Tax4Fun2是一个基于16S rRNA数据集预测微生物群落功能的R包,是Tax4Fun的升级版本。
其发布在Github项目bwemheu / Tax4Fun2下,目前已更新到Tax4Fun2 v1.1.6。
下面以自带示例简单学习一下它的使用过程:
1.下载、安装和配置
#shell
wget https://github.com/bwemheu/Tax4Fun2/releases/download/v1.1.6/Tax4Fun2_1.1.6.tar.gz
#R
install.packages(pkgs = "Tax4Fun2_1.1.6.tar.gz", repos = NULL, source = TRUE)
library(Tax4Fun2)
#简单配置
buildReferenceData(path_to_working_directory = ".")#构建参考数据库
buildDependencies(path_to_reference_data = "./Tax4Fun2_ReferenceData_v2")#安装依赖程序blast
getExampleData(path_to_working_directory = ".")#下载并构建 Tax4Fun2 测试数据
2.仅使用默认参考数据进行功能预测
####物种注释####
runRefBlast(path_to_otus = 'KELP_otus.fasta',
path_to_reference_data = './Tax4Fun2_ReferenceData_v2',
path_to_temp_folder = 'Kelp_Ref99NR',
database_mode = 'Ref99NR',
use_force = TRUE,
num_threads = 4)
####预测群落功能####
makeFunctionalPrediction(path_to_otu_table = 'KELP_otu_table.txt',
path_to_reference_data = './Tax4Fun2_ReferenceData_v2',
path_to_temp_folder = 'Kelp_Ref99NR',
database_mode = 'Ref99NR',
normalize_by_copy_number = TRUE, #默认,用参考数据库中每个序列计算的16S rRNA拷贝数的平均值进行归一化
min_identity_to_reference = 0.97,
normalize_pathways = FALSE)#默认,将把每个KO的相对丰度关联到它所属的每个路径上
#或者
makeFunctionalPrediction(path_to_otu_table = 'KELP_otu_table.txt',
path_to_reference_data = './Tax4Fun2_ReferenceData_v2',
path_to_temp_folder = 'Kelp_Ref99NR',
database_mode = 'Ref99NR',
normalize_by_copy_number = TRUE,
min_identity_to_reference = 0.97,
normalize_pathways = TRUE)#非默认,将把每个KO的相对丰度平均分配到所有它所属的路径上。
3.使用默认数据库和用户生成的数据库进行功能预测,需要自己从源文件构建数据库,一共需要三步
####提取SSU序列####
# 1.1 Extracting SSU sequences from a single genome
extractSSU(genome_file = "OneProkaryoticGenome.fasta", file_extension = "fasta",
path_to_reference_data = "Tax4Fun2_ReferenceData_v2")
# 1.1 Extracting SSU sequences from multiple genomes
extractSSU(genome_folder = "MoreProkaryoticGenomes", file_extension = "fasta",
path_to_reference_data = "Tax4Fun2_ReferenceData_v2")
####为原核基因组分配功能####
# 2.1 Assigning function to a single genome
assignFunction(genome_file = "OneProkaryoticGenome.fasta", file_extension = "fasta",
path_to_reference_data = "Tax4Fun2_ReferenceData_v2", num_of_threads = 8, fast = TRUE)
# 2.2 Assigning function to multiple genomes
assignFunction(genome_folder = "MoreProkaryoticGenomes/", file_extension = "fasta",
path_to_reference_data = "Tax4Fun2_ReferenceData_v2", num_of_threads = 1, fast = TRUE)
####生成参考数据(程序提供了 3 种方法)####
# 3.1 Generate user-defined reference data without uclust from a single genome
generateUserData(path_to_reference_data = './Tax4Fun2_ReferenceData_v2', path_to_user_data = '.',
name_of_user_data = 'User_Ref0', SSU_file_extension = '_16SrRNA.ffn', KEGG_file_extension = '_funPro.txt')
# 3.2 Generate user-defined reference data without uclust
generateUserData(path_to_reference_data = './Tax4Fun2_ReferenceData_v2', path_to_user_data = 'MoreProkaryoticGenomes',
name_of_user_data = 'User_Ref1', SSU_file_extension = '_16SrRNA.ffn', KEGG_file_extension = '_funPro.txt')
# 3.3 Generate user-defined reference data with uclust
generateUserDataByClustering(path_to_reference_data = './Tax4Fun2_ReferenceData_v2', path_to_user_data = 'MoreProkaryoticGenomes',
