Generative Structure Floe

Category Paths

Follow one of these paths in the Orion user interface, to find the floe.

  • Solution-based/Hit to Lead/Generative Design/Match Molecular Pairs (MMP)

  • Solution-based/Hit to Lead/Generative Design/Fragment-based

  • Task-based/Virtual Screening - Structure-Based

Description

This floe provides methods to perform Generative Design alterations on the input lead molecule.

There are currently four methods: a custom method called Graft, a Matched Molecular Pairs (MMP) method, the Sprout method, and a Trim method.

For each lead molecule, there can be a 50–500 fold increase in the number of output structures for each molecule; therefore it is recommended to use relatively small input datasets. The default input limit is one structure, and care should be used when choosing any large limits. This default limit can be altered in the GD Advanced Parameters group of the floe run parameters.

Input/Output molecules: Lead molecules will be transformed to analogs and saved to the output dataset on the output molecule field. For comparisons, a new field is added to the output records that contains the original molecule, stored as a SMILES. The lead molecule is removed from the output records unless the input field name is different than the output molecule field.

Methods: You can select one or more of Graft, MMP, Sprout, or Trim for examining the generative output, but at least one method must be selected. Methods that require an external index provide a default version for use. There are additional floes in this package that allow users to generate their custom Graft or MMP or indexes based on their own structures. Each method has tunable properties available on their respective cubes for additional control of the method’s activities: Graft – Graft Database and Graft Analogs; MMP – Filter Transforms and MMP Analogs; Sprout – Sprout Analogs; and Trim – Trim Analogs.

Graft: A fragment replacement algorithm that replaces single fragments sequentially from the lead molecule, preserving 80% of the original structure. A default fragment index is provided, or a user-generated index can be selected. The default index is based on tcams (malaria dataset), but other indexes may be available in the OpenEye Org stack data, or custom indexes can be generated from the Advanced Floes offerings.

MMP: A method that applies Matched Molecular Pair transformations from an internal default index or a user-generated index. The default index is a set of matched pairs derived from ChEMBL, but other indexes may be available in the OpenEye Org stack data, or custom indexes can be generated from the advanced floes offerings.

Sprout: A simplistic atom sprouting method that can sprout atoms at site(s) specified by the user.

Trim: A simple side-chain trimming editor that trims atoms from terminal sites on the input structure(s). After each atom is removed, the new terminal atom alpha to the deletion site is validated against the user-selected atom type, and deletion continues until the specified shell-depth is reached, or until no new terminal atoms are found or are valid.

Properties: Simple properties can be computed on the generated analogs; any, or none, of the properties can be selected for output.

Filtering: Molecule filtering of various types can either be applied to the generated analogs or disabled entirely.

Promoted Parameters

Title in user interface (promoted name)

GD Promoted Parameters

Input Mol Field (gd_in_molfield): Name of the field containing the molecule(s) to be transformed

  • Type: field_parameter::mol

Output Mol Field (gd_out_molfield): Name of the field to contain the transformed molecule(s)

  • Type: field_parameter::mol

Select Generative Method (gd_method): The generative method(s) to be used

  • Required

  • Type: string

  • Default: [‘Graft’, ‘Matched Molecular Pairs’, ‘Sprout’, ‘Trim’]

  • Choices: [‘Graft’, ‘Matched Molecular Pairs’, ‘Sprout’, ‘Trim’]

Compute Molecule Properties (gd_mol_props): Which molecule properties to calculate

  • Type: string

  • Default: [‘HeavyAtoms’, ‘MedChemInterest’, ‘MolComplexity’, ‘MolWeight’, ‘TPSA’, ‘XLogP’]

  • Choices: [‘HeavyAtoms’, ‘MedChemInterest’, ‘MolComplexity’, ‘MolWeight’, ‘TPSA’, ‘XLogP’]

Filter Output (gd_filtering): Enable molecule filtering of the generated analogs (see type specified by [Mol Filter])

  • Required

  • Type: boolean

  • Default: True

  • Choices: [True, False]

Mol Filter (gd_filter_type): Default type of molecule filter to apply to the generated analogs

  • Type: string

  • Default: BlockBuster

  • Choices: [‘Lead’, ‘Drug’, ‘BlockBuster’, ‘BlockBuster+PAINS’, ‘PAINS’, ‘Custom’]

GD Advanced Parameters

Lead Molecule Minimum Records (gd_rec_min): The minimum number of lead molecule records allowed (default:1) Input lead molecule datasets that do not meet this threshold will terminate the floe

  • Type: integer

  • Default: 1

Lead Molecule Maximum Records (gd_rec_max): The maximum number of lead molecule records allowed (default:1) Input lead molecule datasets that exceed this threshold will terminate the floe

  • Type: integer

  • Default: 1

Similarity FP Type (gd_sim_fptype): Select one fingerprint type to use for generating analog similarity values or None to disable. Only the first specified fingerprint type will be used

  • Type: string

  • Default: [‘None’]

  • Choices: [‘None’, ‘Circular’, ‘CircularVS’]

Analog Similarity (gd_sim_range): Targeted similarity range for generated analogs, or use min/max for a custom range

  • Type: string

  • Default: Unspecified

  • Choices: [‘Unspecified’, ‘dissimilar (0-0.3)’, ‘somewhat similar (0.3-0.6)’, ‘moderately similar (0.6-0.8)’, ‘highly similar (0.8-1.0)’]

Minimum FP Similarity (gd_sim_min): Minimum Tanimoto similarity value threshold for analogs

  • Type: decimal

  • Default: 0.1

Maximum FP Similarity (gd_sim_max): Maximum Tanimoto similarity value threshold for analogs

  • Type: decimal

  • Default: 1.0

Annotate Method (gd_dedupe_annotate): Annotate output records with the method that generated each unique structure (On), or use a faster method that just deduplicates (Off)

  • Required

  • Type: boolean

  • Default: True

  • Choices: [True, False]

Deduplication Memory Limit (gd_dedupe_memory): Structure deduplication may require significant memory resources, specify the desired memory limit in Mb

  • Type: decimal

  • Default: 1800

Retain Input Dataset Fields (gd_keepfields): If ON copies the input datarecord, if OFF, discards all but the structure (which will change) and sends it downstream for processing

  • Type: boolean

  • Default: True

  • Choices: [True, False]

Output Linked Field Format (gd_linkfields): If ON, a link to the original input record is output rather than a copy of the input fields - preferable for very large input records

  • Type: boolean

  • Default: False

  • Choices: [True, False]

Atom Limit (gd_atom_limit): Only generate analogs for input molecules that have <= this limit on the number of heavy atoms

  • Type: integer

  • Default: 500

Check Valences (gd_check_val): How to handle valence issues in generated analog structures

  • Required

  • Type: string

  • Default: reject

  • Choices: [‘reject’, ‘allow’, ‘fix’]

Eliminate halide (change) products (gd_no_halides): Do not output products related to halide changes

  • Type: boolean

  • Default: False

  • Choices: [True, False]

Verbosity (gd_verbosity): Sets the output logging verbosity

  • Type: string

  • Default: warning

  • Choices: [‘info’, ‘warning’, ‘error’, ‘debug’, ‘ddebug’]

GD Matched Molecular Pair Method

Transform Collection (mmp_xformcoll): The name of the collection containing the MMP transformations, or None to use the default: chembl_25_dbprep_SD_70_100_xforms

  • Type: collection_source

Transformation Context (mmp_bondcontext): Amount of neighboring chemistry context from the substitution site to include with the transformation: bond0 - less precise, bond3 - more precise

  • Type: string

  • Default: [‘bond1’]

  • Choices: [‘any’, ‘bond0’, ‘bond1’, ‘bond2’, ‘bond3’]

Min MMPs (mmp_minmmps): Require >= this limit for the MMPs associated with the transformation (0: no limit)

  • Type: integer

Max MMPs (mmp_maxmmps): Require <= this limit for the MMPs associated with the transformation (0: no limit)

  • Type: integer

Maximum Matches (mmp_maxmatches): Limit the number of times the transformation(s) will be applied to the input molecule(s)

  • Type: integer

  • Default: 10

Limit Matches (mmp_limitmatches): Require this limit on the number of transformation(s) sites on the input molecule(s) for the transformation to be applied (0:unconstrained)

  • Type: integer

  • Default: 0

Validate Kekule (mmp_validatekekule): Whether to verify Kekulization during application of the transformation(s)

  • Type: boolean

  • Default: True

  • Choices: [True, False]

Strict Valences (mmp_strictvalences): If Check Valences is active, any valence issues found after the transformation is applied terminates further application

  • Type: boolean

  • Default: True

  • Choices: [True, False]

Strict SMIRKS (mmp_strictsmirks): Whether to require strict SMIRKS parsing of the transformation(s)

  • Type: boolean

  • Default: True

  • Choices: [True, False]

GD Sprout Method

Atom sites allowed (spr_allowedsites): Choose the allowed sites for substitution

  • Required

  • Type: string

  • Default: [‘neutral_C’]

  • Choices: [‘neutral_C’, ‘terminal_C’, ‘aromatic_C’, ‘any_C’, ‘any_heavy’]

Atom type(s) to sprout (spr_sprouttypes): Sprout Atoms

  • Required

  • Type: string

  • Default: [‘Carbon’, ‘Fluorine’, ‘Oxygen’]

  • Choices: [‘Carbon’, ‘Nitrogen’, ‘Fluorine’, ‘Oxygen’, ‘HaloSubset:[F,Cl,Br]’]

Min Site Hydrogens (spr_minhyds): Require subsitution sites to have >= this number of hydrogens (default:1, unconstrained:0)

  • Type: integer

  • Default: 1

Max Site Hydrogens (spr_maxhyds): Require subsitution sites to have <= this number of hydrogens (0: no limit)

  • Type: integer

  • Default: 0

Strict Stereo (spr_strictstereo): Whether restrict sprout atom sites to non-stereo atoms only (default: On)

  • Type: boolean

  • Default: True

  • Choices: [True, False]

Prohibit Hetero-Hetero Sprout (spr_heterohetero): Disallow sprouting of heteroatoms at heteroatom sites (default: On)

  • Type: boolean

  • Default: True

  • Choices: [True, False]

GD Trim Method

Atom sites allowed (trm_allowedtrimsites): Choose the allowed site(s) for initiating the trimming activity

  • Required

  • Type: string

  • Default: [‘terminal_C’]

  • Choices: [‘terminal_C’, ‘terminal_N’, ‘terminal_O’, ‘terminal_any’, ‘halogen’]

Trimming Distance (trm_depth): Defines the maximum bond distance for the trimming activity (0:allowed site atoms only)

  • Required

  • Type: integer

  • Default: 99

GD Graft Method

Graft Database (gd_graftdb): The name of the Graft database to use, or None to use the default database

  • Type: file_in

Hmember selection (gft_Hmembers): For input molecule selections, also process the H-member equivalent input structure

  • Type: boolean

  • Default: False

  • Choices: [True, False]

Unique Analogs (gft_unique): Whether to deduplicate generated analogs

  • Type: boolean

  • Default: True

  • Choices: [True, False]

Retain Percentage (keeppcnt): Percentage of top graft analogs to retain

  • Type: integer

  • Default: 50

Inputs

Input or Append Lead Molecule Dataset (input): The input lead molecule dataset(s) to read records from and/or to append to when the appending option is enabled. If OFF, the dataset specified as the Output Dataset (see Output parameters) is created.

  • Required

  • Type: data_source

Append Records (append_records): Appends the records to the specified input dataset (On) or creates the named Output Dataset (Off).

  • Required

  • Type: boolean

  • Default: False

  • Choices: [True, False]

Outputs

Output Dataset (output): Output dataset for Generative Design analogs.

  • Required

  • Type: dataset_out

  • Default: GenDesign_analogs