Below is a reference for the commands invoked for the tested pipelines, for each species. The format of commands for each pipeline are essentially the same.

# build the images

```
# requires presence of specific versions of software, some of which require licenses
# https://megasun.bch.umontreal.ca/matt/eukan-manuscript/dockerised-annotation-pipelines/
docker build -t base -f Dockerfile-base
docker build -t base -f Dockerfile-braker
docker build -t base -f Dockerfile-maker
docker build -t base -f Dockerfile-gemoma
docker build -t base -f Dockerfile-eukannotpass # eukan pipeline
```

# aspergillus nidulans
```
# assembly script mapping # 0.16s user 0.28s system 0% cpu 40:41.37 total
time nice -19 docker run --mount type=bind,source="$(pwd)",target=/root/tmp annot-pipelines-stack transcriptome_assembly.sh -l /root/tmp/SRR4368892_1.fastq.gz,/root/tmp/SRR4368902_1.fastq.gz,/root/tmp/SRR4368910_1.fastq.gz -r  /root/tmp/SRR4368892_2.fastq.gz,/root/tmp/SRR4368902_2.fastq.gz,/root/tmp/SRR4368910_2.fastq.gz -g /root/tmp/Aspergillus_nidulans_FGSCA4.fna -M 5000 -S RF -A

# run eukannotpass: 3.74s user 0.97s system 0% cpu 10:10:18.66 total
time nice -19 annot-docker eukannotpass eukannotpass -g Aspergillus_nidulans_FGSCA4.fna -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs Aspergillus_nidulans_FGSCA4.sqlite --fungus -n 20

# run braker: 0.51s user 0.42s system 0% cpu 2:07:39.61 total
time ./annot-docker braker braker.pl --species=Aspergillus_nidulans_FGSCA4 --genome=Aspergillus_nidulans_FGSCA4.fna --hints=hints_introns.gff --prot_seq=GCA_000002655.1_ASM265v1_protein.faa,GCA_000002715.1_ASM271v1_protein.faa,GCA_000002855.2_ASM285v2_protein.faa,GCA_000006275.2_JCVI-afl1-v2.0_protein.faa,GCA_000149615.1_ASM14961v1_protein.faa,GCA_000149645.2_ASM14964v1_protein.faa,GCA_000184455.3_ASM18445v3_protein.faa,GCA_000239835.2_Akaw_assembly01_protein.faa,GCA_000600275.1_Eurhe1_protein.faa,GCA_000812125.1_Austus1.0_protein.faa --alternatives-from-evidence=true --cores=20 --softmasking --etpmode --fungus

# run gemoma; 0.32s user 0.14s system 0% cpu 47:55.23 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20 
t=Aspergillus_nidulans_FGSCA4.fna s=own i=GCA_000002855 g=GCA_000002855.2_ASM285v2_genomic.fna a=GCA_000002855.2_ASM285v2_genomic.gff s=own i=GCA_000006275 g=GCA_000006275.2_JCVI-afl1-v2.0_genomic.fna a=GCA_000006275.2_JCVI-afl1-v2.0_genomic.gff s=own i=GCA_000149615 g=GCA_
000149615.1_ASM14961v1_genomic.fna a=GCA_000149615.1_ASM14961v1_genomic.gff s=own i=GCA_000513255 g=GCA_000513255.1_PROQFM164_20130607_genomic.fna a=GCA_000513255.1_PROQFM164_20130607_genomic.gff s=own i=GCA_000513335 g=GCA_000513335.1_PCAMFM013_20131106_genomic.fna a=GCA_0
00513335.1_PCAMFM013_20131106_genomic.gff s=own i=GCA_001511075 g=GCA_001511075.1_Acal_Allpaths_LG_genomic.fna a=GCA_001511075.1_Acal_Allpaths_LG_genomic.gff s=own i=GCA_001890905 g=GCA_001890905.1_Aspac1_genomic.fna a=GCA_001890905.1_Aspac1_genomic.gff s=own i=GCA_0020722 g=GCA_002072245.1_ASM207224v1_genomic.fna a=GCA_002072245.1_ASM207224v1_genomic.gff s=own i=GCA_002072375 g=GCA_002072375.1_ASM207237v1_genomic.fna a=GCA_002072375.1_ASM207237v1_genomic.gff s=own i=GCA_002072425 g=GCA_002072425.1_ASM207242v1_genomic.fna a=GCA_002072425.1$
ASM207242v1_genomic.gff outdir=gemoma_out r=MAPPED ERE.m=STAR_Aligned.sortedByCoord.out.bam

# maker 8.66s user 8.93s system 0% cpu 8:04:04.40 total
time docker run --mount type=bind,source="$(pwd)",target=/root/tmp annot-pipelines-stack  maker_annotation.sh -F -g Aspergillus_nidulans_FGSCA4.fna -p GCA_000002655.1_ASM265v1_protein.f
aa,GCA_000002715.1_ASM271v1_protein.faa,GCA_000002855.2_ASM285v2_protein.faa,GCA_000006275.2_JCVI-afl1-v2.0_protein.faa,GCA_000149615.1_ASM14961v1_protein.faa,GCA_000149645.2_ASM14964v1_protein.faa,GCA_000184455.3_ASM18445v3_protein.faa,GCA_000239835.2_Akaw_assembly01_prote
in.faa,GCA_000600275.1_Eurhe1_protein.faa,GCA_000812125.1_Austus1.0_protein.faa -e nr_transcripts.fasta -a nr_transcripts.gff3 -i introns.gff -n 20
```

