Advanced search

Filter By:

Journal Check one or more journals to show results from those journals only.

Choose more journals

Article type Check one or more article types to show results from those article types only.
Subject Check one or more subjects to show results from those subjects only.
Date Choose a date option to show results from those dates only.

Custom date range

Clear all filters
Sort by:
Showing 1–28 of 28 results
Advanced filters: Author: Jason Hein Clear advanced filters

  • Federated learning (FL) algorithms have emerged as a promising solution to train models for healthcare imaging across institutions while preserving privacy. Here, the authors describe the Federated Tumor Segmentation (FeTS) challenge for the decentralised benchmarking of FL algorithms and evaluation of Healthcare AI algorithm generalizability in real-world cancer imaging datasets.

    • Maximilian Zenk
    • Ujjwal Baid
    • Spyridon Bakas
    ResearchOpen Access
    Nature Communications
    Volume: 16, P: 1-20

  • The true promise of automation lies not in throughput, but in the new kind of researcher it enables, argues Jason Hein.

    • Jason Hein
    Comments & Opinion
    Nature Chemical Engineering
    Volume: 2, P: 276

  • The use of a universal chemical programming language (χDL) to encode and execute synthesis procedures for a variety of chemical reactions is reported, including reductive amination, ring formation, esterification, carbon–carbon bond formation and amide coupling. These procedures are validated and repeated in two international laboratories and on three independent robots.

    • Robert Rauschen
    • Mason Guy
    • Leroy Cronin
    Research
    Nature Synthesis
    Volume: 3, P: 488-496

  • Directed evolution is a powerful method to optimize protein fitness. Here, authors develop an active learning workflow using machine learning to more efficiently explore the design space of proteins.

    • Jason Yang
    • Ravi G. Lal
    • Frances H. Arnold
    ResearchOpen Access
    Nature Communications
    Volume: 16, P: 1-12

  • Federated ML (FL) provides an alternative to train accurate and generalizable ML models, by only sharing numerical model updates. Here, the authors present the largest FL study to-date to generate an automatic tumor boundary detector for glioblastoma.

    • Sarthak Pati
    • Ujjwal Baid
    • Spyridon Bakas
    ResearchOpen Access
    Nature Communications
    Volume: 13, P: 1-17

  • The Suzuki-Miyaura coupling (SMC) is widely used in C-C bond forming reactions but the dominant mode of transmetalation remains controversial. Here the authors report a mechanistic study of a Pd catalyzed SMC under biphasic conditions where using phase transfer catalysts shifts the dominant mode of transmetalation resulting in rate enhancement.

    • Yao Shi
    • Joshua S. Derasp
    • Jason E. Hein
    ResearchOpen Access
    Nature Communications
    Volume: 15, P: 1-12

  • An accessible machine-learning tool has been developed that can accelerate the optimization of a wide range of synthetic reactions — and reveals how cognitive bias might have undermined optimization by humans.

    • Jason E. Hein
    News & Views
    Nature
    Volume: 590, P: 40-41

  • Though tractography is widely used, it has not been systematically validated. Here, authors report results from 20 groups showing that many tractography algorithms produce both valid and invalid bundles.

    • Klaus H. Maier-Hein
    • Peter F. Neher
    • Maxime Descoteaux
    ResearchOpen Access
    Nature Communications
    Volume: 8, P: 1-13

  • The phenomenon of „ring-walking‟, wherein a metal catalyst remains bound to a pi system as it migrates to another coupling site, is supported largely by circumstantial evidence. Here the authors perform an in-depth kinetic study of Buchwald- Hartwig animations with several catalytic systems delineating the phenomenon of ring walking from diffusion-controlled coupling.

    • Madeleine C. Deem
    • Joshua S. Derasp
    • Jason E. Hein
    ResearchOpen Access
    Nature Communications
    Volume: 13, P: 1-11

  • Association analysis identifies 65 new breast cancer risk loci, predicts target genes for known risk loci and demonstrates a strong overlap with somatic driver genes in breast tumours.

