mlsanityData to 7 Oct 2026

UBio-MolFM: A Universal Molecular Foundation Model for Bio-Systems

arXiv 2602.17709 ↗First posted 13 Feb 2026physics.chem-ph cs.AI physics.bio-phcited by 0

Not on the map. Why?

Abstract (arXiv)

All-atom molecular simulation serves as a quintessential ``computational microscope'' for understanding the machinery of life, yet it remains fundamentally limited by the trade-off between quantum-mechanical (QM) accuracy and biological scale. We present UBio-MolFM, a universal foundation model framework specifically engineered to bridge this gap. UBio-MolFM introduces three synergistic innovations: (1) UBio-Mol26, a large bio-specific dataset constructed via a multi-fidelity ``Two-Pronged Strategy'' that combines systematic bottom-up enumeration with top-down sampling of native protein environments (up to 1,200 atoms); (2) E2Former-V2, a linear-scaling equivariant transformer that integrates Equivariant Axis-Aligned Sparsification (EAAS) and Long-Short Range (LSR) modeling to capture non-local physics with up to ~4x higher inference throughput in our large-system benchmarks; and (3) a Three-Stage Curriculum Learning protocol that transitions from energy initialization to energy-force consistency, with force-focused supervision to mitigate energy offsets. Rigorous benchmarking across microscopic forces and macroscopic observables -- including liquid water structure, ionic solvation, and peptide folding -- demonstrates that UBio-MolFM achieves ab initio-level fidelity on large, out-of-distribution biomolecular systems (up to ~1,500 atoms) and realistic MD observables. By reconciling scalability with quantum precision, UBio-MolFM provides a robust, ready-to-use tool for the next generation of computational biology.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 47 references that are in the map. First posted on arXiv 13 Feb 2026.

Builds on

14 of 47 references.

References · 14

  1. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
  2. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
  3. 2020Directional Message Passing for Molecular Graphscited by 556
  4. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 467
  5. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 258
  6. 2022Learning Local Equivariant Representations for Large-Scale Atomistic Dynamicscited by 254
  7. 2023EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representationscited by 201
  8. 2023Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNscited by 113
  9. 2025UMA: A Family of Universal Models for Atomscited by 99
  10. 2022SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentialscited by 80
  11. 2025Learning Smooth and Expressive Interatomic Potentials for Physical Property Predictioncited by 79
  12. 2025E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Productscited by 12
2 more
  1. 2026E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memorycited by 3
  2. 2026Scalable Machine Learning Force Fields for Macromolecular Systems Through Long-Range Aware Message Passingcited by 2

Built on by

Not cited yet.