Boosting tissue-specific prediction of active cis-regulatory regions through deep learning and bayesian optimization techniques

HIGHLIGHTS

SUMMARY

Subsequently, when the FANTOM5 Consortium published large-scale and high-resolution CRRs locations, ensembles of support vector machines were proposed, and opened the way to the usage of more advanced models such as deep neural_networks (see e_g_[33, 34]) which are able to uncover the underlying information and high-level patterns hidden by complex multi-dimensional manifolds. DeepEnhancer leverages Convolutional Neural_Networks (CNN, "Methods" section), and obtained promising performance by processing one-hot-encoded sequence data for recognizing enhancers against background sequences, which highlighted the feasibility of sequence-based deep learning classifiers. Indeed, as clarified . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or Email

Password

Remember me

Lost your password?

If you don't have an account, you can create one here.