# saccharomyces cerevisiae
```
# transcriptome assembly 0.30s user 0.26s system 0% cpu 1:22:12.69 total
time nice -19 docker run --mount type=bind,source="$(pwd)",target=/root/tmp annot-pipelines transcriptome_assembly.sh -l /root/tmp/MI-R1.fastq.gz -r /root/tmp/MI-R2.fastq.gz -g /root/tmp/Saccharomyces_cerevisiae_S288C.fasta -M 5000 -S RF -A

# eukannotpass 1.48s user 0.76s system 0% cpu 4:53:37.40 total
./annot-docker eukannotpass eukannotpass -g Saccharomyces_cerevisiae_S288C.fasta -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs Saccharomyces_cerevisiae_S288C.sqlite --fungus

# gemoma 0.40s user 0.18s system 0% cpu 1:08:29.87 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFin
alizer.u=YES threads=20 t=Saccharomyces_cerevisiae_S288C.fasta $(ls GCA_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir
=gemoma_out r=MAPPED ERE.m=STAR_Aligned.sortedByCoord.out.bam

# braker 0.43s user 0.12s system 0% cpu 43:15.48 total
time nice -19 ./annot-docker braker braker.pl --species=Saccharomyces_cerevisiae_S288C --genome=Saccharomyces_cerevisiae_S288C.fasta --hints=hints_rnaseq.gff --prot_seq=GCA_000002515.1_ASM251v1_protein.faa,GCA_000002525.1_ASM252v1_protein.faa,GCA_000002545.2_ASM254v2_protein.faa,GCA_000003835.1_ASM383v1_protein.faa,GCA_000006335.3_ASM633v3_protein.faa,GCA_000006445.2_ASM644v2_protein.faa,GCA_000026365.1_ASM2636v1_protein.faa,GCA_000026945.1_ASM2694v1_protein.faa,GCA_001298625.1_SEUB3.0_protein.faa,GCA_001413975.1_ASM141397v1_protein.faa  --alternatives-from-evidence=true --cores=20 --softmasking --etpmode --fungus
```

