Selection of Nter, Cter and 5'end states at topology generation

integration_tests/golden_data/mini_dna.pdb

@@ -0,0 +1,44 @@
+ATOM      1  P    DA B   1       0.315   9.360  -1.520  1.00  0.00      B
+ATOM      2  O1P  DA B   1       0.321  10.697  -2.151  1.00  0.00      B
+ATOM      3  O2P  DA B   1       1.317   9.141  -0.451  1.00  0.00      B
+ATOM      4  O5'  DA B   1      -1.147   9.038  -0.954  1.00  0.00      B
+ATOM      5  C5'  DA B   1      -2.123   8.457  -1.844  1.00  0.00      B
+ATOM      6  C4'  DA B   1      -2.867   7.341  -1.136  1.00  0.00      B
+ATOM      7  O4'  DA B   1      -2.198   6.055  -1.270  1.00  0.00      B
+ATOM      8  C3'  DA B   1      -3.039   7.508   0.371  1.00  0.00      B
+ATOM      9  O3'  DA B   1      -4.314   7.002   0.746  1.00  0.00      B
+ATOM     10  C2'  DA B   1      -1.961   6.613   0.982  1.00  0.00      B
+ATOM     11  C1'  DA B   1      -2.118   5.453   0.006  1.00  0.00      B
+ATOM     12  N9   DA B   1      -0.986   4.531   0.008  1.00  0.00      B
+ATOM     13  C8   DA B   1       0.352   4.845   0.001  1.00  0.00      B
+ATOM     14  N7   DA B   1       1.139   3.798   0.003  1.00  0.00      B
+ATOM     15  C5   DA B   1       0.263   2.721   0.002  1.00  0.00      B
+ATOM     16  C6   DA B   1       0.472   1.332   0.003  1.00  0.00      B
+ATOM     17  N6   DA B   1       1.681   0.764  -0.003  1.00  0.00      B
+ATOM     18  N1   DA B   1      -0.618   0.534   0.002  1.00  0.00      B
+ATOM     19  C2   DA B   1      -1.828   1.103   0.008  1.00  0.00      B
+ATOM     20  N3   DA B   1      -2.154   2.393   0.007  1.00  0.00      B
+ATOM     21  C4   DA B   1      -1.050   3.159   0.008  1.00  0.00      B
+ATOM     22  P    DG B   2      -5.217   7.755   1.698  1.00  0.00      B
+ATOM     23  O1P  DG B   2      -5.968   8.851   1.048  1.00  0.00      B
+ATOM     24  O2P  DG B   2      -4.336   8.150   2.824  1.00  0.00      B
+ATOM     25  O5'  DG B   2      -6.237   6.624   2.192  1.00  0.00      B
+ATOM     26  C5'  DG B   2      -6.636   5.596   1.263  1.00  0.00      B
+ATOM     27  C4'  DG B   2      -6.616   4.244   1.945  1.00  0.00      B
+ATOM     28  O4'  DG B   2      -5.311   3.601   1.866  1.00  0.00      B
+ATOM     29  C3'  DG B   2      -6.931   4.251   3.441  1.00  0.00      B
+ATOM     30  O3'  DG B   2      -7.682   3.085   3.764  1.00  0.00      B
+ATOM     31  C2'  DG B   2      -5.567   4.151   4.125  1.00  0.00      B
+ATOM     32  C1'  DG B   2      -4.959   3.140   3.162  1.00  0.00      B
+ATOM     33  N9   DG B   2      -3.504   3.061   3.233  1.00  0.00      B
+ATOM     34  C8   DG B   2      -2.619   4.111   3.298  1.00  0.00      B
+ATOM     35  N7   DG B   2      -1.373   3.727   3.353  1.00  0.00      B
+ATOM     36  C5   DG B   2      -1.437   2.340   3.332  1.00  0.00      B
+ATOM     37  C6   DG B   2      -0.403   1.370   3.368  1.00  0.00      B
+ATOM     38  O6   DG B   2       0.820   1.550   3.431  1.00  0.00      B
+ATOM     39  N1   DG B   2      -0.911   0.077   3.320  1.00  0.00      B
+ATOM     40  C2   DG B   2      -2.244  -0.243   3.241  1.00  0.00      B
+ATOM     41  N2   DG B   2      -2.536  -1.553   3.207  1.00  0.00      B
+ATOM     42  N3   DG B   2      -3.218   0.650   3.211  1.00  0.00      B
+ATOM     43  C4   DG B   2      -2.747   1.914   3.254  1.00  0.00      B
+END

integration_tests/test_topoaa.py

@@ -1,4 +1,5 @@
 import tempfile
+import copy
 from pathlib import Path
 
 import pytest
@@ -20,17 +21,52 @@ def topoaa_module():
         yield topoaa
 
 
+def extract_nter_cter(fpath) -> tuple[str, str]:
+    """Helper function to extract nter and cter residues as strings."""
+    nter, cter = "", ""
+    nter_resi, cter_resi = None, None
+    # Read file
+    with open(fpath, "r") as fin:
+        # Loop over lines
+        for _ in fin:
+            # Make sure we are looking at coordinates
+            if _.startswith(("ATOM", "HETATM")):
+                # Extract residue id
+                resid = _[22:26].strip()
+                # First residue should be Nter one
+                if nter_resi is None:
+                    nter_resi = resid 
+                # Last residue should be Cter one
+                if cter_resi is None:
+                    cter_resi = resid
+                else:
+                    # Reset last residue to current residue
+                    # until we cannot do this anymore
+                    # should result in extracting last residue
+                    if cter_resi != resid:
+                        # Reset cter residue to empty string
+                        cter = ""
+                        cter_resi = resid
+                # Increment first residue
+                if resid == nter_resi:
+                    nter += _
+                # Increment last residue
+                cter += _
+    return nter, cter
+
+
 def test_topoaa_module_protein(topoaa_module):
     """Topoaa module with protein-protein input"""
     topoaa_module.params["molecules"] = [
         Path(GOLDEN_DATA, "e2aP_1F3G.pdb"),
         Path(GOLDEN_DATA, "hpr_ensemble.pdb"),
     ]
-    topoaa_module.params["mol1"] = {"prot_segid": "A"}
-    topoaa_module.params["mol2"] = {"prot_segid": "B"}
+    topoaa_module.params["mol1"]["prot_segid"] = "A"
+    # Create mol2 parameters by copying the ones found for mol1
+    topoaa_module.params["mol2"] = copy.deepcopy(topoaa_module.params["mol1"])
+    topoaa_module.params["mol2"]["prot_segid"] = "B"
     topoaa_module.params["cns_exec"] = CNS_EXEC
     topoaa_module.params["debug"] = True
-
     topoaa_module.run()
 
     expected_inp = Path(topoaa_module.path, "e2aP_1F3G.inp")
@@ -94,7 +130,7 @@ def test_topoaa_cyclic(topoaa_module):
     ]
     topoaa_module.params["cyclicpept_dist"] = 3.5
     topoaa_module.params["disulphide_dist"] = 4.0
-    topoaa_module.params["mol1"] = {"cyclicpept": True}
+    topoaa_module.params["mol1"]["cyclicpept"] = True
     topoaa_module.params["cns_exec"] = CNS_EXEC
     topoaa_module.params["debug"] = True
 
