mimseq - npm Package Compare versions

Comparing version 1.3.7 to 1.3.8

mimseq.egg-info/PKG-INFO

 Metadata-Version: 2.1
 Name: mimseq
-Version: 1.3.7
+Version: 1.3.8
 Summary: Custom high-throughput tRNA sequencing alignment and quantification pipeline based on modification induced misincorporation cDNA synthesis.
@@ -5,0 +5,0 @@ Home-page: https://github.com/nedialkova-lab/mim-tRNAseq

mimseq.egg-info/requires.txt

@@ -9,2 +9,3 @@ biopython
 pybedtools
+requests
 statsmodels

mimseq.egg-info/SOURCES.txt

@@ -32,3 +32,2 @@ LICENSE.txt
 mimseq/data/modomics
-mimseq/data/modomics_orig
 mimseq/data/tRNAmatureseq.cm
@@ -35,0 +34,0 @@ mimseq/data/araTha1-eColitK/FastaHeadersforMimseq.py

mimseq/mimseq.py

@@ -97,8 +97,5 @@ #! /usr/bin/env python3
 	map_round = 1 #first round of mapping
-
 	# Parse tRNA and modifications, generate SNP index
-	modifications = os.path.dirname(os.path.realpath(__file__))
-	modifications += "/modifications"
 	coverage_bed, snp_tolerance, mismatch_dict, insert_dict, del_dict, mod_lists, Inosine_lists, Inosine_clusters, tRNA_dict, cluster_dict, cluster_perPos_mismatchMembers \
-	= modsToSNPIndex(trnas, trnaout, mito_trnas, plastid_trnas, modifications, name, out, double_cca, threads, snp_tolerance, cluster, cluster_id, posttrans, pretrnas, local_mod)
+	= modsToSNPIndex(gtRNAdb = trnas, tRNAscan_out = trnaout, mitotRNAs = mito_trnas, plastidtRNAs = plastid_trnas, experiment_name = name, out_dir = out, double_cca = double_cca, threads = threads, snp_tolerance = snp_tolerance, cluster = cluster, cluster_id = cluster_id, posttrans_mod_off = posttrans, pretrnas = pretrnas, local_mod = local_mod)
 	structureParser()
@@ -105,0 +102,0 @@ # Generate GSNAP indices

mimseq/tRNAtools.py

@@ -31,7 +31,8 @@ #!/usr/bin/env python3
 
-def tRNAparser (gtRNAdb, tRNAscan_out, mitotRNAs, plastidtRNAs, modifications_table, posttrans_mod_off, double_cca, pretrnas, local_mod):
+def tRNAparser (gtRNAdb, tRNAscan_out, mitotRNAs, plastidtRNAs, posttrans_mod_off, double_cca, pretrnas, local_mod):
 # tRNA sequence files parser and dictionary building
 
 	# Generate modification reference table
-	modifications = modificationParser(modifications_table)
+	modifications_file, fetch = getModifications(local_mod)
+	modifications = modificationParser(modifications_file, fetch)
 	temp_name = gtRNAdb.split("/")[-1]
@@ -218,3 +219,3 @@
 def getModomics(local_mod):
-	# Get full Modomics modified tRNA data from web
+	# Get full Modomics modified tRNA data from API
 	fetch = False
@@ -230,16 +231,136 @@ if not local_mod:
 			log.error("Unable to connect to Modomics database! HTTP error: {}. Check status of Modomics webpage. Using local Modomics files...".format(http_err))
-			modomics_path = os.path.dirname(os.path.realpath(__file__)) + '/data/modomics'
-			modomics = open(modomics_path, "r+", encoding = "utf-8")
+			modomics = openLocalModomics('/data/modomics')
 		except Exception as err:
 			log.error("Error in connecting to Modomics: {}. Using local Modomics files...".format(err))
-			modomics_path = os.path.dirname(os.path.realpath(__file__)) + '/data/modomics'
-			modomics = open(modomics_path, "r+", encoding = "utf-8")
+			modomics = openLocalModomics('/data/modomics')
 	else:
 		log.warning("Retrieval of Modomics database disabled. Using local files instead...")
-		modomics_path = os.path.dirname(os.path.realpath(__file__)) + '/data/modomics'
-		modomics = open(modomics_path, "r+", encoding = "utf-8")
+		modomics = openLocalModomics('/data/modomics')
 
