Enforce start codon + fix bug explicitly setting training data on command line

README.md

@@ -242,7 +242,7 @@ This library is provided under the [GNU General Public License v3.0](https://cho
 The Prodigal code was written by [Doug Hyatt](https://github.com/hyattpd) and is distributed under the
 terms of the GPLv3 as well. See `vendor/Prodigal/LICENSE` for more information.
 
-*This project is in no way not affiliated, sponsored, or otherwise endorsed
+*This project is in no way affiliated, sponsored, or otherwise endorsed
 by the [original Prodigal authors](https://github.com/hyattpd). It was developed
 by [Martin Larralde](https://github.com/althonos/) during his PhD project
 at the [European Molecular Biology Laboratory](https://www.embl.de/) in

docs/guide/cli.rst

@@ -19,6 +19,8 @@ exceptions:
   however the stream cannot be compressed.
 - The GenBank output of Pyrodigal is a full GenBank record including the 
   input sequence, unlike Prodigal which only outputs the features section.
+- Start codons can be enforced now with ``-c start``, for backwards compatibility, 
+  ``-c`` alone is equivalent to ``-c none``.
 
 Flags
 -----
@@ -28,7 +30,7 @@ The Pyrodigal CLI has all the flags of the original CLI:
 .. code-block:: text
 
     -a trans_file         Write protein translations to the selected file.
-    -c                    Closed ends. Do not allow genes to run off edges.
+    -c [mode]             Closed ends. Do not allow genes to run off edges. Can be at start and/or stop site. Options are 'both', 'start', or 'none'. (default: none)
     -d nuc_file           Write nucleotide sequences of genes to the selected file.
     -f output_type        Select output format.
     -g tr_table           Specify a translation table to use.

docs/guide/publications.rst

@@ -38,7 +38,6 @@ Pyrodigal is being used in the following research works:
 - Sirén K., Millard, A., Petersen, B., Gilbert, M. T. P., Clokie, M. RJ., Sicheritz-Pontén, T. Rapid discovery of novel prophages using biological feature engineering and machine learning. bioRxiv 2020.08.09.243022; :doi:`10.1101/2020.08.09.243022`.
 - Turkington, C. J. R., Nezam Abadi, N., Edwards, R. A., Grasis, J. A.  hafeZ: Active prophage identification through read mapping. bioRxiv 2021.07.21.453177; :doi:`10.1101/2021.07.21.453177`.
 - Reynolds, R., Hyun, S., Tully, B., Bien, J., Levine, N. M. Identification of microbial metabolic functional guilds from large genomic datasets. Front Microbiol. 2023 Jun 30;14:1197329. :doi:`10.3389/fmicb.2023.1197329`.
-- Bouras, G., Grigson, S., Papudeshi, B., Mallawaarachchi, V., Roach, M.  Dnaapler: A tool to reorient circular microbial genomes. Journal of Open Source Software, 9(93), 5968. :doi:`10.21105/joss.05968`.
 - Mainguy J, Hoede C. Binette: a fast and accurate bin refinement tool to construct high quality Metagenome Assembled Genomes. bioRxiv 2024.04.20.585171; :doi:`10.1101/2024.04.20.585171`.
 - Ridley, R. S. Jr, Conrad, R. E., Lindner, B. G., Woo, S., Konstantinidis, K. T.  Potential routes of plastics biotransformation involving novel plastizymes revealed by global multi-omic analysis of plastic associated microbes. Sci Rep 14, 8798 (2024). :doi:`10.1038/s41598-024-59279-x`.
 - Figueroa, J. L. III, Dhungel, E., Bellanger, M., Brouwer, C. R., White, R. A. III. MetaCerberus: distributed highly parallelized HMM-based processing for robust functional annotation across the tree of life. Bioinformatics, Volume 40, Issue 3, March 2024, btae119. :doi:`10.1093/bioinformatics/btae119`.

src/pyrodigal/cli.py

@@ -78,12 +78,22 @@ def argument_parser(
         metavar="trans_file",
         help="Write protein translations to the selected file.",
     )
+    #parser.add_argument(
+    #    "-c",
+    #    required=False,
+    #    action="store_true",
+    #    help="Closed ends. Do not allow genes to run off edges.",
+    #    default=False,
+    #)
     parser.add_argument(
         "-c",
         required=False,
-        action="store_true",
-        help="Closed ends. Do not allow genes to run off edges.",
-        default=False,
+        metavar="mode",
+        help="Closed ends. Do not allow genes to run off edges. Can be at start and/or stop site. Options are 'both', 'start', or 'none'.",
+        choices={"both", "start", "none"},
+        default="none",
+        nargs='?',
+        const="both",
     )
     parser.add_argument(
         "-d",
@@ -256,10 +266,18 @@ def main(
             # open input (with support for compressed files)
             input_file = stdin if args.i is None else ctx.enter_context(zopen(args.i))
 
+            # select closed type
+            if args.c == "both" or args.c == "":
+                closed = [True, True]
+            elif args.c == "start":
+                closed = [True, False]
+            else:
+                closed = [False, False]
+
             # initialize the ORF finder
             gene_finder = gene_finder_factory(
                 meta=args.p == "meta",
-                closed=args.c,
+                closed=closed,
                 mask=args.m,
                 training_info=training_info,
                 min_gene=args.min_gene,
@@ -268,7 +286,7 @@ def main(
             )
 
