PythiaLabelGenerator 1.0.0__tar.gz → 1.2.0__tar.gz

pythialabelgenerator-1.2.0/.gitattributes

@@ -0,0 +1 @@
+pixi.lock linguist-generated=true

pythialabelgenerator-1.2.0/.github/workflows/publish-pypi.yml

@@ -0,0 +1,63 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: pypi-${{ github.event.release.tag_name }}
+  cancel-in-progress: false
+
+jobs:
+  validate-release:
+    name: Validate release version
+    if: github.event_name == 'release' && github.event.action == 'published' && !github.event.release.draft && !github.event.release.prerelease
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out released commit
+        uses: actions/checkout@v7
+      - name: Set up Python
+        uses: actions/setup-python@v7
+        with:
+          python-version: '3.14'
+      - name: Check tag matches package version
+        env:
+          RELEASE_TAG: ${{ github.event.release.tag_name }}
+        run: |
+          python - <<'PY'
+          import os
+          import pathlib
+          import tomllib
+
+          version = tomllib.loads(pathlib.Path("pyproject.toml").read_text())["project"]["version"]
+          tag = os.environ["RELEASE_TAG"]
+          if tag != version:
+              raise SystemExit(f"Release tag {tag!r} must match package version {version!r}")
+          print(f"Validated release {version}")
+          PY
+
+  test-and-build:
+    name: Test and build release
+    needs: validate-release
+    uses: ./.github/workflows/test-label-generator.yml
+
+  publish:
+    name: Upload distributions to PyPI
+    needs: test-and-build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/project/PythiaLabelGenerator/
+    permissions:
+      id-token: write
+    steps:
+      - name: Download tested distributions
+        uses: actions/download-artifact@v8
+        with:
+          name: python-distributions
+          path: dist/
+      - name: Publish distributions
+        uses: pypa/gh-action-pypi-publish@v1.14.2

pythialabelgenerator-1.2.0/.github/workflows/test-label-generator.yml

@@ -0,0 +1,89 @@
+name: Build and test LabelGenerator
+run-name: Build and test the LabelGenerator Python library
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+  workflow_call:
+
+permissions:
+  contents: read
+
+jobs:
+  pixi-tests:
+    name: Pixi tests (${{ matrix.os }}, ${{ matrix.environment }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+        environment: [py311, py314, legacy-raxml]
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v7
+      - name: Set up Pixi
+        uses: prefix-dev/setup-pixi@v0.10.2
+        with:
+          pixi-version: v0.77.0
+          environments: ${{ matrix.environment }}
+          frozen: true
+          cache: true
+          cache-write: ${{ github.event_name == 'push' && github.ref_name == 'main' }}
+      - name: Check the lock file
+        run: pixi lock --check
+      - name: Check RAxML-NG and IQ-TREE
+        run: pixi run --frozen --environment ${{ matrix.environment }} binary-smoke
+      - name: Run the test suite
+        run: pixi run --frozen --environment ${{ matrix.environment }} test
+      - name: Check the CLI
+        run: pixi run --frozen --environment ${{ matrix.environment }} cli-smoke
+
+  package-smoke:
+    name: Python package smoke test (${{ matrix.os }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v7
+      - name: Set up Pixi
+        uses: prefix-dev/setup-pixi@v0.10.2
+        with:
+          pixi-version: v0.77.0
+          environments: build
+          frozen: true
+          cache: true
+      - name: Check the lock file
+        run: pixi lock --check
+      - name: Build and verify distributions
+        run: pixi run --frozen package-smoke
+      - name: Check distribution filenames
+        run: |
+          pixi run --frozen --environment build python - <<'PY'
+          import pathlib
+          import tomllib
+
+          version = tomllib.loads(pathlib.Path("pyproject.toml").read_text())["project"]["version"]
+          expected = {
+              f"pythialabelgenerator-{version}-py3-none-any.whl",
+              f"pythialabelgenerator-{version}.tar.gz",
+          }
+          actual = {path.name for path in pathlib.Path("dist").iterdir()}
+          if actual != expected:
+              raise SystemExit(f"Expected distributions {sorted(expected)}, found {sorted(actual)}")
+          PY
+      - name: Upload tested distributions
+        if: matrix.os == 'ubuntu-latest'
+        uses: actions/upload-artifact@v7
+        with:
+          name: python-distributions
+          path: |
+            dist/*.whl
+            dist/*.tar.gz
+          if-no-files-found: error
+          overwrite: true

