split3c 0.0.1__tar.gz → 0.0.2__tar.gz

{split3c-0.0.1/src/split3c.egg-info → split3c-0.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: split3c
-Version: 0.0.1
+Version: 0.0.2
 Summary: Toolkit to split and resolve chimeric 3C/Hi-C/Micro-C reads
 Author-email: Samir Bertache <samir.bertache.djenadi@gmail.com>
 License-Expression: AGPL-3.0-or-later
@@ -23,8 +23,8 @@ Requires-Dist: build>=1.2.0; extra == "dev"
 Requires-Dist: twine>=5.0.0; extra == "dev"
 Dynamic: license-file
 
-[![pipeline status](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/badges/main/pipeline.svg)](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/-/pipelines)
-[![coverage report](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/badges/main/coverage.svg?job=tests)](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/-/commits/main)
+[![pipeline status](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/badges/master/pipeline.svg)](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/-/pipelines)
+[![coverage report](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/badges/master/coverage.svg?job=tests)](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/-/commits/main)
 
 # `split3c`
 
@@ -76,7 +76,7 @@ split3c resolve --help
 
 Restriction enzyme-based workflow for Hi-C / HiChIP / 3C-like libraries.
 
-![split3c re-site workflow](docs/images/resite-workflow.png)
+![split3c re-site workflow](doc/img/resite-workflow.png)
 
 ---
 
@@ -84,17 +84,16 @@ Restriction enzyme-based workflow for Hi-C / HiChIP / 3C-like libraries.
 
 Non-specific ligation workflow for Micro-C-like libraries.
 
-![split3c ns-site workflow](docs/images/nssite-workflow.png)
+![split3c ns-site workflow](doc/img/nssite-workflow.png)
 
 ---
 
 ## Benchmark
 
-![split3c benchmark](docs/images/benchmark.png)
+![split3c benchmark](doc/img/benchmark.png)
 
 ---
 
 ## License
 
 split3c is released under the AGPLv3 license.
-

{split3c-0.0.1 → split3c-0.0.2}/README.md

@@ -1,5 +1,5 @@
-[![pipeline status](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/badges/main/pipeline.svg)](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/-/pipelines)
-[![coverage report](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/badges/main/coverage.svg?job=tests)](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/-/commits/main)
+[![pipeline status](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/badges/master/pipeline.svg)](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/-/pipelines)
+[![coverage report](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/badges/master/coverage.svg?job=tests)](https://gitbio.ens-lyon.fr/LBMC/physbio/split3c/-/commits/main)
 
 # `split3c`
 
@@ -51,7 +51,7 @@ split3c resolve --help
 
 Restriction enzyme-based workflow for Hi-C / HiChIP / 3C-like libraries.
 
-![split3c re-site workflow](docs/images/resite-workflow.png)
+![split3c re-site workflow](doc/img/resite-workflow.png)
 
 ---
 
@@ -59,17 +59,16 @@ Restriction enzyme-based workflow for Hi-C / HiChIP / 3C-like libraries.
 
 Non-specific ligation workflow for Micro-C-like libraries.
 
-![split3c ns-site workflow](docs/images/nssite-workflow.png)
+![split3c ns-site workflow](doc/img/nssite-workflow.png)
 
 ---
 
 ## Benchmark
 
-![split3c benchmark](docs/images/benchmark.png)
+![split3c benchmark](doc/img/benchmark.png)
 
 ---
 
 ## License
 
 split3c is released under the AGPLv3 license.
-

{split3c-0.0.1 → split3c-0.0.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "split3c"
-version = "0.0.1"
+version = "0.0.2"
 description = "Toolkit to split and resolve chimeric 3C/Hi-C/Micro-C reads"
 readme = "README.md"
 requires-python = ">=3.12"

{split3c-0.0.1 → split3c-0.0.2}/src/split3c/cli.py

@@ -1,7 +1,7 @@
 """
-This script is a the split3c project, designed to process paired-end FASTQ files by fragmenting DNA sequences at specified restriction enzyme sites.
+This script is a the split3c project ; split3c is a toolkit for preprocessing 3C-type sequencing libraries and converting BAM alignments into .pairs files for chromatin contact analysis.
 
-Copyright © 2024 Samir Bertache
+Copyright © 2026 Samir Bertache
 
 SPDX-License-Identifier: AGPL-3.0-or-later
 

{split3c-0.0.1 → split3c-0.0.2}/src/split3c/nssite/auxiliary.py

@@ -1,3 +1,27 @@
+"""
+This script is a the split3c project, designed to process paired-end FASTQ files by fragmenting DNA sequences at specified unmapped site. Constructs to analyse Micro-C/CAD-C data
+
+Copyright © 2024 Samir Bertache
+
+SPDX-License-Identifier: AGPL-3.0-or-later
+
+===============================================================================
+
+This program is free software: you can redistribute it and/or modify it under
+the terms of the GNU Affero General Public License as published by the
+Free Software Foundation, either version 3 of the License, or (at your option)
+any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+See the GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program. If not, see <https://www.gnu.org/licenses/>.
+"""
+
+
 def signal_handler(sig, frame, out_f, out_r=None):
     """
     Handle termination signals to gracefully terminate processes.
@@ -43,27 +67,37 @@ def signal_handler(sig, frame, out_f, out_r=None):
 
 def partitionning(num_threads: int, single_bam: bool = False) -> tuple[int, int, int]:
     """
-    Heuristique empirique de partition des ressources pour microsplit.
+    Empirical resource partitioning heuristic for microsplit.
+
+    Returns:
+
+    pigz_threads_per_file: pigz threads per file (F and R)
 
-    Retourne:
-      pigz_threads_per_file : threads pigz par fichier (F et R)
-      compute_processes     : nb de workers process_items
-      bam_threads           : threads pysam/htslib par fichier (lecture ET écriture)
+    compute_processes: number of process_items
+
+    bam_threads: pysam/htslib threads per file (read AND write)
 
     IMPORTANT
-    ---------
-    Cette fonction est volontairement empirique (surallocation CPU acceptée).
-    `num_threads` est un *hint* de cœurs disponibles, pas un budget strict.
 
-    Points de calibration (bench observés)
+    --------- This function is intentionally empirical (CPU overallocation is accepted).
+
+    `num_threads` is a *hint* of available cores, not a strict budget.
+
+    Calibration points (observed benchmarks)
+
     --------------------------------------
-    - 4  cœurs -> (1, 1, 1)
-    - 8  cœurs -> (2, 3, 1)
-    - 16 cœurs -> (3, 4, 3)
 
-    En mode single_bam=True :
-    - on double les threads BAM, car un seul flux BAM doit alimenter toute la pipeline
-    - pigz_per_file et compute_processes restent inchangés
+    - ​​4 cores -> (1, 1, 1)
+
+    - 8 cores -> (2, 3, 1)
+
+    - 16 cores -> (3, 4, 3)
+
+    In single_bam=True mode:
+
+    - The number of BAM threads is doubled, as a single BAM stream must feed the entire pipeline.
+
+    - pigz_per_file and compute_processes remain unchanged.
 
     Doctests
     --------

{split3c-0.0.1 → split3c-0.0.2}/src/split3c/nssite/bam.py

@@ -1,7 +1,31 @@
+"""
+This script is a the split3c project, designed to process paired-end FASTQ files by fragmenting DNA sequences at specified unmapped site. Constructs to analyse Micro-C/CAD-C data
+
+Copyright © 2024 Samir Bertache
+
+SPDX-License-Identifier: AGPL-3.0-or-later
+
+===============================================================================
+
+This program is free software: you can redistribute it and/or modify it under
+the terms of the GNU Affero General Public License as published by the
+Free Software Foundation, either version 3 of the License, or (at your option)
+any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+See the GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program. If not, see <https://www.gnu.org/licenses/>.
+"""
+
+
 def get_bam_headers(bam_for_path, bam_rev_path):
     """
-    Ouvre les fichiers BAM, extrait leurs headers sous forme de dictionnaire,
-    et referme les fichiers immédiatement.
+    Open the BAM files, extract their headers as a dictionary,
+    and close the files immediately.
 
