NGSpeciesID 0.3.0__tar.gz → 0.3.1__tar.gz

{NGSpeciesID-0.3.0 → ngspeciesid-0.3.1}/NGSpeciesID

@@ -4,13 +4,12 @@ from __future__ import print_function
 import os,sys
 import argparse
 import tempfile
-import errno
 from time import time
 import shutil
 import random
+import logging
 
 from modules import get_sorted_fastq_for_cluster
-from modules import cluster
 from modules import p_minimizers_shared
 from modules import help_functions
 from modules import parallelize
@@ -30,7 +29,7 @@ def single_clustering(read_array, p_emp_probs, args):
     result_dict = cluster.reads_to_clusters(clusters, representatives, read_array, p_emp_probs, minimizer_database, new_batch_index, args)
     # Unpack result. The result dictionary structure is convenient for multiprocessing return but clumsy in single core mode.
     clusters, representatives, _, _ = list(result_dict.values())[0]
-    print("Time elapesd clustering:", time() - start_cluster)
+    logging.debug(f"Time elapesd clustering: {time() - start_cluster}")
     return clusters, representatives
 
 
@@ -45,28 +44,30 @@ def main(args):
     """
     ##### Sort all reads according to expected errorfree kmers #####
     args.outfile = os.path.join(args.outfolder, "sorted.fastq")
-    print("started sorting seqs")
+    logging.debug("started sorting seqs")
     start = time()
     sorted_reads_fastq_file = get_sorted_fastq_for_cluster.main(args)
-    print("elapsed time sorting:", time() - start)
+    logging.debug(f"elapsed time sorting: {time() - start}")
     #################################################################
 
     ##### Filter and subsample #####
     if args.target_length > 0 and args.target_deviation > 0:
         read_array = [ (i, 0, acc, seq, qual, float(acc.split("_")[-1])) for i, (acc, (seq, qual)) in enumerate(help_functions.readfq(open(sorted_reads_fastq_file, 'r'))) if args.target_length - args.target_deviation <= len(seq) <= args.target_length + args.target_deviation]
-        print("Number of reads with read length in interval [{0},{1}]:".format(args.target_length - args.target_deviation, args.target_length + args.target_deviation), len(read_array))
+        logging.debug("Number of reads with read length in interval [{0},{1}]: {2}".format(args.target_length - args.target_deviation, args.target_length + args.target_deviation, len(read_array)))
     else:
         read_array = [ (i, 0, acc, seq, qual, float(acc.split("_")[-1])) for i, (acc, (seq, qual)) in enumerate(help_functions.readfq(open(sorted_reads_fastq_file, 'r')))]
 
-    if 0 < args.sample_size < len(read_array):
-        read_array = [  read_array[i] for i in sorted(random.sample(range(len(read_array)), args.sample_size))]
+    if args.top_reads:
+        read_array = read_array[:args.sample_size]
+    elif 0 < args.sample_size < len(read_array):
+        read_array = [read_array[i] for i in sorted(random.sample(range(len(read_array)), args.sample_size))]
 
     abundance_cutoff = int( args.abundance_ratio * len(read_array))
     #################################################################
 
 
     ##### Import precalculated probabilities of minimizer matching given the error rates of reads, kmer length, and window length #####
-    print("Started imported empirical error probabilities of minimizers shared:")
+    logging.debug("Started imported empirical error probabilities of minimizers shared:")
     start = time()
     p_min_shared = p_minimizers_shared.read_empirical_p()
     p_emp_probs = {}
@@ -75,21 +76,22 @@ def main(args):
             p_emp_probs[(float(e1),float(e2))] = float(p)
             p_emp_probs[(float(e2),float(e1))] = float(p)
 
-    print(p_emp_probs)
-    print(len(p_emp_probs))
-    print("elapsed time imported empirical error probabilities of minimizers shared:", time() - start)
+    logging.debug(f"{p_emp_probs}")
+    logging.debug(f"{len(p_emp_probs)}")
+    logging.debug(f"elapsed time imported empirical error probabilities of minimizers shared: {time() - start}")
     ##################################################################################################################################
 