{pythialabelgenerator-1.0.0 → pythialabelgenerator-1.2.0}/.gitignore

@@ -2,6 +2,9 @@
 **/*.log
 **/*.csv
 
+# Pixi environments
+.pixi/
+
 *.raxml.*
 !tests/**/*.raxml.*
 

{pythialabelgenerator-1.0.0 → pythialabelgenerator-1.2.0}/.pre-commit-config.yaml

@@ -1,13 +1,13 @@
 repos:
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v2.3.0
+    rev: v6.0.0
     hooks:
     -   id: check-yaml
     -   id: end-of-file-fixer
     -   id: trailing-whitespace
     -   id: detect-private-key
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.7
+    rev: v0.16.6
     hooks:
     # Run the linter.
     -   id: ruff

{pythialabelgenerator-1.0.0 → pythialabelgenerator-1.2.0}/PKG-INFO

@@ -1,28 +1,28 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: PythiaLabelGenerator
-Version: 1.0.0
+Version: 1.2.0
 Summary: Command line tool to generate the ground-truth phylogenetic difficulty of MSAs
 Project-URL: Homepage, https://github.com/tschuelia/PythiaLabelGenerator
 Author-email: Julia Haag <info@juliaschmid.com>
 License-Expression: GPL-3.0-or-later
 License-File: LICENSE
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Python: <3.13,>=3.9
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: <3.15,>=3.11
 Requires-Dist: loguru
-Requires-Dist: pythiaphylopredictor>=2.0.0
+Requires-Dist: pythiaphylopredictor>=2.1.0
 Requires-Dist: regex
 Provides-Extra: test
 Requires-Dist: pytest; extra == 'test'
 Description-Content-Type: text/markdown
 
-# Pythia Difficulty Label Generator
+# Pythia Difficulty Label Generator (PyDLG)
 
 ![Label Generator GH actions CI](https://github.com/tschuelia/PythiaLabelGenerator/actions/workflows/test-label-generator.yml/badge.svg)
 
-The Pythia Difficulty Label Generator generates the ground-truth phylogenetic difficulty label for an MSA and
+PyDLG generates the ground-truth phylogenetic difficulty label for an MSA and
 corresponds to the prediction target of our difficulty prediction tool [Pythia](https://github.com/tschuelia/PyPythia).
 
 > [!CAUTION]
@@ -59,6 +59,18 @@ Per default, the difficulty is based on $`N_{\text{all}}=100`$ ML trees.
 Note that this number can be adjusted by the user, however, the difficulty will only be an approximation if the number
 of trees is changed.
 
+## RAxML-NG 2 Compatibility
+
+When using RAxML-NG 2, PyDLG automatically passes the following flags to preserve the label-generation procedure
+used in our publications:
+
+- `--adaptive off` disables adaptive search and its early-stopping rule. This ensures that tree searches are not
+  cut short based on estimated difficulty and that label computation follows our published difficulty definition.
+- `--extra brlen-start-fixed` restores the initial branch-length behavior of RAxML-NG 1.2, so labels are computed
+  using the same initialization as in our publications.
+
+These flags are applied automatically; no additional `label` arguments are required.
+
 ## Prediction of Phylogenetic Difficulty
 
 As stated above, computing the ground-truth difficulty for an MSA is very time-consuming and requires a lot of
@@ -70,7 +82,7 @@ comprising [SARS-CoV-2 sequences](https://doi.org/10.1093/molbev/msaa314) (appro
 12 hours on a large compute cluster. Using Pythia instead, we can predict the same MSA to be very difficult in about 2.5
 minutes on a standard MacBook.
 