     Returns:
         tuple: (header_dict_forward, header_dict_reverse)
@@ -76,7 +100,7 @@ def write_bam_pair_from_sam(
     bam_threads=1,
 ):
     """
-    Écrit les paires BAM en utilisant les dictionnaires de header fournis.
+    Writes the BAM pairs using the provided header dictionaries.
     """
     import sys
 
@@ -122,8 +146,9 @@ def write_bam_pair_from_sam(
 
 def get_bam_header_single(bam_path):
     """
-    Ouvre un BAM unique, extrait son header sous forme de dictionnaire,
-    puis referme le fichier.
+    Opens a single BAM file, extracts its header as a dictionary,
+    then closes the file.
+
 
     Returns
     -------
@@ -138,23 +163,25 @@ def get_bam_header_single(bam_path):
 
 def _pair_reads_from_single_bam(read_a, read_b, strict=True):
     """
-    Ordonne deux lectures provenant d'un BAM interleavé en (forward/read1, reverse/read2).
+    Orders two reads from a BAM interleaved as (forward/read1, reverse/read2).
 
-    Paramètres
+    Parameters
     ----------
-    read_a, read_b : pysam.AlignedSegment
-    strict : bool
-        Si True, lève une erreur en cas d'incohérence forte.
-        Si False, tente un fallback par ordre d'apparition.
+    read_a, read_b: pysam.AlignedSegment
+    strict: bool
+    If True, raises an error in case of a strong inconsistency.
+
+    If False, attempts a fallback in order of appearance.
 
     Returns
-    -------
+    ------
     tuple
-        (read_for, read_rev)
+
+    (read_for, read_rev)
 
     Notes
     -----
-    On utilise en priorité les flags 0x40 / 0x80 (is_read1 / is_read2).
+    Flags 0x40 / 0x80 (is_read1 / is_read2) are used as the primary method.
     """
     if read_a is None or read_b is None:
         raise ValueError("Pairing failure: one of the reads is None.")
@@ -178,28 +205,30 @@ def read_bam_interleaved(
     strict=True,
 ):
     """
-    Lit un BAM unique interleavé (une ligne forward/read1 suivie de la ligne reverse/read2) et envoie des batchs de paires SAM dans input_queue.
+    Reads a single interleaved BAM (a forward/read1 line followed by a reverse/read2 line) and sends batches of SAM pairs to input_queue.
+
+    Output contract identical to read_bam_pair:
 
-    Contrat de sortie identique à read_bam_pair:
-        batch = list[(sam_f, sam_r)]
+    batch = list[(sam_f, sam_r)]
 
-    Paramètres
+    Parameters
     ----------
-    bam_file : str
-        Chemin vers un BAM unique interleavé.
-    input_queue : multiprocessing.Queue
-    num_processes : int
-        Nombre de workers compute, pour envoyer les sentinelles None.
-    bam_threads : int
-        Threads pysam/htslib.
-    batch_size : int
-        Taille des batchs.
-    strict : bool
-        Si True, échoue si les paires ne sont pas parfaitement cohérentes.
-
-    Exigences
+    bam_file: str
+    Path to a single interleaved BAM.
+    input_queue: multiprocessing.Queue
+
+    num_processes: int
+    Number of compute workers, to send sentinels. None.
+    bam_threads: int
+    Pysam/htslib threads.
+    batch_size: int
+    Batch size.
+    strict: bool
+    If True, fails if the pairs are not perfectly matched.
+
+    Requirements
     ---------
-    Le BAM doit être ordonné par nom ou au minimum avoir les deux mates consécutives.
+    The BAM must be ordered by name or, at a minimum, have two consecutive pairs.
     """
     import sys
 
@@ -250,21 +279,25 @@ def write_bam_interleaved_from_sam(
     bam_threads=1,
 ):
     """
-    Écrit les paires BAM non splittables dans un BAM unique interleavé.
+    Writes non-splittable BAM pairs into a single interleaved BAM.
 
-    Contrat d'entrée:
-        queue contient des batchs list[(sam_f, sam_r)]
+    Input contract:
 
-    Sortie:
-        un seul BAM avec read1 puis read2 à la suite.
+    queue contains batches `list[(sam_f, sam_r)]`
 
-    Paramètres
+    Output:
+
+    a single BAM with `read1` followed by `read2`.
+
+    Parameters
     ----------
-    queue : multiprocessing.Queue
-    out_bam_path : str
-    header_dict : dict
-    num_procs_finished_signal : int
-    bam_threads : int
+    queue: multiprocessing.Queue
+
+    out_bam_path: str
+
+    header_dict: dict
+    num_procs_finished_signal: int
+    bam_threads: int
     """
     import sys
 

{split3c-0.0.1 → split3c-0.0.2}/src/split3c/nssite/fastq.py

@@ -1,3 +1,27 @@
+"""
+This script is a the split3c project, designed to process paired-end FASTQ files by fragmenting DNA sequences at specified unmapped site. Constructs to analyse Micro-C/CAD-C data
+
+Copyright © 2024 Samir Bertache
+
+SPDX-License-Identifier: AGPL-3.0-or-later
+
+===============================================================================
+
+This program is free software: you can redistribute it and/or modify it under
+the terms of the GNU Affero General Public License as published by the
+Free Software Foundation, either version 3 of the License, or (at your option)
+any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+See the GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program. If not, see <https://www.gnu.org/licenses/>.
+"""
+
+
 def open_output(output_forward, output_reverse, write_processes):
     """
     Open output files for writing with pigz compression.

