v1.2.4

Added a Percolator feature.
qzhang503 · Apr 24, 2023 · b3d4702 · b3d4702
1 parent d2ca103
commit b3d4702
Show file tree

Hide file tree

Showing 99 changed files with 1,589 additions and 717 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -24,6 +24,7 @@ Imports:
     data.table,
     digest,
     dplyr,
+    e1071,
     fastmatch,
     ggplot2,
     purrr,

diff --git a/R/batchMS2.R b/R/batchMS2.R
@@ -162,7 +162,7 @@ hbatch_ms2ions <- function (ms1_time = NULL, type_ms2ions = "by",
           c("gen_ms2ions_base", 
             "ms2ions_by_type", 
             "byions", "czions", "axions"), 
-          envir = environment(mzion:::gen_ms2ions_base)
+          envir = environment(mzion::matchMS)
         )
 
         ms2s <- parallel::clusterApply(
@@ -237,7 +237,7 @@ hbatch_ms2ions <- function (ms1_time = NULL, type_ms2ions = "by",
             "gen_ms2ions_base", 
             "ms2ions_by_type", 
             "byions", "czions", "axions"), 
-          envir = environment(mzion:::gen_ms2ions_a0_vnl0_fnl1)
+          envir = environment(mzion::matchMS)
         )
 
         ms2s <- parallel::clusterApply(
@@ -316,7 +316,7 @@ hbatch_ms2ions <- function (ms1_time = NULL, type_ms2ions = "by",
             "ms2ions_by_type", 
             "byions", "czions", "axions", 
             "add_hexcodes"), 
-          envir = environment(mzion:::gen_ms2ions_a1_vnl0_fnl0)
+          envir = environment(mzion::matchMS)
         )
 
         ms2s <- parallel::clusterApply(
@@ -395,7 +395,7 @@ hbatch_ms2ions <- function (ms1_time = NULL, type_ms2ions = "by",
             "ms2ions_by_type", 
             "byions", "czions", "axions", 
             "add_hexcodes_vnl2"), 
-          envir = environment(mzion:::gen_ms2ions_a1_vnl1_fnl0)
+          envir = environment(mzion::matchMS)
         )
 
         ms2s <- parallel::clusterApply(
@@ -475,7 +475,7 @@ hbatch_ms2ions <- function (ms1_time = NULL, type_ms2ions = "by",
             "ms2ions_by_type", 
             "byions", "czions", "axions", 
             "add_hexcodes_fnl2"), 
-          envir = environment(mzion:::gen_ms2ions_a1_vnl0_fnl1)
+          envir = environment(mzion::matchMS)
         )
 
         ms2s <- parallel::clusterApply(

diff --git a/R/bin_masses.R b/R/bin_masses.R
@@ -130,7 +130,7 @@ bin_ms1masses <- function (res = NULL, min_mass = 200L, max_mass = 4500L,
           "binTheoSeqs2", 
           "bin_theoseqs", 
           "find_ms1_cutpoints"), 
-        envir = environment(mzion:::binTheoSeqs_i))
+        envir = environment(mzion::matchMS))
 
       # No need of flatten() as saveRDS by INDIVIDUAL idx (and return NULL)
       parallel::clusterApplyLB(
@@ -320,7 +320,7 @@ binTheoSeqs <- function (idxes = NULL, res = NULL, min_mass = 200L,
   parallel::clusterExport(cl, list("qread", "qsave"), envir = environment(qs::qsave))
 
   parallel::clusterExport(cl, c("bin_theoseqs", "find_ms1_cutpoints"), 
-                          envir = environment(mzion:::bin_theoseqs))
+                          envir = environment(mzion::matchMS))
 
   out <- parallel::clusterMap(cl, bin_theoseqs, 
                               res, file.path(out_dir, out_nms), 

