Predicting hepatotoxicity using cell based assays

• US 20060228695A1
• Filed: 03/13/2006
• Published: 10/12/2006
• Est. Priority Date: 07/18/2003
• Status: Abandoned Application

• Current Assignee: Cytokinetics, Inc.
• Original Assignee: Cytokinetics, Inc.
• Inventors: Fan, Jinhong, Vaisberg, Eugeni, Trautman, Jay, Rao, Aibing, Mattheakis, Larry, Adams, Cynthia, Solar, Gregg
• Application Number:
  US11/375,597
• Publication Number:
  US 20060228695A1
• Time in Patent Office: Days
• US Class Current: 435/4
• CPC Class Codes: G01N 1/30 Staining; Impregnating ; Fixation; Dehydration; Multistep processes for preparing samples of tissue, cell or nucleic acid material and the like for analysis
• CPC Class Codes: G01N 33/5067 Liver cells
• CPC Class Codes: G06T 2207/10056 Microscopic image
• CPC Class Codes: G06T 2207/10064 Fluorescence image
• CPC Class Codes: G06T 2207/20152 Watershed segmentation
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/41 based on statistical description of texture
• CPC Class Codes: G06V 20/698 Matching; Classification

Abstract

Cell based assays are used to assess the hepatotoxicity of a stimulus. Imaging technologies are used to analyze the effects of a stimulus on hepatocytes. Image analysis may characterize the stimulus on the basis of whether it is hepatotoxic, and if so what type of pathology is exhibited; e.g., apoptosis, necrosis, cholestasis, and/or steatosis.

Claims

1. A method of determining whether a stimulus induces a hepatotoxic response or a pathology, the method comprising:

(a) receiving one or more images of hepatocytes that have been exposed to a stimulus;

(b) from the images, automatically generating a plurality features characterizing the hepatocytes; and

(c) applying the plurality of features to a hepatotoxicity model or a pathology model to thereby classify the stimulus as to hepatotoxicity or pathology.

2. The method of claim 1, wherein the stimulus comprises exposure to a compound.

3. The method of claim 1, wherein automatically generating the plurality of features comprising extracting information about a marker or markers for hepatocyte components from the images.

4. The method of claim 1, wherein generating a plurality of the features comprises segmenting the one or more images to identify regions from which said features are generated.

5. The method of claim 1, further comprising generating a stimulus response path for hepatocytes exposed to said stimulus, wherein the one or more images show hepatocytes exposed to multiple levels of said stimulus.

6. The method of claim 1, wherein the (c) comprises applying the plurality of features to a model for cholestasis to thereby classify the stimulus as to cholestasis.

7. The method of claim 1, wherein the (c) comprises applying the plurality of features to a model for steatosis to thereby classify the stimulus as to steatosis.

8. The method of claim 1, wherein the (c) comprises applying the plurality of features to a model for apoptosis to thereby classify the stimulus as to apoptosis.

17. The computer program product of claim 1, wherein the hepatotoxicity model or pathology model comprises a model for cholestasis for classifying the stimulus as to cholestasis.

18. The computer program product of claim 1, wherein the hepatotoxicity model or pathology model comprises a model for steatosis for classifying the stimulus as to steatosis.

19. The computer program product of claim 1, wherein the hepatotoxicity model or pathology model comprises a model for apoptosis for classifying the stimulus as to apoptosis.

9. A method of generating a hepatotoxicity model or pathology model for determining whether a stimulus induces a hepatotoxic response or a pathology, the method comprising:

(a) receiving a training set for generating the hepatotoxicity or pathology model, wherein the training set comprises phenotypic information for various stimuli some of which are known to induce hepatotoxic responses or pathology responses and others which are known to not induce hepatotoxic or pathology responses, wherein the phenotypic information for each stimulus comprises a plurality of features derived from images of the hepatocytes exposed to said stimuli; and

(b) from the training set, generating the hepatotoxicity model or pathology model for classifying stimuli as to hepatotoxicity or pathology based on at least some of the plurality of features obtained from hepatocytes treated with a stimulus to be classified by the hepatotoxicity model or pathology model.

10. The method of claim 9, wherein the plurality of features are derived from a marker or markers for hepatocyte components.

11. The method of claim 9, further comprising selecting a subset of the plurality of features for use in the hepatotoxicity model or pathology model.

12. The method of claim 9, further comprising validating the model.

13. A computer program product comprising a machine readable medium on which is provided program instructions for determining whether a stimulus induces a hepatotoxic response or a pathology, the program instructions comprising:

(a) code for receiving one or more images of hepatocytes that have been exposed to a stimulus;

(b) code for automatically generating, from the images, a plurality features characterizing the hepatocytes; and

(c) code for applying the plurality of features to a hepatotoxicity model or pathology model to thereby classify the stimulus as to hepatotoxicity or pathology.

14. The computer program product of claim 13, wherein the code for automatically generating the plurality of features comprising code for extracting information about a marker or markers for hepatocyte components from the images.

15. The computer program product of claim 13, wherein code for generating a plurality of the features comprises code for segmenting the one or more images to identify regions from which said features are generated.

16. The computer program product of claim 13, further comprising code for generating a stimulus response path for hepatocytes exposed to said stimulus, wherein the one or more images show hepatocytes exposed to multiple levels of said stimulus.

20. A computer program product comprising a machine readable medium on which is provide program instructions for generating a hepatotoxicity model or pathology model for determining whether a stimulus induces a hepatotoxic response or a pathology, the program instructions comprising:

(a) code for receiving a training set for generating the hepatotoxicity or pathology model, wherein the training set comprises phenotypic information for various stimuli some of which are known to induce hepatotoxic responses or pathology responses and others which are known to not induce hepatotoxic or pathology responses, wherein the phenotypic information for each stimulus comprises a plurality of features derived from images of the hepatocytes exposed to said stimuli; and

(b) code for generating, from the training set, the hepatotoxicity model or pathology model for classifying stimuli as to hepatotoxicity or pathology based on at least some of the plurality of features obtained from hepatocytes treated with a stimulus to be classified by the hepatotoxicity model or pathology model.

21. The computer program product of claim 20, further comprising code for deriving the plurality of features from a marker or markers for hepatocyte components.

22. The computer program product of claim 20, further comprising code for selecting a subset of the plurality of features for use in the hepatotoxicity model or pathology model.

23. The computer program product of claim 20, further comprising code for validating the model.