Skip to content

SMILES: <invalid> #7

@entropybit

Description

@entropybit

Hi,

I just tried the model with a heteromacrocycle from a publication: https://www.nature.com/articles/s41598-021-99072-8.
And got a result like this:

{'predicted_smiles': '<invalid>', 'predicted_molfile': '', 'atom_sets': [{'atom_number': '0', 'atom_symbol': 'C', 'coords': (0.286, 0.143)}, {'atom_number': '1', 'atom_symbol': 'C', 'coords': (0.302, 0.222)}, {'atom_number': '2', 'atom_symbol': 'C', 'coords': (0.365, 0.254)}, {'atom_number': '3', 'atom_symbol': 'C', 'coords': (0.444, 0.222)}, {'atom_number': '4', 'atom_symbol': 'C', 'coords': (0.524, 0.254)}, {'atom_number': '5', 'atom_symbol': 'N', 'coords': (0.524, 0.333)}, {'atom_number': '6', 'atom_symbol': 'C', 'coords': (0.619, 0.333)}, {'atom_number': '7', 'atom_symbol': 'C', 'coords': (0.651, 0.413)}, {'atom_number': '8', 'atom_symbol': 'C', 'coords': (0.619, 0.476)}, {'atom_number': '9', 'atom_symbol': 'C', 'coords': (0.651, 0.54)}, {'atom_number': '10', 'atom_symbol': 'C', 'coords': (0.73, 0.556)}, {'atom_number': '11', 'atom_symbol': 'C', 'coords': (0.587, 0.603)}, {'atom_number': '12', 'atom_symbol': 'C', 'coords': (0.603, 0.683)}, {'atom_number': '13', 'atom_symbol': 'C', 'coords': (0.683, 0.698)}, {'atom_number': '14', 'atom_symbol': 'C', 'coords': (0.698, 0.778)}, {'atom_number': '15', 'atom_symbol': '[OCH3]', 'coords': (0.778, 0.81)}, {'atom_number': '16', 'atom_symbol': 'O', 'coords': (0.635, 0.825)}, {'atom_number': '17', 'atom_symbol': 'C', 'coords': (0.524, 0.571)}, {'atom_number': '18', 'atom_symbol': 'N', 'coords': (0.524, 0.492)}, {'atom_number': '19', 'atom_symbol': '[M]', 'coords': (0.444, 0.413)}, {'atom_number': '20', 'atom_symbol': 'N', 'coords': (0.349, 0.492)}, {'atom_number': '21', 'atom_symbol': 'C', 'coords': (0.27, 0.476)}, {'atom_number': '22', 'atom_symbol': 'C', 'coords': (0.238, 0.413)}, {'atom_number': '23', 'atom_symbol': 'C', 'coords': (0.27, 0.333)}, {'atom_number': '24', 'atom_symbol': 'N', 'coords': (0.349, 0.333)}, {'atom_number': '25', 'atom_symbol': 'C', 'coords': (0.238, 0.27)}, {'atom_number': '26', 'atom_symbol': '[R]', 'coords': (0.159, 0.254)}, {'atom_number': '27', 'atom_symbol': 'C', 'coords': (0.238, 0.54)}, {'atom_number': '28', 'atom_symbol': 'C', 'coords': (0.159, 0.556)}, {'atom_number': '29', 'atom_symbol': 'C', 'coords': (0.302, 0.603)}, {'atom_number': '30', 'atom_symbol': 'C', 'coords': (0.286, 0.683)}, {'atom_number': '31', 'atom_symbol': 'C', 'coords': (0.349, 0.73)}, {'atom_number': '32', 'atom_symbol': 'C', 'coords': (0.333, 0.794)}, {'atom_number': '33', 'atom_symbol': '[OCH3]', 'coords': (0.397, 0.841)}, {'atom_number': '34', 'atom_symbol': 'O', 'coords': (0.254, 0.825)}, {'atom_number': '35', 'atom_symbol': 'C', 'coords': (0.365, 0.571)}, {'atom_number': '36', 'atom_symbol': 'C', 'coords': (0.444, 0.603)}, {'atom_number': '37', 'atom_symbol': 'C', 'coords': (0.651, 0.27)}, {'atom_number': '38', 'atom_symbol': 'C', 'coords': (0.73, 0.254)}, {'atom_number': '39', 'atom_symbol': 'C', 'coords': (0.587, 0.222)}, {'atom_number': '40', 'atom_symbol': '[R]', 'coords': (0.603, 0.143)}], 'bond_sets': [{'atom_number': '0', 'bond_type': 'single', 'endpoints': (0, 1)}, {'atom_number': '1', 'bond_type': 'single', 'endpoints': (1, 2)}, {'atom_number': '1', 'bond_type': 