Applying Machine Learning to Ultrafast Shape Recognition in Ligand-Based Virtual Screening

In this study we explore the use of suitable Machine Learning techniques that can be trained using USR descriptors, so as to improve the similarity detection of potential new leads. We use molecules from the Directory for Useful Decoys-Enhanced to construct machine learning models based on three different algorithms: Gaussian Mixture Models (GMMs), Isolation Forests and Artificial Neural Networks (ANNs). We train models based on full molecule conformer models, as well as the Lowest Energy Conformations (LECs) only. We also investigate the performance of our models when trained on smaller datasets so as to model virtual screening scenarios when only a small number of actives are known a priori. Our results indicate significant performance gains over a state of the art USR-derived method, ElectroShape 5D, with GMMs obtaining a mean performance up to 430% better than that of ElectroShape 5D in terms of Enrichment Factor with a maximum improvement of up to 940%. Additionally, we demonstrate that our models are capable of maintaining their performance, in terms of enrichment factor, within 10% of the mean as the size of the training dataset is successively reduced. Furthermore, we also demonstrate that running times for retrospective screening using the machine learning models we selected are faster than standard USR, on average by a factor of 10, including the time required for training. Our results show that machine learning techniques can significantly improve the virtual scree...
Source: Frontiers in Pharmacology - Category: Drugs & Pharmacology Source Type: research

Related Links:

This study was conducted over a period of one year where all smokers presenting to a chest clinic in a tertiary centre were enrolled, each was classified on the basis of stage of readiness to change and underwent repeated counselling for a period of six months and each session was preceded and succeeded with filling of Fagerstorm test for nicotine dependence. Over the period of a year, 207 patients participated in this study, the mean age was 50.74±14.74 years; mean duration of tobacco use was 29.43±14.72 years; 64.3% were illiterate, 11.6% primary education, 14.1% were matric and while 10.1% were graduate. A...
Source: Monaldi Archives for Chest Disease - Category: Respiratory Medicine Tags: Monaldi Arch Chest Dis Source Type: research
Publication date: Available online 8 April 2020Source: Zoologischer AnzeigerAuthor(s): Martín I. Lorusso, María P. Sal Moyano, María A. Gavio, Colin L. McLay
Source: A Journal of Comparative Zoology - Category: Zoology Source Type: research
Publication date: Available online 7 April 2020Source: Small Ruminant ResearchAuthor(s): Wilson Kaumbata, Liveness Banda, Gábor Mészáros, Timothy Gondwe, M.J. Woodward-Greene, Benjamin D. Rosen, Curtis P. Van Tassell, Johann Sölkner, Maria Wurzinger
Source: Small Ruminant Research - Category: Zoology Source Type: research
DISCUSSION:  The study showed a higher LTBI prevalence among returnees after assignments abroad than among medical personnel in Germany after TB contact who had been investigated in previous studies. In order to be able to detect LTBI infections acquired abroad, routine testing before and after an assignment abroad seems to be necessary. PMID: 32259872 [PubMed - as supplied by publisher]
Source: Pneumologie - Category: Respiratory Medicine Tags: Pneumologie Source Type: research
Authors: Herth F, Weidmann B PMID: 32259871 [PubMed - as supplied by publisher]
Source: Pneumologie - Category: Respiratory Medicine Tags: Pneumologie Source Type: research
Publication date: Available online 8 April 2020Source: Research in Veterinary ScienceAuthor(s): Nanhua Chen, Yanzhao Xiao, Mengxue Ye, Xinshuai Li, Shubin Li, Ningjun Xie, Yue Wei, Jialin Wang, Jianzhong Zhu
Source: Research in Veterinary Science - Category: Veterinary Research Source Type: research
Publication date: Available online 7 April 2020Source: Preventive Veterinary MedicineAuthor(s): Christien Masmeijer, Katharina van Leenen, Lieze De Cremer, Piet Deprez, Eric Cox, Bert Devriendt, Bart Pardon
Source: Preventive Veterinary Medicine - Category: Veterinary Research Source Type: research
Publication date: Available online 7 April 2020Source: Artificial Intelligence in MedicineAuthor(s): Siva Teja Kakileti, Himanshu J. Madhu, Geetha Manjunath, Leonard Wee, Andre Dekker, Sudhakar Sampangi
Source: Artificial Intelligence in Medicine - Category: Bioinformatics Source Type: research
Conclusion: Our findings suggest that level of LDH, CRP, ALT and NEU can be used to predict the result of COVID-19 test. They can help in detection of COVID-19 patients. PMID: 32259132 [PubMed - as supplied by publisher]
Source: Accident and Emergency Nursing - Category: Emergency Medicine Authors: Tags: Arch Acad Emerg Med Source Type: research
Conclusion: The most important finding of one-month ticagrelor consumption were dyspnea, bleeding, and hypersensitivity reaction. No case of bradycardia and stent thrombosis was detected. In our study , iranian population has more susceptibility to dyspnea than PLATO result. The rate of drug discontinuation in this series of cases was 6.4 %. PMID: 32259131 [PubMed - as supplied by publisher]
Source: Accident and Emergency Nursing - Category: Emergency Medicine Authors: Tags: Arch Acad Emerg Med Source Type: research
More News: Drugs & Pharmacology | Learning | Study | Training | Universities & Medical Training