Chemistry-informed macromolecule graph representation for similarity computation, unsupervised and supervised learning

The near-infinite chemical diversity of natural and artificial macromolecules arises from the vast range of possible component monomers, linkages, and polymers topologies. This enormous variety contributes to the ubiquity and indispensability of macromolecules but hinders the development of general machine learning methods with macromolecules as input. To address this, we developed a chemistry-informed graph representation of macromolecules that enables quantifying structural similarity, and interpretable supervised learning for macromolecules. Our work enables quantitative chemistry-informed decision-making and iterative design in the macromolecular chemical space.

• Publication year

  2022

• Venue

  Machine Learning: Science and Technology

• Publication date

  2022-02-11

• Fields of study

  Physics, Chemistry, Computer Science

• Identifiers
  DOI 10.1088/2632-2153/ac545e
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Deep learning to design nuclear-targeting abiotic miniproteins

  2021cited by this paper
• Using graph convolutional neural networks to learn a representation for glycans

  2021cited by this paper
• Pushing the boundaries of molecular representation for drug discovery with graph attention mechanism.

  2020cited by this paper
• Polymer Chemistry

  2020cited by this paper
• Transfer learning with graph neural networks for optoelectronic properties of conjugated oligomers.

  2020cited by this paper
• Evaluating Attribution for Graph Neural Networks

  2020cited by this paper
• Polymer Informatics: Current Status and Critical Next Steps

  2020cited by this paper
• Deep-Learning Resources for Studying Glycan-Mediated Host-Microbe Interactions.

  2020influential reference
• Topological Polymer Chemistry Enters Materials Science: Expanding the Applicability of Cyclic Polymers.

  2020cited by this paper
• 100th Anniversary of Macromolecular Science Viewpoint: Integrating Chemistry and Engineering to Enable Additive Manufacturing with High-Performance Polymers.

  2020cited by this paper
• 100th Anniversary of Macromolecular Science Viewpoint: Engineering Supramolecular Materials for Responsive Applications-Design and Functionality.

  2020cited by this paper
• 100th Anniversary of Macromolecular Science Viewpoint: Biological Stimuli-Sensitive Polymer Prodrugs and Nanoparticles for Tumor-Specific Drug Delivery.

  2020cited by this paper
• Quantitative Mapping of Molecular Substituents to Macroscopic Properties Enables Predictive Design of Oligoethylene Glycol-Based Lithium Electrolytes

  2020cited by this paper
• ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised Deep Learning and High Performance Computing

  2020cited by this paper
• Hierarchical Generation of Molecular Graphs using Structural Motifs

  2020cited by this paper
• Identifying glycan motifs using a novel subtree mining approach

  2020cited by this paper
• Magic-BLAST, an accurate RNA-seq aligner for long and short reads

  2019cited by this paper
• Analyzing Learned Molecular Representations for Property Prediction

  2019cited by this paper
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments, and Partial Charges.

  2019cited by this paper
• Unified rational protein engineering with sequence-based deep representation learning

  2019cited by this paper
• BigSMILES: A Structurally-Based Line Notation for Describing Macromolecules

  2019cited by this paper
• Machine Learning for Scent: Learning Generalizable Perceptual Representations of Small Molecules

  2019cited by this paper
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks.

  2019cited by this paper
• Polymer-based sensors: A review

  2018cited by this paper
• Polymer Genome: A Data-Powered Polymer Informatics Platform for Property Predictions

  2018cited by this paper
• Using attribution to decode binding mechanism in neural network models for chemistry

  2018cited by this paper
• GraKeL: A Graph Kernel Library in Python

  2018influential reference
• Message-passing neural networks for high-throughput polymer screening

  2018cited by this paper
• UMAP: Uniform Manifold Approximation and Projection

  2018cited by this paper
• Representation Learning on Graphs: Methods and Applications

  2017cited by this paper
• Learning Important Features Through Propagating Activation Differences

  2017cited by this paper
• Development and application of an algorithm to compute weighted multiple glycan alignments

  2017cited by this paper
• SchNet - A deep learning architecture for molecules and materials.

