v1.6.3a

GetOrganelleLib/assembly_parser.py

@@ -37,11 +37,11 @@ def minimize(self, fun=None, x0=None, jac=None, method=None, bounds=None, constr
 import random
 from copy import deepcopy
 
-major_version, minor_version = sys.version_info[:2]
-if major_version == 2 and minor_version >= 7:
+MAJOR_VERSION, MINOR_VERSION = sys.version_info[:2]
+if MAJOR_VERSION == 2 and MINOR_VERSION >= 7:
     python_version = "2.7+"
     RecursionError = RuntimeError
-elif major_version == 3 and minor_version >= 5:
+elif MAJOR_VERSION == 3 and MINOR_VERSION >= 5:
     python_version = "3.5+"
 else:
     sys.stdout.write("Python version have to be 2.7+ or 3.5+")
@@ -50,7 +50,7 @@ def minimize(self, fun=None, x0=None, jac=None, method=None, bounds=None, constr
 
 
 class ProcessingGraphFailed(Exception):
-    def __init__(self, value):
+    def __init__(self, value=""):
         self.value = value
 
     def __str__(self):
@@ -3001,16 +3001,16 @@ def export_path(self, in_path):
         return Sequence(",".join(seq_names), "".join(seq_segments))
 
 
-class NaiveDeBruijnGraph(Assembly):
-    def __init__(self, fasta_file, kmer_len=55, circular="auto", circular_head_ends="(circular)"):
+class NaiveKmerNodeGraph(Assembly):
+    def __init__(self, fasta_file, kmer_len=55, circular="auto", circular_head_ends="(circular)", single_chain=False):
         """
         :param fasta_file:
         :param kmer_len:
         :param circular: "auto" (default), "yes", "no"
         :param circular_head_ends:
         :return:
         """
-        super(NaiveDeBruijnGraph, self).__init__(overlap=kmer_len - 1)
+        super(NaiveKmerNodeGraph, self).__init__(overlap=kmer_len - 1)
         assert circular in ("auto", "yes", "no")
         assert kmer_len >= 3 and kmer_len % 2 == 1
         self.__kmer = kmer_len  # overlap is actually kmer_len - 1
@@ -3033,7 +3033,8 @@ def __init__(self, fasta_file, kmer_len=55, circular="auto", circular_head_ends=
                     self.vertex_info[this_vertex] = this_v_info = Vertex(this_vertex, kmer_len, 1., this_kmer_seq)
                     # record the connection as dict() rather than set() for counting
                     self.vertex_info[this_vertex].connections = {True: {}, False: {}}
-                    recorded_kmers[this_v_info.seq[False]] = this_vertex, not this_end
+                    if not single_chain:
+                        recorded_kmers[this_v_info.seq[False]] = this_vertex, not this_end
                 if go_circle:
                     # add connection between the first kmer and the last kmer if the seq is circular
                     prev_kmer_seq = kmer_list[- 1]
@@ -3045,7 +3046,8 @@ def __init__(self, fasta_file, kmer_len=55, circular="auto", circular_head_ends=
                         recorded_kmers[prev_kmer_seq] = prev_vertex, prev_end = str(count_vertices), True
                         self.vertex_info[prev_vertex] = prev_v_info = Vertex(prev_vertex, kmer_len, 0., prev_kmer_seq)
                         self.vertex_info[prev_vertex].connections = {True: {}, False: {}}
-                        recorded_kmers[prev_v_info.seq[False]] = prev_vertex, not prev_end
+                        if not single_chain:
+                            recorded_kmers[prev_v_info.seq[False]] = prev_vertex, not prev_end
                     if (this_vertex, not this_end) not in self.vertex_info[prev_vertex].connections[prev_end]:
                         self.vertex_info[prev_vertex].connections[prev_end][(this_vertex, not this_end)] = 0
                     self.vertex_info[prev_vertex].connections[prev_end][(this_vertex, not this_end)] += 1
@@ -3064,7 +3066,8 @@ def __init__(self, fasta_file, kmer_len=55, circular="auto", circular_head_ends=
                         recorded_kmers[this_kmer_seq] = this_vertex, this_end = str(count_vertices), True
                         self.vertex_info[this_vertex] = this_v_info = Vertex(this_vertex, kmer_len, 1., this_kmer_seq)
                         self.vertex_info[this_vertex].connections = {True: {}, False: {}}
-                        recorded_kmers[this_v_info.seq[False]] = this_vertex, not this_end
+                        if not single_chain:
+                            recorded_kmers[this_v_info.seq[False]] = this_vertex, not this_end
                     # add the connection between this_kmer_seq and prev_kmer_seq
                     prev_kmer_seq = kmer_list[go_to - 1]
                     prev_vertex, prev_end = recorded_kmers[prev_kmer_seq]

