provides a running blackbox for Rosetta (#222)

Co-authored-by: Simon Bartels <[email protected]>
Co-authored-by: Miguel González Duque <[email protected]>
Co-authored-by: Richard Michael <[email protected]>
Co-authored-by: Richard Michael <[email protected]>

.github/workflows/python-tox-testing-rosetta-env.yml

@@ -0,0 +1,39 @@
+name: poli rosetta (conda, py3.9)
+
+on:
+  push:
+    branches:
+      - dev
+      - master
+  pull_request:
+    types: [opened, synchronize, reopened, ready_for_review, closed]
+    branches:
+      - dev
+      - master
+  schedule:
+    - cron: '0 0 * * 0'
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-latest
+    timeout-minutes: 8
+    if: github.event.pull_request.draft == false
+    strategy:
+      max-parallel: 5
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python 3.9
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.10'
+    - name: Add conda to system path
+      run: |
+        # $CONDA is an environment variable pointing to the root of the miniconda directory
+        echo $CONDA/bin >> $GITHUB_PATH
+    - name: Install dependencies
+      run: |
+        python -m pip install tox
+    - name: Test rosetta-related black boxes with tox and pytest
+      run: |
+        tox -c tox.ini -e poli-rosetta_energy-py310

CITATION.cff

@@ -8,6 +8,6 @@ authors:
 - family-names: "Michael"
   given-names: "Richard"
 title: "poli: a libary of discrete sequence objectives"
-version: 1.0.1
+version: 1.1.0
 date-released: 2024-01-23
 url: "https://github.com/MachineLearningLifeScience/poli"

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "poli-core"
-version = "1.0.1"
+version = "1.1.0"
 description = "poli, a library of discrete objective functions"
 readme = "README.md"
 authors = [{name="Miguel González-Duque", email="[email protected]"}, {name="Simon Bartels", email="[email protected]"}]
@@ -57,6 +57,10 @@ dockstring = [
 rmf = [
     "scipy",
 ]
+rosetta_energy = [
+    "biopython",
+    "pyrosetta",
+]
 dev = ["black", "tox", "pytest", "bump-my-version"]
 docs = ["sphinx", "furo"]
 
@@ -72,6 +76,7 @@ markers = [
     "poli__protein: marks tests that run in the poli__protein environment",
     "poli__rasp: marks tests that run in the poli__rasp environment",
     "poli__rmf: marks tests that run in poli__rmf environment",
+    "poli__rosetta_energy: marks tests that run in poli__rosetta_energy",
     "poli__ehrlich_holo: marks tests that run in poli__ehrlich_holo environment",
     "unmarked: All other tests, which usually run in the base environment",
 ]
@@ -83,7 +88,7 @@ profile = "black"
 exclude = ["src/poli/core/util/proteins/rasp/inner_rasp", "src/poli/objective_repository/gfp_cbas"]
 
 [tool.bumpversion]
-current_version = "1.0.1"
+current_version = "1.1.0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = poli-core
-version = "1.0.1"
+version = "1.1.0"
 author = Miguel González-Duque
 author_email = [email protected]
 description = A library of discrete objective functions

src/poli/__init__.py

@@ -1,6 +1,6 @@
 """poli, a library for discrete black-box objective functions."""
 
-__version__ = "1.0.1"
+__version__ = "1.1.0"
 from .core.util.isolation.instancing import instance_function_as_isolated_process
 
 # from .core import get_problems

src/poli/objective_repository/__init__.py

@@ -76,6 +76,7 @@
 )
 from .rfp_rasp.register import RFPRaspBlackBox, RFPRaspProblemFactory
 from .rmf_landscape.register import RMFBlackBox, RMFProblemFactory
+from .rosetta_energy.register import RosettaEnergyBlackBox, RosettaEnergyProblemFactory
 from .sa_tdc.register import SABlackBox, SAProblemFactory
 from .scaffold_hop.register import ScaffoldHopBlackBox, ScaffoldHopProblemFactory
 from .sitagliptin_mpo.register import (
@@ -142,6 +143,7 @@
     "rfp_foldx_stability": RFPFoldXStabilityProblemFactory,
     "rfp_foldx_stability_and_sasa": RFPFoldXStabilityAndSASAProblemFactory,
     "rmf_landscape": RMFProblemFactory,
+    "rosetta_energy": RosettaEnergyProblemFactory,
     "sa_tdc": SAProblemFactory,
     "super_mario_bros": SuperMarioBrosProblemFactory,
     "white_noise": WhiteNoiseProblemFactory,
@@ -190,6 +192,7 @@
     "rfp_foldx_stability": RFPFoldXStabilityBlackBox,
     "rfp_foldx_stability_and_sasa": FoldXStabilityAndSASABlackBox,
     "rmf_landscape": RMFBlackBox,
+    "rosetta_energy": RosettaEnergyBlackBox,
     "sa_tdc": SABlackBox,
     "super_mario_bros": SuperMarioBrosBlackBox,
     "white_noise": WhiteNoiseBlackBox,

src/poli/objective_repository/rosetta_energy/README.md

@@ -0,0 +1,11 @@
+This black-box function uses PyRosetta-4.
+
+Created at JHU by Sergey Lyskov and the PyRosetta Team.
+
+(C) Copyright remains with the Rosetta Commons Member Institutions.
+
+
+By using the `rosetta_energy` black-box you agree that you have read and are in compliance with the PyRosetta 
+license agreement.
+
+See LICENSE.PyRosetta.md or email [email protected].

src/poli/objective_repository/rosetta_energy/environment.yml

@@ -0,0 +1,12 @@
+name: poli__rosetta_energy
+channels:
+  - defaults
+  - conda-forge
+  - https://conda.rosettacommons.org
+dependencies:
+  - python=3.10
+  - pyrosetta
+  - pip:
+    - numpy
+    - "git+https://github.com/MachineLearningLifeScience/poli.git@dev"
+    - biopython==1.72

src/poli/objective_repository/rosetta_energy/information.py

@@ -0,0 +1,15 @@
+import numpy as np
+
+from poli.core.black_box_information import BlackBoxInformation
+from poli.core.util.proteins.defaults import AMINO_ACIDS
+
+rosetta_energy_information = BlackBoxInformation(
+    name="rosetta_energy",
+    max_sequence_length=np.inf,
+    alphabet=AMINO_ACIDS,
+    aligned=True,
+    fixed_length=True,
+    discrete=True,
+    deterministic=False,
+    padding_token="",
+)