REAT transcriptome

1 Run reat transcriptome on Arabidopsis illumina short read and PacBio IsoSeq

cd /home/train/Annotation_workshop/Reat_transcriptome/Arabidopsis/Chr3-1065466-1464870

activate_reat

(
reat \
    --jar_cromwell Inputs/Configs/cromwell.jar \
    --runtime_configuration Inputs/Configs/cromwell_noserver_local.conf \
    --workflow_options_file Inputs/Configs/options.json \
    --computational_resources Inputs/Configs/compute_inputs.json \
    transcriptome \
    --csv_long_samples ./csv_long_sample.csv \
    --csv_paired_samples ./csv_paired_samples.csv \
    --all_scoring_file Inputs/Configs/plant_update.yaml \
    --all_extra_config Inputs/Configs/external_plants.yaml \
    --long_scoring_file Inputs/Configs/plant_update.yaml \
    --long_extra_config Inputs/Configs/external_plants.yaml \
    --homology_proteins Inputs/Homology/selected_species.fa \
    --short_reads_aligner hisat \
    --HQ_aligner minimap2 \
    --min_identity 95 \
    --min_intron_len 20 \
    --max_intron_len 50000 \
    --HQ_min_coverage 90 \
    --HQ_min_identity 95 \
    --skip_mikado_long \
    --reference Inputs/Reference/Athaliana_447_TAIR10_Chr3_clean.fa \
    > log.out 2> log.err &
)

You can follow the progress in the log file. It takes about ~15 minutes to complete.

tail -f log.out

To clean up to just the original files

cd /home/train/Annotation_workshop/Reat_transcriptome/Arabidopsis/Chr3-1065466-1464870
rm -rf log.err scoring all long reat_input.json cromwell-workflow-logs cromwell-executions run_details.json outputs log.out

2 Run reat transcriptome on Human ONT long reads

cd /home/train/Annotation_workshop/Reat_transcriptome/Human/20-1-12500000

(
reat \
    --jar_cromwell Inputs/Configs/cromwell.jar \
    --runtime_configuration Inputs/Configs/cromwell_noserver_local.conf \
    --workflow_options_file Inputs/Configs/options.json \
    --computational_resources Inputs/Configs/compute_inputs.json \
    transcriptome \
    --csv_long_samples ./csv_long_samples_ONT_chr20regionA.csv \
    --homology_proteins ./Inputs/Homology/Mus_musculus.GRCm39.103.chr.pep.fa \
    --LQ_aligner 2pass_merged \
    --skip_2pass_alignment \
    --LQ_assembler stringtie \
    --LQ_min_identity 80 \
    --LQ_min_coverage 80 \
    --min_intron_len 20 \
    --max_intron_len 200000 \
    --all_scoring_file Inputs/Configs/mammalian_LQ_relaxed_splicing.yaml \
    --skip_mikado_long \
    --all_extra_config Inputs/Configs/template_configuration_relaxed_splicing_requirements_sv2_noport.yaml \
    --reference ./Inputs/Reference/Homo_sapiens.GRCh38.dna.primary_assembly_chr20regionA.fa \
    > log.out 2> log.err &
)

You can follow the progress in the log file. It takes about ~10 minutes to complete.

tail -f log.out

To clean up to just the original files

cd /home/train/Annotation_workshop/Reat_transcriptome/Human/20-1-12500000
rm -rf log.err scoring all long reat_input.json cromwell-workflow-logs cromwell-executions run_details.json outputs log.out

To deactivate the conda environment

deactivate