-Only use this tool if you need the ground-truth difficulty for a specific MSA and you are sure that Pythia is unable to
+Only use PyDLG if you need the ground-truth difficulty for a specific MSA and you are sure that Pythia is unable to
 predict the difficulty accurately.
 The only case where we observed Pythia to fail is for language MSAs, so if you are working with DNA, Protein, or
 biological morphological data, Pythia should work just fine 😉
@@ -79,16 +91,20 @@ biological morphological data, Pythia should work just fine 😉
 
 #### Requirements
 
-To use this labelling tool, you need to install
+To use PyDLG, you need to install
 
 - RAxML-NG: See [the RAxML-NG GitHub repository](https://github.com/amkozlov/raxml-ng) for installation instructions.
-  Please make sure that you install a RAxML-NG version < 2.
+  PyDLG supports both RAxML-NG 1.x and 2.x.
 - IQ-TREE: See [the IQ-TREE website](http://www.iqtree.org) for installation instructions. Please install IQ-TREE
   version 2 or higher.
 
 #### Install via conda (recommended)
 
-This package will soon be available on conda-forge :)
+You can install the package using conda:
+
+```bash
+conda install pythialabelgenerator -c conda-forge
+```
 
 #### Install using pip
 
@@ -98,9 +114,41 @@ You can install the package using pip:
 pip install pythialabelgenerator
 ```
 
+This installs the Python package but not RAxML-NG or IQ-TREE. Install both programs separately as described in
+[Requirements](#requirements).
+
+#### Develop using Pixi
+
+Pixi is the supported way to create a development environment containing the Python package and both phylogenetic
+binaries:
+
+```bash
+git clone https://github.com/tschuelia/PythiaLabelGenerator.git
+cd PythiaLabelGenerator
+pixi install --frozen
+pixi run binary-smoke
+pixi run cli-smoke
+pixi run test
+```
+
+Unlike released-package installations, these project-local Pixi environments install the tested binaries from
+Bioconda. The default environment contains RAxML-NG 2.0.2 and IQ-TREE 2.4.0, while `legacy-raxml` contains RAxML-NG
+1.2.2. PyPythia 2.1.0 or newer is installed from conda-forge.
+
+The default environment uses Python 3.14 and RAxML-NG 2.0.2. Use `pixi run --environment py311 ...` or
+`pixi run --environment py314 ...` to reproduce the minimum and maximum Python versions tested in CI, or
+`pixi run --environment legacy-raxml ...` to test with RAxML-NG 1.2.2. PyDLG supports Python 3.11 through Python 3.14.
+
+Install the pre-commit hooks once and run all checks on demand using the dedicated environment:
+
+```bash
+pixi run --environment pre-commit pre-commit-install
+pixi run --environment pre-commit pre-commit-run
+```
+
 ## Usage
 
-This label-generator is primarily a command line tool. You can call it using the `label` command, for instance, to
+PyDLG is primarily a command line tool. You can call it using the `label` command, for instance, to
 compute the difficulty for the example MSA provided in the `examples` directory run
 
 ```bash
@@ -112,9 +160,9 @@ to the console.
 The output will look something like this:
 
 ```text
-Difficulty LabelGenerator version 1.0.0 released by The Exelixis Lab
+PyDLG version 1.2.0 released by The Exelixis Lab
 Developed by: Julia Haag
-Latest version: https://github.com/tschuelia/LabelGenerator
+Latest version: https://github.com/tschuelia/PythiaLabelGenerator
 Questions/problems/suggestions? Please open an issue on GitHub.
 
 LabelGenerator was called at 06-Mar-2025 15:15:03 as follows:
@@ -142,14 +190,14 @@ Depending on your system setup, you might need to pass a RAxML-NG and IQ-TREE bi
 You can do this using the `-r` and `-i` options, respectively. This is required in case `raxml-ng` and/or `iqtree2` are
 not in your `$PATH`.
 
-Note that this `examply.phy` MSA is not the same exemplary MSA as we provide in the PyPythia repository, so please don't compare this ground-truth lable to the exemplary prediction in PyPythia 😉
+Note that this `example.phy` MSA is not the same exemplary MSA as we provide in the PyPythia repository, so please don't compare this ground-truth label to the exemplary prediction in PyPythia 😉
 
 For a full list of command line options, run `label -h`:
 