  2017cited by this paper
• Neural Message Passing for Quantum Chemistry

  2017cited by this paper
• Axiomatic Attribution for Deep Networks

  2017influential reference
• hdbscan: Hierarchical density based clustering

  2017cited by this paper
• Semi-Supervised Classification with Graph Convolutional Networks

  2016cited by this paper
• Quantum-chemical insights from deep tensor neural networks

  2016cited by this paper
• DBAASP v.2: an enhanced database of structure and antimicrobial/cytotoxic activity of natural and synthetic peptides

  2016cited by this paper
• Glycan characterization of biopharmaceuticals: Updates and perspectives.

  2016cited by this paper
• Molecular graph convolutions: moving beyond fingerprints

  2016cited by this paper
• From precision polymers to complex materials and systems

  2016cited by this paper
• InChI, the IUPAC International Chemical Identifier

  2015cited by this paper
• Coding Macromolecules: Inputting Information in Polymers Using Monomer-Based Alphabets

  2015cited by this paper
• Hydrocarbon stapled peptides as modulators of biological function.

  2015cited by this paper
• An Exact Graph Edit Distance Algorithm for Solving Pattern Recognition Problems

  2015cited by this paper
• Propagation kernels: efficient graph kernels from propagated information

  2014influential reference
• Polypeptoids: a model system to study the effect of monomer sequence on polymer properties and self-assembly

  2013cited by this paper
• Sequence-Controlled Polymers

  2013cited by this paper
• HELM: A Hierarchical Notation Language for Complex Biomolecule Structure Representation

  2012cited by this paper
• Protein data bank

  2012cited by this paper
• CurlySMILES: a chemical language to customize and annotate encodings of molecular and nanodevice structures

  2011cited by this paper
• Core-clickable PEG-branch-azide bivalent-bottle-brush polymers by ROMP: grafting-through and clicking-to.

  2011cited by this paper
• Extended-Connectivity Fingerprints

  2010cited by this paper
• A weighted q-gram method for glycan structure classification

  2010cited by this paper
• Exploring Network Structure, Dynamics, and Function using NetworkX

  2008cited by this paper
• Graph Kernels

  2008cited by this paper
• Visualizing Data using t-SNE

  2008cited by this paper
• Polymer Nanocomposites: The “Nano” Effect on Mechanical Properties

  2007cited by this paper
• Synthesis of Star Polymers by a Combination of ATRP and the “Click” Coupling Method

  2006cited by this paper
• Where did the BLOSUM62 alignment score matrix come from?

  2004cited by this paper
• Efficient tree-matching methods for accurate carbohydrate database queries.

  2003cited by this paper
• Mixtures of Probabilistic Principal Component Analyzers

  1999cited by this paper
• Modern Multidimensional Scaling: Theory and Applications

  1999cited by this paper
• Gapped BLAST and PSI-BLAST: a new generation of protein database search programs.

  1997cited by this paper
• Unnatural oligomers and unnatural oligomer libraries.

  1997cited by this paper
• Synthesis of branched and hyperbranched polystyrenes

  1996cited by this paper
• An unnatural biopolymer.

  1993cited by this paper
• Basic local alignment search tool.

  1990cited by this paper
• Binding and Linkage: Functional Chemistry of Biological Macromolecules

  1990cited by this paper
• Identification of common molecular subsequences.

  1981cited by this paper
• BIOINFORMATICS ORIGINAL PAPER doi:10.1093/bioinformatics/btm090 Structural bioinformatics Glycan classification with tree kernels

  year unknowncited by this paper

• Exploring the Strengths and Limitations of Polymer Chemistry Informed Neural Networks

  2026cites this paper
• From prediction to understanding: A review of XAI applications and innovations in materials science

  2026cites this paper
• Graph Neural Networks for Polymer Characterization and Property Prediction: Opportunities and Challenges

  2026cites this paper
• MacroSimGNN: Efficient and Accurate Prediction of Macromolecule Pairwise Similarity via A Graph Neural Network