+    logging.info(f"Starting Clustering: {len(read_array)} reads")
     ##### Cluster reads, bulk of code base is here #####
-    print("started clustring")
+    logging.debug("started clustring")
     start = time()
     if args.nr_cores > 1:
         clusters, representatives = parallelize.parallel_clustering(read_array, p_emp_probs, args)
     else:
-        print("Using 1 core.")
+        logging.debug("Using 1 core.")
         clusters, representatives = single_clustering(read_array, p_emp_probs, args)
     # clusters, representatives = cluster.cluster_seqs(read_array, p_emp_probs,  args)
-    print("Time elapsed clustering:", time() - start)
+    logging.debug(f"Time elapsed clustering: {time() - start}")
     ####################################################
 
 
@@ -101,7 +103,7 @@ def main(args):
     output_cl_id = 0
     for c_id, all_read_acc in sorted(clusters.items(), key = lambda x: (len(x[1]),representatives[x[0]][5]), reverse=True):
     # for c_id, all_read_acc in sorted(clusters.items(), key = lambda x: (len(x[1]),x[0]), reverse=True):
-        read_cl_id, b_i, acc, c_seq, c_qual, score, error_rate = representatives[c_id]
+        read_cl_id, b_i, acc, c_seq, c_qual, score, error_rate, _ = representatives[c_id]
         origins_outfile.write("{0}\t{1}\t{2}\t{3}\t{4}\t{5}\n".format(output_cl_id, "_".join([item for item in acc.split("_")[:-1]]), c_seq, c_qual, score, error_rate))
 
         for r_acc in sorted(all_read_acc, key = lambda x: float(x.split("_")[-1]) , reverse=True):
@@ -111,20 +113,19 @@ def main(args):
         
         output_cl_id +=1
 
-    print("Nr clusters larger than 1:", nontrivial_cluster_index) #, "Non-clustered reads:", len(archived_reads))
-    print("Nr clusters (all):", len(clusters)) #, "Non-clustered reads:", len(archived_reads))
+    logging.debug(f"Nr clusters larger than 1: {nontrivial_cluster_index}") #, "Non-clustered reads:", len(archived_reads))
+    logging.debug(f"Nr clusters (all): {len(clusters)}") #, "Non-clustered reads:", len(archived_reads))
     outfile.close()
     origins_outfile.close()
     ############################
 
+    logging.info(f"Finished Clustering: {nontrivial_cluster_index} clusters formed")
 
     if args.consensus:
-        print()
-        print("STARTING TO CREATE CLUSTER CONSENSUS")
-        print()
+        logging.info(f"Starting Consensus creation and polishing")
         work_dir = tempfile.mkdtemp()
-        print("Temporary workdirektory for consensus and polishing:", work_dir)
-        print(
+        logging.debug(f"Temporary workdirectory for consensus and polishing: {work_dir}")
+        logging.debug(
             f"Forming draft consensus with abundance_cutoff >= {abundance_cutoff} "
             f"({args.abundance_ratio * 100}% of {len(read_array)} reads)"
         )
@@ -132,27 +133,29 @@ def main(args):
 
         if args.primer_file or args.remove_universal_tails:
             if args.remove_universal_tails:
-                print("Detecting and removing universal tails")
+                logging.debug("Detecting and removing universal tails")
                 barcodes = barcode_trimmer.get_universal_tails()
             else:
-                print("Detecting and removing primers")
+                logging.debug("Detecting and removing primers")
                 barcodes = barcode_trimmer.read_barcodes(args.primer_file)
 
             barcode_trimmer.remove_barcodes(centers, barcodes, args)
 
