DeepSTARR

Authors: Bernardo P. de Almeida , Franziska Reiter , Michaela Pagani , Alexander Stark

License: MIT

Contributed by: Bernardo P. de Almeida

Cite as: https://doi.org/10.1101/2021.10.05.463203

Type: None

Postprocessing: None

Trained on: Developmental and housekeeping quantitative enhancer activity. Held-out second half of chromosome 2R.

Source files

Model predicting the activities of developmental and housekeeping enhancers in Drosophila S2 cells

Create a new conda environment with all dependencies installed
kipoi env create DeepSTARR
source activate kipoi-DeepSTARR
Install model dependencies into current environment
kipoi env install DeepSTARR
Test the model
kipoi test DeepSTARR --source=kipoi
Make a prediction
kipoi get-example DeepSTARR -o example
kipoi predict DeepSTARR \
  --dataloader_args='{"intervals_file": "example/intervals_file", "fasta_file": "example/fasta_file"}' \
  -o '/tmp/DeepSTARR.example_pred.tsv'
# check the results
head '/tmp/DeepSTARR.example_pred.tsv'
Get the model
import kipoi
model = kipoi.get_model('DeepSTARR')
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$get_model('DeepSTARR')
Make a prediction for example files
predictions <- model$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:deepstarr
Get the activated conda environment inside the container
docker run -it kipoi/kipoi-docker:deepstarr
Test the model
docker run kipoi/kipoi-docker:deepstarr kipoi test DeepSTARR --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:deepstarr \
kipoi get-example DeepSTARR -o /app/example 
docker run -v $PWD/kipoi-example:/app/ kipoi/kipoi-docker:deepstarr \
kipoi predict DeepSTARR \
--dataloader_args='{'intervals_file': '/app/example/intervals_file', 'fasta_file': '/app/example/fasta_file'}' \
-o '/app/DeepSTARR.example_pred.tsv' 
# check the results
head $PWD/kipoi-example/DeepSTARR.example_pred.tsv
Install singularity
conda install --yes -c conda-forge singularity
Make prediction for custom files directly
kipoi get-example DeepSTARR -o example
kipoi predict DeepSTARR \
--dataloader_args='{"intervals_file": "example/intervals_file", "fasta_file": "example/fasta_file"}' \
-o 'DeepSTARR.example_pred.tsv' \
--singularity 
# check the results
head DeepSTARR.example_pred.tsv

Schema

Inputs

Single numpy array

Name: None

    Shape: (249, 4, 1) 

    Doc: DNA sequence


Targets

Single numpy array

Name: None

    Shape: (2,) 

    Doc: Developmental and housekeeping enhancer activity


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.

label_dtype (optional): None, datatype of the task labels taken from the intervals_file. Example: str, int, float, np.float32

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


Model dependencies
conda:
  • python=3.7
  • h5py=3.6.0
  • pip=21.2.2

pip:
  • keras==2.7.0
  • tensorflow==2.7.0

Dataloader dependencies
conda:
  • bioconda::pybedtools
  • bioconda::pyfaidx
  • bioconda::pyranges
  • numpy
  • pandas

pip:
  • kipoiseq