# neurospora crassa
```
# transcriptome assembly 0.16s user 0.18s system 0% cpu 45:11.04 total
time nice -19 docker run -e USER='matt' --mount type=bind,source="$(pwd)",target=/root/tmp annot-pipelines transcriptome_assembly.sh -l /root/tmp/SRR500048_1.fastq.gz -r /root/tmp/SRR500048_2.fastq.gz -g /root/tmp/Neurospora_crassa.fna -M 5000 -S RF -A

# eukannotpass 7.27s user 0.54s system 0% cpu 16:33:17.59 total
time nice -19 annot-docker eukannotpass eukannotpass -g Neurospora_crassa.fasta -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs Neurospora_crassa.sqlite --fungus

# braker 0.91s user 0.21s system 0% cpu 2:40:45.50 total
./annot-docker braker nice -19 braker.pl --species=Neurospora_crassa --genome=Neurospora_crassa.fasta --hints=hints_rnaseq.gff --prot_seq=GCA_000143365.1_ASM14336v1_protein.faa,GCA_000149955.2_ASM14995v2_protein.faa,GCA_000182805.2_ASM18280v2_protein.faa,GCA_000213175.1_v2.0_protein.faa,GCA_000221225.1_CTHT_3.0_protein.faa,GCA_000226095.1_ASM22609v1_protein.faa,GCA_000226115.1_ASM22611v1_protein.faa,GCA_000226545.1_ASM22654v1_protein.faa,GCA_001275765.2_ASM127576v2_protein.faa,GCA_900290415.1_version1_protein.faa --alternatives-from-evidence=true --cores=20 --softmasking --etpmode --fungus

# gemoma 1.24s user 0.26s system 0% cpu 2:30:11.86 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES thr
eads=20 t=Neurospora_crassa.fasta $(ls GCA_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=MAPPED ERE.m=ST
AR_Aligned.sortedByCoord.out.bam

# maker 11.25s user 9.62s system 0% cpu 11:38:37.78 total
time nice -19 annot-docker maker  maker_annotation.sh -F -g Neurospora_crassa.fna -p GCA_000143365.1_ASM14336v1_protein.faa,GCA_000149955.2_ASM14995v2_protein.faa,GCA_000182805.2_ASM18280v2_protein.faa,GCA_000213175.1_v2.0_protein.faa,GCA_000221225.1_CTHT_3.0_protein.faa,GCA_000226095.1_ASM22609v1_protein.faa,GCA_000226115.1_ASM22611v1_protein.faa,GCA_000226545.1_ASM22654v1_protein.faa,GCA_001275765.2_ASM127576v2_protein.faa,GCA_900290415.1_version1_protein.faa,GCF_000149205.2_ASM14920v2_protein.faa -e nr_transcripts.fasta -a nr_transcripts.gff3 -i hints_introns.gff -n 20
```

# ustilago maydis
```
# transcriptome assembly
time nice -19 docker run -e USER='matt' --mount type=bind,source="$(pwd)",target=/root/tmp annot-pipelines transcriptome_assembly.sh -l /root/tmp/MI-R1.fastq.gz -r  /root/tmp/MI-R2.fastq.gz -g /root/tmp/Ustilago_maydis_521.fna -M 5000 -S RF -P -j

# braker 0.59s user 0.22s system 0% cpu 1:39:11.10 total
time nice -19 ./annot-docker braker braker.pl --species=Ustilago_maydis_521 --genome=Ustilago_maydis_521.fna --hints=hints_rnaseq.gff --prot_seq=GCA_000181695.1_ASM18169
v1_protein.faa,GCA_000349305.2_ASM34930v2_protein.faa,GCA_000403515.1_ASM40351v1_protein.faa,GCA_000417875.1_Pflocc_1.0_protein.faa,GCA_000497045.1_PSEUBRA1_protein.faa,GCA_000517465.1_PseuAph1.0_protein.faa,GCA_000747765.1_ASM74776v1_protein.faa,GCA_003144125.1_Tescy1_protein.faa,GCA_900080155.1_UBRO_v3_protein.faa,GCA_900162835.1_version_2_protein.faa --alternatives-from-evidence=true --cores=20 --softmasking --etpmode --fungus

# eukannotpass 6.80s user 0.13s system 0% cpu 13:57:30.03 total
time nice -19 annot-docker eukannotpass eukannotpass -g Ustilago_maydis_521.fna -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs Ustilago_maydis_521.sqlite --fungus -n 20

# maker 4.33s user 3.98s system 0% cpu 4:01:42.39 total
time nice -19 annot-docker maker maker_annotation.sh -F -g Ustilago_maydis_521.fna -p GCA_000181695.1_ASM18169v1_protein.faa,GCA_000349305.2_ASM34930v2_protein.faa,GCA_000403515.1_ASM
40351v1_protein.faa,GCA_000417875.1_Pflocc_1.0_protein.faa,GCA_000497045.1_PSEUBRA1_protein.faa,GCA_000517465.1_PseuAph1.0_protein.faa,GCA_000747765.1_ASM74776v1_protein.faa,GCA_003144125.1_Tescy1_protein.faa,GCA_900080155.1_UBRO_v3_protein.faa,GCA_900162835.1_version_2_pro
tein.faa  -e nr_transcripts.fasta -a nr_transcripts.gff3 -i hints_introns.gff -n 20

# gemoma 0.31s user 0.17s system 0% cpu 57:29.70 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20 t=Ustilago_maydis_521.fna $(ls GCA_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=MAPPED ERE.m=STAR_Aligned.sortedByCoord.out.bam
```

