Zero-Origin Manifold (ZOM): Deterministic Algebraic Unification of 2D Molecular Graph Topology, 3D Inertial Geometry, Cross-Domain Property Prediction, and Millisecond Inverse Design

Complete mathematical formulation and large-scale benchmark validation of the Zero-Origin Manifold (ZOM) framework—a deterministic algebraic system integrating a zero-anchored, space-filling-attenuated 71D count manifold (M_0) with an orthogonally overlaid 14D Gram-eigenvalue geometric spectrum (g_14). Validated across 175,984 unique 2D molecular structures spanning 11 elements and N = 1-484, ZOM establishes exact algebraic existence-boundary laws, 100.00% topological uniqueness across QM9 without string comparison, unified mean R^2 = 0.7141 across 32 physicochemical and ADMET properties, higher accuracy (0.7649 vs. 0.6972) and 3.5x faster execution than 1024-bit ECFP4-HistGBDT baselines, macromolecular extrapolation up to N = 484, and 100% valid millisecond-scale inverse design.

Authors

Publication Details

Journal
Figshare
Published
2026-11-21
DOI
https://doi.org/10.6084/m9.figshare.35081809
Primary Topic
Computational Drug Discovery Methods
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Zero-Origin Manifold (ZOM): Deterministic Algebraic Unification of 2D Molecular Graph Topology, 3D Inertial Geometry, Cross-Domain Property Prediction, and Millisecond Inverse Design

Shoji Fujita
Figshare
Computational Drug Discovery Methods
preprint

Zero-Origin Manifold (ZOM): Deterministic Algebraic Unification of 2D Molecular Graph Topology, 3D Inertial Geometry, Cross-Domain Property Prediction, and Millisecond Inverse Design

Shoji Fujita
preprint en

Abstract

Complete mathematical formulation and large-scale benchmark validation of the Zero-Origin Manifold (ZOM) framework—a deterministic algebraic system integrating a zero-anchored, space-filling-attenuated 71D count manifold (M_0) with an orthogonally overlaid 14D Gram-eigenvalue geometric spectrum (g_14). Validated across 175,984 unique 2D molecular structures spanning 11 elements and N = 1-484, ZOM establishes exact algebraic existence-boundary laws, 100.00% topological uniqueness across QM9 without string comparison, unified mean R^2 = 0.7141 across 32 physicochemical and ADMET properties, higher accuracy (0.7649 vs. 0.6972) and 3.5x faster execution than 1024-bit ECFP4-HistGBDT baselines, macromolecular extrapolation up to N = 484, and 100% valid millisecond-scale inverse design.

Figshare
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.

Laika access coming soon