GetOrganelleLib/pipe_control_func.py

@@ -5,10 +5,10 @@
 import os
 from multiprocessing import Pool
 
-major_version, minor_version = sys.version_info[:2]
-if major_version == 2 and minor_version >= 7:
+MAJOR_VERSION, MINOR_VERSION = sys.version_info[:2]
+if MAJOR_VERSION == 2 and MINOR_VERSION >= 7:
     python_version = "2.7+"
-elif major_version == 3 and minor_version >= 5:
+elif MAJOR_VERSION == 3 and MINOR_VERSION >= 5:
     python_version = "3.5+"
 else:
     sys.stdout.write("Python version have to be 2.7+ or 3.5+")
@@ -74,6 +74,15 @@ def timed_log(log, output_base, prefix, log_level="NOTSET"):
     return log_timed
 
 
+if MAJOR_VERSION == 2:
+    class TimeoutError(Exception):
+        def __init__(self, value=""):
+            self.value = value
+
+        def __str__(self):
+            return repr(self.value)
+
+
 def set_time_limit(num, flag_str="'--time-limit'"):
     def wrap(func):
         def handle(sig_num, interrupted_stack_frame):

GetOrganelleLib/versions.py

@@ -5,22 +5,26 @@ def get_versions():
 
 
 versions = [
+    {"number": "1.6.3a",
+     "features": [
+         "1. Minor bugs fixes",
+     ],
+     "time": "2020-02-27 17:14 GMT-6"},
     {"number": "1.6.3-beta",
      "features": [
-         "1. log plastome info",
-         "2. get_organelle_from_assembly.py & disentangle_organelle_assembly.py: --max-multiplicity added",
-         "3. Assembly.estimate_copy_and_depth_precisely() modified: constraint_max_function() for --max-multiplicity",
-         "4. Assembly.tag_in_between() modified",
-         "5. Assembly.estimate_copy_and_depth_by_cov() modified: min average coverage limit",
-         "6. Assembly.processing_polymorphism():"
+         "1. get_organelle_from_assembly.py & disentangle_organelle_assembly.py: --max-multiplicity added",
+         "2. Assembly.estimate_copy_and_depth_precisely() modified: constraint_max_function() for --max-multiplicity",
+         "3. Assembly.tag_in_between() modified",
+         "4. Assembly.estimate_copy_and_depth_by_cov() modified: min average coverage limit",
+         "5. Assembly.processing_polymorphism():"
          "   fix a bug when kmer-len repeats shared by two contigs; fix a bug that cause RuntimeError",
-         "7. Assembly: too many results due to palindromic repeats, problem solved",
-         "8. Utilities/reconstruct_graph_from_fasta.py & NaiveDeBruijnGraph added",
-         "9. Utilities/gfa_to_fasta.py, Utilities/fastg_to_gfa.py: description corrected",
-         "10. Assembly.parse_gfa(): compatibility increased",
-         "11. Utilities/gfa2fastg.py: compatibility increased",
-         "12. Assembly.estimate_copy_and_depth_precisely(): fix a bug on a rare case that multiplicities res are 4,8,4",
-         "13. README.md: updated",
+         "6. Assembly: too many results due to palindromic repeats, problem solved",
+         "7. Utilities/reconstruct_graph_from_fasta.py & NaiveKmerNodeGraph added",
+         "8. Utilities/gfa_to_fasta.py, Utilities/fastg_to_gfa.py: description corrected",
+         "9. Assembly.parse_gfa(): compatibility increased",
+         "10. Utilities/gfa2fastg.py: compatibility increased",
+         "11. Assembly.estimate_copy_and_depth_precisely(): fix a bug on a rare case that multiplicities res are 4,8,4",
+         "12. README.md: updated",
      ],
      "time": "2020-02-22 02:40 GMT-6"},
     {"number": "1.6.2e",

README.md

@@ -114,7 +114,7 @@ Perl is required for the wrapper of Bowtie2, but we assume that it was builtin i
 
 <a href=' '>Bandage</a > is a fantastic tool to view the assembly graph (`*.fastg`/`*.gfa`). If you have Bandage correctly configured and add the binary folder of Bandage (which is `Bandage.app/Contents/MacOS` for MacOS) to the $PATH, get_organelle_from_*.py would automatically generate the a png formatted image of the assembly graph. 
 
-If you installed python library psutil (version >= 3.0; pip install psutil), the memory cost of get_organelle_from_reads.py will be automatically logged. If you want to evaluate your results and plot the evaluation with `evaluate_assembly_using_mapping.py` and `round_statistics.py`, you have to further install python library matplotlib (pip install matplotlib).
+If you installed python library psutil (version >= 3.0; pip install -U psutil), the memory cost of get_organelle_from_reads.py will be automatically logged. If you want to evaluate your results and plot the evaluation with `evaluate_assembly_using_mapping.py` and `round_statistics.py`, you have to further install python library matplotlib (pip install matplotlib).
 
