Семинар лаборатории биоинформатики: Обучение представлений вторичных структур РНК в графовых нейросетях для предсказания РНК-белковых взаимодействий

Приглашаем на научный семинар доцента факультета компьютерных наук, заведующей лабораторией биоинформатики Марии Попцовой "Методы машинного обучения
в биоинформатике. Современные приложения машинного обучения к анализу геномных данных".

Когда: 4 марта 2022 (пт), 20:00-21:30
 

Обучение представлений вторичных структур РНК в графовых нейросетях для предсказания РНК-белковых взаимодействий

Работа ученых Школы компьютерных наук Университета Макгилла, Канада (“Graph neural representational learning of RNA secondary structures for predicting RNA-protein interactions”, Yan et al.). Публикация в журнале Bioinformatics, 2020 г.

RNA-protein interactions are key effectors of post-transcriptional regulation. Significant experimental and bioinformatics efforts have been expended on characterizing protein binding mechanisms on the molecular level, and on highlighting the sequence and structural traits of RNA that impact the binding specificity for different proteins. Yet our ability to predict these interactions in silico remains relatively poor.

In this study, we introduce RPI-Net, a graph neural network approach for RNA-protein interaction prediction. RPI-Net learns and exploits a graph representation of RNA molecules, yielding significant performance gains over existing state-of-the-art approaches. We also introduce an approach to rectify an important type of sequence bias caused by the RNase T1 enzyme used in many CLIP-Seq experiments, and we show that correcting this bias is es- sential in order to learn meaningful predictors and properly evaluate their accuracy. Finally, we provide new approaches to interpret the trained models and extract simple, biologically interpretable representations of the learned sequence and structural motifs.

Source code can be accessed at https://www.github.com/HarveyYan/RNAonGraph