From 02492a7e1d38728e0b09b6f0508efaf3399ff70e Mon Sep 17 00:00:00 2001
From: VGPReys <v.g.p.reys@uu.nl>
Date: Sat, 8 Aug 2026 16:14:37 +0200
Subject: [PATCH 1/8] fix dna nucleobase atom selection default for capri

---
 src/haddock/libs/libalign.py | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/src/haddock/libs/libalign.py b/src/haddock/libs/libalign.py
index 0af3740c95..baf95aa9ff 100644
--- a/src/haddock/libs/libalign.py
+++ b/src/haddock/libs/libalign.py
@@ -204,7 +204,7 @@
     "martini3" : PROT_SIDE_CHAINS_DICT_MARTINI3
 }
 
-# Bases
+# For DNA, we use nucleo-bases as default atom selection
 DNA_ATOMS = [
     "C5",
     "N9",
@@ -223,14 +223,15 @@
     "C4",
     "O6",
 ]
-DNA_ATOMS_MARTINI2 = ["BB1", "BB2", "BB3"]
-
+DNA_ATOMS_MARTINI2 = ["SC1", "SC2", "SC3", "SC4"]
+DNA_ATOMS_MARTINI3 = ["SC1", "SC2", "SC3", "SC4"]
 DNA_ATOMS_all = {
     "aa" : DNA_ATOMS,
     "martini2" : DNA_ATOMS_MARTINI2,
-    "martini3" : DNA_ATOMS_MARTINI2
+    "martini3" : DNA_ATOMS_MARTINI3,
 }
 
+# Definition of all atoms in DNA
 DNA_FULL_DICT = {
     "DA": [
         "P",
@@ -356,13 +357,15 @@
     "DG" : ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
     "DT" : ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"]
 }
-
+DNA_FULL_DICT_MARTINI3 = DNA_FULL_DICT_MARTINI2
 DNA_FULL_DICT_all = {
     "aa" : DNA_FULL_DICT,
     "martini2" : DNA_FULL_DICT_MARTINI2,
-    "martini3" : DNA_FULL_DICT_MARTINI2
+    "martini3" : DNA_FULL_DICT_MARTINI3,
 }
 
+# RNA definitions
+# Backbone
 RNA_RES = ["A", "G", "C", "U"]
 RNA_ATOMS = ["P", "O5'", "C5'", "C4'", "C3'", "O3'"]
 RNA_ATOMS_MARTINI2 = ["BB1", "BB2", "BB3"]
@@ -373,6 +376,7 @@
     "martini3" : RNA_ATOMS_MARTINI2
 }
 
+# All atoms in RNA
 RNA_FULL_DICT = {
     "A": [
         "P",
@@ -477,11 +481,11 @@
     "G" : ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
     "U" : ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"]
 }
-
+RNA_FULL_DICT_MARTINI3 = RNA_FULL_DICT_MARTINI2
 RNA_FULL_DICT_all = {
     "aa" : RNA_FULL_DICT,
     "martini2" : RNA_FULL_DICT_MARTINI2,
-    "martini3" : RNA_FULL_DICT_MARTINI2
+    "martini3" : RNA_FULL_DICT_MARTINI3,
 }
 
 

From 49f62319e4897c5ecbd38c2761c6d392402fee6c Mon Sep 17 00:00:00 2001
From: VGPReys <v.g.p.reys@uu.nl>
Date: Sat, 8 Aug 2026 16:44:14 +0200
Subject: [PATCH 2/8] lint

---
 src/haddock/libs/libalign.py | 406 ++++++++++++++++++-----------------
 1 file changed, 213 insertions(+), 193 deletions(-)

diff --git a/src/haddock/libs/libalign.py b/src/haddock/libs/libalign.py
index baf95aa9ff..d9965eb169 100644
--- a/src/haddock/libs/libalign.py
+++ b/src/haddock/libs/libalign.py
@@ -42,11 +42,101 @@
     slc_y,
     slc_z,
     split_by_chain,
-    )
+)
 
 
 RES_TO_BE_IGNORED = ["SHA", "WAT"]
 
