library( tidyverse )
ls()
Nerea_18S_V9_raw <- read_tsv( "Nerea_18S-V9_ASVs-90-blastout+taxa.tsv", col_types="ciiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiidciiiiiiidiccccccccc" )
problems( Nerea_18S_V9_raw )
Nerea_18S_V9_raw <- read_tsv( "Nerea_18S-V9_ASVs-90-blastout+taxa.tsv", col_types="ciiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiicdiiiiiiiddccccccccc" )
ATax_Sort  <- function( RT )
    group_by( RT, ASV ) %>%
    arrange( desc( BitScore ), by_group = TRUE ) %>%
    add_tally( n_distinct( Species, na.rm = TRUE ), name = "Sp_ab" ) %>%
    # N_RefSeqs not used for ranking alignments, kept just for info
    add_tally( n_distinct( Subj_ID, na.rm = TRUE ), name = "N_RefSeqs" ) %>%
    add_tally(  wt = n_distinct( keep( Subj_ID, Match >=97 ) ),  name = "N_RefSeqs97" ) %>% 
    slice_head() %>%
    arrange( desc( Total ) )
Gen_Sort  <- function( RT )
    group_by( RT, ASV ) %>%
    arrange( grepl( "X_sp[.]$", Species ), desc( BitScore ), by_group = TRUE ) %>%
    add_tally( n_distinct( Species, na.rm = TRUE ), name = "Sp_ab" ) %>%
    # N_RefSeqs not used for ranking alignments, kept just for info
    add_tally( n_distinct( Subj_ID, na.rm = TRUE ), name = "N_RefSeqs" ) %>%
    add_tally(  wt = n_distinct( keep( Subj_ID, Match >=97 ) ),  name = "N_RefSeqs97" ) %>% 
    slice_head() %>%
    arrange( desc( Total ) )
Sp_Sort  <- function( RT )
    group_by( RT, ASV ) %>%
    arrange( grepl( "X_sp[.]$", Species ), grepl( "_sp[.]$", Species ), desc( BitScore ), by_group = TRUE ) %>%
    add_tally( n_distinct( Species, na.rm = TRUE ), name = "Sp_ab" ) %>%
    # N_RefSeqs not used for ranking alignments, kept just for info
    add_tally( n_distinct( Subj_ID, na.rm = TRUE ), name = "N_RefSeqs" ) %>%
    add_tally(  wt = n_distinct( keep( Subj_ID, Match >=97 ) ),  name = "N_RefSeqs97" ) %>% 
    slice_head() %>%
    arrange( desc( Total ) )
ls
ls()
Gen_Sort
Nerea_18S_V9_GenSort <- Nerea_18S_V9_raw %>% Gen_Sort()
write_tsv( Nerea_18S_V9_GenSort, "Nerea_18S-V9_ASVs-90-GenSort.tsv" )
savehistory()
