Reads filtration change seq length + RF model update

CHANGELOG.md

@@ -0,0 +1,34 @@
+# Change Log
+All notable changes to this project will be documented in this file.
+
+### [1.2.0] - 2021-10-05
+
+### Changes
+- Changed default values of parameters:
+    - Phase 1: 
+        - Changed maximum_length_required from 12 to 14
+        - Calculate rpm by default unless using flag no_calculate_rpm
+    - Phase 2:
+        - Changed aln_cutoff from 20 to 24
+        - Changed pcc_cutoff from 0.6 to 0.7
+        - Changed threshold from 0.5 to 0.6
+        - Changed word_length from 2 to 4
+        - Changed discard from 1 to 4
+    - Phase 3:    
+        - Changed shuffles from 5 to 10
+        - Scanning with using rpm faa file unless using no_use_rpm_faa_scanning
+        - Log the hit sequences while scanning unless using no_output_sequences_scanning
+- Changed the position of stop machines AWS to be after create done file. 
+
+### Added
+- Added CHANGELOG file.
+
+### [1.1.0] - 2021-09-22
+
+### Added
+- Added new file - positive motifs: keep only positive motifs before the random forest.
+
+### [1.0.0] - 2021-08-01
+
+- 🎉 first stable release!
+

Dockerfile

@@ -25,6 +25,9 @@ WORKDIR /app
 COPY requirements.txt /app
 RUN python3 -m venv .venv && \
     . .venv/bin/activate && \
+    python -m pip install -U pip && \
+    pip install -U setuptools && \
+    pip install -U wheel && \
     pip install -r requirements.txt
 
 COPY . /app
@@ -38,5 +41,6 @@ RUN cd UnitePSSMs && \
     g++ *.cpp -std=c++11 -O3 -o tfidf
 
 ENV APP_FILE IgOmeProfiling_pipeline.py
+RUN chmod +x entrypoint.sh
 ENTRYPOINT ["./entrypoint.sh"]
 CMD ["-h"]

DockerfileWorker

@@ -1,3 +1,3 @@
 FROM webiks/igome-profile:latest
-
+RUN chmod +x worker_entrypoint.sh
 ENTRYPOINT ["./worker_entrypoint.sh"]

PSSM_score_Peptide/SEQ.cpp

@@ -53,11 +53,13 @@ string SEQ::getStringOfSeq(size_t pos) const {
 	return res;
 }
 
-SEQ::SEQ(string & SeqString, const string & SeqName, const double CopyNumber, alphabet& alph) :  _Seq_Name(SeqName), _CopyNumber(CopyNumber), _alph(alph) {
+SEQ::SEQ(string & SeqString, const string & SeqName, const double CopyNumber, alphabet& alph, bool isSetCopyNumber = true) :  _Seq_Name(SeqName), _CopyNumber(CopyNumber), _alph(alph) {
 	for (size_t k = 0; k < SeqString.length(); ++k) {
 		char i = SeqString.at(k);
 		_Seq.push_back(alph._alphabetMap[i]);
 	}
 	setSeq_Type();
-	setCopyNmber();
+	if (isSetCopyNumber) {
+		setCopyNmber();
+	}
 };

PSSM_score_Peptide/SEQ.h

@@ -21,7 +21,7 @@ class SEQ {
 		setSeq_Type();
 		setCopyNmber();
 	};
-	SEQ(string & SeqString, const string & SeqName, const double CopyNumber, alphabet& alph);
+	SEQ(string & SeqString, const string & SeqName, const double CopyNumber, alphabet& alph, bool isSetCopyNumber);
 
 	~SEQ(){};
 	void setName(const string name ){ _Seq_Name = name;}

PSSM_score_Peptide/computePSSM_cutoffs.cpp

@@ -10,12 +10,18 @@ computePSSM_cutoffs::computePSSM_cutoffs(vector<PSSM> & PSSM_array,
 	size_t TotalNumberOfRandoSeq,
 	alphabet& alph,
 	const string & CutofsPerPSSM_FileName,
-	int totalMemes) : 
+	int totalMemes,
+	double PercentOfRandomHitsPerPSSM,
+	int minLibraryLength,
+	int maxLibraryLength) : 
 	_PSSM_array(PSSM_array), 
 	_totalNumberOfRandoSeq(TotalNumberOfRandoSeq), 
 	_alph(alph), 
 	_CutofsPerPSSM_FileName(CutofsPerPSSM_FileName),
-	_totalMemes(totalMemes)
+	_totalMemes(totalMemes),
+	_PercentOfRandomHitsPerPSSM(PercentOfRandomHitsPerPSSM),
+	_minLibraryLength(minLibraryLength),
+	_maxLibraryLength(maxLibraryLength)
 {
 	generateRandomPeptides();
 	computecCutoffsBasedOnRandomPeptides();
@@ -31,7 +37,7 @@ void computePSSM_cutoffs::generateRandomPeptides() {
 	size_t NumberOfRandoSeq = _totalNumberOfRandoSeq;  
 	srand(931); // Set srand for generating random pepties // TODO set srand from input argument
 	map<string, randomPeptides>::iterator it = _randomPeptideDataSet.begin(); // use iteration and insert to add values to map
-	for (size_t length = 5; length <= 12; length++)
+	for (size_t length = _minLibraryLength; length <= _maxLibraryLength; length++)
 	{
 		randomPeptides tmp(_alph._aaFreq, NumberOfRandoSeq, length);
 		tmp.generateRandomSequences();
@@ -79,8 +85,7 @@ void computePSSM_cutoffs::computecCutoffsBasedOnRandomPeptides() {
 	// determin cutoff for each seq type and print to file
 	ofstream PSSM_Scores_Cutoff;
 	PSSM_Scores_Cutoff.open(_CutofsPerPSSM_FileName);
-
-	double PercentOfAcceptedPeptidesPerType = PercentOfRandomHitsPerPSSM / _totalMemes; // for each seq type the cutoff will be the percent of hits accepted for all PSSMs devided by the number of PSSMs
+	double PercentOfAcceptedPeptidesPerType = _PercentOfRandomHitsPerPSSM / _totalMemes; // for each seq type the cutoff will be the percent of hits accepted for all PSSMs devided by the number of PSSMs
 	for (size_t i = 0; i<_PSSM_array.size(); ++i)
 	{
 		PSSM_Scores_Cutoff << "###\t" << _PSSM_array[i].PSSM_name << "\t";

PSSM_score_Peptide/computePSSM_cutoffs.h

@@ -18,7 +18,10 @@ class computePSSM_cutoffs{
 						size_t TotalNumberOfRandoSeq,
 						alphabet & alph,
 						const string & CutofsPerPSSM_FileName,
-						int totalMemes);
+						int totalMemes,
+						double PercentOfRandomHitsPerPSSM,
+						int minLibraryLength, 
+						int maxLibraryLength);
 
 private:
 	void generateRandomPeptides();
@@ -31,9 +34,12 @@ class computePSSM_cutoffs{
 	//vector<char> const & _correspondingCharacters;
 	map<string, randomPeptides> _randomPeptideDataSet; // map between seqType and object containing the random peptides dataset
 	string const & _CutofsPerPSSM_FileName;
-	const double PercentOfRandomHitsPerPSSM = 0.05;
 	alphabet& _alph;
 	int _totalMemes;
+	double _PercentOfRandomHitsPerPSSM;
+	int _minLibraryLength; 
+	int _maxLibraryLength;
+