+ResCode = Literal[
+    "C",
+    "D",
+    "S",
+    "Q",
+    "K",
+    "I",
+    "P",
+    "T",
+    "F",
+    "N",
+    "G",
+    "H",
+    "L",
+    "R",
+    "W",
+    "A",
+    "V",
+    "E",
+    "Y",
+    "M",
+    "A",
+    "G",
+    "C",
+    "T",
+    "X",
+]
+"""
+The single letter code of a residue.
+
+Unrecognized residues' code is `X`.
+"""
+
+RES_3L1L = dict(
+    [
+        ("CYS", "C"),
+        ("ASP", "D"),
+        ("SER", "S"),
+        ("GLN", "Q"),
+        ("LYS", "K"),
+        ("ILE", "I"),
+        ("PRO", "P"),
+        ("THR", "T"),
+        ("PHE", "F"),
+        ("ASN", "N"),
+        ("GLY", "G"),
+        ("HIS", "H"),
+        ("LEU", "L"),
+        ("ARG", "R"),
+        ("TRP", "W"),
+        ("ALA", "A"),
+        ("VAL", "V"),
+        ("GLU", "E"),
+        ("TYR", "Y"),
+        ("MET", "M"),
+        ("DA", "A"),
+        ("DG", "G"),
+        ("DC", "C"),
+        ("DT", "T"),
+        ("A", "A"),
+        ("G", "G"),
+        ("C", "C"),
+        ("U", "U"),
+        # 9/8/2023: adding non-standard amino-acids (src/haddock/cns/toppar/protein-allhdg5-4.top) # noqa: E501
+        ("ALY", "K"),
+        ("ASH", "D"),
+        ("CFE", "C"),
+        ("CSP", "C"),
+        ("CYC", "C"),
+        ("CYF", "C"),
+        ("CYM", "C"),
+        ("DDZ", "A"),
+        ("GLH", "E"),
+        ("HLY", "P"),
+        ("HY3", "P"),
+        ("HYP", "P"),
+        ("M3L", "K"),
+        ("MLY", "K"),
+        ("MLZ", "K"),
+        ("MSE", "M"),
+        ("NEP", "H"),
+        ("PNS", "S"),
+        ("PTR", "Y"),
+        ("SEP", "S"),
+        ("TOP", "T"),
+        ("TYP", "Y"),
+        ("TYS", "Y"),
+    ]
+)
+
 PROT_RES = [
     "ALA",
     "ARG",
@@ -75,9 +165,9 @@
 PROT_ATOMS = ["C", "N", "CA", "O"]
 PROT_ATOMS_MARTINI2 = ["BB"]
 PROT_ATOMS_all = {
-    "aa" : PROT_ATOMS,
-    "martini2" : PROT_ATOMS_MARTINI2,
-    "martini3" : PROT_ATOMS_MARTINI2 # The backbone particle is identical between MARTINI 2 and 3
+    "aa": PROT_ATOMS,
+    "martini2": PROT_ATOMS_MARTINI2,
+    "martini3": PROT_ATOMS_MARTINI2, # The backbone particle is identical between MARTINI 2 and 3
 }
 
 # Side chains
@@ -133,75 +223,75 @@
 }
 
 PROT_SIDE_CHAINS_DICT_MARTINI2 = {
-    "GLY": ['BB'],
-    "ALA": ['BB'],
-    "CYS": ['BB', 'SC1'],
-    "VAL": ['BB', 'SC1'],
-    "LEU": ['BB', 'SC1'],
-    "ILE": ['BB', 'SC1'],
-    "MET": ['BB', 'SC1'],
-    "PRO": ['BB', 'SC1'],
-    "ASN": ['BB', 'SC1'],
-    "GLN": ['BB', 'SC1'],
-    "ASP": ['BB', 'SC1'],
-    "ASP0": ['BB', 'SC1'],
-    "GLU": ['BB', 'SC1'],
-    "GLU0": ['BB', 'SC1'],
-    "THR": ['BB', 'SC1'],
-    "SER": ['BB', 'SC1'],
-    "LYS": ['BB', 'SC1', 'SC2'],
-    "LSN": ['BB', 'SC1', 'SC2'],
-    "ARG": ['BB', 'SC1', 'SC2'],
-    "ARG0": ['BB', 'SC1', 'SC2'],
-    "HIS": ['BB', 'SC1', 'SC2', 'SC3'],
-    "HSE": ['BB', 'SC1', 'SC2', 'SC3'],
-    "HSD": ['BB', 'SC1', 'SC2', 'SC3'],
-    "HSP": ['BB', 'SC1', 'SC2', 'SC3'],
-    "PHE": ['BB', 'SC1', 'SC2', 'SC3'],
-    "TYR": ['BB', 'SC1', 'SC2', 'SC3'],
-    "TRP": ['BB', 'SC1', 'SC2', 'SC3', 'SC4'],
+    "GLY": ["BB"],
+    "ALA": ["BB"],
+    "CYS": ["BB", "SC1"],
+    "VAL": ["BB", "SC1"],
+    "LEU": ["BB", "SC1"],
+    "ILE": ["BB", "SC1"],
+    "MET": ["BB", "SC1"],
+    "PRO": ["BB", "SC1"],
+    "ASN": ["BB", "SC1"],
+    "GLN": ["BB", "SC1"],
+    "ASP": ["BB", "SC1"],
+    "ASP0": ["BB", "SC1"],
+    "GLU": ["BB", "SC1"],
+    "GLU0": ["BB", "SC1"],
+    "THR": ["BB", "SC1"],
+    "SER": ["BB", "SC1"],
+    "LYS": ["BB", "SC1", "SC2"],
+    "LSN": ["BB", "SC1", "SC2"],
+    "ARG": ["BB", "SC1", "SC2"],
+    "ARG0": ["BB", "SC1", "SC2"],
+    "HIS": ["BB", "SC1", "SC2", "SC3"],
+    "HSE": ["BB", "SC1", "SC2", "SC3"],
+    "HSD": ["BB", "SC1", "SC2", "SC3"],
+    "HSP": ["BB", "SC1", "SC2", "SC3"],
+    "PHE": ["BB", "SC1", "SC2", "SC3"],
+    "TYR": ["BB", "SC1", "SC2", "SC3"],
+    "TRP": ["BB", "SC1", "SC2", "SC3", "SC4"],
 }
 
