Used Transdecoder to identify open reading frames (ORFs) for use in annotating Pgenerosa_v074 genome assembly. Relies on BLASTp, Pfam, and HMM scanning to ID ORFs.

Trinity notebook:

20190409_trinity_geoduck_EPI116_RNAseq

SBATCH script (GitHub):

20190627_transdecoder_geoduck_EPI116_RNAseq.sh

#!/bin/bash
## Job Name
#SBATCH --job-name=transdecoder
## Allocation Definition
#SBATCH --account=coenv
#SBATCH --partition=coenv
## Resources
## Nodes
#SBATCH --nodes=1
## Walltime (days-hours:minutes:seconds format)
#SBATCH --time=25-00:00:00
## Memory per node
#SBATCH --mem=120G
##turn on e-mail notification
#SBATCH --mail-type=ALL
#SBATCH --mail-user=samwhite@uw.edu
## Specify the working directory for this job
#SBATCH --workdir=/gscratch/scrubbed/samwhite/outputs/20190627_transdecoder_geoduck_EPI116_RNAseq

# Load Python Mox module for Python module availability

module load intel-python3_2017

# Document programs in PATH (primarily for program version ID)

date >> system_path.log
echo "" >> system_path.log
echo "System PATH for $SLURM_JOB_ID" >> system_path.log
echo "" >> system_path.log
printf "%0.s-" {1..10} >> system_path.log
echo "${PATH}" | tr : \\n >> system_path.log


wd="$(pwd)"


# Paths to input/output files
blastp_out_dir="${wd}/blastp_out"
transdecoder_out_dir="${wd}/Trinity.fasta.transdecoder_dir"
pfam_out_dir="${wd}/pfam_out"
blastp_out="${blastp_out_dir}/blastp.outfmt6"

pfam_out="${pfam_out_dir}/pfam.domtblout"
lORFs_pep="${transdecoder_out_dir}/longest_orfs.pep"
pfam_db="/gscratch/srlab/programs/Trinotate-v3.1.1/admin/Pfam-A.hmm"
sp_db="/gscratch/srlab/programs/Trinotate-v3.1.1/admin/uniprot_sprot.pep"

# From 20190409 Trinity assembly
trinity_fasta="/gscratch/srlab/sam/data/P_generosa/transcriptomes/juvenile/EPI116/Trinity.fasta"

# Paths to programs
blast_dir="/gscratch/srlab/programs/ncbi-blast-2.8.1+/bin"
blastp="${blast_dir}/blastp"
hmmer_dir="/gscratch/srlab/programs/hmmer-3.2.1/src"
hmmscan="${hmmer_dir}/hmmscan"
transdecoder_dir="/gscratch/srlab/programs/TransDecoder-v5.5.0"
transdecoder_lORFs="${transdecoder_dir}/TransDecoder.LongOrfs"
transdecoder_predict="${transdecoder_dir}/TransDecoder.Predict"

# Make output directories
mkdir "${blastp_out_dir}"
mkdir "${pfam_out_dir}"

# Record FastA checksum for verification, if needed.
md5sum ${trinity_fasta} > fasta.md5

# Extract long open reading frames
${transdecoder_lORFs} \
-t ${trinity_fasta}

# Run blastp on long ORFs
${blastp} \
-query "${lORFs_pep}" \
-db ${sp_db} \
-max_target_seqs 1 \
-outfmt 6 \
-evalue 1e-5 \
-num_threads 28 \
> "${blastp_out}"

# Run pfam search
${hmmscan} \
--cpu 28 \
--domtblout "${pfam_out}" \
${pfam_db} \
"${lORFs_pep}"

# Run Transdecoder with blastp and Pfam results
${transdecoder_predict} \
-t ${trinity_fasta} \
--retain_pfam_hits "${pfam_out}" \
--retain_blastp_hits "${blastp_out}"

RESULTS

Run time:

Output folder:

20190627_transdecoder_geoduck_EPI116_RNAseq/

CDS FastA:

20190627_transdecoder_geoduck_EPI116_RNAseq/Trinity.fasta.transdecoder.cds

Peptide FastA:

20190627_transdecoder_geoduck_EPI116_RNAseq/Trinity.fasta.transdecoder.pep

BED file:

20190627_transdecoder_geoduck_EPI116_RNAseq/Trinity.fasta.transdecoder.bed

GFF file:

20190627_transdecoder_geoduck_EPI116_RNAseq/Trinity.fasta.transdecoder.gff3