    • Kyriaki Michailidou
    • Sara Lindström
    • Douglas F. Easton
    Research
    Nature
    Volume: 551, P: 92-94

  • Bayesian optimization is applied in chemical synthesis towards the optimization of various organic reactions and is found to outperform scientists in both average optimization efficiency and consistency.

    • Benjamin J. Shields
    • Jason Stevens
    • Abigail G. Doyle
    Research
    Nature
    Volume: 590, P: 89-96

  • A study of SARS-CoV-2 variants examining their transmission, infectivity, and potential resistance to therapies provides insights into the biology of the Delta variant and its role in the global pandemic.

    • Petra Mlcochova
    • Steven A. Kemp
    • Ravindra K. Gupta
    ResearchOpen Access
    Nature
    Volume: 599, P: 114-119

  • Roger Milne and colleagues conduct a genome-wide association study for estrogen receptor (ER)-negative breast cancer combined with BRCA1 mutation carriers in a large cohort. They identify ten new risk variants and find high genetic correlation between breast cancer risk for BRCA1 mutation carriers and risk of ER-negative breast cancer in the general population.

    • Roger L Milne
    • Karoline B Kuchenbaecker
    • Jacques Simard
    Research
    Nature Genetics
    Volume: 49, P: 1767-1778

  • Previous studies identified an association between the 2q35 locus and breast cancer. Here, the authors show that a SNP at 2q35, rs4442975, is associated with oestrogen receptor positive disease and suggest that this effect is mediated through the downregulation of a known breast cancer gene, IGFBP5.

    • Maya Ghoussaini
    • Stacey L. Edwards
    • Anna De Fazio
    Research
    Nature Communications
    Volume: 5, P: 1-12

  • Anion recognition in competitive, aqueous media remains a critical challenge. Bulk and local solvation models for anion recognition events are herein explored, as well as targeted design approaches to retain strong anion binding in highly polar media.

    • Sophie C. Patrick
    • Paul D. Beer
    • Jason J. Davis
    Reviews
    Nature Reviews Chemistry
    Volume: 8, P: 256-276

  • A drawback of recently reported prebiotic routes to RNA is a requirement for enantioenriched reactants. Here, the presence of a slightly enantioenriched amino acid in the reaction mixture is shown to drive the formation of enantiopure RNA precursors. This provides a plausible scenario in which single-handed biological molecules were formed prior to the emergence of self-replicating informational polymers.

    • Jason E. Hein
    • Eric Tse
    • Donna G. Blackmond
    Research
    Nature Chemistry
    Volume: 3, P: 704-706

  • The spike protein of the Omicron variant of SARS-CoV-2 has a higher affinity for ACE2 than Delta, and a marked change in its antigenicity increases Omicron’s evasion of therapeutic and vaccine-elicited neutralizing antibodies.

    • Bo Meng
    • Adam Abdullahi
    • Ravindra K. Gupta
    ResearchOpen Access
    Nature
    Volume: 603, P: 706-714

  • Automation and real-time reaction monitoring have enabled data-rich experimentation, which is critically important in navigating the complexities of chemical synthesis. Linking real-time analysis with machine learning and artificial intelligence tools provides the opportunity to accelerate the identification of optimal reaction conditions and facilitate error-free autonomous synthesis. This Comment provides a viewpoint underscoring the growing significance of data-rich experiments and interdisciplinary approaches in driving future progress in synthetic chemistry.

    • Junliang Liu
    • Jason E. Hein
    Comments & Opinion
    Nature Synthesis
    Volume: 2, P: 464-466

  • Automated experiments can accelerate research and development. ‘Flexible automation’ enables the cost- and time-effective design, construction and reconfiguration of automated experiments. Flexible automation is empowering researchers to deploy new science and technology faster than ever before.

    • Benjamin P. MacLeod
    • Fraser G. L. Parlane
    • Curtis P. Berlinguette
    Comments & Opinion
    Nature Materials
    Volume: 21, P: 722-726

  • An automated closed-loop system optimizes a stereoselective Suzuki-Miyaura reaction using a machine learning algorithm that incorporates unbiased and categorical process parameters.

    • Melodie Christensen
    • Lars P. E. Yunker
    • Jason E. Hein
    ResearchOpen Access
    Communications Chemistry
    Volume: 4, P: 1-12