-        print("{0} centers formed".format(len(centers)))
+        logging.debug("{0} centers formed".format(len(centers)))
         centers_filtered = consensus.detect_reverse_complements(centers, args.rc_identity_threshold)
         centers_polished = consensus.polish_sequences(centers_filtered, args)
 
         if args.primer_file or args.remove_universal_tails: # check if barcode is found after polishing with medaka
-            barcode_trimmer.remove_barcodes(centers_polished, barcodes, args)
-            centers_filtered = consensus.detect_reverse_complements(centers_polished, args.rc_identity_threshold)
-            centers_polished = consensus.polish_sequences(centers_filtered, args)
+            centers_updated = barcode_trimmer.remove_barcodes(centers_polished, barcodes, args)
+            if centers_updated:
+                centers_filtered = consensus.detect_reverse_complements(centers_polished, args.rc_identity_threshold)
+                centers_polished = consensus.polish_sequences(centers_filtered, args)
 
 
-        print("removing temporary workdir")
+        logging.debug("removing temporary workdir")
         shutil.rmtree(work_dir)
 
+        logging.info(f"Finished Consensus creation: {len(centers_filtered)} created")
 
 
 def write_fastq(args):
@@ -183,19 +186,17 @@ def write_fastq(args):
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description="Reference-free clustering and consensus forming of targeted ONT or PacBio reads", formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-    parser.add_argument('--version', action='version', version='%(prog)s 0.3.0')
-
-    parser.add_argument('--fastq', type=str,  default=False, help='Path to consensus fastq file(s)')
-    parser.add_argument('--flnc', type=str, default=False, help='The flnc reads generated by the isoseq3 algorithm (BAM file)')
-    parser.add_argument('--ccs', type=str, default=False, help='Path to consensus BAM file(s)')
-    # parser.add_argument('--mapping', action="store_true", help='Only infer clusters by mapping, no alignment is performed.')
+    parser.add_argument('--version', action='version', version='%(prog)s 0.3.1')
+    parser.add_argument('--debug', action='store_true', help='Enable debug logging')
+    reads_file = parser.add_mutually_exclusive_group(required=True)
+    reads_file.add_argument('--fastq', type=str, help='Path to consensus fastq file(s)')
+    reads_file.add_argument('--use_old_sorted_file', action='store_true', help='Using already existing sorted file if present in specified output directory.')
     parser.add_argument('--t', dest="nr_cores", type=int, default=8, help='Number of cores allocated for clustering')
     parser.add_argument('--d', dest="print_output", type=int, default=10000, help='For debugging, prints status of clustering and minimizer database every p reads processed.')
     parser.add_argument('--q', dest="quality_threshold", type=float, default=7.0, help='Filters reads with average phred quality value under this number (default = 7.0).')
 
     parser.add_argument('--ont', action="store_true", help='Clustering of ONT transcript reads.')
     parser.add_argument('--isoseq', action="store_true", help='Clustering of PacBio Iso-Seq reads.')
-    parser.add_argument('--use_old_sorted_file', action="store_true", help='Using already existing sorted file if present in specified output directory.')
 
     parser.add_argument('--consensus', action="store_true", help='After clustering, (1) run spoa on all clusters, (2) detect reverse complements, (3) run medaka.')
     parser.add_argument('--abundance_ratio', type=float, default=0.1, help='Threshold for --consensus algorithm. Consider only clusters larger than a fraction of number of total reads (default 0.1)')
@@ -207,6 +208,7 @@ if __name__ == '__main__':
     group.add_argument('--racon', action="store_true", help='Run final racon polishing algorithm.')
 
