Attract init

integration_tests/__init__.py

@@ -3,6 +3,7 @@
 
 import pytest
 
+
 if "CNS_EXEC" in os.environ:
     CNS_EXEC = os.environ["CNS_EXEC"]
 else:
@@ -17,3 +18,10 @@
 
 tests_path = Path(__file__).resolve().parents[0]
 GOLDEN_DATA = Path(tests_path, "golden_data")
+
+# Placeholder decorator to check if ATTRACT is installed
+# TODO: Implement
+ATTRACT_IS_INSTALLED = False
+has_attract = pytest.mark.skipif(
+    not ATTRACT_IS_INSTALLED, reason="ATTRACT not installed"
+)

integration_tests/golden_data/rna.pdb

@@ -0,0 +1,89 @@
+ATOM    666  O5'   G B  87     -27.630  38.463 -14.109  1.00 42.87           O  
+ATOM    667  C5'   G B  87     -28.602  38.855 -13.151  1.00 42.27           C  
+ATOM    668  C4'   G B  87     -29.933  39.139 -13.799  1.00 48.64           C  
+ATOM    669  O4'   G B  87     -29.779  40.178 -14.803  1.00 43.31           O  
+ATOM    670  C3'   G B  87     -30.564  37.982 -14.561  1.00 44.60           C  
+ATOM    671  O3'   G B  87     -31.242  37.065 -13.721  1.00 56.31           O  
+ATOM    672  C2'   G B  87     -31.474  38.697 -15.548  1.00 41.13           C  
+ATOM    673  O2'   G B  87     -32.656  39.153 -14.903  1.00 47.54           O  
+ATOM    674  C1'   G B  87     -30.621  39.913 -15.906  1.00 44.86           C  
+ATOM    675  N9    G B  87     -29.775  39.659 -17.088  1.00 45.69           N  
+ATOM    676  C8    G B  87     -28.407  39.541 -17.117  1.00 44.82           C  
+ATOM    677  N7    G B  87     -27.938  39.311 -18.313  1.00 52.84           N  
+ATOM    678  C5    G B  87     -29.064  39.272 -19.124  1.00 47.42           C  
+ATOM    679  C6    G B  87     -29.183  39.057 -20.521  1.00 42.22           C  
+ATOM    680  O6    G B  87     -28.286  38.852 -21.348  1.00 61.13           O  
+ATOM    681  N1    G B  87     -30.512  39.100 -20.935  1.00 45.00           N  
+ATOM    682  C2    G B  87     -31.588  39.318 -20.108  1.00 54.13           C  
+ATOM    683  N2    G B  87     -32.796  39.322 -20.693  1.00 54.04           N  
+ATOM    684  N3    G B  87     -31.490  39.520 -18.804  1.00 50.61           N  
+ATOM    685  C4    G B  87     -30.207  39.484 -18.382  1.00 56.23           C  
+ATOM    686  P     G B  88     -31.281  35.502 -14.096  1.00 53.68           P  
+ATOM    687  OP1   G B  88     -31.907  34.794 -12.951  1.00 54.68           O  
+ATOM    688  OP2   G B  88     -29.910  35.116 -14.509  1.00 39.00           O  
+ATOM    689  O5'   G B  88     -32.256  35.463 -15.355  1.00 57.66           O  
+ATOM    690  C5'   G B  88     -33.614  35.868 -15.241  1.00 57.35           C  
+ATOM    691  C4'   G B  88     -34.327  35.784 -16.567  1.00 58.96           C  
+ATOM    692  O4'   G B  88     -33.726  36.709 -17.509  1.00 56.45           O  
+ATOM    693  C3'   G B  88     -34.258  34.440 -17.273  1.00 57.94           C  
+ATOM    694  O3'   G B  88     -35.199  33.508 -16.775  1.00 73.51           O  
+ATOM    695  C2'   G B  88     -34.483  34.816 -18.732  1.00 63.36           C  
+ATOM    696  O2'   G B  88     -35.863  35.029 -18.990  1.00 43.75           O  
+ATOM    697  C1'   G B  88     -33.761  36.163 -18.812  1.00 50.86           C  
+ATOM    698  N9    G B  88     -32.375  36.021 -19.299  1.00 55.68           N  
+ATOM    699  C8    G B  88     -31.223  35.986 -18.549  1.00 49.61           C  
+ATOM    700  N7    G B  88     -30.145  35.851 -19.273  1.00 46.05           N  
+ATOM    701  C5    G B  88     -30.611  35.792 -20.580  1.00 52.57           C  
+ATOM    702  C6    G B  88     -29.908  35.650 -21.807  1.00 55.72           C  
+ATOM    703  O6    G B  88     -28.688  35.544 -21.994  1.00 50.01           O  
+ATOM    704  N1    G B  88     -30.778  35.638 -22.894  1.00 55.41           N  
+ATOM    705  C2    G B  88     -32.146  35.747 -22.816  1.00 63.24           C  
+ATOM    706  N2    G B  88     -32.812  35.713 -23.980  1.00 54.57           N  
