Deep Learning Approaches for Studying Protein-Protein Interactions

Student: Gavrilova Alina

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Applied Mathematics (Bachelor)

Year of Graduation: 2024

Foundation models that are widely used in natural language processing are gradually beginning to gain popularity in other fields, which include genomics. The space of nucleotide sequences can become a potential source of information that will expand the understanding of diseases and ways to combat them. When training foundation models, extensive datasets are used and then they can be adapted for more specific tasks. This approach allows to significantly reduce the number of resources that would be required to train the model from scratch. This study is devoted to exploring the possibilities of HyenaDNA, GENA-LM and Nucleotide Transformer models pre-trained on genomic data. They will be applied in a binary classification task, the purpose of which is to learn how to distinguish Z-flipons from random DNA sequences.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses