Molecule Similarity Calculation

../../../../../_images/CalculationInitCubeIcon.svg

This cube calculates fingerprint similarity scores between input molecules and a query (reference) molecule.

The input molecules are read from the intake port, from the field specified by the Input Molecule Field parameter.

The query molecule is read from the first record on the init initialization port, from the field specified by the Query Field parameter.

The type of the generated fingerprint is determined by the Fingerprint Type parameter. The similarity measure that is used to calculate the score is determined by the Similarity Measure parameter.

The calculated score is stored in the field specified by Similarity Score Field, and the record is sent to the success port.

Note

This cube generates fingerprints on-the-fly in order to calculate the similarity score, but only the score will be stored on the output record.

See also

Main Parameters

Parameter Name Associated Port Port Type
Similarity Score Field    

Related Cubes

Calculation Parameters

  • CPUs (integer) : The number of CPUs to run this cube with
    Default: 1 Min: 1 Max: 128
  • Cube Metrics (string) : Set of metrics to be collected

    Choices: cpu, disk, memory, network
  • Temporary Disk Space (MiB) (decimal) : The minimum amount of disk space in MiB (1048576 B) this cube requires. Due to overhead, request a couple hundred MiB more than required.
    Default: 5120.0 Min: 128.0 Max: 8589934592
  • Fingerprint Type (string) : The fingerprint type generated for similarity calculation.
    Default: Tree
    Choices: Circular, Lingo, MACCS, Path, Tree
  • GPUs (integer) : The number of GPUs to run this cube with
    Default: 0 Max: 16
  • Instance Tags (string) : Only run on machines with matching tags (comma separated)
    Default: “”
  • Instance Type (string) : The type of instance that this cube needs to be run on
  • Max Rotors (integer) : Cutoff of rotatable bonds. The cube will skip molecules with rotors more than the cutoff.
    Default: 20 Min: 1 Max: 9999
  • Memory (MiB) (decimal) : The minimum amount of memory in MiBs (1048576 B) this cube requires. Due to overhead, request a couple hundred MiB more than required.
    Default: 1800 Min: 256.0 Max: 8589934592
  • Metric Period (decimal) : How often to sample metrics, in seconds
    Default: 60 Min: 1 Max: 300
  • Similarity Measure (string) : The similarity measure used to 2D similarity calculation.
    Default: Tanimoto
    Choices: Cosine, Dice, Euclid, Manhattan, Tanimoto, Tversky
  • Spot policy (string) : Control cube placement on spot market instances
    Default: Prohibited
    Choices: Allowed, Preferred, NotPreferred, Prohibited, Required

Field parameters

  • None (Field Type: StringVec) : Message extended log field
    Default: Extended Log Field
  • None (Field Type: Chem.Mol) :
  • Query Field (Field Type: Chem.Mol) : The name of the field on the initialization record that stores the query molecule. If left blank, the primary molecule field will be used.
  • None (Field Type: String) : Message log field
    Default: Log Field
  • Similarity Score Field (Field Type: Float) : Name for the field that stores fingerprint similarity scores.

2D Similarity Parameters

The parameters of the 2D fingerprint similarity calculation.

  • Fingerprint Type (string) : The fingerprint type generated for similarity calculation.
    Default: Tree
    Choices: Circular, Lingo, MACCS, Path, Tree
  • Similarity Measure (string) : The similarity measure used to 2D similarity calculation.
    Default: Tanimoto
    Choices: Cosine, Dice, Euclid, Manhattan, Tanimoto, Tversky

Hardware Parameters

Machine hardware requirements

  • Memory (MiB) (decimal) : The minimum amount of memory in MiBs (1048576 B) this cube requires. Due to overhead, request a couple hundred MiB more than required.
    Default: 1800 Min: 256.0 Max: 8589934592
  • Temporary Disk Space (MiB) (decimal) : The minimum amount of disk space in MiB (1048576 B) this cube requires. Due to overhead, request a couple hundred MiB more than required.
    Default: 5120.0 Min: 128.0 Max: 8589934592
  • GPUs (integer) : The number of GPUs to run this cube with
    Default: 0 Max: 16
  • CPUs (integer) : The number of CPUs to run this cube with
    Default: 1 Min: 1 Max: 128
  • Instance Type (string) : The type of instance that this cube needs to be run on
  • Spot policy (string) : Control cube placement on spot market instances
    Default: Prohibited
    Choices: Allowed, Preferred, NotPreferred, Prohibited, Required
  • Instance Tags (string) : Only run on machines with matching tags (comma separated)
    Default: “”

Metrics Parameters

Cube Metric Parameters

  • Metric Period (decimal) : How often to sample metrics, in seconds
    Default: 60 Min: 1 Max: 300
  • Cube Metrics (string) : Set of metrics to be collected

    Choices: cpu, disk, memory, network

Parallel Molecule Similarity Calculation

The parallel version adds these extra parameters.

  • Number of messages to distribute at a time (integer) : The maximum number of messages to bundle together for a parallel cube.
    Default: 1 Min: 1 Max: 65535
  • Maximum Failures (integer) : The maximum number of times to attempt processing a work item
    Default: 10 Min: 1 Max: 100
  • Autoscale this Cube (boolean) : If True, let Orion manage the parallelism of this Cube
    Default: True
  • Maximum number of Cubes (integer) : The maximum number of concurrently running copies of this Cube
    Default: 1000 Min: 1
  • Minimum number of Cubes (integer) : The minimum number of concurrently running copies of this Cube
    Default: 0

Tip

filename: snowball/graphsim/sim2d_mol.py