name_of_user_data = 'User_Ref2', SSU_file_extension = '_16SrRNA.ffn', KEGG_file_extension = '_funPro.txt', use_force = TRUE)
#推荐选择generateUserDataByClustering,该命令包含一个uclust聚类步骤,可消除数据中的冗余
4.以非聚类方式进行功能预测
####从上述3.2生成参考数据开始,以非聚类方式####
generateUserData(path_to_reference_data = "Tax4Fun2_ReferenceData_v2",
path_to_user_data = "KELP_UserData", #指定用户要自定义数据库的数据源文件位置,是运行第一步extractSSU和第二步assignFunction之后得到的,此处提供已经运行好的以节省运行时间
name_of_user_data = "KELP1", #为您的数据库提供一个名称
SSU_file_extension = ".ffn", #运行第一步extractSSU后得到
KEGG_file_extension = ".txt")#运行第二步assignFunction后得到
####物种注释####
runRefBlast(path_to_otus = "KELP_otus.fasta",
path_to_reference_data = "Tax4Fun2_ReferenceData_v2",
path_to_temp_folder = "Kelp_Ref99NR_withUser1",
database_mode = "Ref99NR",
use_force = T,
num_threads = 6,
include_user_data = T, path_to_user_data = "KELP_UserData", name_of_user_data = "KELP1")
####预测群落功能####
makeFunctionalPrediction(path_to_otu_table = "KELP_otu_table.txt",
path_to_reference_data = "Tax4Fun2_ReferenceData_v2",
path_to_temp_folder = "Kelp_Ref99NR_withUser1",
database_mode = "Ref99NR",
normalize_by_copy_number = T,
min_identity_to_reference = 0.97,
normalize_pathways = F,
include_user_data = T, path_to_user_data = "KELP_UserData", name_of_user_data = "KELP1")
5.以Vsearch聚类方式进行功能预测
####从上述3.3生成参考数据开始,以Vsearch聚类方式####
generateUserDataByClustering(path_to_reference_data = "Tax4Fun2_ReferenceData_v2",
path_to_user_data = "KELP_UserData",
name_of_user_data = "KELP2",
SSU_file_extension = ".ffn",
KEGG_file_extension = ".txt",
similarity_threshold = 0.99)#使用uclust对提取的SSU序列进行聚类
####物种注释####
runRefBlast(path_to_otus = "KELP_otus.fasta",
path_to_reference_data = "Tax4Fun2_ReferenceData_v2",
path_to_temp_folder = "Kelp_Ref99NR_withUser2",
database_mode = "Ref99NR",
use_force = T,
num_threads = 6,
include_user_data = T, path_to_user_data = "KELP_UserData", name_of_user_data = "KELP2")
####预测群落功能####
makeFunctionalPrediction(path_to_otu_table = "KELP_otu_table.txt",
path_to_reference_data = "Tax4Fun2_ReferenceData_v2",
path_to_temp_folder = "Kelp_Ref99NR_withUser2",
database_mode = "Ref99NR",
normalize_by_copy_number = T,
min_identity_to_reference = 0.97,
normalize_pathways = F,
include_user_data = T, path_to_user_data = "KELP_UserData", name_of_user_data = "KELP2")
6.计算(多)功能冗余指数(实验性功能)
计算KEGG功能的系统发育分布(高FRI->高冗余度,低FRI->低冗余度,可能会随着群落变化而丢失)
####物种注释####
runRefBlast(path_to_otus = "Water_otus.fna",
path_to_reference_data = "Tax4Fun2_ReferenceData_v2",
path_to_temp_folder = "Water_Ref99NR",
database_mode = "Ref99NR",
use_force = T,
num_threads = 6)
####计算functional redundancy indices(FRI)####
calculateFunctionalRedundancy(path_to_otu_table = "Water_otu_table.txt",
path_to_reference_data = "Tax4Fun2_ReferenceData_v2",
path_to_temp_folder = "Water_Ref99NR",
database_mode = "Ref99NR",
min_identity_to_reference = 0.97)
#或者
calculateFunctionalRedundancy(path_to_otu_table = "Water_otu_table.txt",
path_to_reference_data = "Tax4Fun2_ReferenceData_v2",
path_to_temp_folder = "Water_Ref99NR",
database_mode = "Ref99NR",
min_identity_to_reference = 0.97,
prevalence_cutoff = 1.0)#自定义prevalence_cutoff值,此截止值用于将功能配置文件转换为二元向量(功能x存在或者不存在)
PS:感觉学到2就够日常使用了