# schizosaccharomyces pombe
```
time nice -19 docker run -e USER='matt' --mount type=bind,source="$(pwd)",target=/root/tmp annot-pipelines transcriptome_assembly.sh -l /root/tmp/R1.
fastq.gz -r  /root/tmp/R2.fastq.gz -g /root/tmp/Schizosaccharomyces_pombe.fasta -M 5000 -S RF -P -j

# eukannotpass 2.74s user 0.96s system 0% cpu 8:26:19.45 total
time nice -19 annot-docker eukannotpass eukannotpass -g Schizosaccharomyces_pombe.fasta -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs Schizosaccharomyces_pombe.sqlite --fungus -n 20

# braker 0.73s user 0.27s system 0% cpu 2:02:58.45 total
time nice -19 ./annot-docker braker braker.pl --species=Schizosaccharomyces_pombe --genome=Schizosaccharomyces_pombe.fasta --hints=hints_rnaseq.gff --prot_seq=GCF_00000
4155.1_SCY4_protein.faa,GCF_000149205.2_ASM14920v2_protein.faa,GCF_000149845.2_SJ5_protein.faa,GCF_000149955.1_ASM14995v2_protein.faa,GCF_000150505.1_SO6_protein.faa,GCF_000182925.2_NC12_protein.faa,GCF_000349005.2_Pneumo_murina_B123_V4_protein.faa,GCF_001477535.1_Pneu_jiro
_RU7_V2_protein.faa,GCF_001477545.1_Pneu_cari_B80_V3_protein.faa,GCF_001661265.1_Saico1_protein.faa   --alternatives-from-evidence=true --cores=20 --softmasking --etpmode --fungus

# maker 4.55s user 2.38s system 0% cpu 4:05:48.13 total
time nice -19 annot-docker maker  maker_annotation.sh -F -g Schizosaccharomyces_pombe.fasta -p GCF_000004155.1_SCY4_protein.faa,GCF_000149205.2_ASM14920v2_protein.faa,GC
F_000149845.2_SJ5_protein.faa,GCF_000149955.1_ASM14995v2_protein.faa,GCF_000150505.1_SO6_protein.faa,GCF_000182925.2_NC12_protein.faa,GCF_000349005.2_Pneumo_murina_B123_V4_protein.faa,GCF_001477535.1_Pneu_jiro_RU7_V2_protein.faa,GCF_001477545.1_Pneu_cari_B80_V3_protein.faa,
GCF_001661265.1_Saico1_protein.faa  -e nr_transcripts.fasta -a nr_transcripts.gff3 -i hints_introns.gff -n 20

# gemoma 0.72s user 0.14s system 0% cpu 1:48:15.73 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20 t=Schizosaccharomyces_pombe.fasta $(ls GCF_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=MAPPED ERE.m=STAR_Aligned.sortedByCoord.out.bam
```