     parser.add_argument('--medaka_model', type=str, default="", help='Set specific medaka model.')
+    parser.add_argument('--medaka_fastq', action="store_true", help='Request Medaka to output a FASTQ file, instead of FASTA')
     parser.add_argument('--racon_iter', type=int, default=2, help='Number of times to run racon iteratively')
 
     group2 = parser.add_mutually_exclusive_group()
@@ -217,8 +219,7 @@ if __name__ == '__main__':
     parser.add_argument('--m', dest="target_length", type=int, default=0, help='Intended amplicon length. Invoked to filter out reads with length greater than m + s or smaller than m - s (default = 0 which means no filtering)')
     parser.add_argument('--s', dest="target_deviation", type=int, default=0, help='Maximum allowed amplicon-length deviation.  Invoked to filter out reads with length greater than m + s or smaller than m - s (default = 0 which means no filtering)')
     parser.add_argument('--sample_size', type=int, default=0, help='Use sample_size reads in the NGSpecies pipeline (default = 0 which means all reads considered). If sample size is larger than actual number of reads, all reads will be used.')
-    
-
+    parser.add_argument('--top_reads', action='store_true', help='Use the top --sample_size reads instead of a random selection (default = false, which means random reads considered). ')
 
 
     parser.add_argument('--k', type=int, default=13, help='Kmer size')
@@ -226,6 +227,7 @@ if __name__ == '__main__':
     parser.add_argument('--min_shared', type=int, default=5, help='Minmum number of minimizers shared between read and cluster')
     parser.add_argument('--mapped_threshold', type=float, default=0.7, help='Minmum mapped fraction of read to be included in cluster. The density of minimizers to classify a region as mapped depends on quality of the read.')
     parser.add_argument('--aligned_threshold', type=float, default=0.4, help='Minmum aligned fraction of read to be included in cluster. Aligned identity depends on the quality of the read.')
+    parser.add_argument('--symmetric_map_align_thresholds', action='store_true', help='Apply mapped threshold and aligned threshold to fraction of cluster representative which maps onto the read')
     parser.add_argument('--batch_type', type=str, default='total_nt', help='In parrallel mode, how to split the reads into chunks "total_nt", "nr_reads", or "weighted" (default: total_nt) ')
     parser.add_argument('--min_fraction', type=float, default=0.8, help='Minmum fraction of minimizers shared compared to best hit, in order to continue mapping.')
     parser.add_argument('--min_prob_no_hits', type=float, default=0.1, help='Minimum probability for i consecutive minimizers to be different between read and representative and still considered as mapped region, under assumption that they come from the same transcript (depends on read quality).')
@@ -244,21 +246,20 @@ if __name__ == '__main__':
 
     args = parser.parse_args()
 
+    loglevel = logging.DEBUG if args.debug else logging.INFO
+
+    logging.basicConfig(
+        level=loglevel,
+        format='%(message)s'
+    )
+
     if args.which == 'write_fastq':
         write_fastq(args)
-        print("Wrote clusters to separate fastq files.")
+        logging.info("Wrote clusters to separate fastq files.")
         sys.exit(0)
 
-    if (args.fastq and (args.flnc or args.ccs)):
-        print("Either (1) only a fastq file, or (2) a ccs and a flnc file should be specified. ")
-        sys.exit()
-
-    if (args.flnc != False and args.ccs == False ) or (args.flnc == False and args.ccs != False ):
-        print("isONclust needs both the ccs.bam file produced by ccs and the flnc file produced by isoseq3 cluster. ")
-        sys.exit()
-
     if args.ont and args.isoseq :
-        print("Arguments mutually exclusive, specify either --isoseq or --ont. ")
+        logging.error("Arguments mutually exclusive, specify either --isoseq or --ont. ")
         sys.exit()
     elif args.isoseq:
         args.k = 15
@@ -271,24 +272,16 @@ if __name__ == '__main__':
     if len(sys.argv)==1:
         parser.print_help()
         sys.exit()
-    if not args.fastq and not args.flnc and not  args.ccs:
-        parser.print_help()
-        sys.exit()
-
 
     if args.outfolder and not os.path.exists(args.outfolder):
         os.makedirs(args.outfolder)
 
