bio-terrier 0.3.1__tar.gz

bio_terrier-0.3.1/LICENSE

@@ -0,0 +1,192 @@
+
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2023 Robert Turnbull
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

bio_terrier-0.3.1/PKG-INFO

@@ -0,0 +1,201 @@
+Metadata-Version: 2.3
+Name: bio-terrier
+Version: 0.3.1
+Summary: Transposable Element Repeat Result classifIER
+License: Apache-2.0
+Keywords: torchapp,pytorch,deep learning,command-line interface
+Author: Robert Turnbull
+Author-email: robert.turnbull@unimelb.edu.au
+Requires-Python: >=3.10,<3.13
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Dist: bio-corgi (>=0.5.0a1)
+Requires-Dist: h5py (>=3.8.0)
+Requires-Dist: numpy (<2.0.0)
+Requires-Dist: pandas (<=2.2.0)
+Requires-Dist: pyfastx (>=1.1.0)
+Requires-Dist: toml (>=0.10.2)
+Project-URL: Documentation, https://rbturnbull.github.io/terrier
+Project-URL: Homepage, https://github.com/rbturnbull/terrier/
+Project-URL: Repository, https://github.com/rbturnbull/terrier/
+Description-Content-Type: text/x-rst
+
+.. image:: https://raw.githubusercontent.com/rbturnbull/terrier/main/docs/images/terrier-banner.png
+
+.. start-badges
+
+|pypi badge| |colab badge| |testing badge| |docs badge| |black badge| |torchapp badge|
+
+.. |pypi badge| image:: https://img.shields.io/pypi/v/terrier?color=blue
+   :alt: PyPI - Version
+   :target: https://pypi.org/project/terrier/
+
+.. |testing badge| image:: https://github.com/rbturnbull/terrier/actions/workflows/testing.yml/badge.svg
+    :target: https://github.com/rbturnbull/terrier/actions
+
+.. |docs badge| image:: https://github.com/rbturnbull/terrier/actions/workflows/docs.yml/badge.svg
+    :target: https://rbturnbull.github.io/terrier
+    
+.. |black badge| image:: https://img.shields.io/badge/code%20style-black-000000.svg
+    :target: https://github.com/psf/black
+    
+.. |coverage badge| image:: https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/rbturnbull/5e0c3115955fde132a8b7c131da68b86/raw/coverage-badge.json
+    :target: https://rbturnbull.github.io/terrier/coverage/
+
+.. |torchapp badge| image:: https://img.shields.io/badge/torch-app-B1230A.svg
+    :target: https://rbturnbull.github.io/torchapp/
+
+.. |colab badge| image:: https://colab.research.google.com/assets/colab-badge.svg
+   :target: https://colab.research.google.com/github/rbturnbull/terrier/blob/main/terrier_colab.ipynb
+
+    
+.. end-badges
+
+.. start-quickstart
+
+Transposable Element Repeat Result classifIER
+
+Terrier is a Neural Network model to classify transposable element sequences.
+
+It is based on ‘corgi’ which was trained to do hierarchical taxonomic classification of DNA sequences.
+
+This model was trained using the Repbase library of repetitive DNA elements and trained to do hierarchical classification according to the RepeatMasker schema.
+
+Installation
+==================================
+
+Install using pip:
+
+.. code-block:: bash
+
+    pip install bio-terrier
+
+.. warning ::
+
+    Do not try just ``pip install terrier`` because that is a different package.
+
+Or install the latest version from GitHub:
+
+.. code-block:: bash
+
+    pip install git+https://github.com/rbturnbull/terrier.git
+
+
+Google Colab Version
+==================================
+
+Follow this link to launch a Google Colab notebook where you can run the model on your own data: |colab badge2|
+
+.. |colab badge2| image:: https://colab.research.google.com/assets/colab-badge.svg
+   :target: https://colab.research.google.com/github/rbturnbull/terrier/blob/main/terrier_colab.ipynb
+
+Usage
+==================================
+
+To run inference on a FASTA file, run this command:
+
+.. code-block:: bash
+
+    terrier --file INPUT.fa --output-fasta OUTPUT.fa
+
+That will add the classification to after the sequence ID in the `OUTPUT.fa` FASTA file.
+
+If you want to save the probabilities for all classes run this:
+
+.. code-block:: bash
+
+    terrier --file INPUT.fa --output-csv OUTPUT.csv
+
+The columns will be the probability of each classification and the rows correspond to each sequence in ``INPUT.fa``.
+
+If you want to output a visualization of the prediction probabilities:
+
+.. code-block:: bash
+
+    terrier --file INPUT.fa --image-dir OUTPUT-IMAGES/
+
+The outputs for the above can be combined together. For more options run 
+
+.. code-block:: bash
+
+    terrier --help
+
+To see the options to train the model, run:
+
+.. code-block:: bash
+
+    terrier-tools --help
+
+Programmatic Usage
+==================================
+
+You can also use the model programmatically:
+
+.. code-block:: python
+
+    from terrier import Terrier
+
+    terrier = Terrier()
+    terrier(file="INPUT.fa", output_fasta="OUTPUT.fa")
+
+.. end-quickstart
+
+
+Credits
+==================================
+
+.. start-credits
+
+Terrier was developed by:
+
+- `Robert Turnbull <https://robturnbull.com>`_
+- `Neil D. Young <https://findanexpert.unimelb.edu.au/profile/249669-neil-young>`_
+- `Edoardo Tescari <https://findanexpert.unimelb.edu.au/profile/428364-edoardo-tescari>`_
+- `Lee F. Skerratt <https://findanexpert.unimelb.edu.au/profile/451921-lee-skerratt>`_
+- `Tiffany A. Kosch <https://findanexpert.unimelb.edu.au/profile/775927-tiffany-kosch>`_
+
+If you use this software, please cite the following preprint:
+
+    Robert Turnbull, Neil D. Young, Edoardo Tescari, Lee F. Skerratt, and Tiffany A. Kosch. (2025). 'Terrier: A Deep Learning Repeat Classifier'. `arXiv:2503.09312 <https://arxiv.org/abs/2503.09312>`_.
+
+This command will generate a bibliography for the Terrier project.
+
+.. code-block:: bash
+
+    terrier --bibliography
+
+Here it is in BibTeX format:
+
+.. code-block:: bibtex
+
+    @article{terrier,
+        title = {{Terrier: A Deep Learning Repeat Classifier}},
+        author = {Turnbull, Robert and Young, Neil D. and Tescari, Edoardo and Skerratt, Lee F. and Kosch, Tiffany A.},
+        year = {2025},
+        journal = {arXiv},
+        url = {https://arxiv.org/abs/2503.09312},
+        doi = {10.48550/arXiv.2503.09312}
+    }
+
+Run the following command to get the latest BibTeX entry:
+
+.. code-block:: bash
+
+    terrier --bibtex
+
+
+This will be updated with the final publication details when available.
+
+
+
+Created using torchapp (https://github.com/rbturnbull/torchapp).
+
+.. end-credits
+
+