+ATOM    707  N3    G B  88     -32.811  35.881 -21.680  1.00 54.18           N  
+ATOM    708  C4    G B  88     -31.987  35.895 -20.612  1.00 56.47           C  
+ATOM    709  P     U B  89     -34.726  32.337 -15.783  1.00 72.44           P  
+ATOM    710  OP1   U B  89     -35.625  32.374 -14.602  1.00 52.31           O  
+ATOM    711  OP2   U B  89     -33.266  32.503 -15.573  1.00 82.19           O  
+ATOM    712  O5'   U B  89     -35.004  31.025 -16.635  1.00 80.12           O  
+ATOM    713  C5'   U B  89     -35.939  30.056 -16.196  1.00 65.85           C  
+ATOM    714  C4'   U B  89     -36.896  29.668 -17.291  1.00 76.34           C  
+ATOM    715  O4'   U B  89     -37.915  28.785 -16.746  1.00 63.91           O  
+ATOM    716  C3'   U B  89     -37.686  30.811 -17.917  1.00 82.48           C  
+ATOM    717  O3'   U B  89     -36.974  31.513 -18.934  1.00 99.92           O  
+ATOM    718  C2'   U B  89     -38.956  30.123 -18.405  1.00 89.18           C  
+ATOM    719  O2'   U B  89     -38.721  29.436 -19.626  1.00 91.14           O  
+ATOM    720  C1'   U B  89     -39.175  29.087 -17.304  1.00 88.15           C  
+ATOM    721  N1    U B  89     -40.055  29.598 -16.225  1.00 82.95           N  
+ATOM    722  C2    U B  89     -41.420  29.461 -16.387  1.00 61.44           C  
+ATOM    723  O2    U B  89     -41.925  28.945 -17.370  1.00 78.44           O  
+ATOM    724  N3    U B  89     -42.177  29.953 -15.353  1.00 62.09           N  
+ATOM    725  C4    U B  89     -41.727  30.556 -14.197  1.00 67.62           C  
+ATOM    726  O4    U B  89     -42.543  30.948 -13.359  1.00 75.18           O  
+ATOM    727  C5    U B  89     -40.304  30.660 -14.099  1.00 60.41           C  
+ATOM    728  C6    U B  89     -39.541  30.188 -15.090  1.00 48.05           C  
+ATOM    729  P     A B  90     -35.937  30.752 -19.910  1.00110.96           P  
+ATOM    730  OP1   A B  90     -36.589  29.495 -20.359  1.00102.79           O  
+ATOM    731  OP2   A B  90     -34.637  30.668 -19.201  1.00 98.18           O  
+ATOM    732  O5'   A B  90     -35.811  31.758 -21.135  1.00 85.89           O  
+ATOM    733  C5'   A B  90     -36.772  31.757 -22.177  1.00101.33           C  
+ATOM    734  C4'   A B  90     -36.131  31.497 -23.516  1.00 89.35           C  
+ATOM    735  O4'   A B  90     -35.196  32.562 -23.827  1.00 82.67           O  
+ATOM    736  C3'   A B  90     -35.288  30.236 -23.620  1.00 85.67           C  
+ATOM    737  O3'   A B  90     -36.061  29.062 -23.805  1.00 81.70           O  
+ATOM    738  C2'   A B  90     -34.369  30.554 -24.789  1.00 88.06           C  
+ATOM    739  O2'   A B  90     -35.057  30.404 -26.023  1.00 84.48           O  
+ATOM    740  C1'   A B  90     -34.107  32.043 -24.563  1.00 74.25           C  
+ATOM    741  N9    A B  90     -32.865  32.273 -23.800  1.00 69.68           N  
+ATOM    742  C8    A B  90     -32.700  32.486 -22.452  1.00 66.88           C  
+ATOM    743  N7    A B  90     -31.446  32.652 -22.096  1.00 64.42           N  
+ATOM    744  C5    A B  90     -30.739  32.537 -23.287  1.00 65.35           C  
+ATOM    745  C6    A B  90     -29.369  32.614 -23.602  1.00 49.71           C  
+ATOM    746  N6    A B  90     -28.396  32.835 -22.714  1.00 56.28           N  
+ATOM    747  N1    A B  90     -29.018  32.453 -24.895  1.00 67.75           N  
+ATOM    748  C2    A B  90     -29.971  32.230 -25.806  1.00 61.21           C  
+ATOM    749  N3    A B  90     -31.286  32.138 -25.636  1.00 68.13           N  
+ATOM    750  C4    A B  90     -31.605  32.302 -24.341  1.00 75.90           C  
+ATOM    751  P     A B  91     -35.474  27.632 -23.362  1.00 83.80           P  
+ATOM    752  OP1   A B  91     -36.622  26.694 -23.287  1.00 91.65           O  
+ATOM    753  OP2   A B  91     -34.652  27.853 -22.146  1.00 84.63           O  
+