diff --git a/R/funs.R b/R/funs.R
@@ -18,9 +18,6 @@
 # $funs.R
 # character(0)
 # 
-# $hello.R
-# [1] "hello"
-# 
 # $ion_ladder.R
 #  [1] "ms2ions_by_type" "byions"          "czions"          "axions"          "bions_base"      "yions_base"     
 #  [7] "b2ions_base"     "bstarions"       "bstar2ions"      "b0ions"          "b02ions"         "y2ions"         
@@ -32,7 +29,7 @@
 #  [1] "mapMS2ions"             "match_mgf_path"         "match_raw_id"           "add_raw_ids"           
 #  [5] "find_secion_types"      "find_psm_rows"          "find_psm_rows1"         "find_psm_rows2"        
 #  [9] "find_theoexpt_pair"     "find_mgf_query"         "combine_prisec_matches" "check_existed_psms"    
-# [13] "get_mzion_coltypes"  
+# [13] "get_mzion_coltypes"    
 # 
 # $mgfs.R
 #  [1] "load_mgfs"          "readMGF"            "post_readmgf"       "readlineMGFs"       "  f"               
@@ -81,11 +78,14 @@
 # $msmsmatches2.R
 # [1] "ms2match"              "hcalc_tmtint"          "reverse_peps_in_frame" "reverse_seqs"          "calib_ms1masses"      
 # 
+# $mzion.R
+# character(0)
+# 
 # $mztab.R
 # [1] "make_mztab"
 # 
-# $mzion.R
-# character(0)
+# $percolator.R
+# [1] "creat_folds"        "cv_svm"             "perco_svm"          "probco_bypepcharge" "calc_z_pepfdr"     
 # 
 # $quant2.R
 #  [1] "calc_tmtint"        "add_rptrs"          "find_reporter_ints" "find_reporters_ppm" "msub_protpep"      
@@ -101,12 +101,13 @@
 #  [5] "calc_probi"             "scalc_pepprobs"         "calc_pepprobs_i"        "calc_pepscores"        
 #  [9] "find_decoy"             "find_targets"           "calcpepsc"              "add_primatches"        
 # [13] "collapse_vecs"          "post_pepscores"         "find_pepscore_co1"      "find_pepscore_co2"     
-# [17] "probco_bypeplen"        "find_optlens"           "find_probco_valley"     "calc_pepfdr"           
-# [21] "fill_probco_nas"        "fill_probs"             "post_pepfdr"            "calc_protfdr"          
-# [25] "aggr_prot_es"           "calc_protfdr_i"         "fit_protfdr"            "  f"                   
-# [29] "find_ppm_outer_bycombi" "match_ex2th2"           "calc_peploc"            "calcpeprank_1"         
-# [33] "calcpeprank_2"          "calcpeprank_3"          "find_chunkbreaks"       "findLocFracsDF"        
-# [37] "concatFracs"            "na.interp"              "is.constant"            "tsoutliers"            
+# [17] "probco_bypeplen"        "sub_td_byfdrtype"       "find_optlens"           "find_probco_valley"    
+# [21] "prep_pepfdr_td"         "keep_pepfdr_best"       "calc_pepfdr"            "fill_probco_nas"       
+# [25] "fill_probs"             "post_pepfdr"            "calc_protfdr"           "aggr_prot_es"          
+# [29] "calc_protfdr_i"         "fit_protfdr"            "  f"                    "find_ppm_outer_bycombi"
+# [33] "match_ex2th2"           "calc_peploc"            "calcpeprank_1"          "calcpeprank_2"         
+# [37] "calcpeprank_3"          "find_chunkbreaks"       "findLocFracsDF"         "concatFracs"           
+# [41] "na.interp"              "is.constant"            "tsoutliers"            
 # 
 # $silac.R
 # [1] "matchMS_silac_mix"   "matchMS_par_groups"  "add_fixedlab_masses" "matchMS_noenzyme"    "combine_ion_matches"

diff --git a/R/mgfs.R b/R/mgfs.R
@@ -469,7 +469,7 @@ read_mgf_chunks <- function (filepath = "~/mzion/mgf/temp_1",
       "index_mz", 
       "integerize_ms2ints", 
       "find_ms1_interval"), 
-    envir = environment(mzion:::proc_mgf_chunks)
+    envir = environment(mzion::matchMS)
   )
 
   out <- parallel::clusterApply(cl, file.path(filepath, filelist),

diff --git a/R/ms1_precursors.R b/R/ms1_precursors.R
@@ -351,7 +351,7 @@ calc_pepmasses2 <- function (aa_masses = NULL,
         c("hsemipeps_byprots", 
           "semipeps_byprots", 
           "calc_semipepmasses"), 
-        envir = environment(mzion:::calc_semipepmasses)
+        envir = environment(mzion::matchMS)
       )
 
       fwd_peps <- parallel::clusterApply(
@@ -383,7 +383,7 @@ calc_pepmasses2 <- function (aa_masses = NULL,
         "ct_counts", 
         "rm_char_in_nfirst", 
         "rm_char_in_nlast"), 
-      envir = environment(mzion:::distri_peps)
+      envir = environment(mzion::matchMS)
     )
 