@@ -115,3 +151,149 @@ def test_topoaa_cyclic(topoaa_module):
 
     assert "detected" in file_content
     assert "disulphide" in file_content
+
+
+def test_topoaa_module_protein_noCter(topoaa_module):
+    """Topoaa module with uncharged Cter and charged Nter."""
+    topoaa_module.params["molecules"] = [
+        Path(GOLDEN_DATA, "2oob_A.pdb"),
+    ]
+    topoaa_module.params["mol1"]["charged_nter"] = True
+    topoaa_module.params["mol1"]["charged_cter"] = False
+    topoaa_module.params["cns_exec"] = CNS_EXEC
+    topoaa_module.params["debug"] = True
+    topoaa_module.run()
+
+    expected_inp = Path(topoaa_module.path, "2oob_A.inp")
+    expected_psf = Path(topoaa_module.path, "2oob_A_haddock.psf")
+    expected_pdb = Path(topoaa_module.path, "2oob_A_haddock.pdb")
+    expected_gz = Path(topoaa_module.path, "2oob_A.out.gz")
+    assert expected_inp.exists()
+    assert expected_psf.exists()
+    assert expected_pdb.exists()
+    assert expected_gz.exists()
+
+    nter, cter = extract_nter_cter(expected_pdb)
+    assert "OXT" not in cter
+    assert all([nh in nter for nh in ("HT1", "HT2", "HT3",)])
+
+
+def test_topoaa_module_protein_noNter(topoaa_module):
+    """Topoaa module with charged Cter and uncharged Nter."""
+    topoaa_module.params["molecules"] = [
+        Path(GOLDEN_DATA, "2oob_A.pdb"),
+    ]
+    topoaa_module.params["mol1"]["charged_nter"] = False
+    topoaa_module.params["mol1"]["charged_cter"] = True
+    topoaa_module.params["cns_exec"] = CNS_EXEC
+    topoaa_module.params["debug"] = True
+    topoaa_module.run()
+
+    expected_inp = Path(topoaa_module.path, "2oob_A.inp")
+    expected_psf = Path(topoaa_module.path, "2oob_A_haddock.psf")
+    expected_pdb = Path(topoaa_module.path, "2oob_A_haddock.pdb")
+    expected_gz = Path(topoaa_module.path, "2oob_A.out.gz")
+    assert expected_inp.exists()
+    assert expected_psf.exists()
+    assert expected_pdb.exists()
+    assert expected_gz.exists()
+
+    nter, cter = extract_nter_cter(expected_pdb)
+    assert "OXT" in cter
+    assert not any([nh in nter for nh in ("HT1", "HT2", "HT3",)])
+
+def test_topoaa_module_protein_noter(topoaa_module):
+    """Topoaa module without charged termini."""
+    topoaa_module.params["molecules"] = [
+        Path(GOLDEN_DATA, "2oob_A.pdb"),
+    ]
+    topoaa_module.params["mol1"]["charged_nter"] = False
+    topoaa_module.params["mol1"]["charged_cter"] = False
+    topoaa_module.params["cns_exec"] = CNS_EXEC
+    topoaa_module.params["debug"] = True
+    topoaa_module.run()
+
+    expected_inp = Path(topoaa_module.path, "2oob_A.inp")
+    expected_psf = Path(topoaa_module.path, "2oob_A_haddock.psf")
+    expected_pdb = Path(topoaa_module.path, "2oob_A_haddock.pdb")
+    expected_gz = Path(topoaa_module.path, "2oob_A.out.gz")
+    assert expected_inp.exists()
+    assert expected_psf.exists()
+    assert expected_pdb.exists()
+    assert expected_gz.exists()
+
