Nature computational science最新文献_第8页

Virtual node graph neural network for full phonon prediction 用于全声子预测的虚拟节点图神经网络。

IF 12

Nature computational science Pub Date : 2024-07-12 DOI: 10.1038/s43588-024-00661-0

Ryotaro Okabe, Abhijatmedhi Chotrattanapituk, Artittaya Boonkird, Nina Andrejevic, Xiang Fu, Tommi S. Jaakkola, Qichen Song, Thanh Nguyen, Nathan Drucker, Sai Mu, Yao Wang, Bolin Liao, Yongqiang Cheng, Mingda Li

{"title":"Virtual node graph neural network for full phonon prediction","authors":"Ryotaro Okabe, Abhijatmedhi Chotrattanapituk, Artittaya Boonkird, Nina Andrejevic, Xiang Fu, Tommi S. Jaakkola, Qichen Song, Thanh Nguyen, Nathan Drucker, Sai Mu, Yao Wang, Bolin Liao, Yongqiang Cheng, Mingda Li","doi":"10.1038/s43588-024-00661-0","DOIUrl":"10.1038/s43588-024-00661-0","url":null,"abstract":"Understanding the structure–property relationship is crucial for designing materials with desired properties. The past few years have witnessed remarkable progress in machine-learning methods for this connection. However, substantial challenges remain, including the generalizability of models and prediction of properties with materials-dependent output dimensions. Here we present the virtual node graph neural network to address the challenges. By developing three virtual node approaches, we achieve Γ-phonon spectra and full phonon dispersion prediction from atomic coordinates. We show that, compared with the machine-learning interatomic potentials, our approach achieves orders-of-magnitude-higher efficiency with comparable to better accuracy. This allows us to generate databases for Γ-phonon containing over 146,000 materials and phonon band structures of zeolites. Our work provides an avenue for rapid and high-quality prediction of phonon band structures enabling materials design with desired phonon properties. The virtual node method also provides a generic method for machine-learning design with a high level of flexibility. In this study, the authors present a virtual node graph neural network to enable the prediction of material properties with variable output dimensions. This method offers fast and accurate predictions of phonon band structures in complex solids.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"4 7","pages":"522-531"},"PeriodicalIF":12.0,"publicationDate":"2024-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141602338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Structure-based prediction of T cell receptor recognition of unseen epitopes using TCRen 利用 TCRen 基于结构预测 T 细胞受体对未知表位的识别能力

IF 12

Nature computational science Pub Date : 2024-07-10 DOI: 10.1038/s43588-024-00653-0

Vadim K. Karnaukhov, Dmitrii S. Shcherbinin, Anton O. Chugunov, Dmitriy M. Chudakov, Roman G. Efremov, Ivan V. Zvyagin, Mikhail Shugay

{"title":"Structure-based prediction of T cell receptor recognition of unseen epitopes using TCRen","authors":"Vadim K. Karnaukhov, Dmitrii S. Shcherbinin, Anton O. Chugunov, Dmitriy M. Chudakov, Roman G. Efremov, Ivan V. Zvyagin, Mikhail Shugay","doi":"10.1038/s43588-024-00653-0","DOIUrl":"10.1038/s43588-024-00653-0","url":null,"abstract":"T cell receptor (TCR) recognition of foreign peptides presented by major histocompatibility complex protein is a major event in triggering the adaptive immune response to pathogens or cancer. The prediction of TCR–peptide interactions has great importance for therapy of cancer as well as infectious and autoimmune diseases but remains a major challenge, particularly for novel (unseen) peptide epitopes. Here we present TCRen, a structure-based method for ranking candidate unseen epitopes for a given TCR. The first stage of the TCRen pipeline is modeling of the TCR–peptide–major histocompatibility complex structure. Then a TCR–peptide residue contact map is extracted from this structure and used to rank all candidate epitopes on the basis of an interaction score with the target TCR. Scoring is performed using an energy potential derived from the statistics of TCR–peptide contact preferences in existing crystal structures. We show that TCRen has high performance in discriminating cognate versus unrelated peptides and can facilitate the identification of cancer neoepitopes recognized by tumor-infiltrating lymphocytes. TCRen predicts TCR specificity by modeling the TCR–peptide–MHC structure and estimating the TCR–peptide interaction energy using a statistical potential. The use of structural information allows TCRen to generalize to unseen epitopes, such as cancer neoepitopes.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"4 7","pages":"510-521"},"PeriodicalIF":12.0,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141567219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unlocking T-cell receptor–epitope insights with structural analysis 通过结构分析揭开 T 细胞受体表位的神秘面纱