# plasmodium falciparum
```
time nice -19 docker run -e USER='matt' --mount type=bind,source="$(pwd)",target=/root/tmp annot-pipelines transcriptome_assembly.sh -l /root/tmp/R1.
fastq.gz -r  /root/tmp/R2.fastq.gz -g /root/tmp/Plasmodium_falciparum_3D7.fna -M 5000 -S RF -P -j

# gemoma 0.40s user 0.19s system 0% cpu 1:00:07.01 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO Annotatio
nFinalizer.u=YES threads=20 t=Plasmodium_falciparum_3D7.fna $(ls GCA_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=ge
moma_out r=MAPPED ERE.m=STAR_Aligned.sortedByCoord.out.bam

# braker 0.64s user 0.40s system 0% cpu 2:04:00.65 total
time annot-docker braker nice -19 braker.pl --species=Plasmodium_falciparum_3D7 --genome=Plasmodium_falciparum_3D7.fna --hints=hints_rnaseq.gff --prot_seq=$(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') --alternatives-from-evidence=true --cores=20 --softmasking --etpmode

# maker 7.76s user 3.12s system 0% cpu 8:35:47.26 total
time annot-docker maker nice -19 maker_annotation.sh -g Plasmodium_falciparum_3D7.fna -p $(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') -e nr_transcripts.fasta -a nr_transcripts.gff3 -i hints_introns.gff -n 20

# eukannotpass 1.18s user 0.43s system 0% cpu 4:07:59.60 total
time annot-docker eukannotpass nice -19 eukannotpass -g Plasmodium_falciparum_3D7.fna -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs Plasmodium_falciparum_3D7.sqlite --protist -n 20
```

# dictyostelium
```
# gemoma 1.90s user 0.42s system 0% cpu 5:21:59.91 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20 t=Dictyostelium_discoideum.fna $(ls GCA_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=MAPPED ERE.m=STAR_Aligned.sortedByCoord.out.bam
```

# trypanosoma
```
# transcriptome assembly
annot-docker annot-base transcriptome_assembly.sh -l ERR141315_1.fastq.gz -r  ERR141315_2.fastq.gz -g Trypanosoma_brucei.fna -M 5000 -S RF -A -T -P -j

# gemoma 0.36s user 0.18s system 0% cpu 48:37.49 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20 t=Thalassiosira_pseudonana.fna $(ls GCA_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=MAPPED ERE.m=STAR_Aligned.sortedByCoord.out.bam

# braker 0.34s user 0.17s system 0% cpu 37:05.14 total
# braker 0.70s user 0.05s system 0% cpu 2:10:18.11 total
time annot-docker braker nice -19 braker.pl --species=Trypanosoma_brucei.fna  --genome=Trypanosoma_brucei.fna --hints=hints_rnaseq.gff --prot_seq=$(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') --alternatives-from-evidence=true --cores=20 --softmasking --etpmode
time annot-docker braker nice -19 braker.pl --species=Trypanosoma_brucei.fna  --genome=Trypanosoma_brucei.fna --hints=hints.gff --alternatives-from-evidence=true --cores=20 --softmasking --geneMarkGtf=genemark.gtf --skipGeneMark-ES --skipGeneMark-EP --skipGeneMark-ET --skipGeneMark-ETP

# maker real 6.63s user 4.81s system 0% cpu 8:20:06.00 total
time nice -19 maker_annotation.sh -g Trypanosoma_brucei.fna -p $(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') -e nr_transcripts.fasta -a nr_transcripts.gff3 -i hints_introns.gff -n 20

# eukannotpass 3152.11s user 12.89s system 786% cpu 6:42.45 total
# eukannotpass 1.67s user 1.58s system 0% cpu 8:05:01.51 total
time nice -19 annot-docker eukannotpass eukannotpass -g Trypanosoma_brucei.fna -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs Trypanosoma_brucei.sqlite --numcpu 20
```

