LGOct 31, 2018Code
Technical Note on Transcription Factor Motif Discovery from Importance Scores (TF-MoDISco) version 0.5.6.5Avanti Shrikumar, Katherine Tian, Žiga Avsec et al.
TF-MoDISco (Transcription Factor Motif Discovery from Importance Scores) is an algorithm for identifying motifs from basepair-level importance scores computed on genomic sequence data. This technical note focuses on version v0.5.6.5. The implementation is available at https://github.com/kundajelab/tfmodisco/tree/v0.5.6.5
LGMay 5, 2016
Not Just a Black Box: Learning Important Features Through Propagating Activation DifferencesAvanti Shrikumar, Peyton Greenside, Anna Shcherbina et al.
Note: This paper describes an older version of DeepLIFT. See https://arxiv.org/abs/1704.02685 for the newer version. Original abstract follows: The purported "black box" nature of neural networks is a barrier to adoption in applications where interpretability is essential. Here we present DeepLIFT (Learning Important FeaTures), an efficient and effective method for computing importance scores in a neural network. DeepLIFT compares the activation of each neuron to its 'reference activation' and assigns contribution scores according to the difference. We apply DeepLIFT to models trained on natural images and genomic data, and show significant advantages over gradient-based methods.