'double', 'endpoints': (1, 25)}, {'atom_number': '2', 'bond_type': 'double', 'endpoints': (2, 3)}, {'atom_number': '2', 'bond_type': 'single', 'endpoints': (2, 24)}, {'atom_number': '3', 'bond_type': 'single', 'endpoints': (3, 4)}, {'atom_number': '4', 'bond_type': 'single', 'endpoints': (4, 5)}, {'atom_number': '4', 'bond_type': 'double', 'endpoints': (4, 39)}, {'atom_number': '5', 'bond_type': 'single', 'endpoints': (5, 6)}, {'atom_number': '5', 'bond_type': 'single', 'endpoints': (5, 19)}, {'atom_number': '6', 'bond_type': 'single', 'endpoints': (6, 7)}, {'atom_number': '6', 'bond_type': 'double', 'endpoints': (6, 37)}, {'atom_number': '7', 'bond_type': 'double', 'endpoints': (7, 8)}, {'atom_number': '8', 'bond_type': 'single', 'endpoints': (8, 9)}, {'atom_number': '8', 'bond_type': 'single', 'endpoints': (8, 18)}, {'atom_number': '9', 'bond_type': 'single', 'endpoints': (9, 10)}, {'atom_number': '9', 'bond_type': 'double', 'endpoints': (9, 11)}, {'atom_number': '11', 'bond_type': 'single', 'endpoints': (11, 12)}, {'atom_number': '11', 'bond_type': 'single', 'endpoints': (11, 17)}, {'atom_number': '12', 'bond_type': 'single', 'endpoints': (12, 13)}, {'atom_number': '13', 'bond_type': 'single', 'endpoints': (13, 14)}, {'atom_number': '14', 'bond_type': 'single', 'endpoints': (14, 15)}, {'atom_number': '14', 'bond_type': 'double', 'endpoints': (14, 16)}, {'atom_number': '17', 'bond_type': 'double', 'endpoints': (17, 18)}, {'atom_number': '17', 'bond_type': 'single', 'endpoints': (17, 36)}, {'atom_number': '18', 'bond_type': 'single', 'endpoints': (18, 19)}, {'atom_number': '19', 'bond_type': 'single', 'endpoints': (19, 20)}, {'atom_number': '19', 'bond_type': 'single', 'endpoints': (19, 24)}, {'atom_number': '20', 'bond_type': 'single', 'endpoints': (20, 21)}, {'atom_number': '20', 'bond_type': 'single', 'endpoints': (20, 35)}, {'atom_number': '21', 'bond_type': 'double', 'endpoints': (21, 22)}, {'atom_number': '21', 'bond_type': 'single', 'endpoints': (21, 27)}, {'atom_number': '22', 'bond_type': 'single', 'endpoints': (22, 23)}, {'atom_number': '23', 'bond_type': 'double', 'endpoints': (23, 24)}, {'atom_number': '23', 'bond_type': 'single', 'endpoints': (23, 25)}, {'atom_number': '25', 'bond_type': 'single', 'endpoints': (25, 26)}, {'atom_number': '27', 'bond_type': 'single', 'endpoints': (27, 28)}, {'atom_number': '27', 'bond_type': 'double', 'endpoints': (27, 29)}, {'atom_number': '29', 'bond_type': 'single', 'endpoints': (29, 30)}, {'atom_number': '29', 'bond_type': 'single', 'endpoints': (29, 35)}, {'atom_number': '30', 'bond_type': 'single', 'endpoints': (30, 31)}, {'atom_number': '31', 'bond_type': 'single', 'endpoints': (31, 32)}, {'atom_number': '32', 'bond_type': 'single', 'endpoints': (32, 33)}, {'atom_number': '32', 'bond_type': 'double', 'endpoints': (32, 34)}, {'atom_number': '35', 'bond_type': 'double', 'endpoints': (35, 36)}, {'atom_number': '37', 'bond_type': 'single', 'endpoints': (37, 38)}, {'atom_number': '37', 'bond_type': 'single', 'endpoints': (37, 39)}, {'atom_number': '39', 'bond_type': 'single', 'endpoints': (39, 40)}]}
MolFile:

SMILES:
<invalid>

Are those molecules just too far away from your training set or what is the problem ?
Thanks in Advance - Ben

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions