#!/usr/bin/env python3 # (C) 2026 Cadence Design Systems, Inc. (Cadence) # All rights reserved. # TERMS FOR USE OF SAMPLE CODE The software below ("Sample Code") is # provided to current licensees or subscribers of Cadence products or # SaaS offerings (each a "Customer"). # Customer is hereby permitted to use, copy, and modify the Sample Code, # subject to these terms. Cadence claims no rights to Customer's # modifications. Modification of Sample Code is at Customer's sole and # exclusive risk. Sample Code may require Customer to have a then # current license or subscription to the applicable Cadence offering. # THE SAMPLE CODE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, # EXPRESS OR IMPLIED. OPENEYE DISCLAIMS ALL WARRANTIES, INCLUDING, BUT # NOT LIMITED TO, WARRANTIES OF MERCHANTABILITY, FITNESS FOR A # PARTICULAR PURPOSE AND NONINFRINGEMENT. In no event shall Cadence be # liable for any damages or liability in connection with the Sample Code # or its use. """Similarity search in monomer set.""" import argparse import json import os import pathlib import sys import rich.console import rich.table from openeye import oechem, oegraphsim from rich_argparse import HelpPreviewAction, RichHelpFormatter __SCRIPT_NAME__ = pathlib.Path(__file__).absolute().stem __SCRIPT_DESC__ = "Similarity search in monomer set." __SCRIPT_TOOLKITS__ = ["oechem", "oegraphsim"] __SCRIPT_KEYWORDS__ = [ "monomer", "peptide", "peptide-informatics", "similarity", "search", ] __SCRIPT_CATEGORIES__ = ["peptide-informatics"] MONOMER_SET_STANDARD = "Standard" MONOMER_SET_OPENEYE = "OpenEye" def parse_options() -> argparse.Namespace: """Parse command-line options for monomer similarity search.""" parser = argparse.ArgumentParser( add_help=True, formatter_class=RichHelpFormatter, description="[yellow]" + __SCRIPT_DESC__ + "[/yellow]", ) search_group = parser.add_argument_group("Query options") exclusive_search_group = search_group.add_mutually_exclusive_group(required=True) exclusive_search_group.add_argument( "--smiles", type=str, metavar="SMILES", help="smiles of the query structure", ) exclusive_search_group.add_argument( "--code", type=str, help="monomer code in any code-set in loaded monomers", ) monomers_group = parser.add_argument_group("Monomer set options") _add_monomer_collection(monomers_group) sim_group = parser.add_argument_group("Similarity options") sim_group.add_argument( "--cutoff", type=float, metavar="[0.0, 1.0]", default=0.3, help="similarity score cutoff value in range (default: %(default)s)", ) sim_group.add_argument( "--limit", type=int, metavar="INT", default=20, help="maximum number of similar monomers (default: %(default)s)", ) parser.add_argument("--help-image", action=HelpPreviewAction) parser.add_argument( "--save-console-svg", default=False, action="store_true", help=f"run command and capture console output in {__SCRIPT_NAME__}.svg file", ) return parser.parse_args() def main() -> int: """Run monomer similarity search and print results.""" args = parse_options() console = rich.console.Console(record=args.save_console_svg, highlight=False) monomers = _get_monomer_collection(args) query_mol = _get_query_mol(args, monomers, console) if query_mol is None: # warning was already printed return os.EX_DATAERR console.print(f"[green]Query {oechem.OEMolToSmiles(query_mol)}[/green]") # generating fingerprints fp_type = oegraphsim.OEGetFPType(oegraphsim.OEFPType_Path) console.print(f"[green]Using fingerprint {fp_type.GetFPTypeString()}[/green]") query_fp = oegraphsim.OEFingerPrint() oegraphsim.OEMakeFP(query_fp, query_mol, fp_type) scores: list[tuple[float, oechem.OEMonomer]] = [] for monomer in monomers.GetMonomers(): score = _get_sim_score(monomer, query_fp) scores.append((score, monomer)) oegraphsim.OEMakeFP(query_fp, query_mol, fp_type) limit = min(max(1, args.limit), len(scores)) scores.sort(key=lambda s: s[0], reverse=True) scores = scores[:limit] cutoff = min(max(0.01, args.cutoff), 1.0) primary_code_set = monomers.GetPrimaryCodeSet() code_sets: list[str] = [ primary_code_set, *[c for c in monomers.GetCodeSets() if c != primary_code_set], ] columns = ["idx", "tanimoto", *code_sets, "monomer smiles"] table = rich.table.Table(*columns) color_gradient = oechem.OELinearColorGradient() color_gradient.AddStop(oechem.OEColorStop(0.0, oechem.OERedOrange)) color_gradient.AddStop(oechem.OEColorStop(1.0, oechem.OESeaGreen)) for index, (score, monomer) in enumerate(scores, start=1): if score < cutoff: break score_color = color_gradient.GetColorAt(score) row_data: list[str | rich.text.Text] = [ rich.text.Text(f"{index}", justify="right"), rich.text.Text( f"{score:.4f}", style=score_color.GetText(), justify="right" ), *[ rich.text.Text(monomer.GetCode(s)) if monomer.HasCode(s) else "" for s in code_sets ], monomer.GetCanonicalSmiles(), ] table.add_row(*row_data) console.print(table, markup=False) if args.save_console_svg: console.save_svg(f"{__SCRIPT_NAME__}.svg", title="output") return os.EX_OK def _get_sim_score( monomer: oechem.OEMonomer, query_fp: oegraphsim.OEFingerPrint ) -> float: """Compute Tanimoto similarity between a monomer and a query fingerprint.""" mol = oechem.OEGraphMol() oechem.OESmilesToMol(mol, monomer.GetCanonicalSmiles()) fp = oegraphsim.OEFingerPrint() oegraphsim.OEMakeFP(fp, mol, query_fp.GetFPTypeBase()) return oegraphsim.OETanimoto(query_fp, fp) class MonomerSetParameter: # noqa: PLW1641 """Utility class to handle both built-in and user defined monomer sets.""" def __init__(self) -> None: # noqa: D107 self._monomer_sets = [ MONOMER_SET_STANDARD, MONOMER_SET_OPENEYE, "JSON-FILENAME", ] def __repr__(self) -> str: # noqa: D105 return ",".join(self._monomer_sets) def __eq__(self, param: object) -> bool: # noqa: D105 if not isinstance(param, str): return False if param in [MONOMER_SET_STANDARD, MONOMER_SET_OPENEYE]: return True console = rich.console.Console() monomer_set_filepath = pathlib.Path(param) if ( not monomer_set_filepath.exists() or monomer_set_filepath.suffix.lower() != ".json" ): console.print(f"[red]Invalid monomer set file '{param}' ![/red]") return False is_valid = True try: with monomer_set_filepath.open("r") as json_file: json.load(json_file) except json.JSONDecodeError as e: console.print(f"[red]Invalid monomer set file '{param}' ![/red]") console.print(f"[red]Error decoding JSON: {e} ![/red]") is_valid = False return is_valid def _add_monomer_collection(arg_group: argparse._ArgumentGroup) -> None: arg_group.add_argument( "-m", "--monomers", type=str, default=MONOMER_SET_STANDARD, choices=[MonomerSetParameter()], help="built-in monomer-set type or json file of monomers", ) def _get_monomer_collection(args: argparse.Namespace) -> oechem.OEMonomerSet: monomers = oechem.OEMonomerSet() match args.monomers: case "Standard": oechem.OELoadStandardMonomerSet(monomers) case "OpenEye": oechem.OELoadOpenEyeMonomerSet(monomers) case _: oechem.OEReadMonomerSet(monomers, args.monomers) return monomers def _get_query_mol( args: argparse.Namespace, monomers: oechem.OEMonomerSet, console: rich.console.Console, ) -> None | oechem.OEMolBase: query_mol = oechem.OEGraphMol() # --smiles if args.smiles: opts = oechem.OEParseSmilesOptions() opts.SetQuiet(True) if ( not oechem.OEParseSmiles(query_mol, args.smiles, opts) or query_mol.NumAtoms() == 0 ): console.print(f"[red]Error: invalid SMILES '{args.smiles}'![/red]") return None return query_mol # --code for code_set in monomers.GetCodeSets(): if (monomer := monomers.GetMonomer(code_set, args.code)) is not None: oechem.OESmilesToMol(query_mol, monomer.GetCanonicalSmiles()) return query_mol console.print(f"[red]Error: no monomer with code '{args.code}' identified![/red]") return None setattr(main, "__SCRIPT_NAME__", __SCRIPT_NAME__) setattr(main, "__SCRIPT_DESC__", __SCRIPT_DESC__) setattr(main, "__SCRIPT_TOOLKITS__", __SCRIPT_TOOLKITS__) setattr(main, "__SCRIPT_KEYWORDS__", __SCRIPT_KEYWORDS__) setattr(main, "__SCRIPT_CATEGORIES__", __SCRIPT_CATEGORIES__) if __name__ == "__main__": sys.exit(main())