# thalassiosira
```
# transcriptome assembly
annot-docker annot-base transcriptome_assembly.sh -l SRR13953375.sra_1.fastq.gz,SRR13953376.sra_1.fastq.gz,SRR13953377.sra_1.fastq.gz,SRR13953378.sra_1.fastq.gz,SRR13953379.sra_1.fastq.gz,SRR13953380.sra_1.fastq.gz,SRR13953381.sra_1.fastq.gz,SRR13953382.sra_1.fastq.gz,SRR13953383.sra_1.fastq.gz,SRR13953384.sra_1.fastq.gz,SRR13953385.sra_1.fastq.gz,SRR13953386.sra_1.fastq.gz,SRR13953387.sra_1.fastq.gz,SRR13953388.sra_1.fastq.gz,SRR13953389.sra_1.fastq.gz,SRR13953390.sra_1.fastq.gz  -r SRR13953375.sra_2.fastq.gz,SRR13953376.sra_2.fastq.gz,SRR13953377.sra_2.fastq.gz,SRR13953378.sra_2.fastq.gz,SRR13953379.sra_2.fastq.gz,SRR13953380.sra_2.fastq.gz,SRR13953381.sra_2.fastq.gz,SRR13953382.sra_2.fastq.gz,SRR13953383.sra_2.fastq.gz,SRR13953384.sra_2.fastq.gz,SRR13953385.sra_2.fastq.gz,SRR13953386.sra_2.fastq.gz,SRR13953387.sra_2.fastq.gz,SRR13953388.sra_2.fastq.gz,SRR13953389.sra_2.fastq.gz,SRR13953390.sra_2.fastq.gz  -g Thalassiosira_pseudonana.fna -M 5000 -S RF -A -T -P -j

# gemoma 0.22s user 0.27s system 0% cpu 48:43.05 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20
 t=Thalassiosira_pseudonana.fna $(ls GCA_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=MAPPED ERE.m=STAR
_Aligned.sortedByCoord.out.bam

# braker 0.73s user 0.35s system 0% cpu 1:44:15.26 total
time annot-docker braker nice -19 braker.pl --species=  --genome=Thalassiosira_pseudonana.fna --hints=hints_rnaseq.gff --prot_seq=$(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') --alternatives-from-evidence=true --cores=20 --softmasking --etpmode

# maker 7.00s user 3.70s system 0% cpu 6:14:08.09 total
time annot-docker maker nice -19 maker_annotation.sh -g Thalassiosira_pseudonana.fna -p $(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') -e nr_transcripts.fasta -a nr_transcripts.gff3 -i hints_rnaseq.gff -n 20

# eukannotpass 5.75s user 0.10s system 0% cpu 11:21:23.08 total
time nice -19 annot-docker eukannotpass eukannotpass -g Thalassiosira_pseudonana.fna -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs *.sqlite --numcpu 20

# funannotate 4.34s user 0.13s system 0% cpu 8:20:53.68 total
time funannotate-docker funannotate train -i Thalassiosira_pseudonana.fna -o funannotate_train --trinity trinity-denovo.fasta --cpus 20 --no_trimmomatic --stranded RF --left R1.fastq.gz --right R2.fastq.gz --max_intronlen 10000
# funannotate predict .55s user 0.53s system 0% cpu 1:34:00.90 total
time funannotate-docker funannotate predict -i Thalassiosira_pseudonana.fna --protein_evidence *faa --rna_bam STAR_Aligned.sortedByCoord.out.bam --genemark_mode ET --optimize_augustus --transcript_evidence nr_transcripts.fasta --transcript_alignments nr_transcripts.gff3 -o funannotate_train -s "funannotate_thal" --organism other --busco_db protists --cpus 20
# fuannotate update 5.89s user 1.08s system 0% cpu 14:20:24.72 total
time funannotate-docker funannotate update -i funannotate_train --cpus 20
```

# leishmania
```
# transcriptome assembly
annot-docker annot-base transcriptome_assembly.sh -l ERR2604475.sra_1.fastq.gz,ERR2604476.sra_1.fastq.gz,ERR2604477.sra_1.fastq.gz,ERR2604478.sra_1.fastq.gz,ERR2604479.sra_1.fastq.gz,ERR2604480.sra_1.fastq.gz -r ERR2604475.sra_2.fastq.gz,ERR2604476.sra_2.fastq.gz,ERR2604477.sra_2.fastq.gz,ERR2604478.sra_2.fastq.gz,ERR2604479.sra_2.fastq.gz,ERR2604480.sra_2.fastq.gz   -g Leishmania_major.fna -M 5000 -S RF -A -j

# gemoma 0.35s user 0.12s system 0% cpu 31:09.93 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20 t=Leishmania_major.fna $(ls GCA_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=MAPPED ERE.m=STAR_Aligned.sortedByCoord.out.bam

# braker 0.48s user 0.26s system 0% cpu 1:21:03.31 total
time annot-docker braker nice -19 braker.pl --species=Leishmania_major.fna  --genome=Leishmania_major.fna --hints=hints_rnaseq.gff --prot_seq=$(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') --alternatives-from-evidence=true --cores=20 --softmasking --etpmode
time annot-docker braker nice -19 braker.pl --species=Leishmania_major.fna  --genome=Leishmania_major.fna --hints=hints_rnaseq.gff --alternatives-from-evidence=true --cores=20 --softmasking --geneMarkGtf=genemark.gtf --skipGeneMark-ES --skipGeneMark-EP --skipGeneMark-ET --skipGeneMark-ETP

# eukannotpass real    18m38.530s user    161m34.088s sys     0m23.404s
# eukannotpass 1.67s 3.98s user 0.41s system 0% cpu 10:47:32.03 total
time nice -19 annot-docker eukannotpass eukannotpass -g Leishmania_major.fna -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs *.sqlite --numcpu 20

# maker 12.64s user 5.60s system 0% cpu 15:00:55.79 total
time annot-docker maker nice -19 ./maker_annotation.sh -g Leishmania_major.fna -p $(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') -e nr_transcripts.fasta -a nr_transcripts.gff3 -i hints_introns.gff -n 20
```