 PROT_SIDE_CHAINS_DICT_MARTINI3 = {
-    "GLY": ['BB'],
-    "ALA": ['BB', 'SC1'],
-    "CYS": ['BB', 'SC1'],
-    "VAL": ['BB', 'SC1'],
-    "LEU": ['BB', 'SC1'],
-    "ILE": ['BB', 'SC1'],
-    "MET": ['BB', 'SC1'],
-    "PRO": ['BB', 'SC1'],
-    "HYP": ['BB', 'SC1'],
-    "ASN": ['BB', 'SC1'],
-    "GLN": ['BB', 'SC1'],
-    "ASP": ['BB', 'SC1'],
-    "ASPP": ['BB', 'SC1'],
-    "ASH": ['BB', 'SC1'],
-    "GLU": ['BB', 'SC1'],
-    "GLUP": ['BB', 'SC1'],
-    "GLH": ['BB', 'SC1'],
-    "LYS": ['BB', 'SC1', 'SC2'],
-    "LSN": ['BB', 'SC1', 'SC2'],
-    "LYN": ['BB', 'SC1', 'SC2'],
-    "THR": ['BB', 'SC1'],
-    "SER": ['BB', 'SC1'],
-    "ARG": ['BB', 'SC1', 'SC2'],
-    "HIS": ['BB', 'SC1', 'SC2', 'SC3'],
-    "HIE": ['BB', 'SC1', 'SC2', 'SC3'],
-    "HSE": ['BB', 'SC1', 'SC2', 'SC3'],
-    "HSD": ['BB', 'SC1', 'SC2', 'SC3'],
-    "HID": ['BB', 'SC1', 'SC2', 'SC3'],
-    "HSP": ['BB', 'SC1', 'SC2', 'SC3'],
-    "HIP": ['BB', 'SC1', 'SC2', 'SC3'],
-    "PHE": ['BB', 'SC1', 'SC2', 'SC3'],
-    "TYR": ['BB', 'SC1', 'SC2', 'SC3', 'SC4'],
-    "TRP": ['BB', 'SC1', 'SC2', 'SC3', 'SC4', 'SC5'],    
+    "GLY": ["BB"],
+    "ALA": ["BB", "SC1"],
+    "CYS": ["BB", "SC1"],
+    "VAL": ["BB", "SC1"],
+    "LEU": ["BB", "SC1"],
+    "ILE": ["BB", "SC1"],
+    "MET": ["BB", "SC1"],
+    "PRO": ["BB", "SC1"],
+    "HYP": ["BB", "SC1"],
+    "ASN": ["BB", "SC1"],
+    "GLN": ["BB", "SC1"],
+    "ASP": ["BB", "SC1"],
+    "ASPP": ["BB", "SC1"],
+    "ASH": ["BB", "SC1"],
+    "GLU": ["BB", "SC1"],
+    "GLUP": ["BB", "SC1"],
+    "GLH": ["BB", "SC1"],
+    "LYS": ["BB", "SC1", "SC2"],
+    "LSN": ["BB", "SC1", "SC2"],
+    "LYN": ["BB", "SC1", "SC2"],
+    "THR": ["BB", "SC1"],
+    "SER": ["BB", "SC1"],
+    "ARG": ["BB", "SC1", "SC2"],
+    "HIS": ["BB", "SC1", "SC2", "SC3"],
+    "HIE": ["BB", "SC1", "SC2", "SC3"],
+    "HSE": ["BB", "SC1", "SC2", "SC3"],
+    "HSD": ["BB", "SC1", "SC2", "SC3"],
+    "HID": ["BB", "SC1", "SC2", "SC3"],
+    "HSP": ["BB", "SC1", "SC2", "SC3"],
+    "HIP": ["BB", "SC1", "SC2", "SC3"],
+    "PHE": ["BB", "SC1", "SC2", "SC3"],
+    "TYR": ["BB", "SC1", "SC2", "SC3", "SC4"],
+    "TRP": ["BB", "SC1", "SC2", "SC3", "SC4", 'SC5'],    
 }
 
