Add proksee and gff output

.github/workflows/main.yml

@@ -67,7 +67,7 @@ jobs:
         ppanggolin spot -p stepbystep/pangenome.h5 --spot_graph --overlapping_match 2 --set_size 3 --exact_match_size 1
         ppanggolin draw -p stepbystep/pangenome.h5 --draw_spots -o stepbystep -f
         ppanggolin module -p stepbystep/pangenome.h5 --transitive 4 --size 3 --jaccard 0.86 --dup_margin 0.05
-        ppanggolin write -p stepbystep/pangenome.h5 --output stepbystep -f --soft_core 0.9 --dup_margin 0.06 --gexf --light_gexf --csv --Rtab --projection --stats --partitions --compress --json --regions --spots --borders --families_tsv --cpu 1
+        ppanggolin write -p stepbystep/pangenome.h5 --output stepbystep -f --soft_core 0.9 --dup_margin 0.06 --gexf --light_gexf --csv --Rtab --projection --stats --partitions --compress --json --regions --spots --borders --families_tsv --cpu 1 --fasta organisms.fasta.list --gff --proksee
         ppanggolin fasta -p stepbystep/pangenome.h5 --output stepbystep -f --prot_families all --gene_families shell --regions all --fasta organisms.fasta.list
         ppanggolin draw -p stepbystep/pangenome.h5 --draw_spots --spots all -o stepbystep -f
         ppanggolin metrics -p stepbystep/pangenome.h5 --genome_fluidity --info_modules --no_print_info -f --log metrics.log
@@ -134,10 +134,10 @@ jobs:
       run: |
         cd testingDataset
         head organisms.gbff.list | sed 's/^/input_org_/g' > organisms.gbff.head.list
-        ppanggolin projection --pangenome stepbystep/pangenome.h5  -o projection_from_lisy_of_gbff --anno organisms.gbff.head.list 
+        ppanggolin projection --pangenome stepbystep/pangenome.h5  -o projection_from_list_of_gbff --anno organisms.gbff.head.list --gff --proksee
 
 
         ppanggolin projection --pangenome mybasicpangenome/pangenome.h5  -o projection_from_single_fasta \
                               --organism_name chlam_A --fasta FASTA/GCF_002776845.1_ASM277684v1_genomic.fna.gz \
-                              --spot_graph --graph_formats graphml --fast --keep_tmp -f
+                              --spot_graph --graph_formats graphml --fast --keep_tmp -f --add_sequences --gff --proksee
 

ppanggolin/annotate/annotate.py

@@ -238,6 +238,9 @@ def read_org_gbff(organism_name: str, gbff_file_path: Path, circular_contigs: Li
         while not line.startswith('//'):
             sequence += line[10:].replace(" ", "").strip().upper()
             line = lines.pop()
+
+        contig.add_contig_length(len(sequence))
+
         # get each gene's sequence.
         for gene in contig.genes:
             gene.add_sequence(get_dna_sequence(sequence, gene))
@@ -368,6 +371,9 @@ def get_id_attribute(attributes_dict: dict) -> str:
     if has_fasta and fasta_string != "":
         contig_sequences = read_fasta(org, fasta_string.split('\n'))  # _ is total contig length
         for contig in org.contigs:
+
+            contig.add_contig_length(len(contig_sequences[contig.name]))
+
             for gene in contig.genes:
                 gene.add_sequence(get_dna_sequence(contig_sequences[contig.name], gene))
             for rna in contig.RNAs:

ppanggolin/context/searchGeneContext.py

@@ -9,7 +9,7 @@
 import logging
 import os
 from typing import List, Dict, Tuple, Iterable, Hashable, Iterator, Set
-from itertools import zip_longest, chain
+from itertools import chain
 from collections import defaultdict
 from pathlib import Path
 
@@ -21,7 +21,7 @@
 # local libraries
 from ppanggolin.formats import check_pangenome_info
 from ppanggolin.genome import Gene, Contig
-from ppanggolin.utils import mk_outdir, restricted_float, create_tmpdir, read_compressed_or_not
+from ppanggolin.utils import mk_outdir, restricted_float, create_tmpdir, read_compressed_or_not, extract_contig_window
 from ppanggolin.pangenome import Pangenome
 from ppanggolin.align.alignOnPang import project_and_write_partition, get_input_seq_to_family_with_rep, \
     get_input_seq_to_family_with_all, get_seq_ids
@@ -445,63 +445,6 @@ def get_n_next_genes_index(current_index: int, next_genes_count: int,
         yield next_gene_index
 
 
-def extract_contig_window(contig_size: int, positions_of_interest: Iterable[int], window_size: int,
-                          is_circular: bool = False):
-    """
-    Extracts contiguous windows around positions of interest within a contig.
-
-    :param contig_size: Number of genes in contig.
-    :param positions_of_interest: An iterable containing the positions of interest.
-    :param window_size: The size of the window to extract around each position of interest.
-    :param is_circular: Indicates if the contig is circular.
-    :return: Yields tuples representing the start and end positions of each contiguous window.
-    """
-    windows_coordinates = []
-
-    # Sort the positions of interest
-    sorted_positions = sorted(positions_of_interest)
-
-    # Check if any position of interest is out of range
-    if sorted_positions[0] < 0 or sorted_positions[-1] >= contig_size:
-        raise IndexError(f'Positions of interest are out of range. '
-                         f"Contig has {contig_size} genes while given min={sorted_positions[0]} & max={sorted_positions[-1]} positions")
-
-    if is_circular:
-        first_position = sorted_positions[0]
-        last_position = sorted_positions[-1]
-        # in a circular contig, if the window of a gene of interest overlaps the end/start of the contig
-        # an out of scope position is added to the sorted positions to take into account those positions
-        # the returned window are always checked that its positions are not out of range... 
-        # so there's no chance to find an out of scope position in final list
-        if first_position - window_size < 0:
-            out_of_scope_position = contig_size + first_position
-            sorted_positions.append(out_of_scope_position)
-
-        if last_position + window_size >= contig_size:
-            out_of_scope_position = last_position - contig_size
-            sorted_positions.insert(0, out_of_scope_position)
-
-    start_po = max(sorted_positions[0] - window_size, 0)
-
-    for position, next_po in zip_longest(sorted_positions, sorted_positions[1:]):
-
-        if next_po is None:
-            # If there are no more positions, add the final window
-            end_po = min(position + window_size, contig_size - 1)
-            windows_coordinates.append((start_po, end_po))
-
-        elif position + window_size + 1 < next_po - window_size:
-            # If there is a gap between positions, add the current window 
-            # and update the start position for the next window
-            end_po = min(position + window_size, contig_size - 1)
-
-            windows_coordinates.append((start_po, end_po))
-
-            start_po = max(next_po - window_size, 0)
-
-    return windows_coordinates
-
-
 def get_contig_to_genes(gene_families: Iterable[GeneFamily]) -> Dict[Contig, Set[Gene]]:
     """
     Group genes from specified gene families by contig.