利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

119 条记录 (耗时 0.058 秒)

    SYSTEMS, METHODS, AND COMPUTER PROGRAM PRODUCTS FOR MERGING A NEW NUCLEOTIDE OR AMINO ACID SEQUENCE INTO OPERATIONAL TAXONOMIC UNITS
    83.
    发明申请
    SYSTEMS, METHODS, AND COMPUTER PROGRAM PRODUCTS FOR MERGING A NEW NUCLEOTIDE OR AMINO ACID SEQUENCE INTO OPERATIONAL TAXONOMIC UNITS 审中-公开
    将新的核酸或氨基酸序列合并到运营单位中的系统，方法和计算机程序产品

    公开(公告)号：US20160103958A1

    公开(公告)日：2016-04-14

    申请号：US14897321

    申请日：2014-06-13

    申请人： UNIVERSITY OF GUELPH

    发明人： Paul Hebert ,  Sujeevan Ratnasingham

    IPC分类号： G06F19/24 ,  G06F17/30 ,  G06F19/14

    CPC分类号： G16B40/00 ,  G06F16/285 ,  G16B10/00 ,  G16B20/00

    摘要： The present disclosure provides a method for filtering sequence clusters during a process of merging a newly generated nucleotide or amino acid sequence with a set of previously clustered sequences. In another aspect, the disclosure provides a method for assigning newly generated nucleotide or amino acid sequences to presumptive species called operational taxonomic units. In yet another embodiment, the sequences are derived from the cytochrome c oxidase I gene.

    摘要翻译： 本公开提供了在将新产生的核苷酸或氨基酸序列与一组先前聚簇序列合并的过程期间过滤序列簇的方法。 在另一方面，本公开提供了一种将新产生的核苷酸或氨基酸序列分配给称为操作分类单位的推定物种的方法。 在另一个实施方案中，序列衍生自细胞色素c氧化酶I基因。

    Genetic markers for skatole metabolism
    87.
    发明申请
    Genetic markers for skatole metabolism 有权
    遗传标记为土壤代谢

    公开(公告)号：US20030228614A1

    公开(公告)日：2003-12-11

    申请号：US10434966

    申请日：2003-05-09

    申请人： University of Guelph

    发明人： E. James Squires ,  Gonzalo J. Diaz

    IPC分类号： C12Q001/68

    CPC分类号： C12Q1/6881 ,  C12Q1/6888 ,  C12Q2600/156

    摘要： Novel metabolites and enzymes involved in skatole metabolism are disclosed. The novel metabolites are 3-OH-3-methylindolenine (HMI); 3-methyloxindole (3MOI); indole-3-carbinol (I-3C); and 2-aminoacetophenone (2-AM). Measuring levels of these metabolites in a pig may be useful in identifying the pig's ability to metabolize skatole and its susceptibility to boar taint. The novel enzymes involved in skatole metabolism are aldehyde oxidase and CYP2A6. Enhancing the activity of these enzymes may be useful in enhancing skatole metabolism and reducing boar taint. The identification of the enzyme also allows the development of screening assays for substances that interact with these enzymes and skatole metabolism or for genetic screening to identify pigs on the basis of their skatole metabolism. Pigs having high levels of these enzymes may be selected and bred to produce pigs that have a lower incidence of boar taint.

    摘要翻译： 公开了与代谢相关的新型代谢物和酶。 新型代谢物为3-OH-3-甲基多巴酚丁胺（HMI）; 3-甲氧基吲哚（3MOI）; 吲哚-3-甲醇（I-3C）; 和2-氨基苯乙酮（2-AM）。 测量猪中这些代谢物的含量可能有助于识别猪代谢粪便的能力及其对野猪污染的敏感性。 涉及粪臭素代谢的新型酶是醛氧化酶和CYP2A6。 提高这些酶的活性可能有助于增强粪便代谢和减少野猪污点。 酶的鉴定还允许开发与这些酶相互作用的物质的筛选测定，并进行遗传筛选以基于其代谢代谢来鉴定猪。 可以选择并培育具有高水平这些酶的猪，以产生具有较低的野猪污染发生率的猪。

    METHOD AND SYSTEM FOR DETERMINATION OF OUT-OF-DISTRIBUTION SAMPLES AND ATTACK SURFACES FOR ARTIFICIAL NEURAL NETWORKS
    89.
    发明公开
    METHOD AND SYSTEM FOR DETERMINATION OF OUT-OF-DISTRIBUTION SAMPLES AND ATTACK SURFACES FOR ARTIFICIAL NEURAL NETWORKS 审中-公开

    公开(公告)号：US20240256660A1

    公开(公告)日：2024-08-01

    申请号：US18403269

    申请日：2024-01-03

    申请人： UNIVERSITY OF GUELPH

    发明人： Amin Azmoodeh ,  Ali Dehghantanha

    IPC分类号： G06F21/55

    CPC分类号： G06F21/554

    摘要： There is provided systems and methods for counteracting an adversarial attack on an artificial neural network by determining out-of-distribution samples. One method including: receiving training data for the artificial neural network including a plurality of in-distribution samples in an input space; embedding the training data in the input space into a lower-dimensional embedded space; receiving one or more inputted samples and embedding the one or more inputted samples into the lower-dimensional embedded space; determining a score for each of the one or more inputted samples by determining a distance from each inputted sample to a distribution of the training data in the embedded space; classifying whether each of the one or more inputted samples is out-of-distribution by determining whether the score is greater than a predetermined distance from the distribution of the training data in the embedded space; and outputting the classification of each of the one or more inputted samples.

    METHOD AND SYSTEM FOR ADVERSARIAL MALWARE THREAT PREVENTION AND ADVERSARIAL SAMPLE GENERATION
    90.
    发明公开
    METHOD AND SYSTEM FOR ADVERSARIAL MALWARE THREAT PREVENTION AND ADVERSARIAL SAMPLE GENERATION 审中-公开

    公开(公告)号：US20240031401A1

    公开(公告)日：2024-01-25

    申请号：US18354784

    申请日：2023-07-19

    申请人： UNIVERSITY OF GUELPH

    发明人： Hamed HADDADPAJOUH ,  Ali DEHGHANTANHA

    IPC分类号： H04L9/40 ,  H04L41/16

    CPC分类号： H04L63/145 ,  H04L41/16

    摘要： There is provided systems and methods for adversarial sample generation and adversarial malware threat prevention. The method including: receiving an input executable sample; extracting features of the input executable sample and applying feature mapping to determine components of the features; determining a binary classifier representing whether the executable sample is adversarial using one or more machine learning models, the one or more machine learning models taking the components as input, the one or more machine learning models trained using, at least, generated adversarial samples, generating the generated adversarial samples includes determining code caves in training executable samples and inserting generated payloads as benign samples at the determined code caves; and where the binary classifier indicates adversarial, dropping the input executable sample, otherwise outputting the input executable sample.