The calculation of electron–phonon couplings (EPCs) is essential for understanding various fundamental physical properties, including electrical transport, optical and superconducting behaviors in materials. However, obtaining EPCs through fully first-principles methods is notably challenging, particularly for large systems or when employing advanced functionals. Here we introduce a machine learning framework to accelerate EPC calculations by utilizing atomic orbital-based Hamiltonian matrices and gradients predicted by an equivariant graph neural network. We demonstrate that our method not only yields EPC values in close agreement with first-principles results but also enhances calculation efficiency by several orders of magnitude. Application to GaAs using the Heyd–Scuseria–Ernzerhof functional reveals the necessity of advanced functionals for accurate carrier mobility predictions, while for the large Kagome crystal CsV3Sb5, our framework reproduces the experimentally observed double domes in pressure-induced superconducting phase diagrams. This machine learning framework offers a powerful and efficient tool for the investigation of diverse EPC-related phenomena in complex materials. A machine learning framework is proposed to accurately predict electron–phonon coupling (EPC) strengths while reducing computational costs compared with first-principles methods. This approach facilitates EPC calculations with advanced functionals, allowing the accurate determination of real-world material properties such as carrier mobility and superconductivity.
{"title":"Accelerating the calculation of electron–phonon coupling strength with machine learning","authors":"Yang Zhong, Shixu Liu, Binhua Zhang, Zhiguo Tao, Yuting Sun, Weibin Chu, Xin-Gao Gong, Ji-Hui Yang, Hongjun Xiang","doi":"10.1038/s43588-024-00668-7","DOIUrl":"10.1038/s43588-024-00668-7","url":null,"abstract":"The calculation of electron–phonon couplings (EPCs) is essential for understanding various fundamental physical properties, including electrical transport, optical and superconducting behaviors in materials. However, obtaining EPCs through fully first-principles methods is notably challenging, particularly for large systems or when employing advanced functionals. Here we introduce a machine learning framework to accelerate EPC calculations by utilizing atomic orbital-based Hamiltonian matrices and gradients predicted by an equivariant graph neural network. We demonstrate that our method not only yields EPC values in close agreement with first-principles results but also enhances calculation efficiency by several orders of magnitude. Application to GaAs using the Heyd–Scuseria–Ernzerhof functional reveals the necessity of advanced functionals for accurate carrier mobility predictions, while for the large Kagome crystal CsV3Sb5, our framework reproduces the experimentally observed double domes in pressure-induced superconducting phase diagrams. This machine learning framework offers a powerful and efficient tool for the investigation of diverse EPC-related phenomena in complex materials. A machine learning framework is proposed to accurately predict electron–phonon coupling (EPC) strengths while reducing computational costs compared with first-principles methods. This approach facilitates EPC calculations with advanced functionals, allowing the accurate determination of real-world material properties such as carrier mobility and superconductivity.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":null,"pages":null},"PeriodicalIF":12.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141908581","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}
Pub Date : 2024-08-08DOI: 10.1038/s43588-024-00680-x
A machine learning framework that uses atomic orbital-based Hamiltonian matrices and gradients predicted by an equivariant graph neural network is established to calculate electron–phonon coupling (EPC). This approach accelerates the calculations by several orders of magnitude, enabling EPC-related properties to be predicted for complex systems using highly accurate functionals.
{"title":"A machine learning tool to efficiently calculate electron–phonon coupling","authors":"","doi":"10.1038/s43588-024-00680-x","DOIUrl":"10.1038/s43588-024-00680-x","url":null,"abstract":"A machine learning framework that uses atomic orbital-based Hamiltonian matrices and gradients predicted by an equivariant graph neural network is established to calculate electron–phonon coupling (EPC). This approach accelerates the calculations by several orders of magnitude, enabling EPC-related properties to be predicted for complex systems using highly accurate functionals.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":null,"pages":null},"PeriodicalIF":12.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141908856","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}
Pub Date : 2024-07-30DOI: 10.1038/s43588-024-00670-z
We look back on the discovery of oxygen in light of its upcoming milestone anniversary and highlight the computational contributions to oxygen reduction and evolution in chemistry.
