Overview:
Our laboratory is interested in developing computational strategies to decipher the transcriptional regulation governing gene expression. We are particularly invested in elucidating the tissue-specific and sex-dimorphic attributes of the circadian clock (Yeung et al., Genome Research, 2018; Talamanca et al., Science, 2023). With the advent of extensive RNA-seq, ChIP-seq, and ATAC-seq databases, there is a possibility to develop new and more sophisticated models to infer gene-specific and condition-specific transcriptional regulation.
Aims:
This project will employ neural networks and bayesian models to infer transcription factor activity and unravel gene regulatory networks, leveraging extensive ChIP-seq, ATAC-seq, and RNA-seq databases. The student will design and implement ML models to infer transcription factor activities and the associated gene regulatory networks. This will involve mining large databases to identify key regulatory transcription factors that elucidate gene expression variations across time, sex, and tissues. Secondly, the student will develop a straightforward application that allows users to input a list of genes and ascertain the principal transcription factors regulating their expression, thus offering a more accessible avenue to explore gene regulatory networks.
Prerequisites:
- A solid background in machine learning and computational biology is crucial.
- An understanding of gene expression data and transcriptional regulation mechanisms is desirable.
- Familiarity with RNA-seq and ChIP-seq analysis techniques will be beneficial.
Contact: [email protected]