-
-    # edlib_module = 'edlib'
     parasail_module = 'parasail'
-    # if edlib_module not in sys.modules:
-    #     print('You have not imported the {0} module. Only performing clustering with mapping, i.e., no alignment.'.format(edlib_module))
     if parasail_module not in sys.modules:
-        print('You have not imported the {0} module. Only performing clustering with mapping, i.e., no alignment!'.format(parasail_module))
+        logging.error('You have not imported the {0} module. Only performing clustering with mapping, i.e., no alignment!'.format(parasail_module))
         sys.exit(1)
     if 100 < args.w or args.w < args.k:
-        print('Please specify a window of size larger or equal to k, and smaller than 100.')
+        logging.error('Please specify a window of size larger or equal to k, and smaller than 100.')
         sys.exit(1)
 
     main(args)

{NGSpeciesID-0.3.0 → ngspeciesid-0.3.1/NGSpeciesID.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: NGSpeciesID
-Version: 0.3.0
+Version: 0.3.1
 Summary: Reconstructs viral consensus sequences from a set of ONT reads.
 Home-page: https://github.com/ksahlin/NGSpeciesID
 Author: Kristoffer Sahlin
@@ -14,6 +14,18 @@ Classifier: Programming Language :: Python :: 3.6
 Classifier: Programming Language :: Python :: 3.7
 Requires-Python: !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, <4
 License-File: LICENSE.txt
+Requires-Dist: parasail==1.2.4
+Requires-Dist: edlib>=1.1.2
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 NGSpeciesID
 ===========
@@ -25,25 +37,44 @@ NGSpeciesID is distributed as a python package supported on Linux / OSX with pyt
 Table of Contents
 =================
 
-  * [INSTALLATION](#INSTALLATION)
-    * [Using conda](#Using-conda)
+  * [INSTALLATION](#installation)
+    * [Using conda](#using-conda)
     * [Testing installation](#testing-installation)
-  * [USAGE](#USAGE)
+  * [USAGE](#usage)
     * [Filtering and subsampling](#filtering-and-subsampling)
     * [Removing primers](#removing-primers)
-    * [Output](#Output)
-  * [EXAMPLE WORKFLOW](#EXAMPLE-WORKFLOW)
-  * [CREDITS](#CREDITS)
-  * [LICENCE](#LICENCE)
+    * [Output](#output)
+  * [EXAMPLE WORKFLOW](#example-workflow)
+  * [CREDITS](#credits)
+  * [LICENCE](#licence)
 
 
 
 INSTALLATION
 ----------------
 
-**NOTE**: If you are experiencing issues (e.g. [this one](https://github.com/rvaser/spoa/issues/26)) with the third party tools  [spoa](https://github.com/rvaser/spoa) or [medaka](https://github.com/nanoporetech/medaka) in the all-in-one installation instructions below, please install the tools manually with their respective installation instructions [here](https://github.com/rvaser/spoa#installation) and [here](https://github.com/nanoporetech/medaka#installation).  
+<!---
+**NOTE**: If you are experiencing issues (e.g. [this one](https://github.com/rvaser/spoa/issues/26)) with the third party tools  [spoa](https://github.com/rvaser/spoa) or [medaka](https://github.com/nanoporetech/medaka) in the installation instructions below, please install the tools manually with their respective installation instructions [here](https://github.com/rvaser/spoa#installation) and [here](https://github.com/nanoporetech/medaka#installation).  
+-->
 
 ### Using conda
+
+**Recent update (2025-04-19)**
+
+There have been many version updates of medaka and spoa since NGSpeciesID was first published. Below are instructions to install 
+NGSpeciesID with newer versions of spoa ([v4.1.4](https://bioconda.github.io/recipes/spoa/README.html)) and medaka (v2.0.1).
+
+```
+conda create -n NGSpeciesID python=3.11 pip
+conda activate NGSpeciesID
+conda install --yes -c conda-forge -c bioconda medaka==2.0.1 openblas==0.3.3 spoa racon minimap2  samtools
+pip install NGSpeciesID
+```
+
+Make sure you [test the installation](#testing-installation).
+
+**Published installation instructions (2021-01-11)**
+
 Conda is the preferred way to install NGSpeciesID.
 
