@article {Liu036129, author = {Feng Liu and Hao Li and Chao Ren and Xiaochen Bo and Wenjie Shu}, title = {PEDLA: predicting enhancers with a deep learning-based algorithmic framework}, elocation-id = {036129}, year = {2016}, doi = {10.1101/036129}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Transcriptional enhancers are non-coding segments of DNA that play a central role in the spatiotemporal regulation of gene expression programs. However, systematically and precisely predicting enhancers remain a major challenge. Although existing methods have achieved some success in enhancer prediction, they still suffer from many issues. We developed a deep learning-based algorithmic framework named PEDLA (https://github.com/wenjiegroup/PEDLA), which can directly learn an enhancer predictor from massively heterogeneous data and generalize in ways that are mostly consistent across various cell types/tissues. We first trained PEDLA with 1,114-dimensional heterogeneous features in H1 cells, and we demonstrated that our PEDLA framework integrates diverse heterogeneous features and gives state-of-the-art performance relative to five existing methods for enhancer prediction. We further extended PEDLA to iteratively learn from 22 training cell types/tissues. Our results showed that PEDLA manifested superior performance consistency in both training and independent test sets. On average, PEDLA achieved 95.0\% accuracy and a 96.8\% geometric mean (GM) across 22 training cell types/tissues, as well as 95.7\% accuracy and a 96.8\% GM across 20 independent test cell types/tissues. Together, our work illustrates the power of harnessing state-of-the-art deep learning techniques to consistently identify regulatory elements at a genome-wide scale from massively heterogeneous data across diverse cell types/tissues.}, URL = {https://www.biorxiv.org/content/early/2016/05/18/036129}, eprint = {https://www.biorxiv.org/content/early/2016/05/18/036129.full.pdf}, journal = {bioRxiv} }