mlsanityData to 14 Oct 2026

Deep Molecular Representation Learning via Fusing Physical and Chemical Information

arXiv 2112.04624 ↗First posted 28 Nov 2021q-bio.QM cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

Molecular representation learning is the first yet vital step in combining deep learning and molecular science. To push the boundaries of molecular representation learning, we present PhysChem, a novel neural architecture that learns molecular representations via fusing physical and chemical information of molecules. PhysChem is composed of a physicist network (PhysNet) and a chemist network (ChemNet). PhysNet is a neural physical engine that learns molecular conformations through simulating molecular dynamics with parameterized forces; ChemNet implements geometry-aware deep message-passing to learn chemical / biomedical properties of molecules. Two networks specialize in their own tasks and cooperate by providing expertise to each other. By fusing physical and chemical information, PhysChem achieved state-of-the-art performances on MoleculeNet, a standard molecular machine learning benchmark. The effectiveness of PhysChem was further corroborated on cutting-edge datasets of SARS-CoV-2.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 23 of its 60 references that are in the map. First posted on arXiv 28 Nov 2021.

Builds on

23 of 60 references.

References · 23

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  4. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  5. 2017A Survey on Multi-Task Learningcited by 840
  6. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
  7. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  8. 2020Directional Message Passing for Molecular Graphscited by 561
  9. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 375
  10. 2018Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generationcited by 364
  11. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 305
  12. 2017Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanicscited by 214
11 more
  1. 2018Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discoverycited by 194
  2. 2021Learning Gradient Fields for Molecular Conformation Generationcited by 163
  3. 2019Molecular geometry prediction using a deep generative graph neural networkcited by 91
  4. 2019SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discoverycited by 90
  5. 2020Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Networkcited by 37
  6. 2020Improved Protein-ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inferencecited by 35
  7. 202086 PFLOPS Deep Potential Molecular Dynamics simulation of 100 million atoms with ab initio accuracycited by 15
  8. 2021HamNet: Conformation-Guided Molecular Representation with Hamiltonian Neural Networkscited by 13
  9. 20183D-PhysNet: Learning the Intuitive Physics of Non-Rigid Object Deformationscited by 7
  10. 2018Three-Dimensionally Embedded Graph Convolutional Network (3DGCN) for Molecule Interpretationcited by 7
  11. 2021High-Throughput Virtual Screening of Small Molecule Inhibitors for SARS-CoV-2 Protein Targets with Deep Fusion Modelscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 6; 2024: 4; 2025: 4; 2026: 3.

21 papers.

Sort:

By area:

  1. 2022Graph-based Molecular Representation Learningcited by 51
  2. 2023Uncovering Neural Scaling Laws in Molecular Representation Learningcited by 23
  3. 2023A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardwarecited by 18
  4. 2023Deep Learning Methods for Small Molecule Drug Discovery: A Surveycited by 10
  5. 2022Improving Molecular Representation Learning with Metric Learning-enhanced Optimal Transportcited by 9
  6. 2024Advancing Molecular Graph-Text Pre-training via Fine-grained Alignmentcited by 9
  7. 2023ODE-based Recurrent Model-free Reinforcement Learning for POMDPscited by 7
  8. 2024Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Surveycited by 6
  9. 2022PEMP: Leveraging Physics Properties to Enhance Molecular Property Predictioncited by 5
  10. 2022Improving Molecular Pretraining with Complementary Featurizationscited by 4
  11. 2024MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insightscited by 4
  12. 20253DMolFormer: A Dual-channel Framework for Structure-based Drug Discoverycited by 4
9 more
  1. 2025Recent Developments in GNNs for Drug Discoverycited by 3
  2. 2023Graph Scattering beyond Wavelet Shacklescited by 2
  3. 2024Molecular Graph Representation Learning Integrating Large Language Models with Domain-specific Small Modelscited by 2
  4. 2023GlycoNMR: Dataset and benchmarks for NMR chemical shift prediction of carbohydrates with graph neural networkscited by 0
  5. 2025TransPlace: Transferable Circuit Global Placement via Graph Neural Networkcited by 0
  6. 2025HSA-Net: Hierarchical and Structure-Aware Framework for Efficient and Scalable Molecular Language Modelingcited by 0
  7. 2026Electron-Informed Coarse-Graining Molecular Representation Learning for Real-World Molecular Physicscited by 0
  8. 2026DMMRL: Disentangled Multi-Modal Representation Learning via Variational Autoencoders for Molecular Property Predictioncited by 0
  9. 2026Universal and efficient graph neural networks with dynamic attention for machine learning interatomic potentialscited by 0