From e4d973703c22071fa6062ff07974f2c6224c3e7f Mon Sep 17 00:00:00 2001
From: junikimm717 <junikimm717@gmail.com>
Date: Wed, 14 Jul 2021 14:01:45 -0400
Subject: [PATCH] print results

---
 specification.md | 10 ++++++++
 src/script.def.R | 60 +++++++++++++++++++++++++++++++++---------------
 2 files changed, 51 insertions(+), 19 deletions(-)

diff --git a/specification.md b/specification.md
index ddc03f7..cc3103a 100644
--- a/specification.md
+++ b/specification.md
@@ -24,6 +24,7 @@ isotopes.
 
 - Independent of the ordering (it might get corrupted)
 - Just search for chlorinated/brominated compounds.
+- Use intensity + relative abundances that `isos` shows.
 - usually, use_charges will be 1
 - Headers to use in script.
 
@@ -59,3 +60,12 @@ isotopes.
 - Forseeable future, adapt to different isotopes.
 - Capture multiple outputs of different isotopes.
 
+## Data Summary
+
+- Flags for certainty of halogenated compounds
+
+# Test Notes
+
+- mztol seems to have a big impact on chlorine/bromine positives.
+
+
diff --git a/src/script.def.R b/src/script.def.R
index 93bf9dd..2e2ab29 100644
--- a/src/script.def.R
+++ b/src/script.def.R
@@ -1,27 +1,33 @@
 library("nontarget")
 library("purrr")
-#library("funprog")
 library("enviPat")
 library("stringr")
 library("parallel")
 
 # Configurations #############################################################
 # file : decides which file to read in data from #############################
-file <- "path/to/file"
+file <- "/home/junikim/programming/patternmatch/data/allcluster_mz.csv"
+#file <- "/home/junikim/programming/patternmatch/data/15_Clusters_for_Tuning_29June21.txt"
 
 # check cluster 2846
 
-search_isos <- c("13C", "37Cl")
+search_isos <- c("37Cl", "81Br")
 
 
 # Minimum size of a cluster
 
-min_cluster_size <- 3
+min_cluster_size <- 2
 
 # Number of cores to be used (will be adjusted if not possible)
-use_cores <- 6 ##############################################################################
+use_cores <- 6
+
+# Do not edit below.
+iso_length <- length(search_isos)
+if (!("13C" %in% search_isos)) {
+    search_isos <- append(search_isos, "13C")
+}
 # Read in the Table ##########################################################
-table <- read.table(file, header=TRUE, sep="\t")
+table <- read.table(file, header=TRUE, sep=",")
 
 # Organize the tables by number ##############################################
 fragments <- max(table[,"Spectra_Number"])
@@ -68,40 +74,56 @@ getdataframe <- function (fragment) {
     mz <- getdata(fragment, "mz")
     time <- getdata(fragment, "time")
     Intensity <- getdata(fragment, "Intensity")
-    return(data.frame(mz=mz, time=time, Intensity=Intensity))
+    return(data.frame(mz=mz, Intensity=Intensity,time=time))
 }
 
-# Incomplete: cannot get pattern.search function to work per cluster. #########
-# Incomplete: Get the diagnostics for a cluster and turn them into a portable#
-# format. (such as through tidyverse) ########################################
-
+# initialize isotopes.
+data(isotopes)
 isos <- make.isos(isotopes,use_isotopes=search_isos, 
                   use_charges=rep(1, length(search_isos)))
 
+# returns both pattern.search result and fragment number.
 diagnostics <- function(fragment) {
     points <- getdataframe(fragment)
     ptrn <- pattern.search(
         points,
         isos,
-        cutint=100000,
-        rttol=c(-0.2,0.2),
-        mztol=1000,
-        mzfrac=1.0,
+        cutint=1000,
+        rttol=c(-20,20),
+        # kept because of gc limitations.
+        mztol=3,
+        mzfrac=0.1,
         ppm=TRUE,
-        inttol=0.2,
+        inttol=0.05,
         # Do not modify anything below.
-        rules=rep(FALSE, 11),
+        rules=rep(TRUE,11),
+        #rules=c(TRUE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, TRUE, FALSE, FALSE, FALSE),
         deter=FALSE,
         entry=50
     );
-    return(ptrn)
+    return(c(ptrn, fragment))
 }
 
 use <- Filter(function(x) usable[x], 1:fragments)
 
 results <- mclapply(use, diagnostics, mc.cores=use_cores)
 
+handle_res <- function(result) {
+    allzero <- function(v) {
+        for (x in v) {
+            if (x != 0)
+                return (FALSE)
+        }
+        return (TRUE)
+    }
+    v <- result$`Counts of isotopes`[seq(1,iso_length),"peak counts"]
+    if (!allzero(v)) {
+        print(result[[13]])
+    }
+}
 
-# Incomplete: Make the analysis more resiliant to different sorting.
+for (result in results) {
+    handle_res(result)
+}
 
 ##############################################################################