Sigma 70 promoter sequence motifs of Escherichia coli.
Their studies start with exact computational methods [1–2] and later turn to machine learning techniques. The simulations are performed on HPC clusters at
CCAST/NDSU. Thanks to the availability of such HPC resources, the tasks can be completed within acceptable time; otherwise, it is impossible to experiment on such a wide range of settings, especially for grid-searching the hyperparameters for deep learning models.
References
[1] Y. Du and C. Yan, “An efficient method for discovering functionally important motifs in a group of protein structures,” International Conference on Computational Science and Computational Intelligence (CSCI; Dec. 12, 2018): 1345-1350. IEEE.
[2] Y. Du and C. Yan, “An improved clique-based method for discovery of novel spatial motifs in protein structures,” BIBE 2018; International Conference on Biological Information and Biomedical Engineering, VDE, 2018: 1-5.