From 3c21d7fc3c5f2b6810e9e2b267f9bfc9df4b1480 Mon Sep 17 00:00:00 2001
From: Laura Cook <l.cook2@student.unimelb.edu.au>
Date: Thu, 15 Oct 2020 10:57:47 +1100
Subject: [PATCH] added links to scripts for lastz ad repeak masker

---
 cross_species_comparison/README.md | 19 ++++++-------------
 1 file changed, 6 insertions(+), 13 deletions(-)

diff --git a/cross_species_comparison/README.md b/cross_species_comparison/README.md
index 85fefdc..73bb4e7 100644
--- a/cross_species_comparison/README.md
+++ b/cross_species_comparison/README.md
@@ -84,14 +84,15 @@ Run RepeatModeler to de novo find repeat regions in the dunnart genome:
 ```
 BuildDatabase -name dunnart -engine ncbi Scras_dunnart_assem1.0_pb-ont-illsr_flyeassem_red-rd-scfitr2_pil2xwgs2_60chr.fasta
 
-RepeatModeler -database dunnart
+nohup RepeatModeler -database dunnart -pa 20 >& repeatmodeler.out
 
 ```
 
-Run RepeatMasker to mask repeats in dunnart genome (makes repeats lowercase):
+Run RepeatMasker to mask repeats in dunnart genome (makes repeats lowercase). Run as an array for scaffolds to make it quicker.
+Create commands for array slurm script: `repeatMasker.sh`
 
 ```
-RepeatMasker -xsmall Scras_dunnart_assem1.0_pb-ont-illsr_flyeassem_red-rd-scfitr2_pil2xwgs2_60chr.fasta -default_search_engine hmmer -trf_prgm /home/lecook/.conda/envs/wga/bin/trf -hmmer_dir /home/lecook/.conda/envs/wga/bin/
+RepeatMasker -q -xsmall Scras_dunnart_assem1.0_pb-ont-illsr_flyeassem_red-rd-scfitr2_pil2xwgs2_60chr.fasta -default_search_engine hmmer -trf_prgm /home/lecook/.conda/envs/wga/bin/trf -hmmer_dir /home/lecook/.conda/envs/wga/bin/
 ```
 
 #### Split into scaffolds
@@ -125,17 +126,9 @@ To align placental mammals, we used previously determined lastz parameters (K =
 
 To align placental mammals, we used the lastz alignment parameters K = 2400, L = 3000, Y = 9400, H = 2000 and the lastz default scoring matrix, correspond- ing to parameter set 2 in Table 1. To align non-placental vertebrates, we used K = 2400, L = 3000, Y = 3400, H = 2000 and the HoxD55 scoring matrix. Citation: Increased alignment sensitivity improves the usage of genome alignments for comparative gene annotation. Nucleic Acids Res. 2017;45(14):8369–77.
 
-```
-TRA=($(for file in *.fa; do echo $file |cut -d "." -f 1;done))
-
-echo ${TRA[@]}
-
-for tr in ${TRA[@]};
+Create commands for running lastZ for all scaffolds: `lastz.sh`
+Run as an array on slurm: `array_wrapper.slurm`
 
-do
-
-echo lastz_32 /data/projects/punim0586/lecook/chipseq-pipeline/cross_species/data/genomes/mm10.fa[multi] /data/projects/punim0586/lecook/chipseq-pipeline/cross_species/data/genomes/smiCra1/${tr}.fa H=2000 K=2400 L=3000 Y=9400 --format=maf > /data/projects/punim0586/lecook/chipseq-pipeline/cross_species/data/genomes/${tr}_mm10.smiCra1.maf
-```
 
 #### Convert maf to axt-format
 
-- 
GitLab