(English follows Japanese)
Japanese Title: Development of high precision toxicity prediction method using machine learning function of JMP
Meiji Pharmaceutical University Associate Professor Yoshihiro Uzawa
Along with the recent awareness of environmental awareness, the momentum to comprehensively investigate the harmfulness to all the chemical substances around us is increasing worldwide.However, since the types of chemical substances are enormous, experimental investigations are unrealistic from the viewpoints of time, budget, and animal experimental ethics.In view of this background, "computational toxicology", which is an academic field aimed at predicting the toxicity of chemical substances statistically and computer scientifically based on known information accumulated up to now, attracts attention.In 2014, the US NIH held a large-scale computational toxicology competition "Tox 21 Data Challenge 2014" using toxicity related data of 10,000 compounds.In this competition where more than 100 teams from 18 countries participated and registered, the performer analyzed the pattern of various information obtained from the chemical structure using bootstrap forest which is one of the machine learning functions installed in JMP Pro , We were able to win the division in terms of predicting female hormone like substances.In this presentation, I would like to introduce about the optimum bootstrap forest model selection based on JMP's flexible function which the performer used for the competition.
Related Sites: http://www.my-pharm.ac.jp/news/info_detail.html?id=599
The Development of Highly Accurate Toxicity Prediction Methods Using the JMP ® Machine Learning Function
The Development of Highly Accurate Toxicity Prediction Methods Using the JMP ® Machine Learning Function
Along with the increase in environmental consciousness in recent years, the exhaustive investigation of all of the hazardous chemical substances around us is gaining momentum around the globe. However, there is a vast number of different types of chemical substances, meaning that experimental investigations are not practical from a perspective, budget perspective, or ethical perspective (animal testing). The academic field of computational toxicology is garnering attention for its ability to predict, statistically and with computer science, the toxicity of chemical substances based on existing information that has been accumulated. In 2014, National Institutes of Health in the United States held the Tox 21 Data Challenge 2014, an ambitious computational toxicology competition using toxicity-related data regarding 10,000 compounds. At this competition, which featured over 100 participating teams from 18 countries, competitors used bootstrap forest, one of the machine learning functions in JMP Pro, to analyze a variety of information patterns acquired from chemical structures. This resulted in a departmental victory related to the prediction of female hormone-like substances. In this presentation, I will discuss the selection of the optimal bootstrap forest model based on the flexible functions in JMP that were used during the competition.
Related site: http: // http://www.my-pharm.ac.jp/news/info_detail.html?id=599