# cyanidioschyzon
```
# gemoma 0.52s user 0.18s system 0% cpu 1:46:26.68 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20 t=Cyanidioschyzon_merolae.fna $(ls GCA_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=MAPPED ERE.m=STAR_Aligned.sortedByCoord.out.bam

# maker 3.94s user 3.50s system 0% cpu 4:09:33.43 total
time annot-docker maker nice -19 ./maker_annotation.sh -g Cyanidioschyzon_merolae.fna -p $(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') -e nr_transcripts.fasta -a nr_transcripts.gff3 -i hints_introns.gff -n 20

# braker 0.67s user 0.33s system 0% cpu 2:09:47.26 total
time annot-docker braker nice -19 braker.pl --species=Cyanidioschyzon_merolae --genome=Cyanidioschyzon_merolae.fna --hints=hints_rnaseq.gff --prot_seq=$(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') --alternatives-from-evidence=true --cores=20 --softmasking --etpmode

# eukannotpass real    12m48.579s user    90m42.420s sys     0m19.700s
# eukannotpass 3.88s user 0.47s system 0% cpu 9:15:15.14 total
time nice -19 annot-docker eukannotpass eukannotpass -g *.fna -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs *.sqlite --numcpu 20
```

# dictyostelium
```
# gemoma 1.10s user 0.99s system 0% cpu 5:40:45.88 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20 t=Dictyostelium_discoideum.fna $(ls GCA_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=
MAPPED ERE.m=STAR_Aligned.sortedByCoord.out.bam

# braker 0.62s user 0.31s system 0% cpu 2:11:53.94 total
time annot-docker braker nice -19 braker.pl --species=Dictyostelium_discoideum.fna --genome=Dictyostelium_discoideum.fna --hints=hints_rnaseq.gff --prot_seq=$(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') --alternatives-from-evidence=true --cores=20 --softmasking --etpmode

# maker 10.26s user 6.35s system 0% cpu 9:45:04.13 total
time annot-docker maker nice -19 maker_annotation.sh -g Dictyostelium_discoideum.fna -p $(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') -e nr_transcripts.fasta -a nr_transcripts.gff3 -i hints_introns.gff -n 20

# eukannotpass 0.40s user 0.14s system 0% cpu 1:23:55.58 total
time nice -19 annot-docker eukannotpass eukannotpass -g *.fna -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs *.sqlite --numcpu 20
```

# arabidopsis
```
# braker 1.99s user 0.40s system 0% cpu 5:45:11.08 total
time annot-docker braker nice -19 braker.pl --species=Arabidopsis_thaliana --genome=Arabidopsis_thaliana.fna --hints=hints_rnaseq.gff --prot_seq=$(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') --alternatives-from-evidence=true --cores=20 --softmasking --etpmode

# gemoma 0.60s user 0.13s system 0% cpu 1:33:56.59 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20 t=Arabidopsis_thaliana.fna $(ls GCA_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=MAPPED ERE.
m=STAR_Aligned.sortedByCoord.out.bam

# maker

# eukannotpass
```