integration_tests/test_attract.py

@@ -0,0 +1,66 @@
+import os
+import shutil
+import tempfile
+from pathlib import Path
+
+import pytest
+
+from haddock.libs.libontology import PDBFile
+from haddock.modules.sampling.attract import \
+    DEFAULT_CONFIG as DEFAULT_ATTRACT_CONFIG
+from haddock.modules.sampling.attract import HaddockModule as AttractModule
+
+from . import GOLDEN_DATA, has_attract
+
+
+class MockPreviousIO:
+    """Mock the previous IO module."""
+
+    def __init__(self, path):
+        self.path = path
+
+    def retrieve_models(self):
+        """Mock the retrieval of some models"""
+        shutil.copy(
+            Path(GOLDEN_DATA, "prot.pdb"),
+            Path(self.path, "prot.pdb"),
+        )
+
+        shutil.copy(
+            Path(GOLDEN_DATA, "rna.pdb"),
+            Path(self.path, "rna.pdb"),
+        )
+
+        return [
+            PDBFile(file_name="prot.pdb", path=self.path),
+            PDBFile(file_name="rna.pdb", path=self.path),
+        ]
+
+    def output(self) -> None:
+        """Mock the output"""
+        return None
+
+
+@pytest.fixture(name="attract_module")
+def fixture_attract_module():
+    """Initialize the attract module"""
+    with tempfile.TemporaryDirectory() as tempdir:
+        os.chdir(tempdir)
+        yield AttractModule(
+            order=0, path=Path("."), initial_params=DEFAULT_ATTRACT_CONFIG
+        )
+
+
+@has_attract
+@pytest.mark.skip(reason="work-in-progress")
+def test_attract(attract_module):
+    """Integration test for the attract module"""
+
+    attract_module.previous_io = MockPreviousIO(path=attract_module.path)
+
+    # attract_module.attract_tools = ???
+    # attract_module.nalib = ???
+
+    attract_module.run()
+
+    assert len(attract_module.output_models) > 0

src/haddock/modules/_template_cat/README.md

@@ -4,25 +4,25 @@ To develop your own HADDOCK3 module follow the patterns used in other modules.
 
