-
公开(公告)号:US07323318B2
公开(公告)日:2008-01-29
申请号:US11082241
申请日:2005-03-15
申请人: Jinhong Fan , Vadim Kutsyy , Eugeni A. Vaisberg
发明人: Jinhong Fan , Vadim Kutsyy , Eugeni A. Vaisberg
IPC分类号: C12Q1/02
CPC分类号: G06K9/00147 , G06T7/0012
摘要: Image analysis methods and apparatus are used for distinguishing live and dead cells. The methods may involve segmenting an image to identify the region(s) occupied by one or more cells and determining the presence of a particular live-dead indicator feature within the region(s). In certain embodiments, the indicator feature is a cytoskeletal component such as tubulin. Prior to producing an image for analysis, cells may be treated with a marker that highlights the live-dead indicator in the image. In the case of tubulin, the marker will co-locate with tubulin and provide a signal that is captured in the image (e.g., a fluorescent emission).
摘要翻译: 图像分析方法和装置用于区分活细胞和死细胞。 所述方法可以包括分割图像以识别由一个或多个单元占用的区域,并确定该区域内特定的活死人指示器特征的存在。 在某些实施方案中,指示剂特征是细胞骨架成分如微管蛋白。 在生成用于分析的图像之前,可以使用突出显示图像中活死人指示符的标记来处理细胞。 在微管蛋白的情况下,标记物将与微管蛋白共同定位,并提供在图像中捕获的信号(例如,荧光发射)。
-
公开(公告)号:US07246012B2
公开(公告)日:2007-07-17
申请号:US10892450
申请日:2004-07-16
CPC分类号: G06K9/6274 , G06K9/00147 , G06K9/00536
摘要: A method for calculating distances between stimulus response curves (e.g., dose response curves) allows classification of stimuli. The response curves show how the phenotype of one or more cells changes in response to varying levels of the stimulus. Each “point” on the curve represents quantitative phenotype or signature for cell(s) at a particular level of stimulus (e.g., dose of a therapeutic). The signatures are multivariate phenotypic representations of the cell(s). They include various features of the cell(s) obtained by image analysis. To facilitate the comparison of stimuli, distances between points on the response curves are calculated. First, the response curves may be aligned on a coordinate representing a separate distance, r, from a common point of negative control (e.g., the point where no stimulus is applied). Integration on r may be used to compute the distance between two response curves. The distance between response curves is used to classify stimuli.
摘要翻译: 用于计算刺激响应曲线(例如,剂量响应曲线)之间的距离的方法允许对刺激进行分类。 响应曲线显示了一种或多种细胞的表型如何响应刺激的不同水平而改变。 曲线上的每个“点”表示特定刺激水平(例如,治疗剂的剂量)的细胞的定量表型或特征。 签名是细胞的多变量表型表达。 它们包括通过图像分析获得的细胞的各种特征。 为了促进刺激的比较,计算响应曲线上的点之间的距离。 首先,响应曲线可以在表示来自负控制的公共点(例如,不施加刺激的点)的单独距离r的坐标上对准。 可以使用r上的积分来计算两个响应曲线之间的距离。 响应曲线之间的距离用于对刺激进行分类。
-
公开(公告)号:US20070031818A1
公开(公告)日:2007-02-08
申请号:US11355258
申请日:2006-02-14
申请人: Vadim Kutsyy , Jinhong Fan , Eugeni Vaisberg
发明人: Vadim Kutsyy , Jinhong Fan , Eugeni Vaisberg
CPC分类号: G06T7/0012 , G06K9/00147 , G06T2207/10056 , G06T2207/20081 , G06T2207/30024
摘要: Image analysis methods and apparatus are used for distinguishing live and dead cells. The methods may involve segmenting an image to identify the region(s) occupied by one or more cells and determining the presence of a particular live-dead indicator feature within the region(s). In certain embodiments, the indicator feature is a cytoskeletal component such as tubulin. In certain embodiments, the methods may involve determining the value of an indicator expression that is based on cellular components such as DNA and/or cellular protein. Prior to producing an image for analysis, cells may be treated with a marker that highlights the live-dead indicator in the image.
摘要翻译: 图像分析方法和装置用于区分活细胞和死细胞。 所述方法可以包括分割图像以识别由一个或多个单元占用的区域,并确定该区域内特定的活死人指示器特征的存在。 在某些实施方案中,指示剂特征是细胞骨架成分如微管蛋白。 在某些实施方案中,所述方法可以涉及确定基于诸如DNA和/或细胞蛋白质的细胞组分的指示物表达的值。 在生成用于分析的图像之前,可以使用突出显示图像中活死人指示符的标记来处理细胞。
-
公开(公告)号:US20060014135A1
公开(公告)日:2006-01-19
申请号:US11082241
申请日:2005-03-15
申请人: Jinhong Fan , Vadim Kutsyy , Eugeni Vaisberg
发明人: Jinhong Fan , Vadim Kutsyy , Eugeni Vaisberg
CPC分类号: G06K9/00147 , G06T7/0012
摘要: Image analysis methods and apparatus are used for distinguishing live and dead cells. The methods may involve segmenting an image to identify the region(s) occupied by one or more cells and determining the presence of a particular live-dead indicator feature within the region(s). In certain embodiments, the indicator feature is a cytoskeletal component such as tubulin. Prior to producing an image for analysis, cells may be treated with a marker that highlights the live-dead indicator in the image. In the case of tubulin, the marker will co-locate with tubulin and provide a signal that is captured in the image (e.g., a fluorescent emission).
