Artificial Intelligence based Autonomous Molecular Design for Medical Therapeutic: A Perspective
Not on the map. Why?
Abstract (arXiv)
Domain-aware machine learning (ML) models have been increasingly adopted for accelerating small molecule therapeutic design in the recent years. These models have been enabled by significant advancement in state-of-the-art artificial intelligence (AI) and computing infrastructures. Several ML architectures are pre-dominantly and independently used either for predicting the properties of small molecules, or for generating lead therapeutic candidates. Synergetically using these individual components along with robust representation and data generation techniques autonomously in closed loops holds enormous promise for accelerated drug design which is a time consuming and expensive task otherwise. In this perspective, we present the most recent breakthrough achieved by each of the components, and how such autonomous AI and ML workflow can be realized to radically accelerate the hit identification and lead optimization. Taken together, this could significantly shorten the timeline for end-to-end antiviral discovery and optimization times to weeks upon the arrival of a novel zoonotic transmission event. Our perspective serves as a guide for researchers to practice autonomous molecular design in therapeutic discovery.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 28 of its 112 references that are in the map. First posted on arXiv 10 Feb 2021.
Builds on
28 of 112 references.
References · 28
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
- 2014Deep Learning in Neural Networks: An Overviewcited by 765
- 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
- 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
- 2018MolGAN: An implicit generative model for small molecular graphscited by 392
- 2019Analyzing Learned Molecular Representations for Property Predictioncited by 373
- 2017Grammar Variational Autoencodercited by 283
- 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 264
- 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
- 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 238
- 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 182
16 more
- 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 171
- 2017Deep Reinforcement Learning for De-Novo Drug Designcited by 161
- 2017Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Modelscited by 116
- 2018Learning Multimodal Graph-to-Graph Translation for Molecular Optimizationcited by 87
- 2019Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Spacecited by 66
- 2020OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Featurescited by 63
- 2017SMILES Enumeration as Data Augmentation for Neural Network Modeling of Moleculescited by 58
- 2020Reinforcement Learning for Molecular Design Guided by Quantum Mechanicscited by 51
- 2019Deep learning for molecular design - a review of the state of the artcited by 38
- 2018Message-passing neural networks for high-throughput polymer screeningcited by 30
- 2019Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representationcited by 22
- 2018Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materialscited by 21
- 2019DeepScaffold: a comprehensive tool for scaffold-based de novo drug discovery using deep learningcited by 15
- 2020A deep-learning view of chemical space designed to facilitate drug discoverycited by 7
- 2019AMPL: A Data-Driven Modeling Pipeline for Drug Discoverycited by 4
- 2019Hierarchical Graph-to-Graph Translation for Moleculescited by 2
Built on by
Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 0; 2025: 0; 2026: 1.
2 papers.