GSTDTAP

浏览/检索结果: 共58条,第1-10条 帮助

限定条件    
已选(0)清除 条数/页:   排序方式:
International evaluation of an AI system for breast cancer screening 期刊论文
NATURE, 2020, 577 (7788) : 89-+
作者:  McKinney, Scott Mayer;  Sieniek, Marcin;  Godbole, Varun;  Godwin, Jonathan;  Antropova, Natasha;  Ashrafian, Hutan;  Back, Trevor;  Chesus, Mary;  Corrado, Greg C.;  Darzi, Ara;  Etemadi, Mozziyar;  Garcia-Vicente, Florencia;  Gilbert, Fiona J.;  Halling-Brown, Mark;  Hassabis, Demis;  Jansen, Sunny;  Karthikesalingam, Alan;  Kelly, Christopher J.;  King, Dominic;  Ledsam, Joseph R.;  Melnick, David;  Mostofi, Hormuz;  Peng, Lily;  Reicher, Joshua Jay;  Romera-Paredes, Bernardino;  Sidebottom, Richard;  Suleyman, Mustafa;  Tse, Daniel;  Young, Kenneth C.;  De Fauw, Jeffrey;  Shetty, Shravya
收藏  |  浏览/下载:15/0  |  提交时间:2020/07/03

Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful(1). Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives(2). Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening.


  
EXPRESSION OF DOUBT 期刊论文
NATURE, 2020, 578 (7796) : 502-504
作者:  Benton, Donald J.;  Gamblin, Steven J.;  Rosenthal, Peter B.;  Skehel, John J.
收藏  |  浏览/下载:4/0  |  提交时间:2020/07/03

Although AI companies market software for recognizing emotions in faces, psychologists debate whether expressions can be read so easily.


Although AI companies market software for recognizing emotions in faces, psychologists debate whether expressions can be read so easily.


  
Editorial Expression of Concern: Exploring the quantum speed limit with computer games 期刊论文
NATURE, 2020, 581 (7808) : E7-E7
作者:  Friedman, Joseph;  York, Hunter;  Graetz, Nicholas;  Woyczynski, Lauren;  Whisnant, Joanna;  Hay, Simon I.;  Gakidou, Emmanuela
收藏  |  浏览/下载:1/0  |  提交时间:2020/07/03
Structure of M-pro from SARS-CoV-2 and discovery of its inhibitors 期刊论文
NATURE, 2020, 582 (7811) : 289-+
作者:  Li, Nan;  Jasanoff, Alan
收藏  |  浏览/下载:10/0  |  提交时间:2020/07/03

A programme of structure-assisted drug design and high-throughput screening identifies six compounds that inhibit the main protease of SARS-CoV-2, demonstrating the ability of this strategy to isolate drug leads with clinical potential.


A new coronavirus, known as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is the aetiological agent responsible for the 2019-2020 viral pneumonia outbreak of coronavirus disease 2019 (COVID-19)(1-4). Currently, there are no targeted therapeutic agents for the treatment of this disease, and effective treatment options remain very limited. Here we describe the results of a programme that aimed to rapidly discover lead compounds for clinical use, by combining structure-assisted drug design, virtual drug screening and high-throughput screening. This programme focused on identifying drug leads that target main protease (M-pro) of SARS-CoV-2: M-pro is a key enzyme of coronaviruses and has a pivotal role in mediating viral replication and transcription, making it an attractive drug target for SARS-CoV-2(5,6). We identified a mechanism-based inhibitor (N3) by computer-aided drug design, and then determined the crystal structure of M-pro of SARS-CoV-2 in complex with this compound. Through a combination of structure-based virtual and high-throughput screening, we assayed more than 10,000 compounds-including approved drugs, drug candidates in clinical trials and other pharmacologically active compounds-as inhibitors of M-pro. Six of these compounds inhibited M-pro, showing half-maximal inhibitory concentration values that ranged from 0.67 to 21.4 mu M. One of these compounds (ebselen) also exhibited promising antiviral activity in cell-based assays. Our results demonstrate the efficacy of our screening strategy, which can lead to the rapid discovery of drug leads with clinical potential in response to new infectious diseases for which no specific drugs or vaccines are available.


