Pub Date : 2024-04-17DOI: 10.1038/s42256-024-00810-0
T. Li, L. Biferale, F. Bonaccorso, M. A. Scarpolini, M. Buzzicotti
Lagrangian turbulence lies at the core of numerous applied and fundamental problems related to the physics of dispersion and mixing in engineering, biofluids, the atmosphere, oceans and astrophysics. Despite exceptional theoretical, numerical and experimental efforts conducted over the past 30 years, no existing models are capable of faithfully reproducing statistical and topological properties exhibited by particle trajectories in turbulence. We propose a machine learning approach, based on a state-of-the-art diffusion model, to generate single-particle trajectories in three-dimensional turbulence at high Reynolds numbers, thereby bypassing the need for direct numerical simulations or experiments to obtain reliable Lagrangian data. Our model demonstrates the ability to reproduce most statistical benchmarks across time scales, including the fat-tail distribution for velocity increments, the anomalous power law and the increased intermittency around the dissipative scale. Slight deviations are observed below the dissipative scale, particularly in the acceleration and flatness statistics. Surprisingly, the model exhibits strong generalizability for extreme events, producing events of higher intensity and rarity that still match the realistic statistics. This paves the way for producing synthetic high-quality datasets for pretraining various downstream applications of Lagrangian turbulence. Modelling the statistical and geometrical properties of particle trajectories in turbulent flows is key to many scientific and technological applications. Li and colleagues introduce a data-driven diffusion model that can generate high-Reynolds-number Lagrangian turbulence trajectories with statistical properties consistent with those of the training set and even generalize to rare, intense events unseen during training.
{"title":"Synthetic Lagrangian turbulence by generative diffusion models","authors":"T. Li, L. Biferale, F. Bonaccorso, M. A. Scarpolini, M. Buzzicotti","doi":"10.1038/s42256-024-00810-0","DOIUrl":"10.1038/s42256-024-00810-0","url":null,"abstract":"Lagrangian turbulence lies at the core of numerous applied and fundamental problems related to the physics of dispersion and mixing in engineering, biofluids, the atmosphere, oceans and astrophysics. Despite exceptional theoretical, numerical and experimental efforts conducted over the past 30 years, no existing models are capable of faithfully reproducing statistical and topological properties exhibited by particle trajectories in turbulence. We propose a machine learning approach, based on a state-of-the-art diffusion model, to generate single-particle trajectories in three-dimensional turbulence at high Reynolds numbers, thereby bypassing the need for direct numerical simulations or experiments to obtain reliable Lagrangian data. Our model demonstrates the ability to reproduce most statistical benchmarks across time scales, including the fat-tail distribution for velocity increments, the anomalous power law and the increased intermittency around the dissipative scale. Slight deviations are observed below the dissipative scale, particularly in the acceleration and flatness statistics. Surprisingly, the model exhibits strong generalizability for extreme events, producing events of higher intensity and rarity that still match the realistic statistics. This paves the way for producing synthetic high-quality datasets for pretraining various downstream applications of Lagrangian turbulence. Modelling the statistical and geometrical properties of particle trajectories in turbulent flows is key to many scientific and technological applications. Li and colleagues introduce a data-driven diffusion model that can generate high-Reynolds-number Lagrangian turbulence trajectories with statistical properties consistent with those of the training set and even generalize to rare, intense events unseen during training.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":null,"pages":null},"PeriodicalIF":23.8,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s42256-024-00810-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140604216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-12DOI: 10.1038/s42256-024-00834-6
Michael Roberts, Alon Hazan, Sören Dittmer, James H. F. Rudd, Carola-Bibiane Schönlieb
{"title":"Publisher Correction: The curious case of the test set AUROC","authors":"Michael Roberts, Alon Hazan, Sören Dittmer, James H. F. Rudd, Carola-Bibiane Schönlieb","doi":"10.1038/s42256-024-00834-6","DOIUrl":"10.1038/s42256-024-00834-6","url":null,"abstract":"","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":null,"pages":null},"PeriodicalIF":23.8,"publicationDate":"2024-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s42256-024-00834-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140642062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-11DOI: 10.1038/s42256-024-00815-9
Ilia Igashov, Hannes Stärk, Clément Vignac, Arne Schneuing, Victor Garcia Satorras, Pascal Frossard, Max Welling, Michael Bronstein, Bruno Correia
Fragment-based drug discovery has been an effective paradigm in early-stage drug development. An open challenge in this area is designing linkers between disconnected molecular fragments of interest to obtain chemically relevant candidate drug molecules. In this work, we propose DiffLinker, an E(3)-equivariant three-dimensional conditional diffusion model for molecular linker design. Given a set of disconnected fragments, our model places missing atoms in between and designs a molecule incorporating all the initial fragments. Unlike previous approaches that are only able to connect pairs of molecular fragments, our method can link an arbitrary number of fragments. Additionally, the model automatically determines the number of atoms in the linker and its attachment points to the input fragments. We demonstrate that DiffLinker outperforms other methods on the standard datasets, generating more diverse and synthetically accessible molecules. We experimentally test our method in real-world applications, showing that it can successfully generate valid linkers conditioned on target protein pockets. Fragment-based molecular design uses chemical motifs and combines them into bio-active compounds. While this approach has grown in capability, molecular linker methods are restricted to linking fragments one by one, which makes the search for effective combinations harder. Igashov and colleagues use a conditional diffusion model to link multiple fragments in a one-shot generative process.