  2026cites this paper
• Atom-level Machine Learning of Protein-Glycan Interactions and Cross-chiral Recognition in Glycobiology

  2025cites this paper
• Deep Generative Models for Therapeutic Peptide Discovery: A Comprehensive Review

  2025cites this paper
• Machine Learning Approaches in Polymer Science: Progress and Fundamental for a New Paradigm

  2025cites this paper
• A systematic review of recent advances in the application of machine learning in membrane-based gas separation technologies

  2025cites this paper
• Atom-level machine learning of protein-glycan interactions and cross-chiral recognition in glycobiology

  2025cites this paper
• Data-efficient Machine Learning for Polymer Informatics

  2025cites this paper
• Scaling law-informed machine learning for predicting thermal and electrical properties of polymers: A physics-based approach

  2025cites this paper
• Design of Cytotoxic T Cell Epitopes by Machine Learning of Human Degrons

  2024cites this paper
• RETRACTED ARTICLE: Application of Generative Artificial Intelligence AIGC Technology Under Neural Network Algorithm in Game Character Art Design

  2024cites this paper
• Calculating Pairwise Similarity of Polymer Ensembles via Earth Mover’s Distance

  2024cites this paper
• Holographic Gaussian Boson Sampling with Matrix Product States on 3D cQED Processors.

  2024cites this paper
• LeGenD: determining N-glycoprofiles using an explainable AI-leveraged model with lectin profiling

  2024cites this paper
• Automated BigSMILES conversion workflow and dataset for homopolymeric macromolecules

  2024cites this paper
• Predicting polymerization reactions via transfer learning using chemical language models

  2023cites this paper
• The Rise of Machine Learning in Polymer Discovery

  2023cites this paper
• A Perspective on Explanations of Molecular Prediction Models

  2023cites this paper
• Accelerating the design and development of polymeric materials via deep learning: Current status and future challenges

  2023cites this paper
• GNNGLY: Graph Neural Networks for Glycan Classification

  2023influential citation
• Sizing up feature descriptors for macromolecular machine learning with polymeric biomaterials

  2023cites this paper
• Artificial intelligence driven design of catalysts and materials for ring opening polymerization using a domain-specific language

  2023cites this paper
• Infrared spectroscopic evaluation for catalytic hydrogenation of biomass and coal using unsupervised and supervised algorithms

  2023cites this paper
• Quantifying Pairwise Similarity for Complex Polymers

  2023cites this paper
• A Model Ensemble Approach Enables Data-Driven Property Prediction for Chemically Deconstructable Thermosets in the Low-Data Regime

  2023cites this paper
• A Survey of GNN-Based Graph Similarity Learning

  2023cites this paper
• Interpretable Machine Learning-Based Model to Classify and Optimize Isoperibolic Batch Reactors

  2023cites this paper
• GlycoNMR: Dataset and benchmarks for NMR chemical shift prediction of carbohydrates with graph neural networks

  2023cites this paper
• Navigating the Expansive Landscapes of Soft Materials: A User Guide for High-Throughput Workflows

  2023cites this paper
• Learning Matter: Materials Design with Machine Learning and Atomistic Simulations

  2022cites this paper
• Photonic Quantum Computing For Polymer Classification

  2022cites this paper
• Polymer Informatics at Scale with Multitask Graph Neural Networks

  2022cites this paper
• nanoNET: machine learning platform for predicting nanoparticles distribution in a polymer matrix.

  2022cites this paper
• Application of Machine Learning Technologies for Transport layer Congestion Control

  2022cites this paper
• Quantum Chemical Roots of Machine-Learning Molecular Similarity Descriptors.

  2022cites this paper
• Predicting aggregate morphology of sequence-defined macromolecules with recurrent neural networks.

  2022cites this paper
• Representing Polymers as Periodic Graphs with Learned Descriptors for Accurate Polymer Property Predictions

  2022cites this paper
• A graph representation of molecular ensembles for polymer property prediction

  2022cites this paper
• Machine learning strategies for the structure-property relationship of copolymers

  2022cites this paper