PharmacoNet

Model pharmacophores—chemical features relevant to binding—from a protein structure and use them to screen a molecular library.

API/CLI tool ID: pharmaconet

Understanding inputs and outputs

A pharmacophore is a spatial arrangement of chemical features that may support binding. proteinPdb is the target protein, refLigandSdf is the reference molecule used to set the search center, and libraryFiles lists candidate molecule files to compare. Execution requires either a reference ligand or explicitly supplied center coordinates; it cannot run if both are absent. The input table below has no center-coordinate fields, so prepare a reference ligand.

score measures how well a candidate matches the pharmacophore model. Higher scores are preferred under the same model and conditions, but they are not experimental measurements of drug activity or binding affinity. Use path to identify the source candidate file. Prepare the molecule files yourself; this input does not retrieve candidates from external databases on your behalf.

Input settings

SettingFormatRequiredDefaultDescription and constraints
proteinPdbpdbRequired—Target protein structure — Extensions pdb · cif
refLigandSdfsdfOptional—Reference ligand for setting the search center. Required when separate center coordinates are not supplied. — Extensions sdf
libraryFilesfileRequired—Ligand files for the virtual screening library — Extensions sdf · mol2, JSON array
cpusnumberOptional1Parallel CPU count for screening — Minimum 1, Maximum 64
useCudabooleanOptionalfalseCUDA acceleration for pharmacophore modeling

Output metrics

ColumnDisplay nameRangeDescription
pathLigand file——
scorePharmacophore score—Sum of matched-feature scores: higher means a better match to the model. Not binding affinity or experimental activity.

See Reading results for metric definitions and interpretation. A range shows possible values; whether higher or lower is better depends on the metric.

Execution availability

Open an execution plan in your project to see available tool versions and costs. Review and approve the inputs, settings, and terms before running.

License

Code, model weights, and accompanying data have their own terms. The table summarizes terms from official sources; check your execution plan for the configuration you will use. License texts are available in Third-party notices.

ComponentLicenseCommercial useSourceNotes
CodeMITAllowed, subject to notice requirementsLicense text—
Model weightsMITAllowed, subject to notice requirementsRepository READMEThese weights are distributed through the official README. They are provided by the MIT-licensed repository, but no separate license statement specific to the weights is given.

Dependency terms apply in addition to those for code and weights. pymol-open-source requires retaining notices and prohibits advertising with the Schrodinger name; molvoxel uses MIT. OpenBabel uses GPL-2.0, so check source-distribution requirements when delivering a container to customers.

Checked on 2026-10-22.

References

On this page