bio_terrier-0.3.1/README.rst

@@ -0,0 +1,172 @@
+.. image:: https://raw.githubusercontent.com/rbturnbull/terrier/main/docs/images/terrier-banner.png
+
+.. start-badges
+
+|pypi badge| |colab badge| |testing badge| |docs badge| |black badge| |torchapp badge|
+
+.. |pypi badge| image:: https://img.shields.io/pypi/v/terrier?color=blue
+   :alt: PyPI - Version
+   :target: https://pypi.org/project/terrier/
+
+.. |testing badge| image:: https://github.com/rbturnbull/terrier/actions/workflows/testing.yml/badge.svg
+    :target: https://github.com/rbturnbull/terrier/actions
+
+.. |docs badge| image:: https://github.com/rbturnbull/terrier/actions/workflows/docs.yml/badge.svg
+    :target: https://rbturnbull.github.io/terrier
+    
+.. |black badge| image:: https://img.shields.io/badge/code%20style-black-000000.svg
+    :target: https://github.com/psf/black
+    
+.. |coverage badge| image:: https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/rbturnbull/5e0c3115955fde132a8b7c131da68b86/raw/coverage-badge.json
+    :target: https://rbturnbull.github.io/terrier/coverage/
+
+.. |torchapp badge| image:: https://img.shields.io/badge/torch-app-B1230A.svg
+    :target: https://rbturnbull.github.io/torchapp/
+
+.. |colab badge| image:: https://colab.research.google.com/assets/colab-badge.svg
+   :target: https://colab.research.google.com/github/rbturnbull/terrier/blob/main/terrier_colab.ipynb
+
+    
+.. end-badges
+
+.. start-quickstart
+
+Transposable Element Repeat Result classifIER
+
+Terrier is a Neural Network model to classify transposable element sequences.
+
+It is based on ‘corgi’ which was trained to do hierarchical taxonomic classification of DNA sequences.
+
+This model was trained using the Repbase library of repetitive DNA elements and trained to do hierarchical classification according to the RepeatMasker schema.
+
+Installation
+==================================
+
+Install using pip:
+
+.. code-block:: bash
+
+    pip install bio-terrier
+
+.. warning ::
+
+    Do not try just ``pip install terrier`` because that is a different package.
+
+Or install the latest version from GitHub:
+
+.. code-block:: bash
+
+    pip install git+https://github.com/rbturnbull/terrier.git
+
+
+Google Colab Version
+==================================
+
+Follow this link to launch a Google Colab notebook where you can run the model on your own data: |colab badge2|
+
+.. |colab badge2| image:: https://colab.research.google.com/assets/colab-badge.svg
+   :target: https://colab.research.google.com/github/rbturnbull/terrier/blob/main/terrier_colab.ipynb
+
+Usage
+==================================
+
+To run inference on a FASTA file, run this command:
+
+.. code-block:: bash
+
+    terrier --file INPUT.fa --output-fasta OUTPUT.fa
+
+That will add the classification to after the sequence ID in the `OUTPUT.fa` FASTA file.
+
+If you want to save the probabilities for all classes run this:
+
+.. code-block:: bash
+
+    terrier --file INPUT.fa --output-csv OUTPUT.csv
+
+The columns will be the probability of each classification and the rows correspond to each sequence in ``INPUT.fa``.
+
+If you want to output a visualization of the prediction probabilities:
+
+.. code-block:: bash
+
+    terrier --file INPUT.fa --image-dir OUTPUT-IMAGES/
+
+The outputs for the above can be combined together. For more options run 
+
+.. code-block:: bash
+
+    terrier --help
+
+To see the options to train the model, run:
+
+.. code-block:: bash
+
+    terrier-tools --help
+
+Programmatic Usage
+==================================
+
+You can also use the model programmatically:
+
+.. code-block:: python
+
+    from terrier import Terrier
+
+    terrier = Terrier()
+    terrier(file="INPUT.fa", output_fasta="OUTPUT.fa")
+
+.. end-quickstart
+
+
+Credits
+==================================
+
+.. start-credits
+
+Terrier was developed by:
+
+- `Robert Turnbull <https://robturnbull.com>`_
+- `Neil D. Young <https://findanexpert.unimelb.edu.au/profile/249669-neil-young>`_
+- `Edoardo Tescari <https://findanexpert.unimelb.edu.au/profile/428364-edoardo-tescari>`_
+- `Lee F. Skerratt <https://findanexpert.unimelb.edu.au/profile/451921-lee-skerratt>`_
+- `Tiffany A. Kosch <https://findanexpert.unimelb.edu.au/profile/775927-tiffany-kosch>`_
+
+If you use this software, please cite the following preprint:
+
+    Robert Turnbull, Neil D. Young, Edoardo Tescari, Lee F. Skerratt, and Tiffany A. Kosch. (2025). 'Terrier: A Deep Learning Repeat Classifier'. `arXiv:2503.09312 <https://arxiv.org/abs/2503.09312>`_.
+
+This command will generate a bibliography for the Terrier project.
+
+.. code-block:: bash
+
+    terrier --bibliography
+
+Here it is in BibTeX format:
+
+.. code-block:: bibtex
+
+    @article{terrier,
+        title = {{Terrier: A Deep Learning Repeat Classifier}},
+        author = {Turnbull, Robert and Young, Neil D. and Tescari, Edoardo and Skerratt, Lee F. and Kosch, Tiffany A.},
+        year = {2025},
+        journal = {arXiv},
+        url = {https://arxiv.org/abs/2503.09312},
+        doi = {10.48550/arXiv.2503.09312}
+    }
+
+Run the following command to get the latest BibTeX entry:
+
+.. code-block:: bash
+
+    terrier --bibtex
+
+
+This will be updated with the final publication details when available.
+
+
+
+Created using torchapp (https://github.com/rbturnbull/torchapp).
+
+.. end-credits
+