 1. Create and activate a new environment called NGSpeciesID

{NGSpeciesID-0.3.0/NGSpeciesID.egg-info → ngspeciesid-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: NGSpeciesID
-Version: 0.3.0
+Version: 0.3.1
 Summary: Reconstructs viral consensus sequences from a set of ONT reads.
 Home-page: https://github.com/ksahlin/NGSpeciesID
 Author: Kristoffer Sahlin
@@ -14,6 +14,18 @@ Classifier: Programming Language :: Python :: 3.6
 Classifier: Programming Language :: Python :: 3.7
 Requires-Python: !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, <4
 License-File: LICENSE.txt
+Requires-Dist: parasail==1.2.4
+Requires-Dist: edlib>=1.1.2
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 NGSpeciesID
 ===========
@@ -25,25 +37,44 @@ NGSpeciesID is distributed as a python package supported on Linux / OSX with pyt
 Table of Contents
 =================
 
-  * [INSTALLATION](#INSTALLATION)
-    * [Using conda](#Using-conda)
+  * [INSTALLATION](#installation)
+    * [Using conda](#using-conda)
     * [Testing installation](#testing-installation)
-  * [USAGE](#USAGE)
+  * [USAGE](#usage)
     * [Filtering and subsampling](#filtering-and-subsampling)
     * [Removing primers](#removing-primers)
-    * [Output](#Output)
-  * [EXAMPLE WORKFLOW](#EXAMPLE-WORKFLOW)
-  * [CREDITS](#CREDITS)
-  * [LICENCE](#LICENCE)
+    * [Output](#output)
+  * [EXAMPLE WORKFLOW](#example-workflow)
+  * [CREDITS](#credits)
+  * [LICENCE](#licence)
 
 
 
 INSTALLATION
 ----------------
 
-**NOTE**: If you are experiencing issues (e.g. [this one](https://github.com/rvaser/spoa/issues/26)) with the third party tools  [spoa](https://github.com/rvaser/spoa) or [medaka](https://github.com/nanoporetech/medaka) in the all-in-one installation instructions below, please install the tools manually with their respective installation instructions [here](https://github.com/rvaser/spoa#installation) and [here](https://github.com/nanoporetech/medaka#installation).  
+<!---
+**NOTE**: If you are experiencing issues (e.g. [this one](https://github.com/rvaser/spoa/issues/26)) with the third party tools  [spoa](https://github.com/rvaser/spoa) or [medaka](https://github.com/nanoporetech/medaka) in the installation instructions below, please install the tools manually with their respective installation instructions [here](https://github.com/rvaser/spoa#installation) and [here](https://github.com/nanoporetech/medaka#installation).  
+-->
 
 ### Using conda
+
+**Recent update (2025-04-19)**
+
+There have been many version updates of medaka and spoa since NGSpeciesID was first published. Below are instructions to install 
+NGSpeciesID with newer versions of spoa ([v4.1.4](https://bioconda.github.io/recipes/spoa/README.html)) and medaka (v2.0.1).
+
+```
+conda create -n NGSpeciesID python=3.11 pip
+conda activate NGSpeciesID
+conda install --yes -c conda-forge -c bioconda medaka==2.0.1 openblas==0.3.3 spoa racon minimap2  samtools
+pip install NGSpeciesID
+```
+
+Make sure you [test the installation](#testing-installation).
+
+**Published installation instructions (2021-01-11)**
+
 Conda is the preferred way to install NGSpeciesID.
 