+    nter, cter = extract_nter_cter(expected_pdb)
+    assert "OXT" not in cter
+    assert not any([nh in nter for nh in ("HT1", "HT2", "HT3",)])
+
+
+def test_topoaa_module_protein_charged_ters(topoaa_module):
+    """Topoaa module with charged termini."""
+    topoaa_module.params["molecules"] = [
+        Path(GOLDEN_DATA, "2oob_A.pdb"),
+    ]
+    topoaa_module.params["mol1"]["charged_nter"] = True
+    topoaa_module.params["mol1"]["charged_cter"] = True
+    topoaa_module.params["cns_exec"] = CNS_EXEC
+    topoaa_module.params["debug"] = True
+    topoaa_module.run()
+
+    expected_inp = Path(topoaa_module.path, "2oob_A.inp")
+    expected_psf = Path(topoaa_module.path, "2oob_A_haddock.psf")
+    expected_pdb = Path(topoaa_module.path, "2oob_A_haddock.pdb")
+    expected_gz = Path(topoaa_module.path, "2oob_A.out.gz")
+    assert expected_inp.exists()
+    assert expected_psf.exists()
+    assert expected_pdb.exists()
+    assert expected_gz.exists()
+
+    nter, cter = extract_nter_cter(expected_pdb)
+    assert "OXT" in cter
+    assert all([nh in nter for nh in ("HT1", "HT2", "HT3",)])
+
+
+def test_topoaa_module_dna_5_phosphate(topoaa_module):
+    """Topoaa module with charged termini."""
+    topoaa_module.params["molecules"] = [
+        Path(GOLDEN_DATA, "mini_dna.pdb"),
+    ]
+    topoaa_module.params["mol1"]["5_phosphate"] = True
+    topoaa_module.params["cns_exec"] = CNS_EXEC
+    topoaa_module.params["debug"] = True
+    topoaa_module.run()
+
+    expected_inp = Path(topoaa_module.path, "mini_dna.inp")
+    expected_psf = Path(topoaa_module.path, "mini_dna_haddock.psf")
+    expected_pdb = Path(topoaa_module.path, "mini_dna_haddock.pdb")
+    expected_gz = Path(topoaa_module.path, "mini_dna.out.gz")
+    assert expected_inp.exists()
+    assert expected_psf.exists()
+    assert expected_pdb.exists()
+    assert expected_gz.exists()
+
+    five_prime, _three_prime = extract_nter_cter(expected_pdb)
+    assert all([fp in five_prime for fp in ("H5T", "O5T", "OP2", "OP1", "P",)])
+
+
+def test_topoaa_module_dna_5_oh(topoaa_module):
+    """Topoaa module with charged termini."""
+    topoaa_module.params["molecules"] = [
+        Path(GOLDEN_DATA, "mini_dna.pdb"),
+    ]
+    topoaa_module.params["mol1"]["5_phosphate"] = False
+    topoaa_module.params["cns_exec"] = CNS_EXEC
+    topoaa_module.params["debug"] = True
+    topoaa_module.run()
+
+    expected_inp = Path(topoaa_module.path, "mini_dna.inp")
+    expected_psf = Path(topoaa_module.path, "mini_dna_haddock.psf")
+    expected_pdb = Path(topoaa_module.path, "mini_dna_haddock.pdb")
+    expected_gz = Path(topoaa_module.path, "mini_dna.out.gz")
+    assert expected_inp.exists()
+    assert expected_psf.exists()
+    assert expected_pdb.exists()
+    assert expected_gz.exists()
+
+    five_prime, _three_prime = extract_nter_cter(expected_pdb)
+    assert not any([fp in five_prime for fp in ("O5T", "OP2", "OP1", "P",)])
+    assert "H5T" in five_prime