  
Operation of a silicon quantum processor unit cell above one kelvin 期刊论文
NATURE, 2020, 580 (7803) : 350-+
作者:  Han, Kyuho;  Pierce, Sarah E.;  Li, Amy;  Spees, Kaitlyn;  Anderson, Grace R.;  Seoane, Jose A.;  Lo, Yuan-Hung;  Dubreuil, Michael;  Olivas, Micah;  Kamber, Roarke A.;  Wainberg, Michael;  Kostyrko, Kaja;  Kelly, Marcus R.;  Yousefi, Maryam;  Simpkins, Scott W.;  Yao, David
收藏  |  浏览/下载:8/0  |  提交时间:2020/07/03

Quantum computers are expected to outperform conventional computers in several important applications, from molecular simulation to search algorithms, once they can be scaled up to large numbers-typically millions-of quantum bits (qubits)(1-3). For most solid-state qubit technologies-for example, those using superconducting circuits or semiconductor spins-scaling poses a considerable challenge because every additional qubit increases the heat generated, whereas the cooling power of dilution refrigerators is severely limited at their operating temperature (less than 100 millikelvin)(4-6). Here we demonstrate the operation of a scalable silicon quantum processor unit cell comprising two qubits confined to quantum dots at about 1.5 kelvin. We achieve this by isolating the quantum dots from the electron reservoir, and then initializing and reading the qubits solely via tunnelling of electrons between the two quantum dots(7-9). We coherently control the qubits using electrically driven spin resonance(10,11) in isotopically enriched silicon(12 28)Si, attaining single-qubit gate fidelities of 98.6 per cent and a coherence time of 2 microseconds during '  hot'  operation, comparable to those of spin qubits in natural silicon at millikelvin temperatures(13-16). Furthermore, we show that the unit cell can be operated at magnetic fields as low as 0.1 tesla, corresponding to a qubit control frequency of 3.5 gigahertz, where the qubit energy is well below the thermal energy. The unit cell constitutes the core building block of a full-scale silicon quantum computer and satisfies layout constraints required by error-correction architectures(8),(17). Our work indicates that a spin-based quantum computer could be operated at increased temperatures in a simple pumped He-4 system (which provides cooling power orders of magnitude higher than that of dilution refrigerators), thus potentially enabling the integration of classical control electronics with the qubit array(18,19).


  
An open-source drug discovery platform enables ultra-large virtual screens 期刊论文
NATURE, 2020, 580 (7805) : 663-+
作者:  Peron, Simon;  Pancholi, Ravi;  Voelcker, Bettina;  Wittenbach, Jason D.;  olafsdottir, H. Freyja;  Freeman, Jeremy;  Svoboda, Karel
收藏  |  浏览/下载:33/0  |  提交时间:2020/07/03

VirtualFlow, an open-source drug discovery platform, enables the efficient preparation and virtual screening of ultra-large ligand libraries to identify molecules that bind with high affinity to target proteins.


On average, an approved drug currently costs US$2-3 billion and takes more than 10 years to develop(1). In part, this is due to expensive and time-consuming wet-laboratory experiments, poor initial hit compounds and the high attrition rates in the (pre-)clinical phases. Structure-based virtual screening has the potential to mitigate these problems. With structure-based virtual screening, the quality of the hits improves with the number of compounds screened(2). However, despite the fact that large databases of compounds exist, the ability to carry out large-scale structure-based virtual screening on computer clusters in an accessible, efficient and flexible manner has remained difficult. Here we describe VirtualFlow, a highly automated and versatile open-source platform with perfect scaling behaviour that is able to prepare and efficiently screen ultra-large libraries of compounds. VirtualFlow is able to use a variety of the most powerful docking programs. Using VirtualFlow, we prepared one of the largest and freely available ready-to-dock ligand libraries, with more than 1.4 billion commercially available molecules. To demonstrate the power of VirtualFlow, we screened more than 1 billion compounds and identified a set of structurally diverse molecules that bind to KEAP1 with submicromolar affinity. One of the lead inhibitors (iKeap1) engages KEAP1 with nanomolar affinity (dissociation constant (K-d) = 114 nM) and disrupts the interaction between KEAP1 and the transcription factor NRF2. This illustrates the potential of VirtualFlow to access vast regions of the chemical space and identify molecules that bind with high affinity to target proteins.


