Amr Alexandari

TL;DR: It is found that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art.

TL;DR: BPNet as discussed by the authors uses DNA sequence to predict base-resolution chromatin immunoprecipitation (ChIP)-nexus binding profiles of pluripotency transcription factor (TF) binding motifs.

TL;DR: A deep learning model is introduced that uses DNA sequence to predict base-resolution ChIP-nexus binding profiles of pluripotency TFs, and interpretation tools are developed to learn predictive motif representations and identify soft syntax rules for cooperative TF binding interactions.

TL;DR: A deep learning model is trained that uses DNA sequence to predict base-resolution binding profiles of four pluripotency transcription factors Oct4, Sox2, Nanog, and Klf4 and finds that instances of strict motif spacing are largely due to retrotransposons, but that soft motif syntax influences motif interactions at protein and nucleosome range.

TL;DR: A new separable fully connected layer is presented that learns a weights tensor that is the outer product of positional weights and cross-channel weights, thereby allowing the same positional patterns to be applied across multiple convolutional channels.