Rapid Characterization of the July 2019 Ridgecrest, California, Earthquake Sequence From Raw Seismic Data Using Machine‐Learning Phase Picker

Abstract The tectonic setting of Timor–Leste and Eastern Indonesia comprises of a complex transition from oceanic lithosphere subduction to arc-continental collision. To better understand the deformation and convergent-zone structure of the region, we derive a new catalog of earthquake hypocenters and magnitudes from a temporary deployment of five years of continuous seismic data using an automated processing procedure. This includes a machine-learning phase picker, EQTransformer, and a sequential earthquake association and location workflow. We detect and locate ∼19,000 events during 2014–2018, which demonstrates that it is possible to characterize earthquake sequences from raw seismic data using a well-trained machine-learning picker for a complex convergent plate setting. This study provides the most complete catalog available for the region for the duration of the temporary deployment, which includes a complex pattern of crustal events across the collision zone and into the back-arc, as well as abundant deep slab seismicity.

Download Full-text

Metaviromic identification of genetic hotspots of coronavirus pathogenicity using machine learning

10.1101/2020.08.13.248575 ◽

2020 ◽

Author(s):

Jonathan J. Park ◽

Sidi Chen

Keyword(s):

Machine Learning ◽

Vaccine Development ◽

Cell Epitope ◽

Learning Approaches ◽

Systematic Map ◽

Functional Studies ◽

Major Threat ◽

Pathogenic Viruses ◽

Rapid Characterization

AbstractThe COVID-19 pandemic caused by SARS-CoV-2 has become a major threat across the globe. Here, we developed machine learning approaches to identify key pathogenic regions in coronavirus genomes. We trained and evaluated 7,562,625 models on 3,665 genomes including SARS-CoV-2, MERS-CoV, SARS-CoV and other coronaviruses of human and animal origins to return quantitative and biologically interpretable signatures at nucleotide and amino acid resolutions. We identified hotspots across the SARS-CoV-2 genome including previously unappreciated features in spike, RdRp and other proteins. Finally, we integrated pathogenicity genomic profiles with B cell and T cell epitope predictions for enrichment of sequence targets to help guide vaccine development. These results provide a systematic map of predicted pathogenicity in SARS-CoV-2 that incorporates sequence, structural and immunological features, providing an unbiased collection of genetic elements for functional studies. This metavirome-based framework can also be applied for rapid characterization of new coronavirus strains or emerging pathogenic viruses.

Download Full-text

Rapid Characterization of the 2015Mw 7.8 Gorkha, Nepal, Earthquake Sequence and Its Seismotectonic Context

Seismological Research Letters ◽

10.1785/0220150145 ◽

2015 ◽

Vol 86 (6) ◽

pp. 1557-1567 ◽

Cited By ~ 64

Author(s):

Gavin P. Hayes ◽

Richard W. Briggs ◽

William D. Barnhart ◽

William L. Yeck ◽

Daniel E. McNamara ◽

...

Keyword(s):

Earthquake Sequence ◽

Nepal Earthquake ◽

Rapid Characterization

Download Full-text

Characterization of Citrullination Sites in Neutrophils and Mast Cells Activated by Ionomycin via Integration of Mass Spectrometry and Machine Learning

Journal of Proteome Research ◽

10.1021/acs.jproteome.1c00028 ◽

2021 ◽

Author(s):

Raghothama Chaerkady ◽

Yebin Zhou ◽

Jared A. Delmar ◽

Shao Huan Samuel Weng ◽

Junmin Wang ◽

...

Keyword(s):

Machine Learning ◽

Mass Spectrometry ◽

Mast Cells

Download Full-text

An evaluation of the InDevR FluChip-8G insight microarray assay in characterizing influenza a viruses

Tropical Diseases Travel Medicine and Vaccines ◽

10.1186/s40794-021-00133-7 ◽

2021 ◽

Vol 7 (1) ◽

Author(s):

Emily S. Bailey ◽

Xinye Wang ◽

Mai-juan Ma ◽

Guo-lin Wang ◽

Gregory C. Gray

Keyword(s):