{split3c-0.0.1 → split3c-0.0.2}/src/split3c/nssite/main.py

@@ -1,5 +1,5 @@
 """
-This script is a the split3c project, designed to process paired-end FASTQ files by fragmenting DNA sequences at specified restriction enzyme sites.
+This script is a the split3c project, designed to process paired-end FASTQ files by fragmenting DNA sequences at specified unmapped site. Constructs to analyse Micro-C/CAD-C data
 
 Copyright © 2024 Samir Bertache
 
@@ -150,7 +150,7 @@ def _print_banner() -> None:
             "[bold blue]Microsplit[/bold blue]\n"
             "Process paired BAM (Micro-C) into paired FASTQ.\n\n"
             "Use --help to see detailed options.",
-            title="[bold green]microsplit-cut[/bold green]",
+            title="[bold green]split3c nssite-cut[/bold green]",
             subtitle=f"Version: {__version__}",
             expand=True,
             width=100,
@@ -202,8 +202,8 @@ def main_cli(argv: Optional[list[str]] = None) -> int:
         ),
         epilog=(
             "Examples:\n"
-            " \tmicrosplit -1 fwd.bam -2 rev.bam -o1 R1.fastq.gz -o2 R2.fastq.gz -t 12 -s 20 -l 0 --pairing-mode cover \n"
-            "  \tmicrosplit -1 merged.bam --single-bam -o1 R1.fastq.gz -o2 R2.fastq.gz -t 12 -s 20 --pairing-mode all\n"
+            " \tsplit3c nssite -1 fwd.bam -2 rev.bam -o1 R1.fastq.gz -o2 R2.fastq.gz -t 12 -s 20 -l 0 --pairing-mode cover \n"
+            "  \tsplit3c nssite -1 merged.bam --single-bam -o1 R1.fastq.gz -o2 R2.fastq.gz -t 12 -s 20 --pairing-mode all\n"
         ),
         formatter_class=_formatter_class(),
     )

{split3c-0.0.1 → split3c-0.0.2}/src/split3c/nssite/processmanager.py

@@ -1,6 +1,30 @@
-from multiprocessing import Process, Queue
+"""
+This script is a the split3c project, designed to process paired-end FASTQ files by fragmenting DNA sequences at specified unmapped site. Constructs to analyse Micro-C/CAD-C data
+
+Copyright © 2024 Samir Bertache
+
+SPDX-License-Identifier: AGPL-3.0-or-later
+
+===============================================================================
+
+This program is free software: you can redistribute it and/or modify it under
+the terms of the GNU Affero General Public License as published by the
+Free Software Foundation, either version 3 of the License, or (at your option)
+any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+See the GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program. If not, see <https://www.gnu.org/licenses/>.
+"""
+
 import sys
 import traceback
+from multiprocessing import Process, Queue
+
 
 class WorkerProcess(Process):
     def __init__(self, target, args, error_queue):
@@ -15,6 +39,7 @@ class WorkerProcess(Process):
             self.error_queue.put((str(e), traceback.format_exc()))
             sys.exit(1)
 
+
 class ProcessManager:
     def __init__(self):
         self.processes = []