{"title":"Equivariant 3D-conditional diffusion model for molecular linker design","authors":"Ilia Igashov, Hannes Stärk, Clément Vignac, Arne Schneuing, Victor Garcia Satorras, Pascal Frossard, Max Welling, Michael Bronstein, Bruno Correia","doi":"10.1038/s42256-024-00815-9","DOIUrl":"10.1038/s42256-024-00815-9","url":null,"abstract":"Fragment-based drug discovery has been an effective paradigm in early-stage drug development. An open challenge in this area is designing linkers between disconnected molecular fragments of interest to obtain chemically relevant candidate drug molecules. In this work, we propose DiffLinker, an E(3)-equivariant three-dimensional conditional diffusion model for molecular linker design. Given a set of disconnected fragments, our model places missing atoms in between and designs a molecule incorporating all the initial fragments. Unlike previous approaches that are only able to connect pairs of molecular fragments, our method can link an arbitrary number of fragments. Additionally, the model automatically determines the number of atoms in the linker and its attachment points to the input fragments. We demonstrate that DiffLinker outperforms other methods on the standard datasets, generating more diverse and synthetically accessible molecules. We experimentally test our method in real-world applications, showing that it can successfully generate valid linkers conditioned on target protein pockets. Fragment-based molecular design uses chemical motifs and combines them into bio-active compounds. While this approach has grown in capability, molecular linker methods are restricted to linking fragments one by one, which makes the search for effective combinations harder. Igashov and colleagues use a conditional diffusion model to link multiple fragments in a one-shot generative process.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":null,"pages":null},"PeriodicalIF":23.8,"publicationDate":"2024-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s42256-024-00815-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140545020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-08DOI: 10.1038/s42256-024-00824-8
Xupeng Chen, Ran Wang, Amirhossein Khalilian-Gourtani, Leyao Yu, Patricia Dugan, Daniel Friedman, Werner Doyle, Orrin Devinsky, Yao Wang, Adeen Flinker
Decoding human speech from neural signals is essential for brain–computer interface (BCI) technologies that aim to restore speech in populations with neurological deficits. However, it remains a highly challenging task, compounded by the scarce availability of neural signals with corresponding speech, data complexity and high dimensionality. Here we present a novel deep learning-based neural speech decoding framework that includes an ECoG decoder that translates electrocorticographic (ECoG) signals from the cortex into interpretable speech parameters and a novel differentiable speech synthesizer that maps speech parameters to spectrograms. We have developed a companion speech-to-speech auto-encoder consisting of a speech encoder and the same speech synthesizer to generate reference speech parameters to facilitate the ECoG decoder training. This framework generates natural-sounding speech and is highly reproducible across a cohort of 48 participants. Our experimental results show that our models can decode speech with high correlation, even when limited to only causal operations, which is necessary for adoption by real-time neural prostheses. Finally, we successfully decode speech in participants with either left or right hemisphere coverage, which could lead to speech prostheses in patients with deficits resulting from left hemisphere damage. Recent research has focused on restoring speech in populations with neurological deficits. Chen, Wang et al. develop a framework for decoding speech from neural signals, which could lead to innovative speech prostheses.
