Search papers, labs, and topics across Lattice.
This paper introduces Rem3Di, a framework that leverages latent features from atomistic foundation models to create smooth, chiral 3D molecular descriptors for property prediction and virtual screening. By combining per-atom features into a fixed-length descriptor that is invariant to atom ordering and sensitive to molecular handedness, Rem3Di enables the differentiation of enantiomers, which is crucial for understanding variations in activity and toxicity. The method shows superior performance on public drug-property benchmarks, outperforming traditional 2D fingerprints and providing a novel pathway for integrating simulation-trained representations into chemical machine learning.
Rem3Di redefines molecular representation by enabling the differentiation of enantiomers without relying on classical 2D fingerprints, achieving state-of-the-art results in property prediction.
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.
