Neural network modeling of differential binding between wild-type and mutant ctcf reveals putative binding preferences for zinc fingers 1-2

HIGHLIGHTS

SUMMARY

Putative motifs of CTCF`s zinc_fingers identified by interpreting wild‑type versus mutant differential peak prediction models To identify motifs related to the binding of each ZF in CTCF, the authors trained and interpreted a neural_network for predicting whether a peak would be significantly weaker according to DESeq2 in the mutant dataset than in the wild-type dataset (Methods, Supporting Website). The authors found that all models performed well for ZFs 3-7, but the neural_networks and the logistic regressions with the TF-MoDISco motif hit score alone had substantially better performance than the . . .

 



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.