bio_terrier-0.3.1/pyproject.toml

@@ -0,0 +1,60 @@
+[tool.poetry]
+name = "bio-terrier"
+version = "0.3.1"
+description = "Transposable Element Repeat Result classifIER"
+authors = ["Robert Turnbull <robert.turnbull@unimelb.edu.au>"]
+license = "Apache-2.0"
+readme = "README.rst"
+repository = "https://github.com/rbturnbull/terrier/"
+documentation = "https://rbturnbull.github.io/terrier"
+homepage = "https://github.com/rbturnbull/terrier/"
+keywords = ["torchapp", "pytorch", "deep learning", "command-line interface"]
+# For classifiers see https://pypi.org/classifiers/
+classifiers = [
+    "License :: OSI Approved :: Apache Software License",
+    "Intended Audience :: Science/Research",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence"
+]
+packages = [
+    {include = "terrier"}
+]
+
+
+[tool.poetry.dependencies]
+python = ">=3.10,<3.13"
+numpy = "<2.0.0"
+pandas = "<=2.2.0"
+h5py = ">=3.8.0"
+bio-corgi = ">=0.5.0a1"
+pyfastx = ">=1.1.0"
+toml = ">=0.10.2"
+
+[tool.poetry.group.dev.dependencies]
+pytest = ">=6.2.5"
+ipykernel = ">=6.6.1"
+coverage = ">=5.5"
+autopep8 = ">=1.5.7"
+Sphinx = ">=4.2.0"
+nbsphinx = ">=0.8.7"
+sphinx-rtd-theme = ">=1.0.0"
+sphinx-autobuild = ">=2021.3.14"
+pre-commit = ">=2.15.0"
+sphinx-copybutton = ">=0.5.2"
+black = ">=21.10b0"
+sphinx-click = {git = "https://github.com/rbturnbull/sphinx-click.git"}
+
+[tool.pytest.ini_options]
+minversion = "6.0"
+testpaths = [
+    "tests",
+]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry.scripts]
+terrier = "terrier.apps:Terrier.main"
+terrier-tools = "terrier.apps:Terrier.tools"
+

bio_terrier-0.3.1/terrier/__init__.py

@@ -0,0 +1 @@
+from .apps import Terrier