Influenza A ◽

Influenza Viruses ◽

Time Range ◽

Influenza B ◽

Influenza A Viruses ◽

Laboratory Methods ◽

Duke University ◽

Multiple Viral Strains ◽

Rapid Characterization

AbstractInfluenza viruses are an important cause of disease in both humans and animals, and their detection and characterization can take weeks. In this study, we sought to compare classical virology techniques with a new rapid microarray method for the detection and characterization of a very diverse, panel of animal, environmental, and human clinical or field specimens that were molecularly positive for influenza A alone (n = 111), influenza B alone (n = 3), both viruses (n = 13), or influenza negative (n = 2) viruses. All influenza virus positive samples in this study were first subtyped by traditional laboratory methods, and later evaluated using the FluChip-8G Insight Assay (InDevR Inc. Boulder, CO) in laboratories at Duke University (USA) or at Duke Kunshan University (China). The FluChip-8G Insight multiplexed assay agreed with classical virologic techniques 59 (54.1%) of 109 influenza A-positive, 3 (100%) of the 3 influenza B-positive, 0 (0%) of 10 both influenza A- and B-positive samples, 75% of 24 environmental samples including those positive for H1, H3, H7, H9, N1, and N9 strains, and 80% of 22 avian influenza samples. It had difficulty with avian N6 types and swine H3 and N2 influenza specimens. The FluChip-8G Insight assay performed well with most human, environmental, and animal samples, but had some difficulty with samples containing multiple viral strains and with specific animal influenza strains. As classical virology methods are often iterative and can take weeks, the FluChip-8G Insight Assay rapid results (time range 8 to 12 h) offers considerable time savings. As the FluChip-8G analysis algorithm is expected to improve over time with addition of new subtypes and sample matrices, the FluChip-8G Insight Assay has considerable promise for rapid characterization of novel influenza viruses affecting humans or animals.

Download Full-text

Rapid characterization of the volatile profiles in Pu‐erh tea by gas phase electronic nose and microchamber/thermal extractor combined with TD‐GC‐MS

Journal of Food Science ◽

10.1111/1750-3841.15723 ◽

2021 ◽

Author(s):

Yanqin Yang ◽

Yuting Rong ◽

Fuqiao Liu ◽

Yongwen Jiang ◽

Yuliang Deng ◽

...

Keyword(s):

Gas Phase ◽

Electronic Nose ◽

Volatile Profiles ◽

Rapid Characterization

Download Full-text

TPUPoint: Automatic Characterization of Hardware-Accelerated Machine-Learning Behavior for Cloud Computing

2021 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) ◽

10.1109/ispass51385.2021.00048 ◽

2021 ◽

Author(s):

Abenezer Wudenhe ◽

Hung-Wei Tseng

Keyword(s):

Machine Learning ◽

Cloud Computing ◽

Learning Behavior

Download Full-text

Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering

Scientific Reports ◽

10.1038/s41598-021-91297-x ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

José Castela Forte ◽

Galiya Yeshmagambetova ◽

Maureen L. van der Grinten ◽

Bart Hiemstra ◽

Thomas Kaufmann ◽

...

Keyword(s):

Machine Learning ◽

High Risk ◽

Mortality Risk ◽

Clustering Algorithms ◽

Kidney Injury ◽

Risk Groups ◽

Admission Diagnosis ◽

Dutch Hospital ◽

Cluster Membership

AbstractCritically ill patients constitute a highly heterogeneous population, with seemingly distinct patients having similar outcomes, and patients with the same admission diagnosis having opposite clinical trajectories. We aimed to develop a machine learning methodology that identifies and provides better characterization of patient clusters at high risk of mortality and kidney injury. We analysed prospectively collected data including co-morbidities, clinical examination, and laboratory parameters from a minimally-selected population of 743 patients admitted to the ICU of a Dutch hospital between 2015 and 2017. We compared four clustering methodologies and trained a classifier to predict and validate cluster membership. The contribution of different variables to the predicted cluster membership was assessed using SHapley Additive exPlanations values. We found that deep embedded clustering yielded better results compared to the traditional clustering algorithms. The best cluster configuration was achieved for 6 clusters. All clusters were clinically recognizable, and differed in in-ICU, 30-day, and 90-day mortality, as well as incidence of acute kidney injury. We identified two high mortality risk clusters with at least 60%, 40%, and 30% increased. ICU, 30-day and 90-day mortality, and a low risk cluster with 25–56% lower mortality risk. This machine learning methodology combining deep embedded clustering and variable importance analysis, which we made publicly available, is a possible solution to challenges previously encountered by clustering analyses in heterogeneous patient populations and may help improve the characterization of risk groups in critical care.

Download Full-text