 	return modomics, fetch
 
-def modsToSNPIndex(gtRNAdb, tRNAscan_out, mitotRNAs, plastidtRNAs, modifications_table, experiment_name, out_dir, double_cca, threads, snp_tolerance = False, cluster = False, cluster_id = 0.95, posttrans_mod_off = False, pretrnas = False, local_mod = False, search='usearch'):
+def openLocalModomics(filepath):
+	# Open the local modomics file for reading
+	modomics_path = os.path.dirname(os.path.realpath(__file__)) + filepath
+	modomics = open(modomics_path, "r", encoding = "utf-8")
+	return modomics
+	
+def getModifications(local_mod):
+	# Get modification lookup table from Modomics via API
+	fetch = False
+	if not local_mod:
+		try:
+			response = requests.get("https://www.genesilico.pl/modomics/api/modifications")
+			response.raise_for_status()
+			modifications = response.json()
+			fetch = True
+			log.info("Modification table retrieved...")
+		except HTTPError as http_err:
+			log.error("Unable to connect to Modomics database! HTTP error: {}. Check status of Modomics webpage. Using local Modomics files...".format(http_err))
+			modifications = openLocalModomics('/modifications')
+		except Exception as err:
+			log.error("Error in connecting to Modomics: {}. Using local Modomics files...".format(err))
+			modifications = openLocalModomics('/modifications')
+	else:
+		log.warning("Retrieval of Modomics database disabled. Using local files instead...")
+		modifications = openLocalModomics('/modifications')
+
+	return modifications, fetch
+
+def modificationParser(modifications_table, fetch):
+	# Read in modifications and build dictionary
+
+	modifications = {}
+
+	if fetch:
+		log.info("Parsing Modification JSON data...")
+		for data in modifications_table.values():
+			modifications[data["abbrev"].strip()] = {'name':data["name"].strip(), 'abbr':data["short_name"].strip(), 'ref':data["reference_moiety"][0].strip()}
+		
+	elif not fetch:
+		log.info("Parsing local Modification data...")
+		for line in modifications_table:
+			if not line.startswith("#"):
+				name, abbr, ref, mod = line.split('\t')
+				# replace unknown modifications with reference of N
+				if not ref or ref.isspace():
+					ref = 'N'
+				if mod and not mod.isspace():
+					modifications[mod.strip()] = {'name':name.strip(), 'abbr':abbr.strip(), 'ref':ref.strip()}
+
+	return(modifications)
+
+def getUnmodSeq(seq, modification_table):
+# Change modified bases into standard ACGT in input sequence
+
+	new_seq = []
+	for char in seq:
+		# for insertions ('_') make reference N - this is not described in the modifications table
+		if char == '_':
+			char = 'N'
+		else:
+			char = modification_table[char]['ref']
+			# Change queuosine to G (reference is preQ0base in modification file)
+			if char == 'preQ0base':
+				char = 'G'
+
+		new_seq.append(char)
+
+	new_seq = ''.join(new_seq)
+	new_seq = new_seq.replace('U','T')
+	return(new_seq)
+
+def initIntronDict(tRNAscan_out):
+# Build dictionary of intron locations
+
+	Intron_dict = {}
+	tRNAscan = open(tRNAscan_out, 'r')
+	intron_count = 0
+	for line in tRNAscan:
+		if not line.startswith(("Sequence", "Name", "-")):
+			tRNA_ID = line.split()[0] + ".trna" + line.split()[1]
+			tRNA_start = int(line.split()[2])
+			intron_start = int(line.split()[6])
+			intron_stop = int(line.split()[7])
+			# if inton boundaries are not 0, i.e. there is an intron then add to dict
+			if (intron_start > 0) & (intron_stop > 0):
+				if tRNA_start > intron_start: # tRNA is on reverse strand
+					intron_count += 1
+					intron_start = tRNA_start - intron_start
+					intron_stop = tRNA_start - intron_stop + 1 # needed for python 0 indexing and correct slicing of intron
+				else: # tRNA is on forward strand
+					intron_count += 1
+					intron_start -= tRNA_start
+					intron_stop -= tRNA_start
+					intron_stop += 1 # python 0 indexing
+
+				Intron_dict[tRNA_ID] = {}
+				Intron_dict[tRNA_ID]['intron_start'] = intron_start
+				Intron_dict[tRNA_ID]['intron_stop'] = intron_stop
+
+	log.info("{} introns registered...".format(intron_count))
+	return(Intron_dict)
+
+
+def intronRemover (Intron_dict, seqIO_dict, seqIO_record, posttrans_mod_off, double_cca):
+# Use Intron_dict to find and remove introns plus add CCA and 5' G for His (if eukaryotic)
+
+	# Find a match, slice intron and add G and CCA
+	ID = re.search("tRNAscan-SE ID: (.*?)\).|\((chr.*?)-",seqIO_dict[seqIO_record].description).groups()
+	ID = list(filter(None, ID))[0]
+	if ID in Intron_dict:
+		seq = str(seqIO_dict[seqIO_record].seq[:Intron_dict[ID]['intron_start']] + seqIO_dict[seqIO_record].seq[Intron_dict[ID]['intron_stop']:])
+	else:
+		seq = str(seqIO_dict[seqIO_record].seq)
+	if posttrans_mod_off == False:
+		if double_cca:
+			seq = seq + 'CCACCA'
+		else:
+			seq = seq + 'CCA'
+		if 'His' in seqIO_record:
+			seq = 'G' + seq
+
+	return(seq)
+
+def modsToSNPIndex(gtRNAdb, tRNAscan_out, mitotRNAs, plastidtRNAs, experiment_name, out_dir, double_cca, threads, snp_tolerance = False, cluster = False, cluster_id = 0.95, posttrans_mod_off = False, pretrnas = False, local_mod = False, search='usearch'):
 # Builds SNP index needed for GSNAP based on modificaiton data for each tRNA and clusters tRNAs
@@ -256,3 +377,3 @@
 	# generate modomics_dict and tRNA_dict
-	tRNA_dict, modomics_dict, species = tRNAparser(gtRNAdb, tRNAscan_out, mitotRNAs, plastidtRNAs, modifications_table, posttrans_mod_off, double_cca, pretrnas, local_mod)
+	tRNA_dict, modomics_dict, species = tRNAparser(gtRNAdb, tRNAscan_out, mitotRNAs, plastidtRNAs, posttrans_mod_off, double_cca, pretrnas, local_mod)
 	temp_dir = out_dir + "/tmp/"
@@ -910,89 +1031,2 @@
 