IF 12

Nature computational science Pub Date : 2024-07-10 DOI: 10.1038/s43588-024-00654-z

Miaozhe Huo, Yuepeng Jiang, Shuai Cheng Li

引用次数: 0

Free-form and multi-physical metamaterials with forward conformality-assisted tracing 采用前向保形辅助追踪技术的自由形态和多物理超材料。

IF 12

Nature computational science Pub Date : 2024-07-09 DOI: 10.1038/s43588-024-00660-1

Liujun Xu, Gaole Dai, Fubao Yang, Jinrong Liu, Yuhong Zhou, Jun Wang, Guoqiang Xu, Jiping Huang, Cheng-Wei Qiu

{"title":"Free-form and multi-physical metamaterials with forward conformality-assisted tracing","authors":"Liujun Xu, Gaole Dai, Fubao Yang, Jinrong Liu, Yuhong Zhou, Jun Wang, Guoqiang Xu, Jiping Huang, Cheng-Wei Qiu","doi":"10.1038/s43588-024-00660-1","DOIUrl":"10.1038/s43588-024-00660-1","url":null,"abstract":"Transformation theory, active control and inverse design have been mainstream in creating free-form metamaterials. However, existing frameworks cannot simultaneously satisfy the requirements of isotropic, passive and forward design. Here we propose a forward conformality-assisted tracing method to address the geometric and single-physical-field constraints of conformal transformation. Using a conformal mesh composed of orthogonal streamlines and isotherms (or isothermal surfaces), this method quasi-analytically produces free-form metamaterials using only isotropic media. The geometric nature of this approach allows for universal regulation of both dissipative thermal fields and non-dissipative electromagnetic fields. We experimentally demonstrate free-form thermal cloaking in both two and three dimensions. Additionally, the multi-physical functionalities of our method, including optical cloaking, bending and thermo-electric transparency, confirm its broad applicability. Our method features improvements in efficiency, accuracy and adaptability over previous approaches. This study provides an effective method for designing complex metamaterials with arbitrary shapes across various physical domains. Here a conformality-assisted tracing method is proposed to devise free-form and three-dimensional conformal metamaterials, featuring accuracy and efficiency in handling complex geometry and adaptability to various diffusion and wave fields.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"4 7","pages":"532-541"},"PeriodicalIF":12.0,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141565251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing human mobility research with open and standardized datasets 利用开放的标准化数据集加强人类流动性研究。

IF 12

Nature computational science Pub Date : 2024-07-02 DOI: 10.1038/s43588-024-00650-3

Takahiro Yabe, Massimiliano Luca, Kota Tsubouchi, Bruno Lepri, Marta C. Gonzalez, Esteban Moro

引用次数: 0

Software in science is ubiquitous yet overlooked 科学领域的软件无处不在，但却被忽视。

IF 12

Nature computational science Pub Date : 2024-07-01 DOI: 10.1038/s43588-024-00651-2

Alexandre Hocquet, Frédéric Wieber, Gabriele Gramelsberger, Konrad Hinsen, Markus Diesmann, Fernando Pasquini Santos, Catharina Landström, Benjamin Peters, Dawid Kasprowicz, Arianna Borrelli, Phillip Roth, Clarissa Ai Ling Lee, Alin Olteanu, Stefan Böschen

引用次数: 0

Promising directions of machine learning for partial differential equations 偏微分方程机器学习的发展方向。

IF 12

Nature computational science Pub Date : 2024-06-28 DOI: 10.1038/s43588-024-00643-2

Steven L. Brunton, J. Nathan Kutz

引用次数: 0

An invitation to social scientists 向社会科学家发出邀请。

IF 12

Nature computational science Pub Date : 2024-06-26 DOI: 10.1038/s43588-024-00656-x

引用次数: 0

The exciting potential and daunting challenge of using GPS human-mobility data for epidemic modeling 利用 GPS 人员流动数据进行流行病建模的巨大潜力和艰巨挑战。

IF 12

Nature computational science Pub Date : 2024-06-19 DOI: 10.1038/s43588-024-00637-0

Francisco Barreras, Duncan J. Watts

引用次数: 0

The whole picture in digital pathology 数字病理学的全貌

IF 12

Nature computational science Pub Date : 2024-06-19 DOI: 10.1038/s43588-024-00655-y

Ananya Rastogi

引用次数: 0