Erill Lab projects
Modeling transcription factors with artificial neural networks
This project aims at modeling and understanding transcription factors through the use of artificial neural networks. The main goal is to improve current methods for searching and discovering transcription factor binding sites by exploiting the data-driven nature of artificial neural networks as modeling tools (read more).
Feature extraction with neural networks
Due to the huge amounts of information usually involved in genomics research (e.g. full genome sequences, microarray expression data), feature extraction is often a key step in the analysis of genomic data. (read more)
Promoter modeling with soft-computing approaches
Promoters are key elements in genetic makeup of an individual, since it is changes in promoter regions, instead of changes in the gene repertoire, that account for most of the phenotypic differences observed among species. Promoters are also loosely defined entities, with few fixed structural rules to assist in their modeling or detection. (read more)
