AI @ MIPT: Big data for mathematical models of the human genome
Hi, Habr! Fiztech resumes the cycle of seminars on artificial intelligence AI @ MIPT. Today, Alexander Frey and Kevin O'Connell from the Norwegian Center for the Study of Psychological Disorders (NORMENT) in the city of Oslo will talk about using big data for mathematical models of the human genome. The speech will be available in the Physics and Teaching Group ; it will be held in English.
Genetics is an area of great machine learning opportunities. The most representative full genomic studies (GWAS) are already being conducted on samples exceeding 1 million people and contain information on tens of millions of associations between genomic variants and phenotypic traits. By some estimates, in aggregate, these studies cover 80% of the variability of complex human traits, including mental disorders. Despite this, the difficulty of moving from acquired scientific knowledge to clinical applications remains. In practice, personal genetic information is extremely rarely used to predict diseases. During the lecture, the most successful full-genome studies and limitations that hinder the effective application of machine learning methods in human genetics will be considered. Part of the lesson will be devoted to the statistical methodology underlying such studies, including the analysis of Bayesian mixed models and the method of limited maximum likelihood. The topics of polygenetic risk assessment and precision medicine, which is already being effectively implemented in the assessment of personal cancer risk and stratification of Alzheimer's disease, will be touched upon.
Previous course lectures can be found here .
Genetics is an area of great machine learning opportunities. The most representative full genomic studies (GWAS) are already being conducted on samples exceeding 1 million people and contain information on tens of millions of associations between genomic variants and phenotypic traits. By some estimates, in aggregate, these studies cover 80% of the variability of complex human traits, including mental disorders. Despite this, the difficulty of moving from acquired scientific knowledge to clinical applications remains. In practice, personal genetic information is extremely rarely used to predict diseases. During the lecture, the most successful full-genome studies and limitations that hinder the effective application of machine learning methods in human genetics will be considered. Part of the lesson will be devoted to the statistical methodology underlying such studies, including the analysis of Bayesian mixed models and the method of limited maximum likelihood. The topics of polygenetic risk assessment and precision medicine, which is already being effectively implemented in the assessment of personal cancer risk and stratification of Alzheimer's disease, will be touched upon.
Previous course lectures can be found here .
')
Source: https://habr.com/ru/post/449956/
All Articles