning the models can be used to forecast a specific drought level. Even if the coefficient of determination is low, the forecast models have a skill better than a climatological forecast, which is shown by analysis of receiver operating characteristics (ROC). Seasonal statistical forecasts in the Limpopo show promising results, and thus it is recommended to employ them complementary to existing forecasts in order to strengthen preparedness for droughts.

scholarly journals Seasonal forecasting of hydrological drought in the Limpopo Basin: a comparison of statistical methods

2017 ◽  
Vol 21 (3) ◽  
pp. 1611-1629 ◽  
Author(s):  
Mathias Seibert ◽  
Bruno Merz ◽  
Heiko Apel
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Random Forest ◽  
Early Warning ◽  
Linear Models ◽  
Regression Trees ◽  
Forecast Skill ◽  
Sea Surface ◽  
Coefficient Of Determination ◽  
Random Forest Regression

Abstract. The Limpopo Basin in southern Africa is prone to droughts which affect the livelihood of millions of people in South Africa, Botswana, Zimbabwe and Mozambique. Seasonal drought early warning is thus vital for the whole region. In this study, the predictability of hydrological droughts during the main runoff period from December to May is assessed using statistical approaches. Three methods (multiple linear models, artificial neural networks, random forest regression trees) are compared in terms of their ability to forecast streamflow with up to 12 months of lead time. The following four main findings result from the study. 1. There are stations in the basin at which standardised streamflow is predictable with lead times up to 12 months. The results show high inter-station differences of forecast skill but reach a coefficient of determination as high as 0.73 (cross validated). 2. A large range of potential predictors is considered in this study, comprising well-established climate indices, customised teleconnection indices derived from sea surface temperatures and antecedent streamflow as a proxy of catchment conditions. El Niño and customised indices, representing sea surface temperature in the Atlantic and Indian oceans, prove to be important teleconnection predictors for the region. Antecedent streamflow is a strong predictor in small catchments (with median 42 % explained variance), whereas teleconnections exert a stronger influence in large catchments. 3. Multiple linear models show the best forecast skill in this study and the greatest robustness compared to artificial neural networks and random forest regression trees, despite their capabilities to represent nonlinear relationships. 4. Employed in early warning, the models can be used to forecast a specific drought level. Even if the coefficient of determination is low, the forecast models have a skill better than a climatological forecast, which is shown by analysis of receiver operating characteristics (ROCs). Seasonal statistical forecasts in the Limpopo show promising results, and thus it is recommended to employ them as complementary to existing forecasts in order to strengthen preparedness for droughts.

Nitric oxide-mediated cytostatic activity on Trypanosoma brucei gambiense and Trypanosoma brucei brucei

1992 ◽  
Vol 75 (3) ◽  
pp. 353-360 ◽  
Author(s):  
Phillippe Vincendeau ◽  
Sylvie Daulouède ◽  
Bernard Veyret ◽  
Marie Laure Darde ◽  
Bernard Bouteille ◽  
...  
Keyword(s):  
Nitric Oxide ◽  
Trypanosoma Brucei ◽  
Cytostatic Activity ◽  
Trypanosoma Brucei Brucei ◽  
Trypanosoma Brucei Gambiense

Different allele frequencies in Trypanosoma brucei brucei and Trypanosoma brucei gambiense populations

1989 ◽  
Vol 32 (1) ◽  
pp. 61-71 ◽  
Author(s):  
Pascale Paindavoine ◽  
Françoise Zampetti-Bosseler ◽  
Hélène Coquelet ◽  
Etienne Pays ◽  
Maurice Steinert
Keyword(s):  
Trypanosoma Brucei ◽  
Allele Frequencies ◽  
Trypanosoma Brucei Brucei ◽  
Trypanosoma Brucei Gambiense

Crop Quality Prediction Using Ml And Neural Networks

2021 ◽  
Vol 10 (02) ◽  
pp. 07-11
Author(s):  
Kanakaveti Narasimha Dheeraj ◽  
Goutham. R. J ◽  
Arthi. L
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Random Forest ◽  
Machine Learning Techniques ◽  
Quality Prediction ◽  
Random Forest Regression ◽  
Power Efficient ◽  
Learning Techniques ◽  
Better Than

Agriculture is said to be the backbone of the economy. Farmers toil hard with different kinds of crops to make good and healthy food for the country. There are more existing systems but uses outdated machine-learning techniques based on RNN( Recurrent neural network) which makes the process slower and more time-consuming. Here We are proposing a new CNN(Convolutional neural network ) based system which is fast and gives accurate results within seconds. CNN is power-efficient and is more suitable for real-time implementation. In this project, we use CNN algorithms which is very much better than the RNN algorithms used in the existing system.More parameters will be taken for the consideration of prediction in the proposed system. And we use Random Forest Regression, Multiple Linear Regression

Sign in / Sign up

Export Citation Format

Share Document