DeepLiver/DeepLiver_Activity

Authors: Carmen Bravo , Stein Aerts

License: Other / Non-commercial (see LICENSE.txt)

Contributed by: Carmen Bravo , Stein Aerts

Cite as: Bravo
González-Blas
Carmen.
(2022).
Enhancer
grammar
of
liver
cell
types
and
hepatocyte
zonation
states.
https://doi.org/10.1101/2022.12.08.519575

Type: None

Postprocessing: None

Trained on: Binarized enhancer activity measured in 12K enhancers in the mouse liver using MPRA.

Source files

Specialized deep learning model to predict hepatocyte enhancer activity in the mouse liver.

Create a new conda environment with all dependencies installed

kipoi env create DeepLiver/DeepLiver_Activity
source activate kipoi-DeepLiver__DeepLiver_Activity

Test the model

kipoi test DeepLiver/DeepLiver_Activity --source=kipoi

Make a prediction

kipoi get-example DeepLiver/DeepLiver_Activity -o example
kipoi predict DeepLiver/DeepLiver_Activity \
  --dataloader_args='{"intervals_file": "example/intervals_file", "fasta_file": "example/fasta_file"}' \
  -o '/tmp/DeepLiver|DeepLiver_Activity.example_pred.tsv'
# check the results
head '/tmp/DeepLiver|DeepLiver_Activity.example_pred.tsv'

Create a new conda environment with all dependencies installed

kipoi env create DeepLiver/DeepLiver_Activity
source activate kipoi-DeepLiver__DeepLiver_Activity

Get the model

import kipoi
model = kipoi.get_model('DeepLiver/DeepLiver_Activity')

Make a prediction for example files

pred = model.pipeline.predict_example(batch_size=4)

Use dataloader and model separately

# Download example dataloader kwargs
dl_kwargs = model.default_dataloader.download_example('example')
# Get the dataloader and instantiate it
dl = model.default_dataloader(**dl_kwargs)
# get a batch iterator
batch_iterator = dl.batch_iter(batch_size=4)
for batch in batch_iterator:
    # predict for a batch
    batch_pred = model.predict_on_batch(batch['inputs'])

Make predictions for custom files directly

pred = model.pipeline.predict(dl_kwargs, batch_size=4)

Get the model

library(reticulate)
kipoi <- import('kipoi')
model <- kipoi$get_model('DeepLiver/DeepLiver_Activity')

Make a prediction for example files

predictions <- model$pipeline$predict_example()

Use dataloader and model separately

# Download example dataloader kwargs
dl_kwargs <- model$default_dataloader$download_example('example')
# Get the dataloader
dl <- model$default_dataloader(dl_kwargs)
# get a batch iterator
it <- dl$batch_iter(batch_size=4)
# predict for a batch
batch <- iter_next(it)
model$predict_on_batch(batch$inputs)

Make predictions for custom files directly

pred <- model$pipeline$predict(dl_kwargs, batch_size=4)

Get the docker image

Not available yet

Get the full sized docker image

Not available yet

Get the activated conda environment inside the container

Not available yet

Test the model

Not available yet

Make prediction for custom files directly

Not available yet

Install apptainer

https://apptainer.org/docs/user/main/quick_start.html#quick-installation-steps

Make prediction for custom files directly

Not available yet

Schema

Inputs

List of numpy arrays

Name: None

Shape: (500, 4)

Doc: DNA sequence

Targets

Single numpy array

Name: topic

Shape: (2,)

Doc: Activity Prediction (0:Active, 1:Not active)

Dataloader

Defined as: .

Doc: Data-loader returning one-hot encoded sequences given genome intervals

Authors: Carmen Bravo

Type: None

License: MIT

Arguments

intervals_file : intervals file bed3

fasta_file : Reference genome FASTA file path.

ignore_targets (optional): if True, don't return any target variables

Model dependencies

conda:

python=3.7
numpy==1.19.5
h5py==2.10.0

pip:

tensorflow>=1.15.0
protobuf==3.20

Dataloader dependencies

conda:

python=3.7
bioconda::pybedtools
bioconda::pysam
bioconda::pyfaidx
numpy
pandas

pip:

kipoiseq