src/haddock/core/cns_paths.py

@@ -26,6 +26,17 @@
 SCATTER_LIB = "scatter.lib"
 INITIAL_POSITIONS_DIR = "initial_positions"
 
+PROTEIN_LINK_FILES = {
+    "NH3+,COO-": "protein-allhdg5-4.link",
+    "NH,COO-": "protein-allhdg5-4-noNter.link",
+    "NH3+,CO": "protein-allhdg5-4-noCter.link",
+    "NH,CO": LINK_FILE,
+}
+NUCL_LINK_FILES = {
+    "5'Phosphate": "dna-rna-pho-1.3.link",
+    "5'OH": "dna-rna-1.3.link",
+}
+
 # default prepared paths
 link_file = Path(toppar_path, LINK_FILE)
 scatter_lib = Path(toppar_path, SCATTER_LIB)

src/haddock/libs/libcns.py

@@ -53,6 +53,56 @@ def generate_default_header(
     )
 
 
+def find_desired_linkfiles(
+        charged_nter: bool = False,
+        charged_cter: bool = False,
+        phosphate_5: bool = False,
+        path: Optional[FilePath] = None,
+        ) -> dict[str, Path]:
+    """Find appropriate link files to use depending on terminis states.
+
+    Parameters
+    ----------
+    charged_nter : bool, optional
+        Must the Nter be charged ?, by default False
+    charged_cter : bool, optional
+        Must the Cter be charged ?, by default False
+    phosphate_5 : bool, optional
+        Must 5' be a phosphate ?, by default False
+    path : Optional[FilePath], optional
+        Path to where CNS topology/parameters are, by default None
+
+    Returns
+    -------
+    linkfiles : dict[str, Path]
+        Dict of CNS parameters/arguments/variable as keys
+        and Path to link files to be used during topology
+        generation.
+    """
+    # Set output variable
+    linkfiles = {}
+    # Logic to find appropriate link for proteins
+    if charged_nter and charged_cter:
+        prot_link_key = "NH3+,COO-"
+    elif not charged_nter and charged_cter:
+        prot_link_key = "NH,COO-"
+    elif charged_nter and not charged_cter:
+        prot_link_key= "NH3+,CO"
+    elif not charged_nter and not charged_cter:
+        prot_link_key = "NH,CO"
+    # Point to corresponding file
+    linkfiles["prot_link_infile"] = cns_paths.PROTEIN_LINK_FILES[prot_link_key]
+
+    # Logic to find linkfile for dna
+    nucl_link_key = "5'Phosphate" if phosphate_5 else "5'OH"
+    # Point to corresponding file
+    linkfiles["nucl_link_infile"] = cns_paths.NUCL_LINK_FILES[nucl_link_key]
+    # Converts to real paths
+    if path is not None:
+        linkfiles = {key: Path(path, p) for key, p in linkfiles.items()}
+    return linkfiles
+
+
 def _is_nan(x: Any) -> bool:
     """Inspect if is nan."""
     try:
@@ -116,10 +166,13 @@ def load_workflow_params(
 
     Returns
     -------
-    str
+    param_header: str
         The string with the CNS parameters defined.
     """
-    non_empty_parameters = ((k, v) for k, v in params.items() if filter_empty_vars(v))
+    non_empty_parameters = (
+        (k, v) for k, v in params.items()
+        if filter_empty_vars(v)
+        )
 
     # types besides the ones in the if-statements should not enter this loop
     for param, v in non_empty_parameters:
@@ -160,7 +213,8 @@ def write_eval_line(param: Any, value: Any, eval_line: str = "eval (${}={})") ->
 def load_link(mol_link: Path) -> str:
     """Add the link header."""
     return load_workflow_params(
-        param_header=f"{linesep}! Link file{linesep}", link_file=mol_link
+        param_header=f"{linesep}! Link file{linesep}",
+        prot_link_infile=mol_link,
     )
 
 

src/haddock/modules/refinement/emref/cns/read_param.cns

@@ -21,9 +21,6 @@ eval ($carbo_parameter_infile="TOPPAR:carbohydrate.param")
 {* solvent parameter file *}
 eval ($solv_parameter_infile="TOPPAR:solvent-allhdg5-4.param")
 
-{* ligand parameter file *}
-eval ($cofac_parameter_infile="TOPPAR:ligand.param")
-
 {* fragment probes parameter file *}
 eval ($ligands_parameter_infile="TOPPAR:fragment_probes.param")
 
@@ -46,7 +43,6 @@ parameter
     @@$carbo_parameter_infile
     @@$solv_parameter_infile
     @@$ligands_parameter_infile
-    @@$cofac_parameter_infile
     @@$heme_parameter_infile
     @@$shape_parameter_infile
     @@$cofactors_parameter_infile