tfmodisco-lite
tfmodisco-lite copied to clipboard
jmschrei
A lite implementation of tfmodisco, a motif discovery algorithm for genomics experiments.
Hello, I have recently run the bpnet-refactor workflow and obtained SHAP attribution scores, which I would now like to load into TF-MoDISco. I'm having some trouble seeing how to do...
Greetings, Thank you so much for your amazing work! I was wondering if there are any options of applying a filter on the peaks that are being used for predicting...
Extension of #20, `MergeMotifsAcrossRuns.ipynb` creates a new seqlet set that combines the results from two different modisco runs. However, it does not take into account that tfmodisco-lite trims each input...
When extracting seqlets with high absolute contribution scores, are the seqlets considered to be high in comparison to all sequences contribution scores or only within it's own sequence?
This code accounts for cases where sequences in the one hot encodings are variable length. In these cases, we don't include seqlets that don't overlap any bp for a sequence....
It'd be nice if --verbose added some more information about progress as the algorithm runs. As it stands, --verbose adds exactly two output lines in the entire program. While the...
This worked for me to get all motifs out: ``` import click import h5py import numpy as np @click.command() @click.option( "--reportFile", "report_file", required=True, multiple=False, type=str, default="modisco_resultshypothetical_contribution_scores_mean_diffTeloHEAC_CTRL_vs_6h.npz.h5", help="e.g. modico output", )...
Chrombpnet defines the peak center as `start + summit`, not the midpoint between `start` and `end`. It would be good to make `write_bed_from_h5` consistent with this convention. https://github.com/jmschrei/tfmodisco-lite/blob/d6716a56c407040e73f48cf0662a432035e4fde2/modiscolite/io.py#L349C1-L350C1 So `absolute_peak_center...
When using the `modisco.h5` to track down original seqlet coordinates, the `example_idx` parameter is arbitrary (i.e. doesn't have a 1:1 match with the dimensions of the original input .npy in...
The seqlet coordinates (per example) are returned relative to the "trimmed" contributions For example, if the user specificies a window of 100 with the "--window" argument, on a full sequence...
