ABSTRACT
Here we report the development of MolPredictX, an innovate and freely accessible web interface for biological activity predictions of query molecules. MolPredictX utilizes in-house QSAR models to provide 27 qualitative predictions (active or inactive), and quantitative probabilities for bioactivity against parasitic (Trypanosoma and Leishmania), viral (Dengue, Sars-CoV and Hepatitis C), pathogenic yeast (Candida albicans), bacterial (Salmonella enterica and Escherichia coli), and Alzheimer disease enzymes. In this article, we introduce the methodology and usability of this webtool, highlighting its potential role in the development of new drugs against a variety of diseases. MolPredictX is undergoing continuous development and is freely available at https://www.molpredictx.ufpb.br/.
Subject(s)
Machine LearningABSTRACT
@#AIM: To evaluate the accuracy of qualitative prediction of cataract surgery by double-pass optical quality analysis system(OQASTMⅡ).<p>METHODS: A retrospective study was conducted. Totally 57 cataract patients(67 eyes)were randomly selected from October 2018 to December 2018 in Renmin Hospital of Wuhan University. According to the objective scattering index(OSI), they were divided into group A(28 eyes, OSI>8.0), group B(28 eyes, OSI≤8.0), and group C(11 eyes, OSI could not be detected due to severe lens opacity). The effect of surgery was predicted by Predicted VA100% and preoperative BCVA.<p>RESULTS: In group A, 26 eyes(93%)comply with the standard, and in group B, 24 eyes(86%)comply with the standard. There was no significant difference between the two groups(<i>P</i>=0.669). Besides, no correlation was found between Predicted VA100% and postoperative 2wk BCVA(<i>r</i><sub>s</sub>=0.103, <i>P</i>>0.5).<p>CONCLUSION: The OQASTMⅡ system can objectively, accurately and intuitively predict the effect of cataract surgery.