-def modificationParser(modifications_table):
-	# Read in modifications and build dictionary
-
-		mods = open(modifications_table, 'r', encoding='utf-8')
-		modifications = {}
-		for line in mods:
-			if not line.startswith("#"):
-				name, abbr, ref, mod = line.split('\t')
-				# replace unknown modifications with reference of N
-				if not ref or ref.isspace():
-					ref = 'N'
-				if mod and not mod.isspace():
-					modifications[mod.strip()] = {'name':name.strip(), 'abbr':abbr.strip(), 'ref':ref.strip()}
-		return(modifications)
-
-def getUnmodSeq(seq, modification_table):
-# Change modified bases into standard ACGT in input sequence
-
-	new_seq = []
-	for char in seq:
-		# for insertions ('_') make reference N - this is not described in the modifications table
-		if char == '_':
-			char = 'N'
-		else:
-			char = modification_table[char]['ref']
-			# Change queuosine to G (reference is preQ0base in modification file)
-			if char == 'preQ0base':
-				char = 'G'
-
-		new_seq.append(char)
-
-	new_seq = ''.join(new_seq)
-	new_seq = new_seq.replace('U','T')
-	return(new_seq)
-
-def initIntronDict(tRNAscan_out):
-# Build dictionary of intron locations
-
-	Intron_dict = {}
-	tRNAscan = open(tRNAscan_out, 'r')
-	intron_count = 0
-	for line in tRNAscan:
-		if not line.startswith(("Sequence", "Name", "-")):
-			tRNA_ID = line.split()[0] + ".trna" + line.split()[1]
-			tRNA_start = int(line.split()[2])
-			intron_start = int(line.split()[6])
-			intron_stop = int(line.split()[7])
-			# if inton boundaries are not 0, i.e. there is an intron then add to dict
-			if (intron_start > 0) & (intron_stop > 0):
-				if tRNA_start > intron_start: # tRNA is on reverse strand
-					intron_count += 1
-					intron_start = tRNA_start - intron_start
-					intron_stop = tRNA_start - intron_stop + 1 # needed for python 0 indexing and correct slicing of intron
-				else: # tRNA is on forward strand
-					intron_count += 1
-					intron_start -= tRNA_start
-					intron_stop -= tRNA_start
-					intron_stop += 1 # python 0 indexing
-
-				Intron_dict[tRNA_ID] = {}
-				Intron_dict[tRNA_ID]['intron_start'] = intron_start
-				Intron_dict[tRNA_ID]['intron_stop'] = intron_stop
-
-	log.info("{} introns registered...".format(intron_count))
-	return(Intron_dict)
-
-
-def intronRemover (Intron_dict, seqIO_dict, seqIO_record, posttrans_mod_off, double_cca):
-# Use Intron_dict to find and remove introns plus add CCA and 5' G for His (if eukaryotic)
-
-	# Find a match, slice intron and add G and CCA
-	ID = re.search("tRNAscan-SE ID: (.*?)\).|\((chr.*?)-",seqIO_dict[seqIO_record].description).groups()
-	ID = list(filter(None, ID))[0]
-	if ID in Intron_dict:
-		seq = str(seqIO_dict[seqIO_record].seq[:Intron_dict[ID]['intron_start']] + seqIO_dict[seqIO_record].seq[Intron_dict[ID]['intron_stop']:])
-	else:
-		seq = str(seqIO_dict[seqIO_record].seq)
-	if posttrans_mod_off == False:
-		if double_cca:
-			seq = seq + 'CCACCA'
-		else:
-			seq = seq + 'CCA'
-		if 'His' in seqIO_record:
-			seq = 'G' + seq
-
-	return(seq)
-
 def countsAnticodon(input_counts, out_dir):
@@ -999,0 +1033,0 @@ # Counts per anticodon

