dorsal/arxiv
View SchemaThe pharmacophore kernel for virtual screening with support vector machines
| Authors | Pierre Mahé, Liva Ralaivola, Véronique Stoven, Jean-Philippe Vert |
|---|---|
| Categories | |
| ArXiv ID | q-bio/0603006 |
| URL | https://arxiv.org/abs/q-bio/0603006 |
Abstract
We introduce a family of positive definite kernels specifically optimized for the manipulation of 3D structures of molecules with kernel methods. The kernels are based on the comparison of the three-points pharmacophores present in the 3D structures of molecul es, a set of molecular features known to be particularly relevant for virtual screening applications. We present a computationally demanding exact implementation of these kernels, as well as fast approximations related to the classical fingerprint-based approa ches. Experimental results suggest that this new approach outperforms state-of-the-art algorithms based on the 2D structure of mol ecules for the detection of inhibitors of several drug targets.
{
"annotation_id": "085bfbf7-af35-4853-9348-4e856fb9ac1d",
"date_created": "2026-03-02T18:01:35.481000Z",
"date_modified": "2026-03-02T18:01:35.481000Z",
"file_hash": "b219b26a40680231351500b8b45fbc03f0a7fab9aa466646ca5412abbc3a2b60",
"private": false,
"record": {
"abstract": "We introduce a family of positive definite kernels specifically optimized for\nthe manipulation of 3D structures of molecules with kernel methods. The kernels\nare based on the comparison of the three-points pharmacophores present in the\n3D structures of molecul es, a set of molecular features known to be\nparticularly relevant for virtual screening applications. We present a\ncomputationally demanding exact implementation of these kernels, as well as\nfast approximations related to the classical fingerprint-based approa ches.\nExperimental results suggest that this new approach outperforms\nstate-of-the-art algorithms based on the 2D structure of mol ecules for the\ndetection of inhibitors of several drug targets.",
"arxiv_id": "q-bio/0603006",
"authors": [
"Pierre Mah\u00e9",
"Liva Ralaivola",
"V\u00e9ronique Stoven",
"Jean-Philippe Vert"
],
"categories": [
"q-bio.QM"
],
"title": "The pharmacophore kernel for virtual screening with support vector machines",
"url": "https://arxiv.org/abs/q-bio/0603006"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "4fb5b5a5-d879-4a36-9617-bc786f7a172e",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}