 PROT_SIDE_CHAINS_DICT_all = {
-    "aa" : PROT_SIDE_CHAINS_DICT,
-    "martini2" : PROT_SIDE_CHAINS_DICT_MARTINI2,
-    "martini3" : PROT_SIDE_CHAINS_DICT_MARTINI3
+    "aa": PROT_SIDE_CHAINS_DICT,
+    "martini2": PROT_SIDE_CHAINS_DICT_MARTINI2,
+    "martini3": PROT_SIDE_CHAINS_DICT_MARTINI3
 }
 
 # For DNA, we use nucleo-bases as default atom selection
@@ -226,9 +316,9 @@
 DNA_ATOMS_MARTINI2 = ["SC1", "SC2", "SC3", "SC4"]
 DNA_ATOMS_MARTINI3 = ["SC1", "SC2", "SC3", "SC4"]
 DNA_ATOMS_all = {
-    "aa" : DNA_ATOMS,
-    "martini2" : DNA_ATOMS_MARTINI2,
-    "martini3" : DNA_ATOMS_MARTINI3,
+    "aa": DNA_ATOMS,
+    "martini2": DNA_ATOMS_MARTINI2,
+    "martini3": DNA_ATOMS_MARTINI3,
 }
 
 # Definition of all atoms in DNA
@@ -352,16 +442,16 @@
 }
 
 DNA_FULL_DICT_MARTINI2 = {
-    "DA" : ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
-    "DC" : ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"],
-    "DG" : ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
-    "DT" : ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"]
+    "DA": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
+    "DC": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"],
+    "DG": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
+    "DT": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"]
 }
 DNA_FULL_DICT_MARTINI3 = DNA_FULL_DICT_MARTINI2
 DNA_FULL_DICT_all = {
-    "aa" : DNA_FULL_DICT,
-    "martini2" : DNA_FULL_DICT_MARTINI2,
-    "martini3" : DNA_FULL_DICT_MARTINI3,
+    "aa": DNA_FULL_DICT,
+    "martini2": DNA_FULL_DICT_MARTINI2,
+    "martini3": DNA_FULL_DICT_MARTINI3,
 }
 
 # RNA definitions
@@ -371,9 +461,9 @@
 RNA_ATOMS_MARTINI2 = ["BB1", "BB2", "BB3"]
 
 RNA_ATOMS_all = {
-    "aa" : RNA_ATOMS,
-    "martini2" : RNA_ATOMS_MARTINI2,
-    "martini3" : RNA_ATOMS_MARTINI2
+    "aa": RNA_ATOMS,
+    "martini2": RNA_ATOMS_MARTINI2,
+    "martini3": RNA_ATOMS_MARTINI2
 }
 
 # All atoms in RNA
@@ -476,16 +566,16 @@
 }
 
 RNA_FULL_DICT_MARTINI2 = {
-    "A" : ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
-    "C" : ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"],
-    "G" : ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
-    "U" : ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"]
+    "A": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
+    "C": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"],
+    "G": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
+    "U": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"]
 }
 RNA_FULL_DICT_MARTINI3 = RNA_FULL_DICT_MARTINI2
 RNA_FULL_DICT_all = {
-    "aa" : RNA_FULL_DICT,
-    "martini2" : RNA_FULL_DICT_MARTINI2,
-    "martini3" : RNA_FULL_DICT_MARTINI3,
+    "aa": RNA_FULL_DICT,
+    "martini2": RNA_FULL_DICT_MARTINI2,
+    "martini3": RNA_FULL_DICT_MARTINI3,
 }
 
 
@@ -587,7 +677,7 @@ def load_coords(
 
     add_resname : bool
         use the residue name in the identifier
-    
+
     keep_hetatm : bool
         Should HETATM lines be considered ?
 