{"title":"A neural speech decoding framework leveraging deep learning and speech synthesis","authors":"Xupeng Chen, Ran Wang, Amirhossein Khalilian-Gourtani, Leyao Yu, Patricia Dugan, Daniel Friedman, Werner Doyle, Orrin Devinsky, Yao Wang, Adeen Flinker","doi":"10.1038/s42256-024-00824-8","DOIUrl":"10.1038/s42256-024-00824-8","url":null,"abstract":"Decoding human speech from neural signals is essential for brain–computer interface (BCI) technologies that aim to restore speech in populations with neurological deficits. However, it remains a highly challenging task, compounded by the scarce availability of neural signals with corresponding speech, data complexity and high dimensionality. Here we present a novel deep learning-based neural speech decoding framework that includes an ECoG decoder that translates electrocorticographic (ECoG) signals from the cortex into interpretable speech parameters and a novel differentiable speech synthesizer that maps speech parameters to spectrograms. We have developed a companion speech-to-speech auto-encoder consisting of a speech encoder and the same speech synthesizer to generate reference speech parameters to facilitate the ECoG decoder training. This framework generates natural-sounding speech and is highly reproducible across a cohort of 48 participants. Our experimental results show that our models can decode speech with high correlation, even when limited to only causal operations, which is necessary for adoption by real-time neural prostheses. Finally, we successfully decode speech in participants with either left or right hemisphere coverage, which could lead to speech prostheses in patients with deficits resulting from left hemisphere damage. Recent research has focused on restoring speech in populations with neurological deficits. Chen, Wang et al. develop a framework for decoding speech from neural signals, which could lead to innovative speech prostheses.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":null,"pages":null},"PeriodicalIF":23.8,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s42256-024-00824-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140534290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-05DOI: 10.1038/s42256-024-00818-6
Taoyong Cui, Chenyu Tang, Mao Su, Shufei Zhang, Yuqiang Li, Lei Bai, Yuhan Dong, Xingao Gong, Wanli Ouyang
Machine learning interatomic potentials (MLIPs) describe the interactions between atoms in materials and molecules by learning them from a reference database generated by ab initio calculations. MLIPs can accurately and efficiently predict such interactions and have been applied to various fields of physical science. However, high-performance MLIPs rely on a large amount of labelled data, which are costly to obtain by ab initio calculations. Here we propose a geometric structure learning framework that leverages unlabelled configurations to improve the performance of MLIPs. Our framework consists of two stages: first, using classical molecular dynamics simulations to generate unlabelled configurations of the target molecular system; and second, applying geometry-enhanced self-supervised learning techniques, including masking, denoising and contrastive learning, to capture structural information. We evaluate our framework on various benchmarks ranging from small molecule datasets to complex periodic molecular systems with more types of elements. We show that our method significantly improves the accuracy and generalization of MLIPs with only a few additional computational costs and is compatible with different invariant or equivariant graph neural network architectures. Our method enhances MLIPs and advances the simulations of molecular systems. Using machine learning methods to model interatomic potentials enables molecular dynamics simulations with ab initio level accuracy at a relatively low computational cost, but requires a large number of labelled training data obtained through expensive ab initio computations. Cui and colleagues propose a geometric learning framework that leverages self-supervised learning pretraining to enhance existing machine learning based interatomic potential models at a negligible additional computational cost.
