LRBinner¶

Description¶

LRBinner is a long-read binning tool that overcomes several limitations of our previous work MetaBCC-LR (ISMB 2020). The tool uses variational auto-encoders to bin error-prone long reads using coverage and composition.

Environment Modules¶

Run module spider lrbinner to find out what environment modules are available for this application.

Environment Variables¶

HPC_LRBINNER_DIR - installation directory
HPC_LRBINNER_BIN - executable directory

Job Script Examples¶

Below is a job script used for testing application installation:

#!/bin/bash
#SBATCH --job-name=lrbinner_0.1_test
#SBATCH --mail-type=NONE
#SBATCH --nodes=1
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=32
#SBATCH --mem-per-cpu=4gb
#SBATCH --gpus=1
#SBATCH --time=24:00:00
#SBATCH --output=lrbinner_0.1_test.log

echo "Setting up test environment..."
TEST_PWD=/data/apps/tests/lrbinner/0.1
TEST_DATADIR=${TEST_PWD}/example_data
TEST_WORKDIR=${TEST_PWD}/test_output

cd ${TEST_PWD}
module load lrbinner/0.1

# Remove any previous test results and re-create a working directory
if [ -d ${TEST_WORKDIR} ]; then rm -rf ${TEST_WORKDIR}/; fi
mkdir ${TEST_WORKDIR}

echo "Starting test run at $(date) on $(hostname)..."

# Based on https://github.com/anuradhawick/LRBinner#test-run-data
###################################
LRBinner \
    reads \
    -r ${TEST_DATADIR}/reads.fasta \
    -bc 10 \
    -bs 32 \
    -o ${TEST_WORKDIR}/lrb \
    --cuda \
    -mbs 5000 \
    --ae-dims 4 \
    --ae-epochs 200 \
    -bit 0 \
    -t ${SLURM_JOB_CPUS_PER_NODE:-4}

# Evaluate results:
eval.py \
    --truth ${TEST_DATADIR}/ids.txt \
    --bins ${TEST_WORKDIR}/lrb/bins.txt \
    --print
###################################

echo "Test complete at $(date)."

Citation¶

If you publish research that uses LRBinner you have to cite it as follows:

Wickramarachchi, A., & Lin, Y. (2021). LRBinner: Binning long reads in metagenomics datasets. In A. Carbone & M. El-Kebir (Eds.), 21st International Workshop on Algorithms in Bioinformatics (WABI 2021) (Vol. 201, pp. 11:1–11:18). Leibniz International Proceedings in Informatics (LIPIcs). Schloss Dagstuhl – Leibniz-Zentrum für Informatik. https://doi.org/10.4230/LIPIcs.WABI.2021.11

Categories¶

biology, genomics