 1. Create and activate a new environment called NGSpeciesID

{NGSpeciesID-0.3.0 → ngspeciesid-0.3.1}/README.md

@@ -8,25 +8,44 @@ NGSpeciesID is distributed as a python package supported on Linux / OSX with pyt
 Table of Contents
 =================
 
-  * [INSTALLATION](#INSTALLATION)
-    * [Using conda](#Using-conda)
+  * [INSTALLATION](#installation)
+    * [Using conda](#using-conda)
     * [Testing installation](#testing-installation)
-  * [USAGE](#USAGE)
+  * [USAGE](#usage)
     * [Filtering and subsampling](#filtering-and-subsampling)
     * [Removing primers](#removing-primers)
-    * [Output](#Output)
-  * [EXAMPLE WORKFLOW](#EXAMPLE-WORKFLOW)
-  * [CREDITS](#CREDITS)
-  * [LICENCE](#LICENCE)
+    * [Output](#output)
+  * [EXAMPLE WORKFLOW](#example-workflow)
+  * [CREDITS](#credits)
+  * [LICENCE](#licence)
 
 
 
 INSTALLATION
 ----------------
 
-**NOTE**: If you are experiencing issues (e.g. [this one](https://github.com/rvaser/spoa/issues/26)) with the third party tools  [spoa](https://github.com/rvaser/spoa) or [medaka](https://github.com/nanoporetech/medaka) in the all-in-one installation instructions below, please install the tools manually with their respective installation instructions [here](https://github.com/rvaser/spoa#installation) and [here](https://github.com/nanoporetech/medaka#installation).  
+<!---
+**NOTE**: If you are experiencing issues (e.g. [this one](https://github.com/rvaser/spoa/issues/26)) with the third party tools  [spoa](https://github.com/rvaser/spoa) or [medaka](https://github.com/nanoporetech/medaka) in the installation instructions below, please install the tools manually with their respective installation instructions [here](https://github.com/rvaser/spoa#installation) and [here](https://github.com/nanoporetech/medaka#installation).  
+-->
 
 ### Using conda
+
+**Recent update (2025-04-19)**
+
+There have been many version updates of medaka and spoa since NGSpeciesID was first published. Below are instructions to install 
+NGSpeciesID with newer versions of spoa ([v4.1.4](https://bioconda.github.io/recipes/spoa/README.html)) and medaka (v2.0.1).
+
+```
+conda create -n NGSpeciesID python=3.11 pip
+conda activate NGSpeciesID
+conda install --yes -c conda-forge -c bioconda medaka==2.0.1 openblas==0.3.3 spoa racon minimap2  samtools
+pip install NGSpeciesID
+```
+
+Make sure you [test the installation](#testing-installation).
+
+**Published installation instructions (2021-01-11)**
+
 Conda is the preferred way to install NGSpeciesID.
 
 1. Create and activate a new environment called NGSpeciesID

{NGSpeciesID-0.3.0 → ngspeciesid-0.3.1}/modules/barcode_trimmer.py

@@ -1,5 +1,6 @@
 
 import edlib
+import logging
 
 from modules import help_functions
 
@@ -15,10 +16,10 @@ def read_barcodes(primer_file):
     barcodes = { acc + '_fw' : seq.strip() for acc, (seq, _) in help_functions.readfq(open(primer_file, 'r'))}
 
     for acc, seq in list(barcodes.items()):
-        print(acc, seq,acc[:-3])
+        logging.debug(f"{acc} {seq} {acc[:-3]}")
         barcodes[acc[:-3] + '_rc'] = reverse_complement(seq.upper())
 
-    print(barcodes)
+    logging.debug(f"{barcodes}")
     return barcodes
 
 def get_universal_tails():
@@ -26,7 +27,7 @@ def get_universal_tails():
                  '2_R_rc' : 'ACTTGCCTGTCGCTCTATCTTC'}
     barcodes['1_F_rc'] = reverse_complement(barcodes['1_F_fw'])
     barcodes['2_R_fw'] = reverse_complement(barcodes['2_R_rc'])
-    print(barcodes)
+    logging.debug(f"{barcodes}")
     return barcodes
 
