Extends the mol-infer MILP framework to copolymers via a mixing vector representation, trains ML predictors achieving R^2 >0.7 on 9/10 datasets, and shows tractable multi-monomer inverse design with external consistency checks.
arXiv preprint arXiv:2011.14115 (2020)
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
baseline 1
method 1
citation-polarity summary
years
2026 9representative citing papers
h-MINT improves ligand-protein binding affinity prediction by 2-4% and virtual screening metrics by 1-3% via overlapping fragment tokenization and hierarchical modeling.
FB-GNN-MBE integrates fragment-based graph neural networks into many-body expansion to predict two- and three-body energies for water, phenol, and mixture systems at chemical accuracy, with a teacher-student protocol enabling transfer to new cluster sizes without full retraining.
SurfDesign introduces surface-conditioned protein design via manifold modeling and equivariant message passing on surfaces integrated with pretrained language models, outperforming prior methods on binder and enzyme design benchmarks.
A tensor-channel equivariant GNN based on PaiNN propagates symmetric rank-2 tensor features during message passing and achieves lower full-tensor and anisotropic error than readout-only and MACE baselines on QM7-X geometries.
TSAgent automates transition state searches at DFT accuracy via an agentic loop, reaching 83% success on 100 OC20NEB examples and 70% on 10 held-out cases versus 73% for human experts.
A new benchmark finds that state-of-the-art ML interatomic potentials struggle with compositional generalization, producing errors an order of magnitude higher on unseen molecular combinations than on training-like cases.
AIRA₂ improves AI research agents via asynchronous multi-GPU workers, hidden consistent evaluation, and interactive ReAct agents, reaching 81.5-83.1% percentile rank on MLE-bench-30 and exceeding human SOTA on 6 of 20 AIRS-Bench tasks.
A systematic survey and benchmark of four deep learning paradigms for molecular property prediction that organizes the field, critiques current data practices, and outlines three future directions.
citing papers explorer
-
Mixing Vector Model for Copolymer Inference via Mixed Integer Linear Programming
Extends the mol-infer MILP framework to copolymers via a mixing vector representation, trains ML predictors achieving R^2 >0.7 on 9/10 datasets, and shows tractable multi-monomer inverse design with external consistency checks.
-
h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Network
h-MINT improves ligand-protein binding affinity prediction by 2-4% and virtual screening metrics by 1-3% via overlapping fragment tokenization and hierarchical modeling.
-
Transferable FB-GNN-MBE Framework for Potential Energy Surfaces: Data-Adaptive Transfer Learning in Deep Learned Many-Body Expansion Theory
FB-GNN-MBE integrates fragment-based graph neural networks into many-body expansion to predict two- and three-body energies for water, phenol, and mixture systems at chemical accuracy, with a teacher-student protocol enabling transfer to new cluster sizes without full retraining.
-
SurfDesign: Effective Protein Design on Molecular Surfaces
SurfDesign introduces surface-conditioned protein design via manifold modeling and equivariant message passing on surfaces integrated with pretrained language models, outperforming prior methods on binder and enzyme design benchmarks.
-
Tensor Channel Equivariant Graph Neural Networks for Molecular Polarizability Prediction
A tensor-channel equivariant GNN based on PaiNN propagates symmetric rank-2 tensor features during message passing and achieves lower full-tensor and anisotropic error than readout-only and MACE baselines on QM7-X geometries.
-
TSAgent: An Agentic Workflow for Autonomous Transition State Search
TSAgent automates transition state searches at DFT accuracy via an agentic loop, reaching 83% success on 100 OC20NEB examples and 70% on 10 held-out cases versus 73% for human experts.
-
Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials
A new benchmark finds that state-of-the-art ML interatomic potentials struggle with compositional generalization, producing errors an order of magnitude higher on unseen molecular combinations than on training-like cases.
-
AIRA_2: Overcoming Bottlenecks in AI Research Agents
AIRA₂ improves AI research agents via asynchronous multi-GPU workers, hidden consistent evaluation, and interactive ReAct agents, reaching 81.5-83.1% percentile rank on MLE-bench-30 and exceeding human SOTA on 6 of 20 AIRS-Bench tasks.
-
A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era
A systematic survey and benchmark of four deep learning paradigms for molecular property prediction that organizes the field, critiques current data practices, and outlines three future directions.