 
 ## How To

Utilities/reconstruct_graph_from_fasta.py

@@ -17,7 +17,7 @@ def get_options():
         usage="reconstruct_graph_from_fasta.py -i fasta_file -o out.gfa")
     parser.add_option("-i", dest="input",
                       help="Input fasta file.")
-    parser.add_option("-o", dest="output",
+    parser.add_option("-o", dest="output", default="",
                       help="Output graph file. The output format is GFA by default, but FASTG only when "
                            "indicated with postfix '.fastg'.")
     parser.add_option("-k", dest="kmer", default=55, type=int,
@@ -26,8 +26,13 @@ def get_options():
                       help="Sequences in input fasta file are all circular (yes/no/auto). "
                            "The auto mode enables detection by checking the existence of '(circular)' in "
                            "the end of the header of each sequence. Default:%default")
+    parser.add_option("--single-chain", dest="single_chain", default=False, action="store_true",
+                      help="The input sequence(s) was by default treated as DNA double-chain with its complementary "
+                           "sequence. Choose this flag to turn off.")
+    parser.add_option("--out-kg", dest="out_kg", default="",
+                      help="Output kmer node graph.")
     options, argv = parser.parse_args()
-    if not (options.output and options.input):
+    if not ((options.output or options.out_kg) and options.input):
         parser.print_help()
         sys.stdout.write("Insufficient arguments!\n")
         sys.exit()
@@ -46,15 +51,20 @@ def main():
     time_0 = time.time()
     options, argv = get_options()
     # detect postfix
-    de_burijn_graph = NaiveDeBruijnGraph(options.input, kmer_len=options.kmer, circular=options.circular)
-    assembly_graph = de_burijn_graph.generate_assembly_graph()
-    if options.output.endswith(".fastg"):
-        sys.stdout.warning("Fastg is not recommended!\n")
-        assembly_graph.write_to_fastg(options.output)
-    else:
-        assembly_graph.write_to_gfa(options.output)
-    # de_burijn_graph.write_to_gfa(options.output + ".db.gfa")
-    sys.stdout.write("Took " + "%.4f" % (time.time() - time_0) + "s in generating " + options.output + "\n")
+    kmer_node_graph = NaiveKmerNodeGraph(options.input, kmer_len=options.kmer,
+                                         circular=options.circular, single_chain=options.single_chain)
+    if options.output:
+        assembly_graph = kmer_node_graph.generate_assembly_graph()
+        if options.output.endswith(".fastg"):
+            sys.stdout.warning("Fastg is not recommended!\n")
+            assembly_graph.write_to_fastg(options.output)
+        else:
+            assembly_graph.write_to_gfa(options.output)
+    if options.out_kg:
+        kmer_node_graph.write_to_gfa(options.out_kg)
+    sys.stdout.write("Took " + "%.4f" % (time.time() - time_0) + "s in generating " +
+                     options.output * int(bool(options.output)) + ", " * int(bool(options.output and options.out_kg)) +
+                     options.out_kg * int(bool(options.out_kg)) + "\n")
 
 
 if __name__ == '__main__':

get_organelle_from_assembly.py

@@ -421,15 +421,6 @@ def get_options(description, version):
         return options, log_handler
 
 
-if MAJOR_VERSION == 2:
-    class TimeoutError(Exception):
-        def __init__(self, value):
-            self.value = value
-
-        def __str__(self):
-            return repr(self.value)
-
-
 def slim_spades_result(organelle_types, in_custom, ex_custom, graph_in, graph_out_base,
                        verbose_log, log_handler, threads, which_slim, which_blast="", other_options="",
                        resume=False, keep_temp=False):
@@ -682,7 +673,7 @@ def disentangle_inside(fastg_f, tab_f, o_p, w_f, log_in, type_f=3., mode_in="emb
             raise e
     except RuntimeError as e:
         log_handler.info("Disentangling failed: RuntimeError: " + str(e).strip())
-    except TimeoutError:
+    except TimeoutError as e:
         log_handler.info("Disentangling timeout. (see " + timeout_flag + " for more)")
     except ProcessingGraphFailed as e:
         log_handler.info("Disentangling failed: " + str(e).strip())
@@ -719,7 +710,7 @@ def disentangle_inside(fastg_f, tab_f, o_p, w_f, log_in, type_f=3., mode_in="emb
             if verbose:
                 log_handler.exception("")
             log_handler.info("Disentangling failed: RuntimeError: " + str(e).strip())
-        except TimeoutError:
+        except TimeoutError as e:
             log_handler.info("Disentangling timeout. (see " + timeout_flag + " for more)")
         except ProcessingGraphFailed as e:
             log_handler.info("Disentangling failed: " + str(e).strip())

get_organelle_from_reads.py

@@ -903,15 +903,6 @@ def get_options(description, version):
         return options, log_handler, previous_attributes
 
 
-if MAJOR_VERSION == 2:
-    class TimeoutError(Exception):
-        def __init__(self, value):
-            self.value = value
-
-        def __str__(self):
-            return repr(self.value)
-
-
 def estimate_maximum_n_reads_using_mapping(
         twice_max_coverage, check_dir, original_fq_list, reads_paired,
         designed_maximum_n_reads, seed_files, organelle_types, target_genome_sizes,