 1. If your module belongs to a new category, create a folder for that category
    under the `modules` folder.
-1. Else, create a folder for your module inside its relevant category.
+2. Else, create a folder for your module inside its relevant category.
    The name of that folder is the name of the module, i.e., the name used to call
    the module in the haddock3 configuration files and used throughout the code base.
-1. Copy the `__init__.py` file here to the new module's folder and edit it accordingly
+3. Copy the `__init__.py` file here to the new module's folder and edit it accordingly
    to the instructions there.
-1. Do the same for the `defaults.yaml` file.
-1. You can then add any extra files needed inside your module's folder in order to
+4. Do the same for the `defaults.yaml` file.
+5. You can then add any extra files needed inside your module's folder in order to
    develop your module fully.
-1. If your module requires any extra libraries, describe how to install those libraries
+6. If your module requires any extra libraries, describe how to install those libraries
    in the `docs/INSTALL.md` file. Unless approved by the Haddock Team, do not add
    those dependencies to the `requirements.*` files.
-1. HADDOCK3 has already many features related to IO, subprocess run, sending jobs,
+7. HADDOCK3 has already many features related to IO, subprocess run, sending jobs,
    etc. Please, look around the `libs` folder for pertinent functions, but, above all,
    feel welcomed to reach out to us with any doubts.
-1. Please write also tests for your module. Our testing machinery already
+8. Please write also tests for your module. Our testing machinery already
    tests for the common patterns, for example, inspecting the `defaults.yaml` file.
    But you should write any additional tests to ensure that your module works properly.
    See other examples in the `tests/` folder.
-1. Finally, add an example of how to use your module in the `examples/` folder.
+9. Finally, add an example of how to use your module in the `examples/` folder.
    The example should have a short sampling scheme. Name the config file ending with
    `-test.cfg`.
 

src/haddock/modules/_template_cat/_template_mod/__init__.py

@@ -60,7 +60,7 @@ def __init__(
             ) -> None:
 
         # if your module uses CNS you might need to define where the main CNS
-        # script is localted. See examples in `topoaa`, `emref`.
+        # script is located. See examples in `topoaa`, `emref`.
         #  else leave it out.
         # cns_script = Path(RECIPE_PATH, "cns", "main.cns")
 

