Tax4Fun2是一個(gè)基于16S rRNA數(shù)據(jù)集預(yù)測微生物群落功能的R包，是Tax4Fun的升級(jí)版本要拂。
其發(fā)布在Github項(xiàng)目bwemheu / Tax4Fun2下，目前已更新到Tax4Fun2 v1.1.6懂诗。
下面以自帶示例簡單學(xué)習(xí)一下它的使用過程：

1.下載绿淋、安裝和配置

#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)

#簡單配置
buildReferenceData(path_to_working_directory = ".")#構(gòu)建參考數(shù)據(jù)庫
buildDependencies(path_to_reference_data = "./Tax4Fun2_ReferenceData_v2")#安裝依賴程序blast
getExampleData(path_to_working_directory = ".")#下載并構(gòu)建 Tax4Fun2 測試數(shù)據(jù)

2.僅使用默認(rèn)參考數(shù)據(jù)進(jìn)行功能預(yù)測

####物種注釋####
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)

####預(yù)測群落功能####
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, #默認(rèn)，用參考數(shù)據(jù)庫中每個(gè)序列計(jì)算的16S rRNA拷貝數(shù)的平均值進(jìn)行歸一化
                         min_identity_to_reference = 0.97, 
                         normalize_pathways = FALSE)#默認(rèn)止毕，將把每個(gè)KO的相對(duì)豐度關(guān)聯(lián)到它所屬的每個(gè)路徑上
#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)#非默認(rèn)，將把每個(gè)KO的相對(duì)豐度平均分配到所有它所屬的路徑上漠趁。

3.使用默認(rèn)數(shù)據(jù)庫和用戶生成的數(shù)據(jù)庫進(jìn)行功能預(yù)測扁凛，需要自己從源文件構(gòu)建數(shù)據(jù)庫，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")

####為原核基因組分配功能####
# 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)

####生成參考數(shù)據(jù)（程序提供了 3 種方法）####
# 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)
#推薦選擇generateUserDataByClustering闯传，該命令包含一個(gè)uclust聚類步驟谨朝，可消除數(shù)據(jù)中的冗余

4.以非聚類方式進(jìn)行功能預(yù)測

####從上述3.2生成參考數(shù)據(jù)開始，以非聚類方式####
generateUserData(path_to_reference_data = "Tax4Fun2_ReferenceData_v2", 
                 path_to_user_data = "KELP_UserData", #指定用戶要自定義數(shù)據(jù)庫的數(shù)據(jù)源文件位置，是運(yùn)行第一步extractSSU和第二步assignFunction之后得到的字币，此處提供已經(jīng)運(yùn)行好的以節(jié)省運(yùn)行時(shí)間
                 name_of_user_data = "KELP1", #為您的數(shù)據(jù)庫提供一個(gè)名稱
                 SSU_file_extension = ".ffn", #運(yùn)行第一步extractSSU后得到
                 KEGG_file_extension = ".txt")#運(yùn)行第二步assignFunction后得到

####物種注釋####
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")

####預(yù)測群落功能####
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聚類方式進(jìn)行功能預(yù)測

####從上述3.3生成參考數(shù)據(jù)開始则披，以Vsearch聚類方式####
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對(duì)提取的SSU序列進(jìn)行聚類

####物種注釋####
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")

####預(yù)測群落功能####
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.計(jì)算（多）功能冗余指數(shù)（實(shí)驗(yàn)性功能）

計(jì)算KEGG功能的系統(tǒng)發(fā)育分布（高FRI->高冗余度，低FRI->低冗余度洗出，可能會(huì)隨著群落變化而丟失）

####物種注釋####
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)

####計(jì)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)#自定義prevalence_cutoff值士复，此截止值用于將功能配置文件轉(zhuǎn)換為二元向量（功能x存在或者不存在）

PS：感覺學(xué)到2就夠日常使用了