             # pre-train if in training mode
-            if args.p == "single":
+            if args.p == "single" and training_info is None:
                 # use the same interleaving logic as Prodigal
                 sequences = list(parse(input_file))
                 training_info = gene_finder.train(

src/pyrodigal/lib.pxd

@@ -236,7 +236,8 @@ cdef class Nodes:
         self,
         Sequence sequence,
         const int translation_table,
-        const bint closed,
+        const bint closed_start,
+        const bint closed_stop,
         const int min_gene,
         const int min_edge_gene
     ) except -1 nogil
@@ -261,7 +262,8 @@ cdef class Nodes:
         self,
         Sequence seq,
         const _training* tinf,
-        const bint closed,
+        const bint closed_start,
+        const bint closed_stop,
         const bint is_meta
     ) except -1 nogil
     cdef int _sort(self) except 1 nogil
@@ -391,7 +393,9 @@ cdef _metagenomic_bin _METAGENOMIC_BINS[NUM_META]
 cdef class GeneFinder:
     cdef readonly size_t          _num_seq
     cdef readonly str             backend
-    cdef readonly bint            closed
+    cdef readonly object            closed
+    cdef readonly bint            closed_start
+    cdef readonly bint            closed_stop
     cdef readonly object          lock
     cdef readonly bint            mask
     cdef readonly int             min_mask

src/pyrodigal/lib.pyi

@@ -3,11 +3,11 @@ import datetime
 import threading
 import typing
 from typing import (
+    Dict,
     FrozenSet,
     Iterable,
     Iterator,
     List,
-    Dict,
     Optional,
     TextIO,
     Tuple,
@@ -42,12 +42,50 @@ IDEAL_SINGLE_GENOME: int
 PRODIGAL_VERSION: str
 
 _TRANSLATION_TABLE = Literal[
-    1, 2, 3, 4, 5, 6, 9, 10, 11, 12, 13, 14, 15, 16, 21, 22, 23, 24, 25,
-    26, 29, 30, 32, 33
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    29,
+    30,
+    32,
+    33,
 ]
 _DIVISION = Literal[
-    "PRI", "ROD", "MAM", "VRT", "INV", "PLN", "BCT", "VRL", "PHG", "SYN",
-    "UNA", "EST", "PAT", "STS", "GSS", "HTG", "HTC", "ENV"
+    "PRI",
+    "ROD",
+    "MAM",
+    "VRT",
+    "INV",
+    "PLN",
+    "BCT",
+    "VRL",
+    "PHG",
+    "SYN",
+    "UNA",
+    "EST",
+    "PAT",
+    "STS",
+    "GSS",
+    "HTG",
+    "HTC",
+    "ENV",
 ]
 
 # --- Sequence mask ----------------------------------------------------------
@@ -158,7 +196,8 @@ class Nodes(typing.Sequence[Node]):
         self,
         sequence: Sequence,
         *,
-        closed: bool = False,
+        closed_start: bool = False,
+        closed_stop: bool = False,
         min_gene: int = 90,
         min_edge_gene: int = 60,
         translation_table: _TRANSLATION_TABLE = 11,
@@ -169,7 +208,8 @@ class Nodes(typing.Sequence[Node]):
         sequence: Sequence,
         training_info: TrainingInfo,
         *,
-        closed: bool = False,
+        closed_start: bool = False,
+        closed_stop: bool = False,
         is_meta: bool = False,
     ) -> None: ...
     def sort(self) -> None: ...
@@ -347,11 +387,15 @@ class TrainingInfo:
     @property
     def upstream_compositions(self) -> memoryview: ...
     @upstream_compositions.setter
-    def upstream_compositions(self, upstream_compositions: Iterable[Iterable[float]]) -> None: ...
+    def upstream_compositions(
+        self, upstream_compositions: Iterable[Iterable[float]]
+    ) -> None: ...
     @property
     def motif_weights(self) -> memoryview: ...
     @motif_weights.setter
-    def motif_weights(self, motif_weights: Iterable[Iterable[Iterable[float]]]) -> None: ...
+    def motif_weights(
+        self, motif_weights: Iterable[Iterable[Iterable[float]]]
+    ) -> None: ...
     @property
     def missing_motif_weight(self) -> float: ...
     @missing_motif_weight.setter
@@ -363,7 +407,6 @@ class TrainingInfo:
     def to_dict(self) -> Dict[str, object]: ...
     def dump(self, fp: typing.BinaryIO) -> None: ...
 
-
 # --- Metagenomic Bins -------------------------------------------------------
 
 class MetagenomicBin:
@@ -384,8 +427,9 @@ class MetagenomicBins(typing.Sequence[MetagenomicBin]):
     @typing.overload
     def __getitem__(self, index: slice) -> MetagenomicBins: ...
     @typing.overload
-    def __getitem__(self, index: Union[int, slice]) -> Union[MetagenomicBin, MetagenomicBins]: ...
-
+    def __getitem__(
+        self, index: Union[int, slice]
+    ) -> Union[MetagenomicBin, MetagenomicBins]: ...
 
 # --- Pyrodigal --------------------------------------------------------------
 
@@ -398,7 +442,7 @@ class GeneFinder:
         *,
         meta: bool = False,
         metagenomic_bins: Optional[MetagenomicBins] = None,
-        closed: bool = False,
+        closed: list = [False, False],
         mask: bool = False,
         min_mask: int = 50,
         min_gene: int = 90,
@@ -413,7 +457,11 @@ class GeneFinder:
     @property
     def meta(self) -> bool: ...
     @property
-    def closed(self) -> bool: ...
+    def closed(self) -> list: ...
+    @property
+    def closed_start(self) -> bool: ...
+    @property
+    def closed_stop(self) -> bool: ...
     @property
     def mask(self) -> bool: ...
     @property