src/haddock/modules/sampling/attract/__init__.py

@@ -0,0 +1,135 @@
+"""attract docking module
+==================================
+
+This module performs a fragment-based single-stranded (ss) RNA-protein docking 
+using ATTRACT docking engine. This docking approach was developed to tackle the 
+flexibility of ssRNA. Its core idea is to split ssRNA chain into overlapping 
+trinucleotides (fragments), and dock them onto the rigid receptor separately, 
+assembling the fragments back into the whole chain models afterwards.
+
+#todo 
+add short description of the protocol, including CG, NAlib, sampling, 
+scoring (two ways) and assembly + possible restraints. 
+."""
+import os
+#import sys
+import tempfile
+import subprocess
+import shutil
+import shlex
+from pathlib import Path
+from haddock.modules.sampling.attract.attractmodule import (
+    rename_and_coarse_grain,
+    process_rna_file,
+)
+
+from haddock import log
+from haddock.core.defaults import MODULE_DEFAULT_YAML
+from haddock.core.typing import FilePath, Any 
+#from haddock.libs import libpdb
+#from haddock.libs.libio import working_directory
+from haddock.libs.libontology import Format, PDBFile
+#from haddock.libs.libutil import check_subprocess
+from haddock.modules import BaseHaddockModule
+
+RECIPE_PATH = Path(__file__).resolve().parent
+DEFAULT_CONFIG = Path(RECIPE_PATH, MODULE_DEFAULT_YAML)
+
+class HaddockModule(BaseHaddockModule):
+    """ATTRACT module."""
+
+    name = RECIPE_PATH.name
+
+    def __init__(self,
+                 order: int,
+                 path: Path,
+                 initial_params: FilePath = DEFAULT_CONFIG) -> None:
+        super().__init__(order, path, initial_params)
+
+    @classmethod
+    def confirm_installation(cls) -> None:
+        """Confirm that ATTRACT and its environment variables are properly set."""
+        try:
+            attract_dir = os.environ['ATTRACTDIR']
+            attract_tools = os.environ['ATTRACTTOOLS']
+            nalib = os.environ['LIBRARY']
+            randsearch = os.environ['RANDSEARCH']
+        except KeyError as e:
+            raise EnvironmentError(f"Required environment variable not found: {e}")
+
+        attract_exec = Path(attract_dir, 'attract')
+        result = subprocess.run([str(attract_exec)], capture_output=True, text=True)
+
+        if "Too few arguments" not in result.stderr:
+            raise RuntimeError('ATTRACT is not installed properly')
+
+        # pass paths to _run for further use
+        cls.attract_dir = attract_dir
+        cls.attract_tools = attract_tools
+        cls.nalib = nalib
+
+    def _run(self) -> None:
+        """Execute module.
+        Currently:
+        1. Converts protein and RNA in ATTRACT coarse-grain 
+        2. Splits RNA into overlapping fragments
+        3. Creates required by ATTRACT files: motif.list, boundfrag.list, nalib
+        4. Passes initial all-atom protein and RNA to next module
+        """
+
+        # Get the models generated in previous step
+        models: list[PDBFile] = [
+            p for p in self.previous_io.output
+            if p.file_type == Format.PDB ]
+
+        # Check that exactly two models are provided
+        # practically attract needs protein structure and RNA *sequence* 
+        # but at this stage it's more practical to ask for RNA structure     
+        if len(models) !=2 : 
+            _msg = "ATTRACT requires exactly two molecules"
+            self.finish_with_error(_msg)
+
+        # Copy each model to the working directory
+        for model in models:
+            src_model = Path(model.path, model.file_name)
+            dest_model = Path(os.getcwd(), model.file_name)
+            shutil.copyfile(src_model, dest_model)
+
+        # Ensure we have exactly protein and RNA molecules
+        model_1 = models[0]
+        model_2 = models[1]
+
+        attracttools = self.attract_tools
+        attrac_reduce_path = Path(attracttools, 'reduce.py')
+
+        _, label_1 = rename_and_coarse_grain(model_1.file_name, attrac_reduce_path)
+        _, label_2 = rename_and_coarse_grain(model_2.file_name, attrac_reduce_path)
+
+        if {label_1, label_2} != {'protein', 'rna'}:
+            _msg = "ATTRACT requires protein and RNA molecules as input"
+            self.finish_with_error(_msg)
+
+        # Add required by ATTRACT files: 
+        log.info("Preparing docking directory")
+
+        nalib = self.nalib
+        cmd = f"ln -s {nalib} nalib"
+        p = subprocess.run(shlex.split(cmd), capture_output=True)
+        err = p.stderr.decode('utf-8')
+
+        process_rna_file('rna-aar.pdb')
+
+        tmp_dir = tempfile.mkdtemp(dir=os.getcwd())
+        # will be used during the docking
+        shutil.rmtree(tmp_dir)
+
+        list_of_created_models = []     
+        created_models = ['protein-aa.pdb','rna-aa.pdb']
+        for model in created_models:
+            pdb_object = PDBFile(Path(model).name,  path=".")
+            list_of_created_models.append(pdb_object)
+
+        self.output_models = list_of_created_models
+        self.export_io_models()
+
+