摘要翻译: 图像分析方法和装置用于区分活细胞和死细胞。 所述方法可以包括分割图像以识别由一个或多个单元占用的区域,并且确定该区域内特定的活死人指示器特征的存在。 在某些实施方案中,指示剂特征是细胞骨架成分如微管蛋白。 在生成用于分析的图像之前,可以使用突出显示图像中活死人指示符的标记来处理细胞。 在微管蛋白的情况下,标记物将与微管蛋白共同定位,并提供在图像中捕获的信号(例如,荧光发射)。
-
公开(公告)号:US20070250270A1
公开(公告)日:2007-10-25
申请号:US11715664
申请日:2007-03-07
申请人: Eugeni Vaisberg , Vadim Kutsyy
发明人: Eugeni Vaisberg , Vadim Kutsyy
IPC分类号: G01N33/48
CPC分类号: G01N33/5014 , C12Q1/6827 , G01N33/5026 , G01N33/5067 , G01N2800/085 , G16B20/00 , G16B40/00
摘要: Methods for generating models for predicting biological activity of a stimulus test population of cells are provided. The models may be used to classify or predict the effect of stimuli on cells. In certain embodiments, the methods involve receiving data comprising values for dependent variables associated with stimuli; preparing a set of cell populations based on the data received; identifying a subset of the cell populations to be used in generating a model from data associated with the subset, wherein the model is provided to predict activity of a test population.
摘要翻译: 提供了用于产生用于预测细胞的刺激试验群体的生物活性的模型的方法。 这些模型可用于分类或预测刺激对细胞的影响。 在某些实施例中,所述方法包括接收包括与刺激相关联的因变量的值的数据; 根据收到的数据准备一组细胞群; 识别要用于从与所述子集相关联的数据生成模型的所述细胞群体的子集,其中提供所述模型以预测测试群体的活动。
-
公开(公告)号:US20050014131A1
公开(公告)日:2005-01-20
申请号:US10621821
申请日:2003-07-16
申请人: Vadim Kutsyy , Eugeni Vaisberg , Daniel Coleman
发明人: Vadim Kutsyy , Eugeni Vaisberg , Daniel Coleman
CPC分类号: G06K9/0014 , G01N33/5008 , G01N33/5014 , G01N33/502
摘要: Methods, apparatus, and computer programs for investigating and characterising side effects of a treatment having an intended or on-target effect on cells are described. The method can include identifying a group of on-target cellular features of the plurality of cells which are affected by the treatment and are related to the on-target effect. A group of off-target cellular features can also be identified which are different to the on-target cellular features and which are also affected by the treatment and which are related to the side effect. A measure of the side effect based on the off-target cellular features can be obtained. The treatment can then be characterised based on the measure of the side effect. A further method involves capturing an image of the population of treated cells and deriving cellular features from the image. An on-target effect signature, which is characteristic of the on-target effect is created from cellular features relating to cellular properties involved in the intended effect. A side effect signature, which is characteristic of a side effect to the on-target effect, is created using cellular features relating to cellular properties not involved in the intended effect. On-target effect and/or side effect metrics are obtained from the signatures which can be used to characterise the treatment.
摘要翻译: 描述了用于调查和表征具有预期或靶向对细胞的作用的治疗的副作用的方法,装置和计算机程序。 该方法可以包括识别受治疗影响并且与目标效应相关的多个细胞的一组目标上细胞特征。 还可以鉴定一组离靶细胞特征,这些特征与目标细胞特征不同,并且还受到治疗的影响并且与副作用相关。 可以获得基于离靶细胞特征的副作用的量度。 然后可以基于副作用的测量来表征治疗。 另一种方法包括捕获处理的细胞群体的图像并从图像中导出细胞特征。 作为目标效果的特征的目标效果特征是从涉及预期效果的细胞特性的细胞特征产生的。 使用与未涉及预期效果的细胞特性相关的细胞特征产生作为靶向效应的副作用特征的副作用特征。 从可用于表征治疗的签名获得目标效应和/或副作用度量。
-
公开(公告)号:US20070250301A1
公开(公告)日:2007-10-25
申请号:US11715665
申请日:2007-03-07
申请人: Eugeni Vaisberg , Vadim Kutsyy , Ke Yang
发明人: Eugeni Vaisberg , Vadim Kutsyy , Ke Yang
IPC分类号: G06G7/48
CPC分类号: G01N33/5067 , G01N15/1475 , G01N33/5014 , G01N2015/1477 , G01N2015/1488 , G06K9/00147 , G06T7/0012 , G06T2207/30024 , G16H50/50
摘要: Methods for generating models for predicting biological activity of a stimulus test population of cells are provided. The models may be used to classify or predict the effect of stimuli on cells. In certain embodiments, the methods involve receiving data comprising values for dependent variables associated with stimuli as applied to cell populations; preparing a set of cell populations based on the data received; identifying a subset of the cell populations to be used in generating a model from data associated with the subset, wherein the model is provided to predict activity of a test population.
