Updated DNACLUST

Author: hsmurali

Environment.yml

@@ -8,3 +8,4 @@ dependencies:
  - seqkit=0.16.0
  - pandas=1.2.4
  - numpy=1.20.2
+ - gxx>=9

Experiments/Summarize_Findings/Comparing Mode to Length for Choice of Centroids.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -56,7 +56,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -73,6 +73,8 @@
     }
    ],
    "source": [
+    "plt.rcParams.update(rcParams)\n",
+    "\n",
     "fig,ax = plt.subplots(1,1, figsize = (16,10))\n",
     "ax.plot(np.cumsum(df_mode_summary['Seq_Counts']), linewidth = 5, label = 'SCRAPT + Mode')\n",
     "ax.plot(np.cumsum(df_length_summary['Seq_Counts']), linewidth = 5, label = 'SCRAPT + Length')\n",
@@ -81,12 +83,13 @@
     "ax.yaxis.set_major_formatter(mtick.FuncFormatter(g))\n",
     "ax.legend()\n",
     "ax.legend(loc=4, frameon = False)\n",
-    "fig.tight_layout()"
+    "fig.tight_layout()\n",
+    "fig.savefig('/Users/harihara/Research-Activities/Plots/Iterative_Clustering/Len_vs_Mode_cum_seq.pdf')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -116,7 +119,8 @@
     "ax.set_ylabel('Total number of sequences from \\n'+r'clusters of size $\\geq$ x')\n",
     "ax.set_xlabel('x: Cluster size (% total number of sequences, N = '+str(n)+\n",
     "              ')\\n Ordered from the largest to the smallest')\n",
-    "fig.tight_layout()"
+    "fig.tight_layout()\n",
+    "fig.savefig('/Users/harihara/Research-Activities/Plots/Iterative_Clustering/Len_vs_Mode_frag.pdf')"
    ]
   },
   {

Experiments/Summarize_Findings/Make_Charts_Clustering.ipynb

@@ -0,0 +1,34 @@
+#PROFILE_FLAGS = -pg -fprofile-arcs -ftest-coverage -g -O1
+CXXFLAGS = -Wall -std=c++17 -pedantic -O2 -static 
+CXX = g++
+#I/fs/cbcb-software/RedHat-7-x86_64/users/hsmurali/venvs/SCRAPT/include
+
+all: dnaclust fastaselect fastasort clean
+
+dnaclust: dnaclust.o fasta.o
+	$(CXX) $(CXXFLAGS) $(PROFILE_FLAGS) dnaclust.o fasta.o -o $@ -lpthread 
+
+dnaclust.o: src/dnaclust.cpp src/search_include.cpp src/utility.hpp src/ternary_sort.hpp src/multi_dim.hpp
+	$(CXX) -c $(CXXFLAGS) $(PROFILE_FLAGS) src/dnaclust.cpp
+
+fastaselect: fastaselect.o fasta.o
+	$(CXX) $(CXXFLAGS) $(PROFILE_FLAGS) fastaselect.o fasta.o -o $@
+
+fastaselect.o: src/fastaselect.cpp
+	$(CXX) -c $(CXXFLAGS) $(PROFILE_FLAGS) src/fastaselect.cpp
+
+fastasort: fastasort.o fasta.o
+	$(CXX) $(CXXFLAGS) $(PROFILE_FLAGS) $+ -o $@
+
+fastasort.o: src/fastasort.cpp
+	$(CXX) -c $(CXXFLAGS) $(PROFILE_FLAGS) $+ -o $@
+
+fasta.o: src/fasta.cpp src/fasta.hpp
+	$(CXX) -c $(CXXFLAGS) src/fasta.cpp
+
+clean:
+	mkdir bin
+	mv dnaclust bin/
+	mv fastaselect bin/
+	mv fastasort bin/
+	rm *.o