Neural Network Potentials and Modern Methods

Building on the gas-phase MB-nrg PEF for polyalanine, Ruihan Zhou and Francesco Paesani add machine-learned 2-body terms for each backbone functional group interacting with water, fit to BSSE-corrected DLPNO-CCSD(T)/aug-cc-pVTZ data, then validate the resulting potential against alanine dipeptide-water dimer scans, free-energy surfaces in explicit MB-pol water, and hydration radial distribution functions.

Ruihan Zhou and co-authors extend the MB-nrg many-body formalism to covalently bonded biomolecules by fragmenting polyalanine into functional-group n-mers, fitting permutationally invariant polynomials to DLPNO-CCSD(T)/aug-cc-pVTZ reference energies, and reproducing alanine dipeptide Ramachandran surfaces, harmonic frequencies, and AceAla9Nme secondary-structure dynamics more faithfully than Amber ff14SB and ff19SB.

Introduces a Dirac notation formalism for atomic environments that unifies SOAP power spectra, Behler-Parrinello symmetry functions, and other density-based structural representations under a single theoretical framework.

A conformation autoencoder converts molecular 3D arrangements into fixed-size latent representations using internal coordinates and graph neural networks, enabling conformer generation and spatial property optimization.

Proposes Ewald message passing, a Fourier-space scheme inspired by Ewald summation that captures long-range interactions in molecular graphs. The method is architecture-agnostic and improves energy MAEs by 10% on OC20 and 16% on OE62 across four baseline GNN models.

PharMolixFM proposes a unified framework for all-atom foundation models using three multi-modal generative approaches (diffusion, flow matching, BFN) and demonstrates competitive docking accuracy with fast inference.

Molecule Attention Transformer (MAT) augments Transformer self-attention with inter-atomic distances and graph adjacency, achieving strong property prediction across diverse molecular tasks with minimal hyperparameter tuning after self-supervised pretraining.

MOFFlow is the first deep generative model tailored for Metal-Organic Framework (MOF) structure prediction. It utilizes Riemannian flow matching on SE(3) to assemble rigid building blocks (metal nodes and organic linkers), achieving higher accuracy and scalability than atom-based methods on large systems.

ICLR 2025 paper introducing DenoiseVAE, which learns adaptive, atom-specific noise distributions through a VAE framework to improve denoising-based pre-training for molecular force field prediction, outperforming fixed Gaussian noise approaches on quantum chemistry benchmarks.

ICML 2025 paper introducing SpaceFormer, a Transformer architecture that challenges the atom-centric paradigm by modeling the continuous 3D space surrounding molecules using adaptive multi-resolution grids, ranking first in 10 of 15 molecular property prediction tasks.

ICML 2025 analysis rigorously quantifying when non-conservative force models (which predict forces directly) fail in molecular dynamics, demonstrating simulation instabilities and proposing hybrid architectures that capture speed benefits without sacrificing physical correctness.

ICML 2025 methodological paper introducing SPHNet, which uses adaptive network sparsification to overcome the computational bottleneck of tensor products in SE(3)-equivariant networks, achieving up to 7x speedup and 75% memory reduction on DFT Hamiltonian prediction tasks.