Guardado en:
Detalles Bibliográficos
Autores principales: Kim, Taehan, Leung, Sarrah Rose Mikhail, Mekala, Bharat, Park, Jeongbin
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2606.01816
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911739515240448
author Kim, Taehan
Leung, Sarrah Rose Mikhail
Mekala, Bharat
Park, Jeongbin
author_facet Kim, Taehan
Leung, Sarrah Rose Mikhail
Mekala, Bharat
Park, Jeongbin
contents Selecting where to intervene on a protein (i.e., choosing a targetable site) is often a more ambiguous and failure-prone bottleneck than selecting what binds, especially for membrane proteins where accessibility, topology, and post-translational modifications (PTMs) constrain actionable regions. We present Site4Drug, a modality-aware site-finding agent that outputs a ranked list of targetable regions with explicit constraints, evidence summaries, risk flags, and a traceable decision log. Rather than requiring users to specify the drug modality upfront, Site4Drug can recommend a binding modality (e.g., antibody/peptide-like vs small-molecule) from the same evidence used for site discovery, including topology, hydropathy, PTM propensity, disulfides, domain context, and sequence. Importantly, this evidence is applied consistently across modalities, including small-molecule pocket discovery, to avoid selecting chemically plausible but biologically occluded sites.
format Preprint
id arxiv_https___arxiv_org_abs_2606_01816
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Site4Drug: Predicting Drug-Binding Target Sites with an AI Agent
Kim, Taehan
Leung, Sarrah Rose Mikhail
Mekala, Bharat
Park, Jeongbin
Biomolecules
Machine Learning
Selecting where to intervene on a protein (i.e., choosing a targetable site) is often a more ambiguous and failure-prone bottleneck than selecting what binds, especially for membrane proteins where accessibility, topology, and post-translational modifications (PTMs) constrain actionable regions. We present Site4Drug, a modality-aware site-finding agent that outputs a ranked list of targetable regions with explicit constraints, evidence summaries, risk flags, and a traceable decision log. Rather than requiring users to specify the drug modality upfront, Site4Drug can recommend a binding modality (e.g., antibody/peptide-like vs small-molecule) from the same evidence used for site discovery, including topology, hydropathy, PTM propensity, disulfides, domain context, and sequence. Importantly, this evidence is applied consistently across modalities, including small-molecule pocket discovery, to avoid selecting chemically plausible but biologically occluded sites.
title Site4Drug: Predicting Drug-Binding Target Sites with an AI Agent
topic Biomolecules
Machine Learning
url https://arxiv.org/abs/2606.01816