{split3c-0.0.1 → split3c-0.0.2}/src/split3c/nssite/split.py

@@ -1,3 +1,26 @@
+"""
+This script is a the split3c project, designed to process paired-end FASTQ files by fragmenting DNA sequences at specified unmapped site. Constructs to analyse Micro-C/CAD-C data
+
+Copyright © 2024 Samir Bertache
+
+SPDX-License-Identifier: AGPL-3.0-or-later
+
+===============================================================================
+
+This program is free software: you can redistribute it and/or modify it under
+the terms of the GNU Affero General Public License as published by the
+Free Software Foundation, either version 3 of the License, or (at your option)
+any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+See the GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program. If not, see <https://www.gnu.org/licenses/>.
+"""
+
 import logging
 import os
 import signal
@@ -256,14 +279,15 @@ def process_cigard(name, sequence, quality, cigar, seed_size, len_add):
 
 def read_name(base_name, tag_i, tag_j, tot_for, tot_rev, tags=None):
     """
-    Construit un header de paire à partir d'un nom de read et de deux tags.
+    Constructs a pair header from a read name and two tags.
+
+    `base_name`: logical name of the read (e.g., '@READ')
+    `tag_i`, `tag_j`: fragment identifiers, typically 'F1', 'R1', etc. (1-based)
+    `tot_for`, `tot_rev`: total number of forward/reverse fragments
 
-    base_name : nom logique du read (ex: '@READ')
-    tag_i, tag_j : identifiants de fragments, typiquement 'F1', 'R1', etc. (1-based)
-    tot_for, tot_rev : nombres totaux de fragments forward / reverse
+    Return (origin/reverse mode):
 
-    Retour (mode origin/o):
-        '<base_name>:[<tag_i>,<tag_j>:FT<tot_for>,RT<tot_rev>]'
+    '<base_name>:[<tag_i>,<tag_j>:FT<tot_for>,RT<tot_rev>]'
 
     Examples
     --------
@@ -288,7 +312,7 @@ def read_name(base_name, tag_i, tag_j, tot_for, tot_rev, tags=None):
 
 def _fraglist_to_entries(frag_list, origin):
     """
-    Transforme une liste de FastQ en tuples (origin, idx, seq, qual).
+    Transforms a list of FastQ into tuples (origin, idx, seq, qual).
 
     Examples
     --------
@@ -308,7 +332,7 @@ def _fraglist_to_entries(frag_list, origin):
 
 def _emit_pair(base_name, e1, e2, tot_for, tot_rev, tags=None):
     """
-    Construit une paire FASTQ textuelle à partir de deux entrées.
+    Constructs a textual FASTQ pair from two inputs.
 
     e = (origin, idx, seq, qual)
     """
@@ -326,15 +350,15 @@ def _emit_pair(base_name, e1, e2, tot_for, tot_rev, tags=None):
 
 def gen_read_pairs_from_frags_cover(base_name, frags_f, frags_r, tags=None):
     """
-    Génère un nombre minimal (ou quasi minimal) de paires pour que
-    chaque fragment apparaisse au moins une fois.
+    Generates a minimal (or near-minimal) number of pairs so that
+    each fragment appears at least once.
 
-    Stratégie:
-    1. appariement F-R tant que possible
-    2. appariement des restes au sein du même côté
-    3. si un fragment reste seul, on le rattache à un anchor déjà utilisé
+    Strategy:
+        1. Match F-R whenever possible
+        2. Match remainders within the same side
+        3. If a fragment remains alone, reattach it to an already used anchor
 
-    Complexité: O(F + R)
+    Complexity: O(F + R)
 
     Examples
     --------
@@ -425,14 +449,14 @@ def gen_read_pairs_from_frags_cover(base_name, frags_f, frags_r, tags=None):
 
 def gen_read_pairs_from_frags_all(base_name, frags_f, frags_r, tags=None):
     """
-    Génère deux chaînes FastQ (forward/reverse) à partir de fragments déjà splittés.
+    Generates two FastQ (forward/reverse) chains from already split fragments.
 
-    `frags_f` et `frags_r` sont des listes de fragments FASTQ complets:
+    `frags_f` et `frags_r` are lists of complete FASTQ fragments :
         '@name\\nSEQ\\n+\\nQUAL\\n'
 
     Examples
     --------
-    Cas simple : 1 fragment forward, 1 fragment reverse (une seule combinaison).
+    Simple case : 1 fragment forward, 1 fragment reverse (only one combinaison).
     >>> frags_f = ["@x\\nAC\\n+\\n??\\n"]
     >>> frags_r = ["@x\\nTG\\n+\\n!!\\n"]
     >>> F, R = gen_read_pairs_from_frags_all("@READ", frags_f, frags_r)
@@ -441,14 +465,14 @@ def gen_read_pairs_from_frags_all(base_name, frags_f, frags_r, tags=None):
     >>> R
     '@READ:[F1,R1:FT1,RT1]\\nTG\\n+\\n!!\\n'
 
