[2607.19977] Rem3Di: Learning smooth, chiral 3D molecular descriptors from atomistic foundation models

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Physics > Chemical Physics

arXiv:2607.19977 (physics)

[Submitted on 22 Jul 2026]

Title:Rem3Di: Learning smooth, chiral 3D molecular descriptors from atomistic foundation models

Authors:Steffen Wedig, Felix Burton, Rokas Elijošius, Christoph Schran, Lars L. Schaaf<br>View a PDF of the paper titled Rem3Di: Learning smooth, chiral 3D molecular descriptors from atomistic foundation models, by Steffen Wedig and 4 other authors

View PDF<br>HTML (experimental)

Abstract:Foundation machine-learned interatomic potentials (MLIPs) are trained on large quantum-mechanical datasets and generalise across broad regions of chemical and configurational space. Beyond their usual role in accelerating sampling-based simulations, their internal representations encode chemically rich local atomic environments. Here, we introduce Rem3Di, a representation-learning framework that repurposes latent features from atomistic foundation models as transferable molecular descriptors for property prediction and virtual screening. Rem3Di combines a potential's per-atom features into a single fixed-length descriptor of the whole molecule that varies smoothly with three-dimensional structure and is invariant to the ordering of the atoms. The descriptor can be used directly or fine-tuned for specific prediction tasks. To capture molecular handedness, Rem3Di constructs pseudoscalar features, which are unchanged by rotation but reverse sign under mirror reflection. This lets the descriptor distinguish enantiomers, which can differ in activity and toxicity. The transformer is pretrained on large molecular datasets by reconstructing corrupted atom features, so no experimental labels are required. Across public drug-property benchmarks, Rem3Di matches or exceeds published baselines without relying on classical 2D fingerprints. Additionally, the same descriptor yields chemically meaningful differentiation of transition-metal complexes without predefined bonding rules or handcrafted representations. Rem3Di therefore provides a route from simulation-trained atomistic representations to transferable, chirality-aware molecular representations for chemical machine learning.

Comments:<br>An earlier version of this work appeared at the NeurIPS 2025 Workshop on Symmetry and Geometry in Neural Representations (NeurReps). Workshop version: this https URL

Subjects:

Chemical Physics (physics.chem-ph); Atomic and Molecular Clusters (physics.atm-clus); Computational Physics (physics.comp-ph)

Cite as:<br>arXiv:2607.19977 [physics.chem-ph]

(or<br>arXiv:2607.19977v1 [physics.chem-ph] for this version)

https://doi.org/10.48550/arXiv.2607.19977

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Lars Leon Schaaf [view email]<br>[v1]<br>Wed, 22 Jul 2026 10:05:09 UTC (4,938 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Rem3Di: Learning smooth, chiral 3D molecular descriptors from atomistic foundation models, by Steffen Wedig and 4 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

physics.chem-ph

next >

new<br>recent<br>| 2026-07

Change to browse by:

physics<br>physics.atm-clus<br>physics.comp-ph

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is...