     # aa_masses_all[[1]] is for the original all-fixed mode not for the coerced,
@@ -423,7 +423,7 @@ calc_pepmasses2 <- function (aa_masses = NULL,
     cl <- parallel::makeCluster(getOption("cl.cores", n_cores))
 
     parallel::clusterExport(cl, c("simple_prots_peps"), 
-                            envir = environment(mzion:::simple_prots_peps))
+                            envir = environment(mzion::matchMS))
 
     prps <- parallel::clusterApply(
       cl, 
@@ -538,7 +538,7 @@ calc_pepmasses2 <- function (aa_masses = NULL,
               "ms1_a0_vnl0_fnl1", 
               "expand_grid_rows", 
               "delta_ms1_a0_fnl1"), 
-            envir = environment(mzion:::ms1_a0_vnl0_fnl1))
+            envir = environment(mzion::matchMS))
 
           fwd_peps[[i]] <- parallel::clusterApply(
             cl, 
@@ -602,7 +602,7 @@ calc_pepmasses2 <- function (aa_masses = NULL,
           "expand_grid_rows", 
           "recur_flatten", 
           "delta_ms1_a0_fnl1"), 
-        envir = environment(mzion:::ms1_a1_vnl0_fnl0))
+        envir = environment(mzion::matchMS))
 
       for (i in inds) {
         amods_i <- amods[[i]]
@@ -1924,7 +1924,7 @@ split_fastaseqs <- function (fasta = NULL, enzyme = "trypsin_p",
     cl,
     c("make_fastapeps0", 
       "keep_n_misses"), 
-    envir = environment(mzion:::make_fastapeps0))
+    envir = environment(mzion::matchMS))
 
   # ---
   message("Splitting fasta sequences.")
@@ -2157,7 +2157,7 @@ split_fastaseqs_noenz <- function (fasta = NULL, acc_type = "uniprot_acc",
       "mmake_noenzpeps", 
       "hmake_noenzpeps", 
       "ms1masses_bare_noenz"), 
-    envir = environment(mzion:::make_noenzpeps))
+    envir = environment(mzion::matchMS))
 
   peps <- parallel::clusterApply(cl, chunksplit(fasta_db, n_cores), 
                                  mmake_noenzpeps, 
@@ -2657,7 +2657,7 @@ ms1masses_bare <- function (seqs = NULL, aa_masses = NULL, ftmass = NULL,
   cl <- parallel::makeCluster(getOption("cl.cores", n_cores))
 
   parallel::clusterExport(cl, c("roll_sum", "accumulate_char"), 
-                          envir = environment(mzion:::roll_sum))
+                          envir = environment(mzion::matchMS))
 
   ms_1 <- parallel::clusterApply(
     cl = cl, 
@@ -2775,7 +2775,7 @@ ms1masses_noterm <- function (aa_seqs, aa_masses, maxn_vmods_per_pep = 5L,
     c("calcms1mass_noterm", 
       "calcms1mass_noterm_byprot", 
       "calcms1mass_noterm_bypep"), 
-    envir = environment(mzion:::calcms1mass_noterm))
+    envir = environment(mzion::matchMS))
 
   out <- parallel::clusterApply(cl, aa_seqs, calcms1mass_noterm,
                                 aa_masses = aa_masses,