@@ -604,9 +694,12 @@ def load_coords(
     idx: int = 0
     # Set types of coordinates lines to extract
     if keep_hetatm:
-        coordinates_line_to_extract = ("ATOM", "HETATM", )
+        coordinates_line_to_extract = (
+            "ATOM",
+            "HETATM",
+        )
     else:
-        coordinates_line_to_extract = ("ATOM", )
+        coordinates_line_to_extract = ("ATOM",)
     # Check filetype
     if isinstance(pdb_f, PDBFile):
         pdb_f = pdb_f.rel_path
@@ -704,9 +797,7 @@ def load_coords(
     return coord_dic, chain_ranges
 
 
-def get_atoms(pdb: PDBPath, 
-              full: bool = False,
-              ff: str = "aa") -> AtomsDict:
+def get_atoms(pdb: PDBPath, full: bool = False, ff: str = "aa") -> AtomsDict:
     """Identify what is the molecule type of each PDB.
 
     Parameters
@@ -771,41 +862,10 @@ def get_atoms(pdb: PDBPath,
     return atom_dic
 
 
-ResCode = Literal[
-    "C",
-    "D",
-    "S",
-    "Q",
-    "K",
-    "I",
-    "P",
-    "T",
-    "F",
-    "N",
-    "G",
-    "H",
-    "L",
-    "R",
-    "W",
-    "A",
-    "V",
-    "E",
-    "Y",
-    "M",
-    "A",
-    "G",
-    "C",
-    "T",
-    "X",
-]
-"""
-The single letter code of a residue.
-
-Unrecognized residues' code is `X`.
-"""
-
-
-def pdb2fastadic(pdb_f: PDBPath, keep_hetatm: bool = False) -> dict[str, dict[int, str]]:
+def pdb2fastadic(
+    pdb_f: PDBPath,
+    keep_hetatm: bool = False,
+) -> dict[str, dict[int, str]]:
     """
     Write the sequence as a fasta.
 
@@ -821,68 +881,22 @@ def pdb2fastadic(pdb_f: PDBPath, keep_hetatm: bool = False) -> dict[str, dict[in
     seq_dic : dict
         dict of fasta sequences (one per chain)
     """
-    res_codes = dict(
-        [
-            ("CYS", "C"),
-            ("ASP", "D"),
-            ("SER", "S"),
-            ("GLN", "Q"),
-            ("LYS", "K"),
-            ("ILE", "I"),
-            ("PRO", "P"),
-            ("THR", "T"),
-            ("PHE", "F"),
-            ("ASN", "N"),
-            ("GLY", "G"),
-            ("HIS", "H"),
-            ("LEU", "L"),
-            ("ARG", "R"),
-            ("TRP", "W"),
-            ("ALA", "A"),
-            ("VAL", "V"),
-            ("GLU", "E"),
-            ("TYR", "Y"),
-            ("MET", "M"),
-            ("DA", "A"),
-            ("DG", "G"),
-            ("DC", "C"),
-            (
-                "DT",
-                "T",
-            ),  # 9/8/2023: adding non-standard amino-acids (src/haddock/cns/toppar/protein-allhdg5-4.top) # noqa: E501
-            ("ALY", "K"),
-            ("ASH", "D"),
-            ("CFE", "C"),
-            ("CSP", "C"),
-            ("CYC", "C"),
-            ("CYF", "C"),
-            ("CYM", "C"),
-            ("DDZ", "A"),
-            ("GLH", "E"),
-            ("HLY", "P"),
-            ("HY3", "P"),
-            ("HYP", "P"),
-            ("M3L", "K"),
-            ("MLY", "K"),
-            ("MLZ", "K"),
-            ("MSE", "M"),
-            ("NEP", "H"),
-            ("PNS", "S"),
-            ("PTR", "Y"),
-            ("SEP", "S"),
-            ("TOP", "T"),
-            ("TYP", "Y"),
-            ("TYS", "Y"),
-        ]
-    )
 
     seq_dic: dict[str, dict[int, str]] = {}
 
     if isinstance(pdb_f, PDBFile):
         pdb_f = pdb_f.rel_path
 
-    coord_req = ("ATOM", "HETATM", ) if keep_hetatm else ("ATOM", )
-    with open(pdb_f) as fh:
+    coord_req = (
+        (
+            "ATOM",
+            "HETATM",
+        )
+        if keep_hetatm
+        else ("ATOM",)
+    )
+
+    with open(pdb_f, "r") as fh:
         for line in fh.readlines():
             if line.startswith(coord_req):
                 res_num = int(line[slc_resseq])
@@ -891,7 +905,7 @@ def pdb2fastadic(pdb_f: PDBPath, keep_hetatm: bool = False) -> dict[str, dict[in
                 if res_name in RES_TO_BE_IGNORED:
                     continue
                 try:
-                    one_letter = res_codes[res_name]
+                    one_letter = RES_3L1L[res_name]
                 except KeyError:
                     one_letter = "X"
                 if chain not in seq_dic:
@@ -901,7 +915,9 @@ def pdb2fastadic(pdb_f: PDBPath, keep_hetatm: bool = False) -> dict[str, dict[in
 