机器学习原子间势(MLIPs)通过学习由 ab initio 计算生成的参考数据库来描述材料和分子中原子间的相互作用。MLIPs 可以准确、高效地预测这种相互作用,已被应用于物理科学的各个领域。然而,高性能的 MLIPs 依赖于大量的标记数据,而通过 ab initio 计算获得这些数据的成本很高。在这里,我们提出了一个几何结构学习框架,利用未标记的构型来提高 MLIPs 的性能。我们的框架包括两个阶段:首先,利用经典分子动力学模拟生成目标分子系统的无标签构型;其次,应用几何增强型自监督学习技术,包括掩蔽、去噪和对比学习,以捕捉结构信息。我们在从小分子数据集到包含更多元素类型的复杂周期分子系统的各种基准上评估了我们的框架。我们的研究表明,我们的方法大大提高了 MLIPs 的准确性和泛化能力,只增加了少量计算成本,而且与不同的不变或等变图神经网络架构兼容。我们的方法增强了 MLIPs,推进了分子系统的模拟。
{"title":"Geometry-enhanced pretraining on interatomic potentials","authors":"Taoyong Cui, Chenyu Tang, Mao Su, Shufei Zhang, Yuqiang Li, Lei Bai, Yuhan Dong, Xingao Gong, Wanli Ouyang","doi":"10.1038/s42256-024-00818-6","DOIUrl":"10.1038/s42256-024-00818-6","url":null,"abstract":"Machine learning interatomic potentials (MLIPs) describe the interactions between atoms in materials and molecules by learning them from a reference database generated by ab initio calculations. MLIPs can accurately and efficiently predict such interactions and have been applied to various fields of physical science. However, high-performance MLIPs rely on a large amount of labelled data, which are costly to obtain by ab initio calculations. Here we propose a geometric structure learning framework that leverages unlabelled configurations to improve the performance of MLIPs. Our framework consists of two stages: first, using classical molecular dynamics simulations to generate unlabelled configurations of the target molecular system; and second, applying geometry-enhanced self-supervised learning techniques, including masking, denoising and contrastive learning, to capture structural information. We evaluate our framework on various benchmarks ranging from small molecule datasets to complex periodic molecular systems with more types of elements. We show that our method significantly improves the accuracy and generalization of MLIPs with only a few additional computational costs and is compatible with different invariant or equivariant graph neural network architectures. Our method enhances MLIPs and advances the simulations of molecular systems. Using machine learning methods to model interatomic potentials enables molecular dynamics simulations with ab initio level accuracy at a relatively low computational cost, but requires a large number of labelled training data obtained through expensive ab initio computations. Cui and colleagues propose a geometric learning framework that leverages self-supervised learning pretraining to enhance existing machine learning based interatomic potential models at a negligible additional computational cost.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":null,"pages":null},"PeriodicalIF":23.8,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140349295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-05DOI: 10.1038/s42256-024-00816-8
Adamo Young, Hannes Röst, Bo Wang
Tandem mass spectra capture fragmentation patterns that provide key structural information about molecules. Although mass spectrometry is applied in many areas, the vast majority of small molecules lack experimental reference spectra. For over 70 years, spectrum prediction has remained a key challenge in the field. Existing deep learning methods do not leverage global structure in the molecule, potentially resulting in difficulties when generalizing to new data. In this work we propose the MassFormer model for accurately predicting tandem mass spectra. MassFormer uses a graph transformer architecture to model long-distance relationships between atoms in the molecule. The transformer module is initialized with parameters obtained through a chemical pretraining task, then fine-tuned on spectral data. MassFormer outperforms competing approaches for spectrum prediction on multiple datasets and accurately models the effects of collision energy. Gradient-based attribution methods reveal that MassFormer can identify compositional relationships between peaks in the spectrum. When applied to spectrum identification problems, MassFormer generally surpasses the performance of existing prediction-based methods. Identifying compounds in tandem mass spectrometry requires extensive databases of known compounds or computational methods to simulate spectra for samples not found in databases. Simulating tandem mass spectra is still challenging, and long-range connections in particular are difficult to model for graph neural networks. Young and colleagues use a graph transformer model to learn patterns of long-distance relations between atoms and molecules.