{"title":"250 years of oxygen chemistry","authors":"","doi":"10.1038/s43588-024-00670-z","DOIUrl":"10.1038/s43588-024-00670-z","url":null,"abstract":"We look back on the discovery of oxygen in light of its upcoming milestone anniversary and highlight the computational contributions to oxygen reduction and evolution in chemistry.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":null,"pages":null},"PeriodicalIF":12.0,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s43588-024-00670-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141857318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-30DOI: 10.1038/s43588-024-00681-w
Christian Gaser, Polona Kalc, James H. Cole
{"title":"Publisher Correction: A perspective on brain-age estimation and its clinical promise","authors":"Christian Gaser, Polona Kalc, James H. Cole","doi":"10.1038/s43588-024-00681-w","DOIUrl":"10.1038/s43588-024-00681-w","url":null,"abstract":"","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":null,"pages":null},"PeriodicalIF":12.0,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s43588-024-00681-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141857317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-30DOI: 10.1038/s43588-024-00664-x
De-en Jiang
Since the first isolation of oxygen, chemists have explored oxygen reduction and evolution reactions. Now, computational chemists are trying to understand and predict the best catalysts for them. Here, the importance of various considerations for such calculations, as well as their challenges and opportunities, are discussed.
{"title":"Computational electrochemistry of oxygen 250 years after Priestley","authors":"De-en Jiang","doi":"10.1038/s43588-024-00664-x","DOIUrl":"10.1038/s43588-024-00664-x","url":null,"abstract":"Since the first isolation of oxygen, chemists have explored oxygen reduction and evolution reactions. Now, computational chemists are trying to understand and predict the best catalysts for them. Here, the importance of various considerations for such calculations, as well as their challenges and opportunities, are discussed.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":null,"pages":null},"PeriodicalIF":12.0,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141857319","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}
Pub Date : 2024-07-24DOI: 10.1038/s43588-024-00659-8
Christian Gaser, Polona Kalc, James H. Cole
Brain-age estimation has gained increased attention in the neuroscientific community owing to its potential use as a biomarker of brain health. The difference between estimated and chronological age based on neuroimaging data enables a unique perspective on brain development and aging, with multiple open questions still remaining in the brain-age research field. This Perspective presents an overview of current advancements in the field and envisions the future evolution of the brain-age framework before its potential deployment in hospital settings. Brain-age estimation is gaining attention as a biomarker for brain health as it provides a unique perspective on aging. This Perspective reviews current advancements and future directions to ensure deployment in hospital settings.
{"title":"A perspective on brain-age estimation and its clinical promise","authors":"Christian Gaser, Polona Kalc, James H. Cole","doi":"10.1038/s43588-024-00659-8","DOIUrl":"10.1038/s43588-024-00659-8","url":null,"abstract":"Brain-age estimation has gained increased attention in the neuroscientific community owing to its potential use as a biomarker of brain health. The difference between estimated and chronological age based on neuroimaging data enables a unique perspective on brain development and aging, with multiple open questions still remaining in the brain-age research field. This Perspective presents an overview of current advancements in the field and envisions the future evolution of the brain-age framework before its potential deployment in hospital settings. Brain-age estimation is gaining attention as a biomarker for brain health as it provides a unique perspective on aging. This Perspective reviews current advancements and future directions to ensure deployment in hospital settings.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":null,"pages":null},"PeriodicalIF":12.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141763150","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}
Pub Date : 2024-07-19DOI: 10.1038/s43588-024-00658-9
Jiancheng Yang
To address the challenge of pretraining foundational models with large datasets, a multi-task approach is proposed, thus helping to overcome the data scarcity problem in biomedical imaging.
{"title":"Multi-task learning for medical foundation models","authors":"Jiancheng Yang","doi":"10.1038/s43588-024-00658-9","DOIUrl":"10.1038/s43588-024-00658-9","url":null,"abstract":"To address the challenge of pretraining foundational models with large datasets, a multi-task approach is proposed, thus helping to overcome the data scarcity problem in biomedical imaging.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":null,"pages":null},"PeriodicalIF":12.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141728401","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}
Pub Date : 2024-07-19DOI: 10.1038/s43588-024-00666-9
Pretraining powerful deep learning models requires large, comprehensive training datasets, which are often unavailable for medical imaging. In response, the universal biomedical pretrained (UMedPT) foundational model was developed based on multiple small and medium-sized datasets. This model reduced the amount of data required to learn new target tasks by at least 50%.
