Tools tl
#
|
Main class to handle training, testing, predicting and calculation of contribution scores. |
|
Task configuration (optimizer, loss, and metrics) for use in tl.Crested. |
|
Get default loss, optimizer, and metrics for an existing task. |
Data#
|
DataModule class which defines how dataloaders should be loaded in each stage. |
|
Pytorch-like DataLoader class for AnnDataset with options for batching, shuffling, and one-hot encoding. |
|
Dataset class for combining genome files and AnnData objects. |
Model Zoo#
|
Construct a Basenji model. |
|
Construct a ChromBPNet like model. |
|
Construct a DeepTopicCNN model. |
|
Construct a Simple ConvNet with standard convolutional and dense blocks. |
Losses#
|
Custom loss function that combines cosine similarity and mean squared error (MSE). |
Metrics#
Concordance correlation coefficient metric. |
|
|
Pearson correlation metric. |
|
Log Pearson correlation metric. |
|
Zero penalty metric. |
Modisco#
|
Run tf-modisco on one-hot encoded sequences and contribution scores stored in .npz files. |
Match .h5 files in a given directory with a list of class names and returns a dictionary mapping. |
|
|
Process genomic patterns from matched HDF5 files, trim based on information content, and match to known patterns. |
|
Create a pattern matrix from classes and patterns, with optional normalization. |
Generate nucleotide sequences from pattern data. |
|
|
Compute the similarity between two patterns. |
|
Find the index of a pattern by its ID. |
|
Find and filter pattern matches from the modisco-lite list of patterns to the motif database from the corresponding HTML paths. |
|
Calculate the similarity matrix for the given patterns. |
Read an AnnData object from an H5AD file and calculates the mean gene expression per cell type subclass. |
|
|
Generate html paths for each pattern in the filtered array. |
|
Read a TSV file mapping motifs to transcription factors (TFs) into a DataFrame. |
Create a dictionary mapping patterns to their associated transcription factors (TFs) and other metadata. |
|
|
Create a tensor (matrix) of transcription factor (TF) expression and cell type contributions. |