This release focuses on attribution methods and other utilities based on better using these attributions.
- Stand-alone implementation of DeepLIFT/SHAP that fixes several small issues with the Captum implementation; bugs, improved batching and throughput for small models, etc.
- Seqlet calling for identifying spans of high-attribution signal
- Plotting and annotations of those plots
- Altered API for
saturation_mutagenesisto be more consistent with the results fromdeep_lift_shap. - Altered API for several functions to allow the passing in of a custom function to apply, e.g., for
marginalizeto allow passing in eitherpredictordeep_lift_shap(or any other function) to apply before and after substituting in a motif of interest