{"title":"Tandem mass spectrum prediction for small molecules using graph transformers","authors":"Adamo Young, Hannes Röst, Bo Wang","doi":"10.1038/s42256-024-00816-8","DOIUrl":"10.1038/s42256-024-00816-8","url":null,"abstract":"Tandem mass spectra capture fragmentation patterns that provide key structural information about molecules. Although mass spectrometry is applied in many areas, the vast majority of small molecules lack experimental reference spectra. For over 70 years, spectrum prediction has remained a key challenge in the field. Existing deep learning methods do not leverage global structure in the molecule, potentially resulting in difficulties when generalizing to new data. In this work we propose the MassFormer model for accurately predicting tandem mass spectra. MassFormer uses a graph transformer architecture to model long-distance relationships between atoms in the molecule. The transformer module is initialized with parameters obtained through a chemical pretraining task, then fine-tuned on spectral data. MassFormer outperforms competing approaches for spectrum prediction on multiple datasets and accurately models the effects of collision energy. Gradient-based attribution methods reveal that MassFormer can identify compositional relationships between peaks in the spectrum. When applied to spectrum identification problems, MassFormer generally surpasses the performance of existing prediction-based methods. Identifying compounds in tandem mass spectrometry requires extensive databases of known compounds or computational methods to simulate spectra for samples not found in databases. Simulating tandem mass spectra is still challenging, and long-range connections in particular are difficult to model for graph neural networks. Young and colleagues use a graph transformer model to learn patterns of long-distance relations between atoms and molecules.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":null,"pages":null},"PeriodicalIF":23.8,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140349138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-05DOI: 10.1038/s42256-024-00823-9
Yanyi Chu, Dan Yu, Yupeng Li, Kaixuan Huang, Yue Shen, Le Cong, Jason Zhang, Mengdi Wang
The 5′ untranslated region (UTR), a regulatory region at the beginning of a messenger RNA (mRNA) molecule, plays a crucial role in regulating the translation process and affects the protein expression level. Language models have showcased their effectiveness in decoding the functions of protein and genome sequences. Here, we introduce a language model for 5′ UTR, which we refer to as the UTR-LM. The UTR-LM is pretrained on endogenous 5′ UTRs from multiple species and is further augmented with supervised information including secondary structure and minimum free energy. We fine-tuned the UTR-LM in a variety of downstream tasks. The model outperformed the best known benchmark by up to 5% for predicting the mean ribosome loading, and by up to 8% for predicting the translation efficiency and the mRNA expression level. The model was also applied to identifying unannotated internal ribosome entry sites within the untranslated region and improved the area under the precision–recall curve from 0.37 to 0.52 compared to the best baseline. Further, we designed a library of 211 new 5′ UTRs with high predicted values of translation efficiency and evaluated them via a wet-laboratory assay. Experiment results confirmed that our top designs achieved a 32.5% increase in protein production level relative to well-established 5′ UTRs optimized for therapeutics. The 5′ untranslated region is a critical regulatory region of mRNA, influencing gene expression regulation and translation. Chu, Yu and colleagues develop a language model for analysing untranslated regions of mRNA. The model, pretrained on data from diverse species, enhances the prediction of mRNA translation activities and has implications for new vaccine design.
{"title":"A 5′ UTR language model for decoding untranslated regions of mRNA and function predictions","authors":"Yanyi Chu, Dan Yu, Yupeng Li, Kaixuan Huang, Yue Shen, Le Cong, Jason Zhang, Mengdi Wang","doi":"10.1038/s42256-024-00823-9","DOIUrl":"10.1038/s42256-024-00823-9","url":null,"abstract":"The 5′ untranslated region (UTR), a regulatory region at the beginning of a messenger RNA (mRNA) molecule, plays a crucial role in regulating the translation process and affects the protein expression level. Language models have showcased their effectiveness in decoding the functions of protein and genome sequences. Here, we introduce a language model for 5′ UTR, which we refer to as the UTR-LM. The UTR-LM is pretrained on endogenous 5′ UTRs from multiple species and is further augmented with supervised information including secondary structure and minimum free energy. We fine-tuned the UTR-LM in a variety of downstream tasks. The model outperformed the best known benchmark by up to 5% for predicting the mean ribosome loading, and by up to 8% for predicting the translation efficiency and the mRNA expression level. The model was also applied to identifying unannotated internal ribosome entry sites within the untranslated region and improved the area under the precision–recall curve from 0.37 to 0.52 compared to the best baseline. Further, we designed a library of 211 new 5′ UTRs with high predicted values of translation efficiency and evaluated them via a wet-laboratory assay. Experiment results confirmed that our top designs achieved a 32.5% increase in protein production level relative to well-established 5′ UTRs optimized for therapeutics. The 5′ untranslated region is a critical regulatory region of mRNA, influencing gene expression regulation and translation. Chu, Yu and colleagues develop a language model for analysing untranslated regions of mRNA. The model, pretrained on data from diverse species, enhances the prediction of mRNA translation activities and has implications for new vaccine design.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":null,"pages":null},"PeriodicalIF":23.8,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140349287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-04DOI: 10.1038/s42256-024-00817-7
Michael Roberts, Alon Hazan, Sören Dittmer, James H. F. Rudd, Carola-Bibiane Schönlieb
The area under the receiver operating characteristic curve (AUROC) of the test set is used throughout machine learning (ML) for assessing a model’s performance. However, when concordance is not the only ambition, this gives only a partial insight into performance, masking distribution shifts of model outputs and model instability.