diff --git a/R/ms2_a0_vnl0_fnl1.R b/R/ms2_a0_vnl0_fnl1.R
@@ -41,6 +41,7 @@ ms2match_a0_vnl0_fnl1 <- function (i, aa_masses, ms1vmods, ms2vmods,
       "gen_ms2ions_a0_vnl0_fnl1", 
       "expand_grid_rows", 
       "gen_ms2ions_base", 
+      "calc_rev_ms2", 
       "ms2ions_by_type", 
       "byions", "czions", "axions", 
       "bions_base", "yions_base",
@@ -51,7 +52,7 @@ ms2match_a0_vnl0_fnl1 <- function (i, aa_masses, ms1vmods, ms2vmods,
       "fuzzy_match_one", 
       "fuzzy_match_one2", 
       "post_frame_adv"), 
-    envir = environment(mzion:::frames_adv)
+    envir = environment(mzion::matchMS)
   )
 
   out <- parallel::clusterMap(

diff --git a/R/ms2_a1_vnl0_fnl0.R b/R/ms2_a1_vnl0_fnl0.R
@@ -40,6 +40,7 @@ ms2match_a1_vnl0_fnl0 <- function (i, aa_masses, ms1vmods, ms2vmods,
     cl,
     c("frames_adv", 
       "gen_ms2ions_a1_vnl0_fnl0", 
+      "calc_rev_ms2", 
       "match_mvmods", 
       "expand_grid_rows", 
       "find_vmodscombi", 
@@ -63,7 +64,7 @@ ms2match_a1_vnl0_fnl0 <- function (i, aa_masses, ms1vmods, ms2vmods,
       "fuzzy_match_one", 
       "fuzzy_match_one2", 
       "post_frame_adv"), 
-    envir = environment(mzion:::frames_adv)
+    envir = environment(mzion::matchMS)
   )
 
   out <- parallel::clusterMap(

diff --git a/R/ms2_a1_vnl0_fnl1.R b/R/ms2_a1_vnl0_fnl1.R
@@ -46,6 +46,7 @@ ms2match_a1_vnl0_fnl1 <- function (i, aa_masses, ms1vmods, ms2vmods,
     c("frames_adv", 
       "gen_ms2ions_a1_vnl0_fnl1", 
       "gen_ms2ions_a1_vnl0_fnl0",
+      "calc_rev_ms2", 
       "match_mvmods", 
       "expand_grid_rows", 
       "find_vmodscombi", 
@@ -69,7 +70,7 @@ ms2match_a1_vnl0_fnl1 <- function (i, aa_masses, ms1vmods, ms2vmods,
       "fuzzy_match_one", 
       "fuzzy_match_one2", 
       "post_frame_adv"), 
-    envir = environment(mzion:::frames_adv)
+    envir = environment(mzion::matchMS)
   )
 
   out <- parallel::clusterMap(

diff --git a/R/ms2_a1_vnl1_fnl0.R b/R/ms2_a1_vnl1_fnl0.R
@@ -43,6 +43,7 @@ ms2match_a1_vnl1_fnl0 <- function (i, aa_masses, ms1vmods, ms2vmods,
     cl,
     c("frames_adv", 
       "gen_ms2ions_a1_vnl1_fnl0", 
+      "calc_rev_ms2", 
       "match_mvmods", 
       "expand_grid_rows", 
       "find_vmodscombi", 
@@ -66,7 +67,7 @@ ms2match_a1_vnl1_fnl0 <- function (i, aa_masses, ms1vmods, ms2vmods,
       "fuzzy_match_one", 
       "fuzzy_match_one2", 
       "post_frame_adv"), 
-    envir = environment(mzion:::frames_adv)
+    envir = environment(mzion::matchMS)
   )
 
   out <- parallel::clusterMap(

diff --git a/R/ms2_base.R b/R/ms2_base.R
@@ -51,6 +51,7 @@ ms2match_base <- function (i, aa_masses, ms1vmods, ms2vmods, ntmass, ctmass,
     cl,
     c("frames_adv", 
       "gen_ms2ions_base", 
+      "calc_rev_ms2", 
       "ms2ions_by_type", 
       "byions", "czions", "axions", 
       "bions_base", "yions_base",
@@ -61,7 +62,7 @@ ms2match_base <- function (i, aa_masses, ms1vmods, ms2vmods, ntmass, ctmass,
       "fuzzy_match_one", 
       "fuzzy_match_one2", 
       "post_frame_adv"), 
-    envir = environment(mzion:::frames_adv)
+    envir = environment(mzion::matchMS)
   )
 
   out <- parallel::clusterMap(