Accelerating material design with the generative toolkit for scientific discovery

Matteo Manica; Jannis Born; Joris Cadow; Dimitrios Christofidellis; Ashish Dave; Dean Clarke; Yves Gaetan Nana Teukam; Giorgio Giannone; Samuel C. Hoffman; Matthew Buchan; Vijil Chenthamarakshan; Timothy Donovan; Hsiang Han Hsu; Federico Zipoli; Oliver Schilter; Akihiro Kishimoto; Lisa Hamada; Inkit Padhi; Karl Wehden; Lauren McHugh; Alexy Khrabrov; Payel Das; Seiji Takeda; John R. Smith

doi:10.1038/s41524-023-01028-1

Accelerating material design with the generative toolkit for scientific discovery

Matteo Manica^*, Jannis Born, Joris Cadow, Dimitrios Christofidellis, Ashish Dave, Dean Clarke, Yves Gaetan Nana Teukam, Giorgio Giannone, Samuel C. Hoffman, Matthew Buchan, Vijil Chenthamarakshan, Timothy Donovan, Hsiang Han Hsu, Federico Zipoli, Oliver Schilter, Akihiro Kishimoto, Lisa Hamada, Inkit Padhi, Karl Wehden, Lauren McHughAlexy Khrabrov, Payel Das, Seiji Takeda, John R. Smith

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

21 Citations (Scopus)

36 Downloads (Pure)

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 organic material design.

Original language	English
Article number	69
Number of pages	6
Journal	npj Computational Materials
Volume	9
DOIs	https://doi.org/10.1038/s41524-023-01028-1
Publication status	Published - 01 May 2023
Externally published	Yes

Access to Document

10.1038/s41524-023-01028-1Licence: CC BY

Accelerating material design with the generative toolkit for scientific discovery
Copyright 2023 The Authors. This is an open access article published under a Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium, provided the author and source are cited.
Final published version, 1.27 MBLicence: CC BY

Accelerating scientific discovery using domain adaptive language modelling
Christofidellis, D. (Author), Vandierendonck, H. (Supervisor) & Manica, M. (Supervisor), Jul 2023
Student thesis: Doctoral Thesis › Doctor of Philosophy

File

Cite this

Manica, M., Born, J., Cadow, J., Christofidellis, D., Dave, A., Clarke, D., Teukam, Y. G. N., Giannone, G., Hoffman, S. C., Buchan, M., Chenthamarakshan, V., Donovan, T., Hsu, H. H., Zipoli, F., Schilter, O., Kishimoto, A., Hamada, L., Padhi, I., Wehden, K., ... Smith, J. R. (2023). Accelerating material design with the generative toolkit for scientific discovery. npj Computational Materials, 9, Article 69. https://doi.org/10.1038/s41524-023-01028-1

@article{918dc5996d684d6080558cfa834ed6e2,

title = "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 organic material design.",

author = "Matteo Manica and Jannis Born and Joris Cadow and Dimitrios Christofidellis and Ashish Dave and Dean Clarke and Teukam, {Yves Gaetan Nana} and Giorgio Giannone and Hoffman, {Samuel C.} and Matthew Buchan and Vijil Chenthamarakshan and Timothy Donovan and Hsu, {Hsiang Han} and Federico Zipoli and Oliver Schilter and Akihiro Kishimoto and Lisa Hamada and Inkit Padhi and Karl Wehden and Lauren McHugh and Alexy Khrabrov and Payel Das and Seiji Takeda and Smith, {John R.}",

year = "2023",

month = may,

day = "1",

doi = "10.1038/s41524-023-01028-1",

language = "English",

volume = "9",

journal = "npj Computational Materials",

publisher = "Nature Publishing Group",

}

Manica, M, Born, J, Cadow, J, Christofidellis, D, Dave, A, Clarke, D, Teukam, YGN, Giannone, G, Hoffman, SC, Buchan, M, Chenthamarakshan, V, Donovan, T, Hsu, HH, Zipoli, F, Schilter, O, Kishimoto, A, Hamada, L, Padhi, I, Wehden, K, McHugh, L, Khrabrov, A, Das, P, Takeda, S & Smith, JR 2023, 'Accelerating material design with the generative toolkit for scientific discovery', npj Computational Materials, vol. 9, 69. https://doi.org/10.1038/s41524-023-01028-1

TY - JOUR

T1 - Accelerating material design with the generative toolkit for scientific discovery

AU - Manica, Matteo

AU - Born, Jannis

AU - Cadow, Joris

AU - Christofidellis, Dimitrios

AU - Dave, Ashish

AU - Clarke, Dean

AU - Teukam, Yves Gaetan Nana

AU - Giannone, Giorgio

AU - Hoffman, Samuel C.

AU - Buchan, Matthew

AU - Chenthamarakshan, Vijil

AU - Donovan, Timothy

AU - Hsu, Hsiang Han

AU - Zipoli, Federico

AU - Schilter, Oliver

AU - Kishimoto, Akihiro

AU - Hamada, Lisa

AU - Padhi, Inkit

AU - Wehden, Karl

AU - McHugh, Lauren

AU - Khrabrov, Alexy

AU - Das, Payel

AU - Takeda, Seiji

AU - Smith, John R.

PY - 2023/5/1

Y1 - 2023/5/1

N2 - 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 organic material design.

AB - 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 organic material design.

U2 - 10.1038/s41524-023-01028-1

DO - 10.1038/s41524-023-01028-1

M3 - Article

VL - 9

JO - npj Computational Materials

JF - npj Computational Materials

M1 - 69

ER -

Accelerating material design with the generative toolkit for scientific discovery

Abstract

Access to Document

Fingerprint

Student theses

Accelerating scientific discovery using domain adaptive language modelling

Cite this