{"title":"The curious case of the test set AUROC","authors":"Michael Roberts, Alon Hazan, Sören Dittmer, James H. F. Rudd, Carola-Bibiane Schönlieb","doi":"10.1038/s42256-024-00817-7","DOIUrl":"10.1038/s42256-024-00817-7","url":null,"abstract":"The area under the receiver operating characteristic curve (AUROC) of the test set is used throughout machine learning (ML) for assessing a model’s performance. However, when concordance is not the only ambition, this gives only a partial insight into performance, masking distribution shifts of model outputs and model instability.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":null,"pages":null},"PeriodicalIF":23.8,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140346272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-04DOI: 10.1038/s42256-024-00822-w
Tao Xu, Haoyuan Shi, Wanling Gao, Xiaosong Wang, Zhenyu Yue
Conditional domain adversarial learning presents a promising approach for enhancing the generalizability of deep learning-based methods. Inspired by the efficacy of conditional domain adversarial networks, Bai and colleagues introduced DrugBAN, a methodology designed to explicitly learn pairwise local interactions between drugs and targets. DrugBAN leverages drug molecular graphs and target protein sequences, employing conditional domain adversarial networks to improve the ability to adapt to out-of-distribution data and thereby ensuring superior prediction accuracy for new drug–target pairs. Here we examine the reusability of DrugBAN and extend the evaluation of its generalizability across a wider range of biomedical contexts beyond the original datasets. Various clustering-based strategies are implemented to resplit the source and target domains to assess the robustness of DrugBAN. We also apply this cross-domain adaptation technique to the prediction of cell line–drug responses and mutation–drug associations. The analysis serves as a stepping-off point to better understand and establish a general template applicable to link prediction tasks in biomedical bipartite networks. In early 2023, Bai and colleagues presented DrugBAN, an interpretable method for drug–target prediction. In this Reusability Report, Xu and colleagues reproduce the original findings and provide a careful exploration of cross-domain adaptability.
{"title":"Reusability report: Uncovering associations in biomedical bipartite networks via a bilinear attention network with domain adaptation","authors":"Tao Xu, Haoyuan Shi, Wanling Gao, Xiaosong Wang, Zhenyu Yue","doi":"10.1038/s42256-024-00822-w","DOIUrl":"10.1038/s42256-024-00822-w","url":null,"abstract":"Conditional domain adversarial learning presents a promising approach for enhancing the generalizability of deep learning-based methods. Inspired by the efficacy of conditional domain adversarial networks, Bai and colleagues introduced DrugBAN, a methodology designed to explicitly learn pairwise local interactions between drugs and targets. DrugBAN leverages drug molecular graphs and target protein sequences, employing conditional domain adversarial networks to improve the ability to adapt to out-of-distribution data and thereby ensuring superior prediction accuracy for new drug–target pairs. Here we examine the reusability of DrugBAN and extend the evaluation of its generalizability across a wider range of biomedical contexts beyond the original datasets. Various clustering-based strategies are implemented to resplit the source and target domains to assess the robustness of DrugBAN. We also apply this cross-domain adaptation technique to the prediction of cell line–drug responses and mutation–drug associations. The analysis serves as a stepping-off point to better understand and establish a general template applicable to link prediction tasks in biomedical bipartite networks. In early 2023, Bai and colleagues presented DrugBAN, an interpretable method for drug–target prediction. In this Reusability Report, Xu and colleagues reproduce the original findings and provide a careful exploration of cross-domain adaptability.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":null,"pages":null},"PeriodicalIF":23.8,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140346228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-01DOI: 10.1038/s42256-024-00814-w
Dylan S. Shah, Joshua P. Powers, Liana G. Tilton, Sam Kriegman, Josh Bongard, Rebecca Kramer-Bottiglio
{"title":"Author Correction: A soft robot that adapts to environments through shape change","authors":"Dylan S. Shah, Joshua P. Powers, Liana G. Tilton, Sam Kriegman, Josh Bongard, Rebecca Kramer-Bottiglio","doi":"10.1038/s42256-024-00814-w","DOIUrl":"10.1038/s42256-024-00814-w","url":null,"abstract":"","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":null,"pages":null},"PeriodicalIF":23.8,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s42256-024-00814-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140642053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}