  
An engineered PET depolymerase to break down and recycle plastic bottles 期刊论文
NATURE, 2020, 580 (7802) : 216-+
作者:  Zhao, Evan Wenbo;  Liu, Tao;  Jonsson, Erlendur;  Lee, Jeongjae;  Temprano, Israel;  Jethwa, Rajesh B.;  Wang, Anqi;  Smith, Holly;  Carretero-Gonzalez, Javier;  Song, Qilei;  Grey, Clare P.
收藏  |  浏览/下载:86/0  |  提交时间:2020/07/03

Present estimates suggest that of the 359 million tons of plastics produced annually worldwide(1), 150-200 million tons accumulate in landfill or in the natural environment(2). Poly(ethylene terephthalate) (PET) is the most abundant polyester plastic, with almost 70 million tons manufactured annually worldwide for use in textiles and packaging(3). The main recycling process for PET, via thermomechanical means, results in a loss of mechanical properties(4). Consequently, de novo synthesis is preferred and PET waste continues to accumulate. With a high ratio of aromatic terephthalate units-which reduce chain mobility-PET is a polyester that is extremely difficult to hydrolyse(5). Several PET hydrolase enzymes have been reported, but show limited productivity(6,7). Here we describe an improved PET hydrolase that ultimately achieves, over 10 hours, a minimum of 90 per cent PET depolymerization into monomers, with a productivity of 16.7 grams of terephthalate per litre per hour (200 grams per kilogram of PET suspension, with an enzyme concentration of 3 milligrams per gram of PET). This highly efficient, optimized enzyme outperforms all PET hydrolases reported so far, including an enzyme(8,9) from the bacterium Ideonella sakaiensis strain 201-F6 (even assisted by a secondary enzyme(10)) and related improved variants(11-14) that have attracted recent interest. We also show that biologically recycled PET exhibiting the same properties as petrochemical PET can be produced from enzymatically depolymerized PET waste, before being processed into bottles, thereby contributing towards the concept of a circular PET economy.


Computer-aided engineering produces improvements to an enzyme that breaks down poly(ethylene terephthalate) (PET) into its constituent monomers, which are used to synthesize PET of near-petrochemical grade that can be further processed into bottles.


  
Deep learning takes on tumours 期刊论文
NATURE, 2020, 580 (7804) : 551-553
作者:  Dance, Amber
收藏  |  浏览/下载:0/0  |  提交时间:2020/07/03

Artificial-intelligence methods are moving into cancer research.


Artificial-intelligence methods are moving into cancer research.


  
Magma reservoir failure and the onset of caldera collapse at Kilauea Volcano in 2018 期刊论文
SCIENCE, 2019, 366 (6470) : 1214-+
作者:  Anderson, Kyle R.;  Johanson, Ingrid A.;  Patrick, Matthew R.;  Gu, Mengyang;  Segall, Paul;  Poland, Michael P.;  Montgomery-Brown, Emily K.;  Miklius, Asta
收藏  |  浏览/下载:9/0  |  提交时间:2020/02/17
Impact of Distinct Origin Locations on the Life Cycles of Landfalling Atmospheric Rivers Over the US West Coast 期刊论文
JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES, 2019, 124 (22) : 11897-11909
作者:  Zhou, Yang;  Kim, Hyemi
收藏  |  浏览/下载:6/0  |  提交时间:2020/02/17
Atmospheric River  Landfalling  US West Coast