-    Même cas, sans tag (nt).
+    Same one, without tag (nt).
     >>> F, R = gen_read_pairs_from_frags_all("@READ", frags_f, frags_r, tags="nt")
     >>> F
     '@READ\\nAC\\n+\\n??\\n'
     >>> R
     '@READ\\nTG\\n+\\n!!\\n'
 
-    Cas combinatoire :
+    Combinatorial case :
       - forward: 2 fragments (F0, F1)
       - reverse: 1 fragment (R0)
       -> combinaisons : (F0,F1), (F0,R0), (F1,R0)
@@ -470,7 +494,7 @@ def gen_read_pairs_from_frags_all(base_name, frags_f, frags_r, tags=None):
     >>> R
     '@READ:[F1,F2:FT2,RT1]\\nBCD\\n+\\n===\\n@READ:[F1,R1:FT2,RT1]\\nWXYZ\\n+\\n>>>>\\n@READ:[F2,R1:FT2,RT1]\\nWXYZ\\n+\\n>>>>\\n'
 
-    Cas combinatoire symétrique (2 fragments forward, 2 fragments reverse).
+    Symmetric combinatorial case (2 fragments forward, 2 fragments reverse).
     >>> frags_f = ["@x\\nA\\n+\\n!\\n", "@x\\nBC\\n+\\n!!\\n"]
     >>> frags_r = ["@x\\nD\\n+\\n#\\n", "@x\\nEF\\n+\\n##\\n"]
     >>> F, R = gen_read_pairs_from_frags_all("@READ", frags_f, frags_r)
@@ -480,17 +504,16 @@ def gen_read_pairs_from_frags_all(base_name, frags_f, frags_r, tags=None):
     """
     from itertools import combinations
 
-    # Cas combinatoire: on annote chaque fragment avec son origine (F/R) et un index local
     def _to_entries(frag_list, origin):
         """
-        Transforme une liste de FastQ en tuples (origin, idx, seq, qual).
+        Transforms a list of FastQ into tuples (origin, idx, seq, qual).
         frag = '@smth\\nSEQ\\n+\\nQUAL\\n'
         """
         entries = []
         for idx, frag in enumerate(frag_list):
             lines = frag.strip().split("\n")
             if len(lines) != 4 or lines[2] != "+":
-                raise ValueError("Fragment FastQ invalide dans process_cigard.")
+                raise ValueError("FastQ Fragment invalid in process_cigard.")
             seq = lines[1]
             qual = lines[3]
             entries.append((origin, idx, seq, qual))
@@ -520,7 +543,7 @@ def gen_read_pairs_from_frags(
     base_name, frags_f, frags_r, tags=None, pairing_mode="all"
 ):
     """
-    Dispatcher entre plusieurs stratégies de génération de paires.
+    Dispatch between several pair generation strategies.
     """
     if pairing_mode == "all":
         return gen_read_pairs_from_frags_all(base_name, frags_f, frags_r, tags=tags)
@@ -530,7 +553,6 @@ def gen_read_pairs_from_frags(
         raise ValueError(f"Unknown pairing_mode: {pairing_mode}")
 
 
-# Pensez à la gestion de seq = "*"
 def sam_fields(sam_line: str):
     """
     Return minimal information

split3c-0.0.2/src/split3c/resite/__init__.py

@@ -0,0 +1,4 @@
+from .frag import process_items
+from .pretreatment import partition_threads, search_in_database
+from .read import read_fastq_gzip_simultaneously
+from .write_control import manage_pigz_problems, open_output, write_pairs

{split3c-0.0.1 → split3c-0.0.2}/src/split3c/resite/frag.py

@@ -1,5 +1,5 @@
 """
-This script is a the split3c project, designed to process paired-end FASTQ files by fragmenting DNA sequences at specified restriction enzyme sites.
+This script is a the split3c project, designed to process paired-end FASTQ files by fragmenting DNA sequences at specified unmapped.
 
 Copyright © 2024 Samir Bertache
 
@@ -286,7 +286,7 @@ def processing_fr(
     """
     Process the sequences to generate buffers for forward and reverse reads
     selon le mode FR (un fragment forward + un fragment reverse).
-    N'ajoute pas de suffixe :ij si une seule paire.
+    Do not add the suffix :ij if there is only one pair.
 
     Doctests:
     >>> seqs = ["AAAACCCCGGGG", "TTTTGGGGCCCC"]