#metgenome assembley and binning
nohup sickle pe -f qjj1_combined_R1.fastq.gz -r qjj1_combined_R1.fastq.gz -t sanger  -o trimmed_output_file1.fastq -p trimmed_output_file2.fastq -s trimmed_singles_file &
nohup spades.py --meta -k 21,33,55,77,99 -t 30  -m 1000 -1 trimmed_output_file1.fastq -2 trimmed_output_file2.fastq -o spades_results &
nohup seqkit seq --min-len 2500 scaffolds.fasta > 2500.fasta  &
nohup bowtie2-build 2500.fasta qjj1 &
nohup bowtie2 -p 50 -k 1 -N 1 -L 20 --reorder -x qjj1 -1 trimmed_output_file1.fastq -2 trimmed_output_file2.fastq  -S qjj1.sam  &
nohup samtools view -bS qjj1.sam > qjj1.bam &
nohup samtools sort qjj1.bam -o qjj1.sorted.bam &
nohup jgi_summarize_bam_contig_depths --outputDepth qjj1.depth.txt qjj1.sorted.bam  &
nohup metabat2 -i 2500.fasta -a qjj1.depth.txt --unbinned -t 10 -o bins_dir/bin  &
nohup checkm lineage_wf -f checkM.txt -t 10 -x fna --tmpdir ./ genome checkM &
nohup checkm qa -o 2 -f genome_checkM_GC.txt -t 10 --tmpdir ./ ./checkM/lineage.ms ./checkM &
nohup gtdbtk classify_wf --genome_dir genome --out_dir gtdb --cpus 30 &

#ressembly
nohup bbsplit.sh in=trimmed_output_file1.fastq in2=trimmed_output_file2.fastq ref=QJJ-5_bin.20.fasta basename=out_%_#.fq.gz outu=rest.fq.gz minratio=0.76 minhits=1 threads=30 &
nohup spades.py --careful -k 21,33,55,77,99,127 -t 30  -m 1000 -1 out_1.fq.gz -2 out_2.fq.gz -o spades_results &
seqkit seq --min-len 2500 scaffolds.fasta > QJJ-5_bin.20.fasta

#Gene prediction
nohup prodigal -i QJJ-5_bin.20.fasta -a QJJ-5_bin.20_pep -d QJJ-5_bin.20_cds -f gff -g 11 -o QJJ-5_bin.20_gff -p single -s QJJ-5_bin.20_stat &

#Tree
nohup perl MarkerScanner_RP_16.pl  QJJ-5_bin.20_pep &
nohup muscle -maxiters 100 -in marker.fasta -out marker.fasta.align -quiet &
nohup trimal -in marker.fasta.align -out marker.fasta.align.trimal.fa -gt 0.95 -cons 50 -htmlout marker.fasta.align.trimal.html &
nohup catfasta2phyml.pl -f --sequential --concatenate *.trimal.fa > genome_all.maker.fasta  &
nohup iqtree -s genome_all.maker.fasta -alrt 1000 -bb 1000 -nt AUTO &

#Gene cluster
nohup cd-hit -i rbcl.fasta -o rbcl_nonredu.fasta -c 0.95 -M 640000 -T 20 -n 5 -d 0 -aS 0.9 -g 1 &

#rRNA
nohup rnammer -S arc -multi -f QJJ-5_bin.20.rRNA.fasta -h QJJ-5_bin.20.rRNA.hmmreport -xml QJJ-5_bin.20.rRNA.xml -gff QJJ-5_bin.20.rRNA.gff2 ./QJJ-5_bin.20.fasta &


#tRNA
nohup tRNAscan-SE -A -o QJJ-5_bin.20.tRNA.out -f QJJ-5_bin.20.tRNA.ss -m QJJ-5_bin.20.tRNA.stat ./QJJ-5_bin.20.fasta &

#AAI
nohup comparem aai_wf  -c 20 ./genome aai &

#Evolutionary history analysis
ALEobserve gene.tree 1000
ALEml_undated species_tree gene.tree.ale sample=100  separators=\"_\""


#R code
library(pheatmap)
a = read.csv("01.csv", header = T ,row.names =1,quote="",encoding = "UTF-8")
pheatmap(a,cellwidth=4,cellheight=4,cluster_col = F,cluster_row= F,fontsize=4)

pheatmap(a,cellwidth=10,cellheight=10,cluster_col = F,cluster_row= F,fontsize=8,treeheight_row = 2,show_rownames= T,
         cutree_row=6,display_numbers = FALSE,
         col = cm.colors(256),
         clustering_distance_rows = "correlation",
)

