Understanding the evolution of crops using deep learning and evolutionary models

点击翻译按钮获取中文摘要

Brassicas are the crop species which are most closely related to the well-studied model plantArabidopsis. Interestingly, they often have multiple copies of Arabidopsis genes, due to polyploidisation(whole genome duplication). This project will investigate how the regulatory DNA sequences ofBrassicas have evolved, using methods that will allow quantitative comparison with alternativeevolutionary models.Artificial intelligence algorithms that are used to annotate texts and images have recently been appliedto interpret DNA sequences. The Ezer lab has developed an AI for annotating new regulatory regions inArabidopsis, based on DNA sequence (unpublished preliminary results acquired through a TuringInstitute research grant). This data is trained on large databases of pre-existing RNA-seq data.The PhD student will refine this AI model and then apply it to Brassicas, where extensive RNA-seqdatasets have recently been made available. In parallel, the student will develop and implement variousevolutionary mathematical models of promoter evolution. They will compare the annotated regulatorysequences with the predictions made by the evolutionary models. This will help us identify whichevolutionary model best explains the evolution of regulatory sequences in Brassicas. As most of thesemodels have been developed in non-plant species and in the absence of polyploidisation, this will shedan important light on the similarities and differences between regulatory sequence evolution acrossbiological kingdoms. The work will also show how mathematical models can be used in conjunctionwith AI to arrive at a practical understanding of the evolution of crop systems.