mimseq/version.py

@@ -1,1 +0,1 @@
-__version__ = "v1.3.7"
+__version__ = "v1.3.8"

PKG-INFO

 Metadata-Version: 2.1
 Name: mimseq
-Version: 1.3.7
+Version: 1.3.8
 Summary: Custom high-throughput tRNA sequencing alignment and quantification pipeline based on modification induced misincorporation cDNA synthesis.
@@ -5,0 +5,0 @@ Home-page: https://github.com/nedialkova-lab/mim-tRNAseq

README.md

@@ -39,8 +39,6 @@ <p align="center">
 
-To use mim-tRNAseq, it is recommended to install the package using `conda`, preferably in its own environment. Significant time and dependency-related improvements can be made to using conda for managing environment and installing mimseq using the [Mambaforge](https://github.com/conda-forge/miniforge) version of conda Miniforge. We recommend installing Mambaforge and then followin the steps below:
+To use mim-tRNAseq, it is recommended to install the package using `conda`, preferably in its own environment. Significant time and dependency-related improvements can be made to using conda for managing environment and installing mimseq using the [Miniforge](https://github.com/conda-forge/miniforge) version of conda which oncludes optional use for Mamba. We recommend installing Miniforge and then following the steps below:
 ```bash
 	conda create -n mimseq python=3.7
 	conda activate mimseq
-	conda config --add channels conda-forge
-	conda install -c conda-forge mamba
 	mamba install -c bioconda mimseq
@@ -62,3 +60,3 @@ ```
 
-Alternatively, mim-tRNAseq can be installed with `pip`, in which case all additional non-python package dependencies (see documentation) will also need to be installed.
+Alternatively, mim-tRNAseq can be installed with `pip`, in which case all additional non-python package dependencies (including `usearch` as above, `BLAST`, `infernal`, `GMAP/GSNAP`, and all required R packages) will also need to be installed manually.
 ```bash
@@ -65,0 +63,0 @@ pip install mimseq

setup.py

@@ -51,2 +51,3 @@ #!/usr/bin/env python
 		"pybedtools",
+        "requests",
 		"statsmodels"],
@@ -53,0 +54,0 @@ classifiers=[

Alert delta unavailable

Currently unable to show alert delta for PyPI packages.

Improved metrics

Lines of code

3610

0.78%

Worsened metrics

Total package byte prevSize

17723397

-0.62%

Number of package files

174

-0.57%