Andreas Gschwind

The correct link for the model is: github.com/karbalayghareh…

The predictions for 352 ENCODE biosamples can be found on encodeproject.org, and the model is available at: github.com/karbalayghareh… All benchmarking pipelines are available on github: - github.com/EngreitzLab/CR… - github.com/EngreitzLab/eQ… - github.com/EngreitzLab/AB… 15/n

Excited to share our latest work on bioRxiv! biorxiv.org/content/10.110… A highly collaborative effort with @ksmualim @karbalayghareh, @mayayayas, @kanishkadey, @evelynjagoda,@WangXijhu, @LarsMSteinmetz, @anshulkundaje, @jengreitz and many others from @ENCODE_NIH! Thread👇

@vedranfranke Here we either use cell-type specific Hi-C (ENCODE-Hi-C) or average Hi-C contact frequency across ~35 cell types. Would be exciting to benchmark other ways to estimate 3D contact.

@argschwind Did you try a two step approach - infering HiC maps from k27, and then using them in E-G prediction?

@lpachter @ENCODE_NIH Sorry about that, should be public now.

@argschwind @ENCODE_NIH The Github repo displays a 404 error. Can you make it public? Thanks.

This has been a wonderful community effort involving countless people from the @ENCODE_NIH consortium and beyond. I would like to thank everybody I had the pleasure to work with during this long and exciting journey! 17/17

Summary: We present a new approach to map genome-wide enhancer-gene regulatory interactions, show how to link variants to genes, and interpret the model to learn about enhancer regulation. Our framework provides a resource for building future, increasingly accurate models. 16/n