Maria Poptsova spoke at the Sber AI Community Conference on January 28, 2022
The AI Community conference, which was held online, was attended by leading international and Russian experts in the field of AI, as well as business representatives.
Maria Poptsova, Head of the International Laboratory of Bioinformatics at the Faculty of Computer Science of the HSE University, gave a talk on “Machine Learning methods in functional genomics”.
Maria pointed out that the genome is a complex system of interactions between functional elements of different levels of organization – the DNA sequence itself, motifs, three-dimensional structure, elements of the epigenetic code and the code of secondary DNA structures. With the help of neural network deep learning methods, it became possible to aggregate information about functional elements of different levels of cellular organization – genomics, epigenomics, proteomics, metabolomics – and other "omics”, in order to predict functional elements for which experiments either did not reach the desired quality or were not available.
In her talk Maria discussed the deep learning methods being developed at the International Laboratory of Bioinformatics for predicting secondary DNA structures. Models based on convolutional (CNN), recurrent (RNN), and generative adversarial (GAN) networks have been developed, as well as transfer learning methods with domain adaptation for G-quadruplex and Z-DNA prediction problems. I will also introduce the approaches developed in the laboratory from the field of explainable artificial intelligence (XAI), which allow us to identify significant patterns of association of the epigenetic code and the code of secondary DNA structures.