PharmCast: rapid generation of three-dimensional pharmacophore fingerprints from two-dimensional structure without conformer generation
- 1Eidogen-Sertanty, Inc.
Abstract
A three-dimensional pharmacophore fingerprint records the binding features a molecule can present. It is a description of a hand in search of a glove. Because it is defined by presented features instead of two-dimensional structure, it can identify pharmacophoric similarity between structurally distinct compounds, which is what scaffold hopping and non-obvious me-too design require. The descriptor has remained a niche tool because its cost is dominated by conformer generation. In the reference pipeline, generating 100 conformers requires 2.82 s of the 2.86 s needed to fingerprint one screening collection compound; the bit calculation requires 0.039 s. We therefore removed the conformational stage. PharmCast is a feedforward neural network that predicts all 10,549 bits of a PharmPrint ensemble fingerprint directly from a SMILES string. On the same machine, PharmCast generated pharmacophore fingerprints for two molecules and compared them in 0.584 ms, whereas the conventional conformer-based pipeline took 5.71 s. PharmCast version 10 was trained on 5,887,229 molecules drawn from a screening collection, activity-backed ChEMBL compounds from 142 to 1000 Da, and peptide loops excised from crystal structures. We evaluated 155,648 purchasable catalog compounds excluded from every training set, 139,700 activity-backed ChEMBL compounds not present in the version 10 training set, and 13,500 peptide loops reserved for testing. Median fingerprint error, Pearson r, and pairwise ranking accuracy were 0.008, 0.980, and 0.936 for screening collection chemistry; 0.016, 0.984, and 0.952 for loop peptides; and 0.027, 0.936, and 0.889 for activity-backed ChEMBL compounds. The reference calculation reproduces itself at an error of 0.006 and r of 0.995. Ensemble pharmacophore fingerprints can therefore be predicted from two-dimensional structure alone at a cost suitable for large-scale collection screening and virtual library exploration. Keywords: pharmacophore, fingerprint, scaffold hopping, surrogate model, virtual screening, applicability domain
Related
- Photocontrolled hERG channel blockade by diazirine integrated into BeKm-1 pharmacophore
- PP-MAPS: Dynamic Pharmacophore Signatures of Protein–Peptide Interfaces from Molecular Dynamics Trajectories
- DCFold: Efficient Protein Structure Generation with Single Forward Pass
- Pocket contrastive learning and conformation fusion for robust structure-conditioned 3D molecular generation under receptor conformational variation.
- Characterizing LLM scientific concept generation: A multi-dimensional measurement study
BibTeX
@misc{muskal2026pharmcast,
title = {{PharmCast: rapid generation of three-dimensional pharmacophore fingerprints from two-dimensional structure without conformer generation}},
author = {S. M. Muskal and M. J. McGregor},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.02.748999},
url = {https://www.biorxiv.org/content/10.64898/2026.09.02.748999v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - PharmCast: rapid generation of three-dimensional pharmacophore fingerprints from two-dimensional structure without conformer generation
AU - S. M. Muskal
AU - M. J. McGregor
PY - 2026
DA - 2026/09/02
PB - bioRxiv
DO - 10.64898/2026.09.02.748999
UR - https://www.biorxiv.org/content/10.64898/2026.09.02.748999v1
AB - A three-dimensional pharmacophore fingerprint records the binding features a molecule can present. It is a description of a hand in search of a glove. Because it is defined by presented features instead of two-dimensional structure, it can identify pharmacophoric similarity between structurally distinct compounds, which is what scaffold hopping and non-obvious me-too design require. The descriptor has remained a niche tool because its cost is dominated by conformer generation. In the reference pipeline, generating 100 conformers requires 2.82 s of the 2.86 s needed to fingerprint one screening collection compound; the bit calculation requires 0.039 s. We therefore removed the conformational stage. PharmCast is a feedforward neural network that predicts all 10,549 bits of a PharmPrint ensemble fingerprint directly from a SMILES string. On the same machine, PharmCast generated pharmacophore fingerprints for two molecules and compared them in 0.584 ms, whereas the conventional conformer-based pipeline took 5.71 s. PharmCast version 10 was trained on 5,887,229 molecules drawn from a screening collection, activity-backed ChEMBL compounds from 142 to 1000 Da, and peptide loops excised from crystal structures. We evaluated 155,648 purchasable catalog compounds excluded from every training set, 139,700 activity-backed ChEMBL compounds not present in the version 10 training set, and 13,500 peptide loops reserved for testing. Median fingerprint error, Pearson r, and pairwise ranking accuracy were 0.008, 0.980, and 0.936 for screening collection chemistry; 0.016, 0.984, and 0.952 for loop peptides; and 0.027, 0.936, and 0.889 for activity-backed ChEMBL compounds. The reference calculation reproduces itself at an error of 0.006 and r of 0.995. Ensemble pharmacophore fingerprints can therefore be predicted from two-dimensional structure alone at a cost suitable for large-scale collection screening and virtual library exploration. Keywords: pharmacophore, fingerprint, scaffold hopping, surrogate model, virtual screening, applicability domain
ER -