 ```text
-Difficulty LabelGenerator version 1.0.0 released by The Exelixis Lab
+PyDLG version 1.2.0 released by The Exelixis Lab
 Developed by: Julia Haag
-Latest version: https://github.com/tschuelia/LabelGenerator
+Latest version: https://github.com/tschuelia/PythiaLabelGenerator
 Questions/problems/suggestions? Please open an issue on GitHub.
 
 usage: label [-h] -m MSA -r RAXMLNG -i IQTREE [-t THREADS] [-s SEED] [-p PREFIX] [--model MODEL] [--ntrees NTREES] [--redo] [-V]
@@ -183,19 +231,19 @@ difficulties, as the difficulty is based on the average pairwise RF distance bet
 
 ### Result Files
 
-Running this labelling tool will result in the following files:
+Running PyDLG will result in the following files:
 
 - `{prefix}.raxml.*`: RAxML-NG log and result files.
 - `{prefix}.iqtree.*`: IQ-TREE log and result files.
 - `{prefix}.labelGen.log`: Log file containing the output of the label generator. This is the same output as printed to
   the terminal.
+- `{prefix}.csv`: The computed ground-truth difficulty and all features required for Pythia for the given MSA.
 
 You can set the prefix of these files using the `-p` option. By default, the prefix is the name of the MSA file.
 Note that RAxML-NG and IQ-TREE refuse to overwrite existing files. If you want to redo the computations, you can use the
 `--redo` option.
 Please also specify the `--redo` option if you want to change the number of trees to infer using the `--ntrees` option
-for the same prefix. Otherwise,
-the label generator will exit with an error message.
+for the same prefix. Otherwise, PyDLG will exit with an error message.
 
 ### Input Data
 
@@ -209,7 +257,6 @@ you can do so using the `--model` option.
 
 
 ## Citation
-We will soon publish a pre-print on bioRxiv with updates on our Pythia difficulty prediction tool that will also include a
-brief description of this new labelling tool. Please cite this pre-print if you use this tool in your research.
+Please cite the following preprint if you use this tool in your research.
 
-The link to the paper will be added soon 🙂
+Haag, J. & Stamatakis, A. (2025). **Pythia 2.0: New Data, New Prediction Model, New Features.** *BioRxiv*. [https://doi.org/10.1101/2025.03.25.645182](https://doi.org/10.1101/2025.03.25.645182)

{pythialabelgenerator-1.0.0 → pythialabelgenerator-1.2.0}/README.md

@@ -1,8 +1,8 @@
-# Pythia Difficulty Label Generator
+# Pythia Difficulty Label Generator (PyDLG)
 
 ![Label Generator GH actions CI](https://github.com/tschuelia/PythiaLabelGenerator/actions/workflows/test-label-generator.yml/badge.svg)
 
-The Pythia Difficulty Label Generator generates the ground-truth phylogenetic difficulty label for an MSA and
+PyDLG generates the ground-truth phylogenetic difficulty label for an MSA and
 corresponds to the prediction target of our difficulty prediction tool [Pythia](https://github.com/tschuelia/PyPythia).
 
 > [!CAUTION]
@@ -39,6 +39,18 @@ Per default, the difficulty is based on $`N_{\text{all}}=100`$ ML trees.
 Note that this number can be adjusted by the user, however, the difficulty will only be an approximation if the number
 of trees is changed.
 
+## RAxML-NG 2 Compatibility
+
+When using RAxML-NG 2, PyDLG automatically passes the following flags to preserve the label-generation procedure
+used in our publications:
+
+- `--adaptive off` disables adaptive search and its early-stopping rule. This ensures that tree searches are not
+  cut short based on estimated difficulty and that label computation follows our published difficulty definition.
+- `--extra brlen-start-fixed` restores the initial branch-length behavior of RAxML-NG 1.2, so labels are computed
+  using the same initialization as in our publications.
+
+These flags are applied automatically; no additional `label` arguments are required.
+
 ## Prediction of Phylogenetic Difficulty
 
 As stated above, computing the ground-truth difficulty for an MSA is very time-consuming and requires a lot of
@@ -50,7 +62,7 @@ comprising [SARS-CoV-2 sequences](https://doi.org/10.1093/molbev/msaa314) (appro
 12 hours on a large compute cluster. Using Pythia instead, we can predict the same MSA to be very difficult in about 2.5
 minutes on a standard MacBook.
 
-Only use this tool if you need the ground-truth difficulty for a specific MSA and you are sure that Pythia is unable to
+Only use PyDLG if you need the ground-truth difficulty for a specific MSA and you are sure that Pythia is unable to
 predict the difficulty accurately.
 The only case where we observed Pythia to fail is for language MSAs, so if you are working with DNA, Protein, or
 biological morphological data, Pythia should work just fine 😉
@@ -59,16 +71,20 @@ biological morphological data, Pythia should work just fine 😉
 
 #### Requirements
 
-To use this labelling tool, you need to install
+To use PyDLG, you need to install
 
 - RAxML-NG: See [the RAxML-NG GitHub repository](https://github.com/amkozlov/raxml-ng) for installation instructions.
-  Please make sure that you install a RAxML-NG version < 2.
+  PyDLG supports both RAxML-NG 1.x and 2.x.
 - IQ-TREE: See [the IQ-TREE website](http://www.iqtree.org) for installation instructions. Please install IQ-TREE
   version 2 or higher.
 
 #### Install via conda (recommended)
 
-This package will soon be available on conda-forge :)
+You can install the package using conda:
+
+```bash
+conda install pythialabelgenerator -c conda-forge
+```
 
 #### Install using pip
 
@@ -78,9 +94,41 @@ You can install the package using pip:
 pip install pythialabelgenerator
 ```
 
+This installs the Python package but not RAxML-NG or IQ-TREE. Install both programs separately as described in
+[Requirements](#requirements).
+
+#### Develop using Pixi
+
+Pixi is the supported way to create a development environment containing the Python package and both phylogenetic
+binaries:
+
+```bash
+git clone https://github.com/tschuelia/PythiaLabelGenerator.git
+cd PythiaLabelGenerator
+pixi install --frozen
+pixi run binary-smoke
+pixi run cli-smoke
+pixi run test
+```
+
+Unlike released-package installations, these project-local Pixi environments install the tested binaries from
+Bioconda. The default environment contains RAxML-NG 2.0.2 and IQ-TREE 2.4.0, while `legacy-raxml` contains RAxML-NG
+1.2.2. PyPythia 2.1.0 or newer is installed from conda-forge.
+
+The default environment uses Python 3.14 and RAxML-NG 2.0.2. Use `pixi run --environment py311 ...` or
+`pixi run --environment py314 ...` to reproduce the minimum and maximum Python versions tested in CI, or
+`pixi run --environment legacy-raxml ...` to test with RAxML-NG 1.2.2. PyDLG supports Python 3.11 through Python 3.14.
+
+Install the pre-commit hooks once and run all checks on demand using the dedicated environment:
+
+```bash
+pixi run --environment pre-commit pre-commit-install
+pixi run --environment pre-commit pre-commit-run
+```
+
 ## Usage
 
-This label-generator is primarily a command line tool. You can call it using the `label` command, for instance, to
+PyDLG is primarily a command line tool. You can call it using the `label` command, for instance, to
 compute the difficulty for the example MSA provided in the `examples` directory run
 
 ```bash
@@ -92,9 +140,9 @@ to the console.
 The output will look something like this:
 
 ```text
-Difficulty LabelGenerator version 1.0.0 released by The Exelixis Lab
+PyDLG version 1.2.0 released by The Exelixis Lab
 Developed by: Julia Haag
-Latest version: https://github.com/tschuelia/LabelGenerator
+Latest version: https://github.com/tschuelia/PythiaLabelGenerator
 Questions/problems/suggestions? Please open an issue on GitHub.
 
 LabelGenerator was called at 06-Mar-2025 15:15:03 as follows:
@@ -122,14 +170,14 @@ Depending on your system setup, you might need to pass a RAxML-NG and IQ-TREE bi
 You can do this using the `-r` and `-i` options, respectively. This is required in case `raxml-ng` and/or `iqtree2` are
 not in your `$PATH`.
 
-Note that this `examply.phy` MSA is not the same exemplary MSA as we provide in the PyPythia repository, so please don't compare this ground-truth lable to the exemplary prediction in PyPythia 😉
+Note that this `example.phy` MSA is not the same exemplary MSA as we provide in the PyPythia repository, so please don't compare this ground-truth label to the exemplary prediction in PyPythia 😉
 
 For a full list of command line options, run `label -h`:
 
 ```text
-Difficulty LabelGenerator version 1.0.0 released by The Exelixis Lab
+PyDLG version 1.2.0 released by The Exelixis Lab
 Developed by: Julia Haag
-Latest version: https://github.com/tschuelia/LabelGenerator
+Latest version: https://github.com/tschuelia/PythiaLabelGenerator
 Questions/problems/suggestions? Please open an issue on GitHub.
 
 usage: label [-h] -m MSA -r RAXMLNG -i IQTREE [-t THREADS] [-s SEED] [-p PREFIX] [--model MODEL] [--ntrees NTREES] [--redo] [-V]
@@ -163,19 +211,19 @@ difficulties, as the difficulty is based on the average pairwise RF distance bet
 
 ### Result Files
 
-Running this labelling tool will result in the following files:
+Running PyDLG will result in the following files:
 
 - `{prefix}.raxml.*`: RAxML-NG log and result files.
 - `{prefix}.iqtree.*`: IQ-TREE log and result files.
 - `{prefix}.labelGen.log`: Log file containing the output of the label generator. This is the same output as printed to
   the terminal.
+- `{prefix}.csv`: The computed ground-truth difficulty and all features required for Pythia for the given MSA.
 
 You can set the prefix of these files using the `-p` option. By default, the prefix is the name of the MSA file.
 Note that RAxML-NG and IQ-TREE refuse to overwrite existing files. If you want to redo the computations, you can use the
 `--redo` option.
 Please also specify the `--redo` option if you want to change the number of trees to infer using the `--ntrees` option
-for the same prefix. Otherwise,
-the label generator will exit with an error message.
+for the same prefix. Otherwise, PyDLG will exit with an error message.
 
 ### Input Data
 
@@ -189,7 +237,6 @@ you can do so using the `--model` option.
 
 
 ## Citation
-We will soon publish a pre-print on bioRxiv with updates on our Pythia difficulty prediction tool that will also include a
-brief description of this new labelling tool. Please cite this pre-print if you use this tool in your research.
+Please cite the following preprint if you use this tool in your research.
 
