Omics-scale polymer computational database transferable to real-world artificial intelligence applications
Abstract
Developing large-scale foundational datasets is a critical milestone in advancing artificial intelligence (AI)-driven scientific innovation. However, unlike AI-mature fields such as natural language processing, materials science, particularly polymer research, has significantly lagged in developing extensive open datasets. This lag is primarily due to the high costs of polymer synthesis and property measurements, along with the vastness and complexity of the chemical space. This study presents PolyOmics, an omics-scale computational database generated through fully automated molecular dynamics simulation pipelines that provide diverse physical properties for over polymeric materials. The PolyOmics database is collaboratively developed by approximately 260 researchers from 48 institutions to bridge the gap between academia and industry. Machine learning models pretrained on PolyOmics can be efficiently fine-tuned for a wide range of real-world downstream tasks, even when only limited experimental data are available. Notably, the generalisation capability of these simulation-to-real transfer models improve significantly as the size of the PolyOmics database increases, exhibiting power-law scaling. The emergence of scaling laws supports the "more is better" principle, highlighting the significance of ultralarge-scale computational materials data for improving real-world prediction performance. This unprecedented omics-scale database reveals vast unexplored regions of polymer materials, providing a foundation for AI-driven polymer science.
Keywords
Cite
@article{arxiv.2511.11626,
title = {Omics-scale polymer computational database transferable to real-world artificial intelligence applications},
author = {Ryo Yoshida and Yoshihiro Hayashi and Hidemine Furuya and Ryohei Hosoya and Kazuyoshi Kaneko and Hiroki Sugisawa and Yu Kaneko and Aiko Takahashi and Yoh Noguchi and Shun Nanjo and Keiko Shinoda and Tomu Hamakawa and Mitsuru Ohno and Takuya Kitamura and Misaki Yonekawa and Stephen Wu and Masato Ohnishi and Chang Liu and Teruki Tsurimoto and Arifin and Araki Wakiuchi and Kohei Noda and Junko Morikawa and Teruaki Hayakawa and Junichiro Shiomi and Masanobu Naito and Kazuya Shiratori and Tomoki Nagai and Norio Tomotsu and Hiroto Inoue and Ryuichi Sakashita and Masashi Ishii and Isao Kuwajima and Kenji Furuichi and Norihiko Hiroi and Yuki Takemoto and Takahiro Ohkuma and Keita Yamamoto and Naoya Kowatari and Masato Suzuki and Naoya Matsumoto and Seiryu Umetani and Hisaki Ikebata and Yasuyuki Shudo and Mayu Nagao and Shinya Kamada and Kazunori Kamio and Taichi Shomura and Kensaku Nakamura and Yudai Iwamizu and Atsutoshi Abe and Koki Yoshitomi and Yuki Horie and Katsuhiko Koike and Koichi Iwakabe and Shinya Gima and Kota Usui and Gikyo Usuki and Takuro Tsutsumi and Keitaro Matsuoka and Kazuki Sada and Masahiro Kitabata and Takuma Kikutsuji and Akitaka Kamauchi and Yusuke Iijima and Tsubasa Suzuki and Takenori Goda and Yuki Takabayashi and Kazuko Imai and Yuji Mochizuki and Hideo Doi and Koji Okuwaki and Hiroya Nitta and Taku Ozawa and Hitoshi Kamijima and Toshiaki Shintani and Takuma Mitamura and Massimiliano Zamengo and Yuitsu Sugami and Seiji Akiyama and Yoshinari Murakami and Atsushi Betto and Naoya Matsuo and Satoru Kagao and Tetsuya Kobayashi and Norie Matsubara and Shosei Kubo and Yuki Ishiyama and Yuri Ichioka and Mamoru Usami and Satoru Yoshizaki and Seigo Mizutani and Yosuke Hanawa and Shogo Kunieda and Mitsuru Yambe and Takeru Nakamura and Hiromori Murashima and Kenji Takahashi and Naoki Wada and Masahiro Kawano and Yosuke Harada and Takehiro Fujita and Erina Fujita and Ryoji Himeno and Hiori Kino and Kenji Fukumizu},
journal= {arXiv preprint arXiv:2511.11626},
year = {2025}
}
Comments
65 pages, 11 figures