Gene Prioritization Through Geometric-Inspired Kernel Data Fusion

شروع رویداد
دوشنبه ۲۹ آبان ۹۶ ۱۰:۳۰
پایان رویداد
دوشنبه ۲۹ آبان ۹۶ ۱۲:۰۰
مکان رویدادتهران
اضافه به تقویم
Gene Prioritization Through Geometric-Inspired Kernel Data Fusion
برگزارکننده‌ی رویداد
تماس با برگزارکننده
۰۲۱-۸۸۶۲۸۹۴۰، ۰۲-۸۸۶۲۸۹۴۵، ۰۲۱-۸۸۶۲۸۹۳۶
گزارش
مهلت ثبت‌نام برای این رویداد به پایان رسیده است.
جزئیات
مهلت ثبت‌نام
قیمت (تومان)
تعداد
بلیت زودهنگام
۲۹ آبان
رایگان
تمام شد

توضیحات بیشتر

مؤسسه بین المللی توسعه دانش فردای ایرانیان با همکاری دانشگاه شهید بهشتی برگزار می کند:

 

سمینار آموزشی 

Gene Prioritization Through Geometric-Inspired Kernel Data Fusion

با حضور 

Pooya Zakeri

PhD Student in Bioinformatics, Department of Electrical Engineering (ESAT), STADIUS, Stadius Centre for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, BelgiumEntrepreneurship and Innovation
 

In biology, there is often the need to discover the most promising genes among a large list of candidate genes to further investigate. In the recent years, several computational approaches based on different genomic data sources and often machine learning methods have been used to crack this problem efficiently. While a single data source might not be effective enough, fusing several complementary genomic data source results in more accurate prediction. Finding an efficient and cost-effective technique for merging these complementary genomic data has received increasing attention. In particular, kernel methods are an interesting class of techniques for data fusion. We propose a kernel-based gene prioritization framework using geometric kernel fusion which we have recently developed as a powerful tool for protein fold classification. We discuss that taking the more involved geometric mean of their corresponding kernel matrices is less sensitive in dealing with complementary and noisy kernel matrices compared to standard multiple kernel learning methods. Since genomic kernels often encode the complementary characteristics of biological data, this leads us to research the application of geometric kernel fusion in the gene prioritization task. Experimental results on our prospective benchmark show that our model can improve the accuracy of the state-of-the-art kernel fusion models for protein fold recognition and gene prioritization.

مدت و زمان بندی: دوشنبه29 آبان ماه 1396، از ساعت 10:30الی 12

 

آدرس محل برگزاری:

تهران، دانشگاه شهید بهشتی، دانشکده علوم ریاضی، تالار دانشکده

سخنرانان

پویا ذاکری

پویا ذاکری

PhD in Bioinformatics, Department of Electrical Engineering (ESAT), STADIUS, Stadius Centre for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium

توضیحات تکمیلی


آدرس:تهران تالار دانشکده علوم ریاضی دانشگاه شهید بهشتی