Fig. 2: A summary view of the major labeled and unlabeled datasets, and the architectures being used in deep-learning methods in computational biology.
From: Current progress and open challenges for applying deep learning across the biosciences

For each of the areas considered in this manuscript, it summarizes estimated sizes of key datasets and databases, as well as the projected growth rate of these. Additionally the rightmost column summarizes the most popular DL architectures applied to the corresponding areas in biosciences.