 
 def get_align(
-    method: str, lovoalign_exec: FilePath, keep_hetatm: bool = False,
+    method: str,
+    lovoalign_exec: FilePath,
+    keep_hetatm: bool = False,
 ) -> partial[dict[str, dict[int, int]]]:
     """
     Get the alignment function.
@@ -962,12 +978,13 @@ def align_strct(
     """
     if lovoalign_exec is None:
         log.error(
-            "Structural alignment needs LovoAlign " "get it at github.com/m3g/lovoalign"
+            "Structural alignment needs LovoAlign "
+            "get it at github.com/m3g/lovoalign"
         )
         raise ALIGNError("Path to LovoAlign executable required.")
 
     if not lovoalign_exec:
-        raise ALIGNError("lovoalign_exec parameter not defined ")
+        raise ALIGNError("lovoalign_exec parameter not defined.")
 
     if not os.access(lovoalign_exec, os.X_OK):
         raise ALIGNError(f"{lovoalign_exec!r} for LovoAlign is not executable")
@@ -1013,7 +1030,7 @@ def align_strct(
                 alignment_end_index = i - 2
             elif "ERROR" in line:
                 failed_pdb = line.split()[-1]
-                _msg = f"LovoAlign could not read {failed_pdb} " "is it a ligand?"
+                _msg = f"LovoAlign could not read {failed_pdb} is it a ligand?"
                 log.warning(_msg)
                 alignment_pass = False
 
@@ -1023,7 +1040,8 @@ def align_strct(
         if not alignment_pass:
             # This alignment failed, move on to the next
             log.warning(
-                f"Skipping alignment of chain {chain}, " "used sequential matching"
+                f"Skipping alignment of chain {chain}, "
+                "used sequential matching"
             )
             continue
 
@@ -1051,7 +1069,10 @@ def align_strct(
                 ", please check the results carefully"
             )
         else:
-            log.info(f'"Structural" identity of chain {chain} is {identity:.2f}%')
+            log.info(
+                f'"Structural" identity of chain {chain} '
+                f"is {identity:.2f}%"
+            )
 
         # logging.debug("Reading alignment and matching numbering")
         for element in alignment:
@@ -1382,8 +1403,7 @@ def dump_as_izone(fname, numbering_dic, model2ref_chain_dict=None):
                 #
                 izone_str = (
                     "ZONE "
-                    f"{chain}{bound_res}:{unb_chain}{unbound_res}"
-                    f"{os.linesep}"
+                    f"{chain}{bound_res}:{unb_chain}{unbound_res}{os.linesep}"
                 )
                 fh.write(izone_str)
 

From 8e33439c8a9e7021fe9af325f1a2cf2c384794e5 Mon Sep 17 00:00:00 2001
From: VGPReys <v.g.p.reys@uu.nl>
Date: Sun, 9 Aug 2026 13:29:32 +0200
Subject: [PATCH 3/8] lint2

---
 src/haddock/libs/libalign.py | 26 +++++++++++---------------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/src/haddock/libs/libalign.py b/src/haddock/libs/libalign.py
index d9965eb169..e0e8698ad4 100644
--- a/src/haddock/libs/libalign.py
+++ b/src/haddock/libs/libalign.py
@@ -167,7 +167,7 @@
 PROT_ATOMS_all = {
     "aa": PROT_ATOMS,
     "martini2": PROT_ATOMS_MARTINI2,
-    "martini3": PROT_ATOMS_MARTINI2, # The backbone particle is identical between MARTINI 2 and 3
+    "martini3": PROT_ATOMS_MARTINI2,  # The backbone particle is identical between MARTINI 2 and 3
 }
 
 # Side chains
@@ -285,13 +285,13 @@
     "HIP": ["BB", "SC1", "SC2", "SC3"],
     "PHE": ["BB", "SC1", "SC2", "SC3"],
     "TYR": ["BB", "SC1", "SC2", "SC3", "SC4"],
-    "TRP": ["BB", "SC1", "SC2", "SC3", "SC4", 'SC5'],    
+    "TRP": ["BB", "SC1", "SC2", "SC3", "SC4", "SC5"],    
 }
 