library(ggplot2)
df= data.frame(bin=c("q5","q7","q9"),'relative_abundance'=c('0.779','1.278','1.473'),"aa"=c('0.5','1','1.5'))
ggplot(data=c,mapping=aes(x=group,y =num,fill=group))+
geom_bar(stat="identity",width=0.5)+theme(panel.grid =element_blank(), axis.title = element_blank())+
geom_text(aes(label =num , vjust = -0.8, hjust = 0.5, color = "black"), show.legend = TRUE)

library(ggplot2)
library(RColorBrewer)
library(reshape2)
b = read.csv("pi_stat.csv", header = T ,encoding = "UTF-8")
a=data_plot = melt(b)
Data1 = data.frame(Group = a$variable,Value = a$value)
ggplot(Data1,aes(x=Group,y=Value))+
stat_boxplot(geom = "errorbar",width=0.15,aes(color="black"))+ 
geom_boxplot(size=0.5,fill="white",outlier.fill="white",outlier.color="white")+ 
geom_jitter(aes(fill=Group),width =0.2,shape = 21,size=2.5)+
theme_bw()+ 
theme(legend.position="none", 
        axis.text.x=element_text(colour="black",family="Times",size=12),
        axis.text.y=element_text(family="Times",size=12,face="plain"),
        axis.title.y=element_text(family="Times",size = 12,face="plain"),
        axis.title.x=element_text(family="Times",size = 12,face="plain"),
        plot.title = element_text(family="Times",size=12,face="bold",hjust = 0.5), 
        panel.grid.major = element_blank(), 
        panel.grid.minor = element_blank())+
        ylab("Pi")+xlab("genome")+theme(axis.text.x = element_text(angle = 90, hjust = 0.1, vjust = 0.5))

library("reshape2")
c= read.csv("common_pidiff.KO.level2.out", header = T ,quote="",encoding = "UTF-8")
data=melt(c,id="func")
ggplot(data, aes(x=func, y=value,fill=variable)) + 
geom_bar(stat="identity",position = "stack")+theme(axis.text.x = element_text(angle = 90, hjust = 0.1, vjust = 0.5))+
theme(panel.background = element_blank(),
        panel.grid.major = element_line(colour = NA),
        panel.border = element_rect(colour="black",fill=NA),panel.grid =element_blank(),legend.position = 'none')

d= read.csv("unique.salt.KO.level2.out", header = T ,quote="",encoding = "UTF-8")
ggplot(data=d,mapping=aes(x=func,y =pi7))+
 geom_bar(stat="identity",width=0.5)+theme(axis.text.x = element_text(angle = 90, hjust = 0.1, vjust = 0.5))+
        theme(panel.background = element_blank(),
        panel.grid.major = element_line(colour = NA),
        panel.border = element_rect(colour="black",fill=NA),panel.grid =element_blank())

library(ggplot2)
library(gggenes)
pili <- read.csv("pili.txt",header = TRUE, sep = "\t")
ggplot(pili, aes(xmin = start, xmax = end, y = molecule, fill = gene,forward = direction)) +
        geom_gene_arrow() +
        facet_wrap(~ molecule, scales = 'free_x', ncol = 1) +
        scale_fill_brewer(palette = "Set3") +
        theme_genes()

library(ggplot2)
library(ggsci)
total = read.csv("pi.csv", header = T ,row.names =1,quote="",encoding = "UTF-8")
salt = read.csv("pi_salt.csv", header = T ,row.names =1,quote="",encoding = "UTF-8")
sea = read.csv("pi_sea.csv", header = T ,row.names =1,quote="",encoding = "UTF-8")
ggplot(sea, aes(x = pi , y =kda, colour = "00BFC4"))+ geom_point()+theme_bw()+
theme(plot.title = element_text(hjust = 0.5),
        title = element_text(size = 15,face = 'bold'),
        axis.text = element_text(size=12,face = 'bold'), 
        legend.text =element_text(size=12,face = 'bold'),  
        legend.title = element_blank(),                   
        legend.position = c(.92, .9),                    
        legend.margin = margin(6, 6, 6, 6),               
        legend.background = element_rect(size = 1, colour = 1))  

ggplot(total, aes(x = pi , y =kda, colour = sample))+ geom_point()+theme_bw()+
 theme(plot.title = element_text(hjust = 0.5),
        title = element_text(size = 15,face = 'bold'),
        axis.text = element_text(size=12,face = 'bold'), 
        legend.text =element_text(size=12,face = 'bold'),  
        legend.title = element_blank(),                    
        legend.position = c(.92, .9),                     
        legend.margin = margin(6, 6, 6, 6),                
        legend.background = element_rect(size = 1, colour = 1)) + 
        scale_discrete_manual(values=c("#00BFC4","#F8766D"),
                        aesthetics = 'colour',
                        labels = c("salt", 'sea')) +
                        scale_discrete_manual(values=c(12,18),
                        aesthetics = 'shape',
                        labels = c("salt", 'sea'))