# chloropicon
```
# braker 0.85s user 0.15s system 0% cpu 1:58:27.49 total
time annot-docker braker nice -19 braker.pl --species=Chloropicon_primus --genome=Chloropicon_primus.fna --hints=hints_rnaseq.gff --prot_seq=$(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') --alternatives-from-evidence=true --cores=20 --softmasking --etpmode

# gemoma 5.82s user 0.35s system 0% cpu 17:13:26.44 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20 t=Chloropicon_primus.fna $(ls GC[AF]_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=MAPPED ERE.
m=STAR_Aligned.sortedByCoord.out.bam

# maker 6.38s user 4.82s system 0% cpu 9:05:22.34 total
time annot-docker maker nice -19 maker_annotation.sh -g Chloropicon_primus.fna -p $(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') -e nr_transcripts.fasta -a nr_transcripts.gff3 -i hints_introns.gff -n 20

# eukannotpass 2.34s user 0.94s system 0% cpu 8:02:30.30 total
time annot-docker eukannotpass nice -19 eukannotpass -g Chloropicon_primus.fna -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs *.sqlite --protist -n 20
```

# chlamydomonas
```
# gemoma 4.26s user 0.22s system 0% cpu 13:12:42.42 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20 t=Chlamydomonas_reinhardtii.fna $(ls GC[A-Z]_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=MAPPED ERE.
m=STAR_Aligned.sortedByCoord.out.bam

# braker 2.18s user 0.34s system 0% cpu 7:33:31.46 total
time annot-docker braker nice -19 braker.pl --species=Chlamydomonas_reinhardtii --genome=Chlamydomonas_reinhardtii.fna --hints=hints_rnaseq.gff --prot_seq=$(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') --alternatives-from-evidence=true --cores=20 --softmasking --etpmode

# eukannotpass 6.05s user 0.28s system 0% cpu 12:07:43.48 total
time annot-docker eukannotpass nice -19 eukannotpass -g *.fna -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs *.sqlite --numcpu 20

# maker 18.64s user 16.60s system 0% cpu 18:08:38.20 total
time annot-docker maker nice -19 maker_annotation.sh -g Chlamydomonas_reinhardtii.fna -p $(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') -e nr_transcripts.fasta -a nr_transcripts.gff3 -i hints_introns.gff -n 20
```

# ostreococcus
```
# braker 1.07s user 0.20s system 0% cpu 2:13:23.89 total
time annot-docker braker nice -19 braker.pl --species=Ostreococcus_lucimarinus --genome=Ostreococcus_lucimarinus.fna --hints=hints_rnaseq.gff --prot_seq=$(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') --alternatives-from-evidence=true --cores=20 --softmasking --etpmode

# maker 3.87s user 3.23s system 0% cpu 4:45:15.45 total
time annot-docker maker nice -19 maker_annotation.sh -g Ostreococcus_lucimarinus.fna -p $(ls GC*faa | tr '\n' ',' | sed 's/,$/\n/') -e nr_transcripts.fasta -a nr_transcripts.gff3 -i hints_introns.gff -n 20

# eukannotpass 2.53s user 0.14s system 0% cpu 5:20:19.04 total
time annot-docker eukannotpass nice -19 eukannotpass -g *.fna -p *faa -tf nr_transcripts.fasta -tg nr_transcripts.gff3 -r hints_rnaseq.gff --strand_specific_transcripts --utrs *.sqlite --numcpu 20

# gemoma 4.38s user 0.67s system 0% cpu 14:30:27.42 total
time annot-docker gemoma nice -19 java -jar /opt/gemoma-1.8/GeMoMa-1.8.jar CLI GeMoMaPipeline o=true GeMoMa.Score=ReAlign AnnotationFinalizer.r=NO AnnotationFinalizer.u=YES threads=20 t=Ostreococcus_lucimarinus.fna $(ls GC[AF]_00* | sed -r 's/\.(fna|gff|faa)$//; s/_(genomic|protein)//' | uniq | awk '{split($1, a, "."); print "s=own", "i="a[1], "g="$1"_genomic.fna", "a="$1"_genomic.gff"}' | tr '\n' ' ' | sed 's/ $/\n/') outdir=gemoma_out r=MAPPED ERE.m=STAR_Aligned.sortedByCoord.out.bam
```