Accelerating Material Design with the Generative Toolkit for Scientific Discovery

Abstract

With the growing availability of data within various scientific domains, generative models hold enormous potential to accelerate scientific discovery. They harness powerful representations learned from datasets to speed up the formulation of novel hypotheses with the potential to impact material discovery broadly. We present the Generative Toolkit for Scientific Discovery (GT4SD). This extensible open-source library enables scientists, developers, and researchers to train and use state-of-the-art generative models to accelerate scientific discovery focused on material design.

15 pages, 2 figures

References in corpus (16)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Automatic chemical design using a data-driven continuous representation of molecules
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
• Skillful Precipitation Nowcasting using Deep Generative Models of Radar
• GuacaMol: Benchmarking Models for De Novo Molecular Design
• Accelerating Antimicrobial Discovery with Controllable Deep Generative Models and Molecular Dynamics
• Benchmarking Materials Property Prediction Methods: The Matbench Test Set and Automatminer Reference Algorithm
• GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
• Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development
• Regression Transformer: Concurrent sequence regression and generation for molecular language modeling
• Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild
• Optimizing Molecules using Efficient Queries from Property Evaluations
• CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models
• TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discovery
• Unifying Molecular and Textual Representations via Multi-task Language Modelling

Cited by in corpus (6)

• Navigating the Evolution of Two-dimensional Carbon Nitride Research: Integrating Machine Learning into Conventional Approaches
• Language models in molecular discovery
• Towards an automated workflow in materials science for combining multi-modal simulative and experimental information using data mining and large language models
• Large Language Models for Combinatorial Optimization: A Systematic Review
• Lean CNNs for mapping electron charge density fields to material properties
• Improving Electrolyte Performance for Target Cathode Loading Using Interpretable Data-Driven Approach