LULU的使用~~

#先利用OTU序列建立参考数据库
makeblastdb -in OTU_sequences.fasta -parse_seqids -dbtype nucl
#OTU与参考数据库进行比对
blastn -db OTU_sequences.fasta -outfmt '6 qseqid sseqid pident' -out match_list.txt -qcov_hsp_perc 80 -perc_identity 84 -query OTU_sequences.fasta

vsearch --usearch_global OTU_sequences.fasta --db OTU_sequences.fasta --self --id .84 --iddef 1 --userout match_list.txt -userfields query+target+id --maxaccepts 0 --query_cov .9 --maxhits 10

#安装
library(devtools)
install_github("tobiasgf/lulu")  
#但是会报错
Error: Failed to install 'unknown package' from GitHub:
  invalid multibyte string, element 1

#原因是编码的问题。参考大神的方法：https://bbs.pinggu.org/thread-3640539-2-1.html
#默认的是中文编码
Sys.setlocale()
[1] "LC_COLLATE=Chinese (Simplified)_China.936;LC_CTYPE=Chinese (Simplified)_China.936;LC_MONETARY=Chinese (Simplified)_China.936;LC_NUMERIC=C;LC_TIME=Chinese (Simplified)_China.936"
#改成英文就行了
Sys.setlocale(category = "LC_ALL", locale = "us")
[1] "LC_COLLATE=English_United States.1252;LC_CTYPE=English_United States.1252;LC_MONETARY=English_United States.1252;LC_NUMERIC=C;LC_TIME=English_United States.1252"
#现在再运行install_github("tobiasgf/lulu") 就不会报错了。

#Usage
#lulu(otutable, matchlist, minimum_ratio_type = "min", minimum_ratio = 1,
#  minimum_match = 84, minimum_relative_cooccurence = 0.95)

#LULU
curated_result <- lulu(otutable_name, matchlist_name)
#原始的OTU表
curated_result$original_table
#提取curated的OTu表
curated_result$curated_table
#剩余的OTU个数
curated_result$curated_count
#丢弃的OTU个数
curated_result$discarded_count
#运行时间
curated_result$runtime
#查看OTU是如何map的
curated_result$otu_map