Geometric Escape Index as a Candidate Structural Descriptor of Viral Drug-Resistance Mutations: A Pilot Study with Two Independent External Validation Sets (n=97)

We propose the Geometric Escape Index (GEI = deltaR_LSP), derived from the Lo-Shu Projection (LSP) geometric framework, as a compact structural descriptor of mutation-induced drug-pocket deformation in viral proteins. Training set (n=21): SARS-CoV-2 Mpro, HIV-1 PR, Influenza A NA (rho=0.930, p<0.0001, AUC=1.000). External validation 1 (n=29): HIV-1 PR from Stanford HIVDB v10.2 (rho=0.823, p<0.0001). External validation 2 (n=47): Influenza A NA across H1N1/H3N2/H5N1/H9N2 (rho=0.933, p<0.0001, AUC=1.000). Combined (n=97): rho=0.890 (p<0.0001). GEI threshold 0.030 separated HIGH-resistance mutations across all datasets. Part of the Genesis Geometric Medicine Framework v4.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-05-11
DOI
https://doi.org/10.5281/zenodo.20127127
Primary Topic
Computational Drug Discovery Methods
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
preprint

Geometric Escape Index as a Candidate Structural Descriptor of Viral Drug-Resistance Mutations: A Pilot Study with Two Independent External Validation Sets (n=97)

Yao-Kai Kao
Zenodo (CERN European Organization for Nuclear Research)
Computational Drug Discovery Methods
preprint

Geometric Escape Index as a Candidate Structural Descriptor of Viral Drug-Resistance Mutations: A Pilot Study with Two Independent External Validation Sets (n=97)

Yao-Kai Kao
preprint en

Abstract

We propose the Geometric Escape Index (GEI = deltaR_LSP), derived from the Lo-Shu Projection (LSP) geometric framework, as a compact structural descriptor of mutation-induced drug-pocket deformation in viral proteins. Training set (n=21): SARS-CoV-2 Mpro, HIV-1 PR, Influenza A NA (rho=0.930, p<0.0001, AUC=1.000). External validation 1 (n=29): HIV-1 PR from Stanford HIVDB v10.2 (rho=0.823, p<0.0001). External validation 2 (n=47): Influenza A NA across H1N1/H3N2/H5N1/H9N2 (rho=0.933, p<0.0001, AUC=1.000). Combined (n=97): rho=0.890 (p<0.0001). GEI threshold 0.030 separated HIGH-resistance mutations across all datasets. Part of the Genesis Geometric Medicine Framework v4.

Zenodo (CERN European Organization for Nuclear Research)
Allen Institute for Brain Science (US)
Good health and well-being
Computational Drug Discovery Methods
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.