-The link to the paper will be added soon 🙂
+Haag, J. & Stamatakis, A. (2025). **Pythia 2.0: New Data, New Prediction Model, New Features.** *BioRxiv*. [https://doi.org/10.1101/2025.03.25.645182](https://doi.org/10.1101/2025.03.25.645182)

{pythialabelgenerator-1.0.0 → pythialabelgenerator-1.2.0}/labelgenerator/iqtree.py

@@ -1,6 +1,5 @@
 import pathlib
 import subprocess
-from typing import Optional
 
 from pypythia.custom_types import DataType
 
@@ -49,7 +48,7 @@ def run_statstests(
     model: str,
     prefix: pathlib.Path,
     seed: int = 0,
-    threads: Optional[int] = None,
+    threads: int | None = None,
     is_morph: bool = False,
     redo: bool = False,
 ) -> None:

{pythialabelgenerator-1.0.0 → pythialabelgenerator-1.2.0}/labelgenerator/label.py

@@ -1,7 +1,6 @@
 import pathlib
-from typing import Optional
 
-from pypythia.msa import parse_msa
+from pypythia.msa import MSA, DataType
 
 from labelgenerator.iqtree import (
     filter_plausible_trees,
@@ -100,14 +99,15 @@ def get_label(
 
 
 def compute_label(
+    msa_obj: MSA,
     msa_file: pathlib.Path,
     raxmlng: pathlib.Path,
     iqtree: pathlib.Path,
     prefix: pathlib.Path,
-    model: Optional[str] = None,
+    model: str | None = None,
     n_trees: int = 100,
     seed: int = 0,
-    threads: Optional[int] = None,
+    threads: int | None = None,
     redo: bool = False,
     log_info: bool = True,
 ) -> float:
@@ -117,6 +117,7 @@ def compute_label(
 
 
     Args:
+        msa_obj (MSA): MSA object containing the input data.
         msa_file (pathlib.Path): Path to the MSA file to compute the label for. Can be either in FASTA or PHYLIP format.
         raxmlng (pathlib.Path): Path to the RAxML-NG executable.
         iqtree (pathlib.Path): Path to the IQ-TREE executable.
@@ -134,7 +135,6 @@ def compute_label(
         float: The ground truth difficulty label for the given MSA.
 
     """
-    msa_obj = parse_msa(msa_file)
     model = model or msa_obj.get_raxmlng_model()
 
     # 1. Infer 100 ML trees for the given MSA using RAxML-NG
@@ -182,6 +182,7 @@ def compute_label(
         seed=seed,
         threads=threads,
         redo=redo,
+        is_morph=msa_obj.data_type == DataType.MORPH,
     )
 
     # 4. Filter the plausible trees

pythialabelgenerator-1.2.0/labelgenerator/logger.py

@@ -0,0 +1,49 @@
+import sys
+import textwrap
+import time
+
+import loguru
+
+from labelgenerator import __version__
+
+SCRIPT_START = time.perf_counter()
+
+
+logger = loguru.logger
+logger.remove()
+logger.add(sys.stderr, format="{message}")
+
+
+def get_header():
+    return textwrap.dedent(
+        f"PyDLG version {__version__} released by The Exelixis Lab\n"
+        f"Developed by: Julia Haag\n"
+        f"Latest version: https://github.com/tschuelia/PythiaLabelGenerator\n"
+        f"Questions/problems/suggestions? Please open an issue on GitHub.\n",
+    )
+
+
+def log_runtime_information(message, log_runtime=True):
+    if log_runtime:
+        seconds = time.perf_counter() - SCRIPT_START
+        fmt_time = time.strftime("%H:%M:%S", time.gmtime(seconds))
+        time_string = f"[{fmt_time}] "
+    else:
+        time_string = ""
+    logger.info(f"{time_string}{message}")
+
+
+def log_runtime(total_runtime: int, runtime_name: str):
+    hours, remainder = divmod(total_runtime, 3600)
+    minutes, seconds = divmod(remainder, 60)
+
+    if hours > 0:
+        logger.info(
+            f"{runtime_name}: {int(hours):02d}:{int(minutes):02d}:{seconds:02d} hours ({round(total_runtime)} seconds)."
+        )
+    elif minutes > 0:
+        logger.info(
+            f"{runtime_name}: {int(minutes):02d}:{int(seconds):02d} minutes ({round(total_runtime)} seconds)."
+        )
+    else:
+        logger.info(f"{runtime_name}: {seconds:.2f} seconds.")