{"title":"A multi-task learning strategy to pretrain models for medical image analysis","authors":"","doi":"10.1038/s43588-024-00666-9","DOIUrl":"10.1038/s43588-024-00666-9","url":null,"abstract":"Pretraining powerful deep learning models requires large, comprehensive training datasets, which are often unavailable for medical imaging. In response, the universal biomedical pretrained (UMedPT) foundational model was developed based on multiple small and medium-sized datasets. This model reduced the amount of data required to learn new target tasks by at least 50%.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":null,"pages":null},"PeriodicalIF":12.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141728533","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}
Pub Date : 2024-07-19DOI: 10.1038/s43588-024-00662-z
Raphael Schäfer, Till Nicke, Henning Höfener, Annkristin Lange, Dorit Merhof, Friedrich Feuerhake, Volkmar Schulz, Johannes Lotz, Fabian Kiessling
Foundational models, pretrained on a large scale, have demonstrated substantial success across non-medical domains. However, training these models typically requires large, comprehensive datasets, which contrasts with the smaller and more specialized datasets common in biomedical imaging. Here we propose a multi-task learning strategy that decouples the number of training tasks from memory requirements. We trained a universal biomedical pretrained model (UMedPT) on a multi-task database including tomographic, microscopic and X-ray images, with various labeling strategies such as classification, segmentation and object detection. The UMedPT foundational model outperformed ImageNet pretraining and previous state-of-the-art models. For classification tasks related to the pretraining database, it maintained its performance with only 1% of the original training data and without fine-tuning. For out-of-domain tasks it required only 50% of the original training data. In an external independent validation, imaging features extracted using UMedPT proved to set a new standard for cross-center transferability. UMedPT, a foundational model for biomedical imaging, has been trained on a variety of medical tasks with different types of label. It has achieved high performance with less training data in various clinical applications.
经过大规模预训练的基础模型在非医疗领域取得了巨大成功。然而,训练这些模型通常需要大型、全面的数据集,这与生物医学成像中常见的更小、更专业的数据集形成了鲜明对比。在这里,我们提出了一种多任务学习策略,将训练任务的数量与内存要求分离开来。我们在一个多任务数据库上训练了一个通用生物医学预训练模型(UMedPT),该数据库包括断层扫描、显微镜和 X 射线图像,并采用了分类、分割和对象检测等多种标记策略。UMedPT 基础模型的表现优于 ImageNet 预训练模型和以前的先进模型。对于与预训练数据库相关的分类任务,只需使用 1%的原始训练数据,无需微调即可保持性能。对于域外任务,它只需要原始训练数据的 50%。在外部独立验证中,使用 UMedPT 提取的成像特征被证明是跨中心可转移性的新标准。
{"title":"Overcoming data scarcity in biomedical imaging with a foundational multi-task model","authors":"Raphael Schäfer, Till Nicke, Henning Höfener, Annkristin Lange, Dorit Merhof, Friedrich Feuerhake, Volkmar Schulz, Johannes Lotz, Fabian Kiessling","doi":"10.1038/s43588-024-00662-z","DOIUrl":"10.1038/s43588-024-00662-z","url":null,"abstract":"Foundational models, pretrained on a large scale, have demonstrated substantial success across non-medical domains. However, training these models typically requires large, comprehensive datasets, which contrasts with the smaller and more specialized datasets common in biomedical imaging. Here we propose a multi-task learning strategy that decouples the number of training tasks from memory requirements. We trained a universal biomedical pretrained model (UMedPT) on a multi-task database including tomographic, microscopic and X-ray images, with various labeling strategies such as classification, segmentation and object detection. The UMedPT foundational model outperformed ImageNet pretraining and previous state-of-the-art models. For classification tasks related to the pretraining database, it maintained its performance with only 1% of the original training data and without fine-tuning. For out-of-domain tasks it required only 50% of the original training data. In an external independent validation, imaging features extracted using UMedPT proved to set a new standard for cross-center transferability. UMedPT, a foundational model for biomedical imaging, has been trained on a variety of medical tasks with different types of label. It has achieved high performance with less training data in various clinical applications.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":null,"pages":null},"PeriodicalIF":12.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11288886/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141728402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}