 PROT_SIDE_CHAINS_DICT_all = {
     "aa": PROT_SIDE_CHAINS_DICT,
     "martini2": PROT_SIDE_CHAINS_DICT_MARTINI2,
-    "martini3": PROT_SIDE_CHAINS_DICT_MARTINI3
+    "martini3": PROT_SIDE_CHAINS_DICT_MARTINI3,
 }
 
 # For DNA, we use nucleo-bases as default atom selection
@@ -445,7 +445,7 @@
     "DA": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
     "DC": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"],
     "DG": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
-    "DT": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"]
+    "DT": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"],
 }
 DNA_FULL_DICT_MARTINI3 = DNA_FULL_DICT_MARTINI2
 DNA_FULL_DICT_all = {
@@ -459,11 +459,11 @@
 RNA_RES = ["A", "G", "C", "U"]
 RNA_ATOMS = ["P", "O5'", "C5'", "C4'", "C3'", "O3'"]
 RNA_ATOMS_MARTINI2 = ["BB1", "BB2", "BB3"]
-
+RNA_ATOMS_MARTINI3 = RNA_ATOMS_MARTINI2
 RNA_ATOMS_all = {
     "aa": RNA_ATOMS,
     "martini2": RNA_ATOMS_MARTINI2,
-    "martini3": RNA_ATOMS_MARTINI2
+    "martini3": RNA_ATOMS_MARTINI3,
 }
 
 # All atoms in RNA
@@ -569,7 +569,7 @@
     "A": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
     "C": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"],
     "G": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3", "SC4"],
-    "U": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"]
+    "U": ["BB1", "BB2", "BB3", "SC1", "SC2", "SC3"],
 }
 RNA_FULL_DICT_MARTINI3 = RNA_FULL_DICT_MARTINI2
 RNA_FULL_DICT_all = {
@@ -978,8 +978,7 @@ def align_strct(
     """
     if lovoalign_exec is None:
         log.error(
-            "Structural alignment needs LovoAlign "
-            "get it at github.com/m3g/lovoalign"
+            "Structural alignment needs LovoAlign get it at github.com/m3g/lovoalign"
         )
         raise ALIGNError("Path to LovoAlign executable required.")
 
@@ -1040,8 +1039,7 @@ def align_strct(
         if not alignment_pass:
             # This alignment failed, move on to the next
             log.warning(
-                f"Skipping alignment of chain {chain}, "
-                "used sequential matching"
+                f"Skipping alignment of chain {chain}, used sequential matching"
             )
             continue
 
@@ -1070,8 +1068,7 @@ def align_strct(
             )
         else:
             log.info(
-                f'"Structural" identity of chain {chain} '
-                f"is {identity:.2f}%"
+                f'"Structural" identity of chain {chain} is {identity:.2f}%'
             )
 
         # logging.debug("Reading alignment and matching numbering")
@@ -1402,8 +1399,7 @@ def dump_as_izone(fname, numbering_dic, model2ref_chain_dict=None):
                     unb_chain = model2ref_chain_dict[chain]
                 #
                 izone_str = (
-                    "ZONE "
-                    f"{chain}{bound_res}:{unb_chain}{unbound_res}{os.linesep}"
+                    f"ZONE {chain}{bound_res}:{unb_chain}{unbound_res}{os.linesep}"
                 )
                 fh.write(izone_str)
 

From 083e68bab6bbb09c862dafe92c8a7459007c804a Mon Sep 17 00:00:00 2001
From: VGPReys <v.g.p.reys@uu.nl>
Date: Sun, 9 Aug 2026 14:40:07 +0200
Subject: [PATCH 4/8] lint3

---
 src/haddock/libs/libalign.py | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/src/haddock/libs/libalign.py b/src/haddock/libs/libalign.py
index e0e8698ad4..1af553d6d9 100644
--- a/src/haddock/libs/libalign.py
+++ b/src/haddock/libs/libalign.py
@@ -285,7 +285,7 @@
     "HIP": ["BB", "SC1", "SC2", "SC3"],
     "PHE": ["BB", "SC1", "SC2", "SC3"],
     "TYR": ["BB", "SC1", "SC2", "SC3", "SC4"],
-    "TRP": ["BB", "SC1", "SC2", "SC3", "SC4", "SC5"],    
+    "TRP": ["BB", "SC1", "SC2", "SC3", "SC4", "SC5"],
 }
 
