BPNet-OSKN

Authors: Žiga Avsec , Melanie Weilert , Avanti Shrikumar , Sabrina Krueger , Amr Alexandari , Khyati Dalal , Robin Fropf , Charles McAnany , Julien Gagneur , Anshul Kundaje , Julia Zeitlinger

License: MIT

Contributed by: Ziga Avsec

Cite as: https://doi.org/10.1101/737981

Type: None

Postprocessing: None

Trained on: ChIP-nexus data in mm10. test chromosomes 1, 8, 9, validation chromosomes 2, 3, 4

Source files

BPNet model predicting the ChIP-nexus profiles of Oct4, Sox2, Nanog and Klf4

Create a new conda environment with all dependencies installed

kipoi env create BPNet-OSKN
source activate kipoi-BPNet-OSKN

Install model dependencies into current environment

kipoi env install BPNet-OSKN

Test the model

kipoi test BPNet-OSKN --source=kipoi

Make a prediction

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

Get the model

import kipoi
model = kipoi.get_model('BPNet-OSKN')

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
it = dl.batch_iter(batch_size=4)
# predict for a batch
batch = 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 model

library(reticulate)
kipoi <- import('kipoi')
model <- kipoi$get_model('BPNet-OSKN')

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

docker pull kipoi/kipoi-docker:bpnet-oskn

Get the activated conda environment inside the container

docker run -it kipoi/kipoi-docker:bpnet-oskn

Test the model

docker run kipoi/kipoi-docker:bpnet-oskn kipoi test BPNet-OSKN --source=kipoi

Make prediction for custom files directly

# Create an example directory containing the data
mkdir -p $PWD/kipoi-example 
# You can replace $PWD/kipoi-example with a different absolute path containing the data 
docker run -v $PWD/kipoi-example:/app/ kipoi/kipoi-docker:bpnet-oskn \
kipoi get-example BPNet-OSKN -o /app/example 
docker run -v $PWD/kipoi-example:/app/ kipoi/kipoi-docker:bpnet-oskn \
kipoi predict BPNet-OSKN \
--dataloader_args='{'intervals_file': '/app/example/intervals_file', 'fasta_file': '/app/example/fasta_file'}' \
-o '/app/BPNet-OSKN.example_pred.tsv' 
# check the results
head $PWD/kipoi-example/BPNet-OSKN.example_pred.tsv

Install singularity

conda install --yes -c conda-forge singularity

Make prediction for custom files directly

kipoi get-example BPNet-OSKN -o example
kipoi predict BPNet-OSKN \
--dataloader_args='{"intervals_file": "example/intervals_file", "fasta_file": "example/fasta_file"}' \
-o 'BPNet-OSKN.example_pred.tsv' \
--singularity 
# check the results
head BPNet-OSKN.example_pred.tsv

Schema

Inputs

Single numpy array

Name: None

Shape: (1000, 4)

Doc: One-hot encoded DNA sequence.

Targets

Dictionary of numpy arrays

Name: Oct4

Shape: (1000, 2)

Doc: Strand-specific ChIP-nexus data for Oct4.

Name: Sox2

Shape: (1000, 2)

Doc: Strand-specific ChIP-nexus data for Sox2.

Name: Nanog

Shape: (1000, 2)

Doc: Strand-specific ChIP-nexus data for Nanog.

Name: Klf4

Shape: (1000, 2)

Doc: Strand-specific ChIP-nexus data for Klf4.

Dataloader

Defined as: kipoiseq.dataloaders.SeqIntervalDl

Doc: Dataloader for a combination of fasta and tab-delimited input files such as bed files. The dataloader extracts regions from the fasta file as defined in the tab-delimited `intervals_file` and converts them into one-hot encoded format. Returned sequences are of the type np.array with the shape inferred from the arguments: `alphabet_axis` and `dummy_axis`.

Authors: Ziga Avsec , Roman Kreuzhuber

Type: Dataset

License: MIT

Arguments

intervals_file : bed3+<columns> file path containing intervals + (optionally) labels

fasta_file : Reference genome FASTA file path.

num_chr_fasta (optional): True, the the dataloader will make sure that the chromosomes don't start with chr.

use_strand (optional): reverse-complement fasta sequence if bed file defines negative strand. Requires a bed6 file

Model dependencies

conda:

python=3.6
bioconda::pybedtools>=0.7.10
bioconda::bedtools>=2.27.1
bioconda::pybigwig>=0.3.10
bioconda::pysam>=0.14.0
bioconda::genomelake==0.1.4
pytorch::pytorch=1.4.0
cython=0.29.22
h5py=2.10.0
numpy=1.19.2
pandas=1.1.5
fastparquet=0.5.0
python-snappy=0.6.0
pip=21.0.1
nb_conda=2.2.1

pip:

tensorflow==1.14.0
git+https://github.com/kundajelab/DeepExplain.git
keras==2.2.4
git+https://github.com/kundajelab/[email protected]

Dataloader dependencies

conda:

bioconda::pybedtools
bioconda::pyfaidx
bioconda::pyranges
numpy
pandas

pip:

kipoiseq