摘要翻译: 提供了用于产生用于预测细胞的刺激试验群体的生物活性的模型的方法。 这些模型可用于分类或预测刺激对细胞的影响。 在某些实施方案中,所述方法包括接收包含与应用于细胞群体的刺激相关的因变量的值的数据; 根据收到的数据准备一组细胞群; 识别要用于从与所述子集相关联的数据生成模型的所述细胞群体的子集,其中提供所述模型以预测测试群体的活动。
-
公开(公告)号:US20070208516A1
公开(公告)日:2007-09-06
申请号:US11653109
申请日:2007-01-12
申请人: Vadim Kutsyy , Ke Yang
发明人: Vadim Kutsyy , Ke Yang
IPC分类号: G06F19/00
CPC分类号: G06K9/00147 , G06K9/6256 , G16B40/00
摘要: A method of generating classification models to predict biological activity of a population of cells is provided. In certain embodiments, the method involves a) receiving a training set having values for independent and dependent variables associated with populations of cells; b) clustering the training set; c) randomly selecting, with replacement, clusters of cell populations to construct multiple bootstrap samples of the size of the training set; and d) generating a random forest model for each bootstrap sample, wherein the ensemble of random forest models may be used to classify the test population. Also provided are methods of predicting whether a test population of cells exhibits a pathology or biological activity. In certain embodiments, the methods involve applying data about the test population of cells to an ensemble of random forest models. The prediction may be made by aggregating the predictions of the random forest models in the ensemble.
摘要翻译: 提供了一种产生分类模型以预测细胞群的生物活性的方法。 在某些实施例中,该方法包括:a)接收具有与细胞群相关联的独立和依赖变量的值的训练集; b)聚类训练集; c)随机选择细胞群体的替换,以构建训练集大小的多个引导样本; 以及d)为每个引导样本生成随机森林模型,其中随机森林模型的整体可以用于对测试群体进行分类。 还提供了预测细胞的测试群体是否呈现病理学或生物学活性的方法。 在某些实施方案中,所述方法包括将关于细胞的测试群体的数据应用于随机森林模型的整体。 可以通过聚合组合中的随机森林模型的预测来进行预测。
-
公开(公告)号:US20050137806A1
公开(公告)日:2005-06-23
申请号:US10892450
申请日:2004-07-16
申请人: Vadim Kutsyy , Daniel Coleman , Eugeni Vaisberg
发明人: Vadim Kutsyy , Daniel Coleman , Eugeni Vaisberg
IPC分类号: A61K49/00 , G01N33/48 , G06F20060101 , G06F19/00
CPC分类号: G06K9/6274 , G06K9/00147 , G06K9/00536
摘要: A method for calculating distances between stimulus response curves (e.g., dose response curves) allows classification of stimuli. The response curves show how the phenotype of one or more cells changes in response to varying levels of the stimulus. Each “point” on the curve represents quantitative phenotype or signature for cell(s) at a particular level of stimulus (e.g., dose of a therapeutic). The signatures are multivariate phenotypic representations of the cell(s). They include various features of the cell(s) obtained by image analysis. To facilitate the comparison of stimuli, distances between points on the response curves are calculated. First, the response curves may be aligned on a coordinate representing a separate distance, r, from a common point of negative control (e.g., the point where no stimulus is applied). Integration on r may be used to compute the distance between two response curves. The distance between response curves is used to classify stimuli.
摘要翻译: 用于计算刺激响应曲线(例如,剂量响应曲线)之间的距离的方法允许对刺激进行分类。 响应曲线显示了一种或多种细胞的表型如何响应刺激的不同水平而改变。 曲线上的每个“点”表示特定刺激水平(例如,治疗剂的剂量)的细胞的定量表型或特征。 签名是细胞的多变量表型表达。 它们包括通过图像分析获得的细胞的各种特征。 为了促进刺激的比较,计算响应曲线上的点之间的距离。 首先,响应曲线可以在表示来自负控制的公共点(例如,不施加刺激的点)的单独距离r的坐标上对准。 可以使用r上的积分来计算两个响应曲线之间的距离。 响应曲线之间的距离用于对刺激进行分类。
-
-
-
-
-
-
-
-