 PROT_SIDE_CHAINS_DICT_all = {
@@ -1067,9 +1067,7 @@ def align_strct(
                 ", please check the results carefully"
             )
         else:
-            log.info(
-                f'"Structural" identity of chain {chain} is {identity:.2f}%'
-            )
+            log.info(f'"Structural" identity of chain {chain} is {identity:.2f}%')
 
         # logging.debug("Reading alignment and matching numbering")
         for element in alignment:

From a5a5f1c65db54ef862da3cd8f31d3eadd59487f2 Mon Sep 17 00:00:00 2001
From: VGPReys <v.g.p.reys@uu.nl>
Date: Mon, 10 Aug 2026 09:01:23 +0200
Subject: [PATCH 5/8] changelog

---
 CHANGELOG.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 35133081ae..b2726e15a6 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,6 @@
 # Changelog
 
+- 2026-08-04: Fixed nucleobase selection for DNA default caprieval - Issue #1658
 - 2026-08-04: Added workflow module ordering validation - related to Issue #1530
 - 2026-08-02: Fixed logging/warning leaks - Issue #1647
 - 2026-07-31: Fixed D-amino acid detection - Issue #1636

From fea5b1aa2ab2b93c7f2555730cb174ebe85a2076 Mon Sep 17 00:00:00 2001
From: VGPReys <v.g.p.reys@uu.nl>
Date: Mon, 10 Aug 2026 09:01:53 +0200
Subject: [PATCH 6/8] changelog

---
 CHANGELOG.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index b2726e15a6..50d9c83391 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,6 @@
 # Changelog
 
-- 2026-08-04: Fixed nucleobase selection for DNA default caprieval - Issue #1658
+- 2026-08-10: Fixed nucleobase selection for DNA default caprieval - Issue #1658
 - 2026-08-04: Added workflow module ordering validation - related to Issue #1530
 - 2026-08-02: Fixed logging/warning leaks - Issue #1647
 - 2026-07-31: Fixed D-amino acid detection - Issue #1636

From 774a448380ff1ef954d1939097395bc970e597aa Mon Sep 17 00:00:00 2001
From: VGPReys <v.g.p.reys@uu.nl>
Date: Mon, 10 Aug 2026 14:12:01 +0200
Subject: [PATCH 7/8] fix

---
 src/haddock/libs/libalign.py | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/src/haddock/libs/libalign.py b/src/haddock/libs/libalign.py
index 1af553d6d9..85d2f479bb 100644
--- a/src/haddock/libs/libalign.py
+++ b/src/haddock/libs/libalign.py
@@ -106,10 +106,6 @@
         ("DG", "G"),
         ("DC", "C"),
         ("DT", "T"),
-        ("A", "A"),
-        ("G", "G"),
-        ("C", "C"),
-        ("U", "U"),
         # 9/8/2023: adding non-standard amino-acids (src/haddock/cns/toppar/protein-allhdg5-4.top) # noqa: E501
         ("ALY", "K"),
         ("ASH", "D"),

From 4a946ff7869d953e40eec81817e7b88dd3fa3804 Mon Sep 17 00:00:00 2001
From: VGPReys <v.g.p.reys@uu.nl>
Date: Mon, 10 Aug 2026 14:45:41 +0200
Subject: [PATCH 8/8] fix atom names in DNA and RNA FULL_DICTs

---
 src/haddock/libs/libalign.py | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/src/haddock/libs/libalign.py b/src/haddock/libs/libalign.py
index 85d2f479bb..61ebd7a40a 100644
--- a/src/haddock/libs/libalign.py
+++ b/src/haddock/libs/libalign.py
@@ -321,8 +321,8 @@
 DNA_FULL_DICT = {
     "DA": [
         "P",
-        "O1P",
-        "O2P",
+        "OP1",
+        "OP2",
         "O5'",
         "C5'",
         "C4'",
@@ -350,8 +350,8 @@
     ],
     "DG": [
         "P",
-        "O1P",
-        "O2P",
+        "OP1",
+        "OP2",
         "O5'",
         "C5'",
         "C4'",
@@ -379,8 +379,8 @@
     ],
     "DC": [
         "P",
-        "O1P",
-        "O2P",
+        "OP1",
+        "OP2",
         "O5'",
         "C5'",
         "C4'",
@@ -408,8 +408,8 @@
     ],
     "DT": [
         "P",
-        "O1P",
-        "O2P",
+        "OP1",
+        "OP2",
         "O5'",
         "C5'",
         "C4'",
@@ -526,13 +526,11 @@
         "C2'",
         "O2'",
         "C1'",
-        "N9",
         "C5",
-        "C6",
         "O6",
         "N1",
         "C2",
-        "N2",
+        "O2",
         "N3",
         "C4",
         "N4",