 
@@ -45,14 +46,13 @@ def find_barcode_locations(center, barcodes, primer_max_ed):
                  ('X', 'T'), ('X', 'C'), ('N', 'G'), ('N', 'A'), ('N', 'T'), ('N', 'C')]
     all_locations = []
     for primer_acc, primer_seq in barcodes.items():
-        # print(primer_acc, primer_seq,center)
         # Add additionalEqualities=IUPAC_map allow edlib to understand IUPAC code
         result = edlib.align(primer_seq, center,
                              mode="HW", task="locations", k=primer_max_ed,
                              additionalEqualities=IUPAC_map)
         ed = result["editDistance"]
         locations = result["locations"]
-        print(locations, ed)
+        logging.debug(f"{locations} {ed}")
         if locations:
             all_locations.append((primer_acc, locations[0][0], locations[0][1], ed))
     return all_locations
@@ -63,7 +63,8 @@ def remove_barcodes(centers, barcodes, args):
         Modifies consensus sequences by copping of at barcode sites.
         This implies changing the datastructure centers with the modified consensus sequeces
     """
-    
+
+    centers_updated = False
     for i, (nr_reads_in_cluster, c_id, center, reads_path_name) in enumerate(centers):
 
         # if consensus is smaller than 2*trim_window we set trim window to half the sequence
@@ -74,53 +75,30 @@ def remove_barcodes(centers, barcodes, args):
 
         barcode_locations_beginning = find_barcode_locations(center[:trim_window], barcodes, args.primer_max_ed) 
         barcode_locations_end = find_barcode_locations(center[-trim_window:], barcodes, args.primer_max_ed) 
-        print(center)
+        logging.debug(f"{center}")
         
         cut_start = 0
         if barcode_locations_beginning:
-            print("FOUND BARCODE BEGINNING", barcode_locations_beginning)
+            logging.debug(f"FOUND BARCODE BEGINNING {barcode_locations_beginning}")
             for bc, start, stop, ed in barcode_locations_beginning:
                 if stop > cut_start:
                     cut_start = stop
             
         cut_end = len(center)
         if barcode_locations_end:
-            print("FOUND BARCODE END", barcode_locations_end)
+            logging.debug(f"FOUND BARCODE END {barcode_locations_end}")
             earliest_hit = len(center)
             for bc, start, stop, ed in barcode_locations_end:
                 if start < earliest_hit:
                     earliest_hit = start
             cut_end = len(center) - (trim_window - earliest_hit)
-        center = center[cut_start: cut_end]
-
-        print(center, "NEW")
-        print("cut start", cut_start, "cut end", cut_end)
-        centers[i][2] = center
-
-    ## Old code scanned all consensus and were prone to errors due to cutting directionality (befause of fwd or rev comp hits of the adapter)
-    # for i, (nr_reads_in_cluster, c_id, center, reads_path_name) in enumerate(centers):
-    #     barcode_locations = find_barcode_locations(center, barcodes, args.primer_max_ed) 
-    #     if barcode_locations:
-    #         print("FOUND BARCODE", barcode_locations)
-    #         cut_start = 0
-    #         cut_end = len(center)
-    #         print(center)
-    #         for bc, start, stop, ed in barcode_locations:
-    #             # print(ed,bc, bc[-4], bc[-2:])
-    #             if bc[-4] == 'F' and bc[-2:] == 'fw':
-    #                 cut_start = stop
-    #             elif bc[-4] == 'R' and bc[-2:] == 'fw': 
-    #                 cut_end = start
-    #             elif bc[-4] == 'R' and bc[-2:] == 'rc':
-    #                 cut_start = stop
-    #             elif bc[-4] == 'F' and bc[-2:] == 'rc': 
-    #                 cut_end = start
-    #             else:
-    #                 print()
-    #                 print("Primer file not in correct format!")
-    #                 print()
-    #         # print(center)
-    #         center = center[cut_start: cut_end]
-    #         print(center, "NEW")
-    #         print("cut start", cut_start, "cut end", cut_end)
-    #         centers[i][2] = center
+
+        if cut_start > 0 or cut_end < len(center):
+            center = center[cut_start: cut_end]
+
+            logging.debug(f"{center} NEW")
+            logging.debug(f"cut start {cut_start} cut end {cut_end}")
+            centers[i][2] = center
+            centers_updated = True
+
+    return centers_updated