A Prediction Model for the Intraocular Pharmacokinetics of Intravitreally Injected Drugs Based on Molecular Physicochemical Properties

Hyeong Min Kim; Kyu Hyung Park; Jae Yong Chung; Se Joon Woo

doi:10.1159/000499529

Prediction model of rice eating quality using physicochemical properties and sensory quality evaluation

Journal of Sensory Studies ◽

10.1111/joss.12273 ◽

2017 ◽

Vol 32 (4) ◽

pp. e12273 ◽

Cited By ~ 5

Author(s):

Hoon Kim ◽

Oui-Woung Kim ◽

Han Sub Kwak ◽

Sang Sook Kim ◽

Hyo-Jai Lee

Keyword(s):

Prediction Model ◽

Physicochemical Properties ◽

Sensory Quality ◽

Quality Evaluation ◽

Eating Quality

Download Full-text

A prediction model for oral bioavailability of drugs using physicochemical properties by support vector machine

Journal of Natural Science Biology and Medicine ◽

10.4103/0976-9668.92325 ◽

2011 ◽

Vol 2 (2) ◽

pp. 168 ◽

Cited By ~ 11

Author(s):

Anju Sharma ◽

PritishKumar Varadwaj ◽

Rajnish Kumar

Keyword(s):

Support Vector Machine ◽

Prediction Model ◽

Physicochemical Properties ◽

Oral Bioavailability ◽

Support Vector

Download Full-text

Prediction Model between Emulsified Water Fractions and Physicochemical Properties of Crude Oil Based on the Exergy Loss Rate

ACS Omega ◽

10.1021/acsomega.1c02819 ◽

2021 ◽

Author(s):

Jiangbo Wen ◽

Haijun Luo ◽

Gang Ai

Keyword(s):

Prediction Model ◽

Physicochemical Properties ◽

Crude Oil ◽

Loss Rate ◽

Exergy Loss ◽

Water Fractions ◽

Emulsified Water

Download Full-text

Development of Machine Learning based blood-brain barrier permeability prediction models using physicochemical properties, MACCS and substructure fingerprints

Current Bioinformatics ◽

10.2174/1574893616666210203104013 ◽

2021 ◽

Vol 16 ◽

Author(s):

Deeksha Saxena ◽

Anju Sharma ◽

Mohammed Haris Siddiqui ◽

Rajnish Kumar

Keyword(s):

Machine Learning ◽

Central Nervous System ◽

Nervous System ◽

Prediction Model ◽

Physicochemical Properties ◽

Prediction Models ◽

Permeability Prediction ◽

The Central Nervous System ◽

Bbb Permeability ◽

The Brain

Background: Blood-Brain Barrier (BBB) protects the central nervous system from the systemic circulation and maintains the homeostasis of the brain. BBB permeability is one of the essential characteristics of drugs acting on the central nervous system to indicate if the drug could reach the brain or not. The available laboratory methods for the prediction of BBB permeability are accurate but expensive and time-consuming. Therefore, many attempts have been made over the years to predict the BBB permeability of compounds using computational approaches. The accuracy of the prediction models with external dataset has always been an issue with the prediction models. Objective: To develop Machine learning-based BBB permeability prediction model using physicochemical properties and molecular fingerprints Method: Support vector machine (SVM), k-nearest neighbor (kNN), Random forest (RF), and Naïve Bayes (NB) algorithms were applied on a large dataset of 1978 compounds using 1917 feature vectors containing physicochemical properties, MACCS fingerprints, and substructure fingerprints to predict the BBB permeability. Results and Discussion: The comparative analysis of performance metrics of developed models suggested that SVM with the radial basis function kernel performed better as compared to the kNN, RF, and NB algorithms. The BBB permeability prediction model's accuracy with the SVM was 96.77%. The prediction performance of the model developed in this study found better than the existing machine learning-based BBB permeability prediction models. Conclusion: The prediction model developed in this study could be useful for screening compounds based on their BBB permeability at the preliminary stages of drug design and development.

Download Full-text

AI4AMP: Sequence-based antimicrobial peptides predictor using physicochemical properties-based encoding method and deep learning

10.1101/2020.12.17.423359 ◽

2020 ◽

Author(s):

Tzu-Tang Lin ◽

Li-Yen Yang ◽

I-Hsuan Lu ◽

Wen-Chih Cheng ◽

Zhe-Ren Hsu ◽

...

Keyword(s):

Antimicrobial Activity ◽

Deep Learning ◽

Antimicrobial Peptides ◽

Prediction Model ◽

Physicochemical Properties ◽

Protein Sequence ◽

Innate Immune ◽

Wet Lab ◽

Encoding Method ◽

User Friendly

AbstractMotivationAntimicrobial peptides (AMPs) are innate immune components that have aroused a great deal of interest among drug developers recently, as they may become a substitution for antibiotics. However, AMPs discovery through traditional wet-lab research is expensive and inefficient. Thus, we developed AI4AMP, a user-friendly web-server that provides an accurate prediction of the antimicrobial activity of a given protein sequence, to accelerate the process of AMP discovery.ResultsOur results show that our prediction model is superior to the existing AMP predictors.AvailabilityAI4AMP is freely accessible at http://symbiosis.iis.sinica.edu.tw/PC_6/[email protected]

Download Full-text

Preparation and characterisation of vanadium pentoxide supported rhodium catalyst

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s042482010010679x ◽

1988 ◽

Vol 46 ◽

pp. 946-947

Author(s):

A. Legrouri

Keyword(s):

Aqueous Solution ◽

Thermal Decomposition ◽

Physicochemical Properties ◽

Surface Area ◽

Vanadium Pentoxide ◽

High Purity ◽

Gas Adsorption ◽

Rhodium Catalyst ◽

Optical Methods ◽

Reducible Oxides

The industrial importance of metal catalysts supported on reducible oxides has stimulated considerable interest during the last few years. This presentation reports on the study of the physicochemical properties of metallic rhodium supported on vanadium pentoxide (Rh/V2O5). Electron optical methods, in conjunction with other techniques, were used to characterise the catalyst before its use in the hydrogenolysis of butane; a reaction for which Rh metal is known to be among the most active catalysts.V2O5 powder was prepared by thermal decomposition of high purity ammonium metavanadate in air at 400 °C for 2 hours. Previous studies of the microstructure of this compound, by HREM, SEM and gas adsorption, showed it to be non— porous with a very low surface area of 6m2/g3. The metal loading of the catalyst used was lwt%Rh on V2Q5. It was prepared by wet impregnating the support with an aqueous solution of RhCI3.3H2O.

Download Full-text