Methods for classification of somatic embryos

Abstract

The present invention is directed towards methods for the classification of plant embryos by the application of one or more classification algorithms to analyze digitized images and absorption, transmittance, or reflectance spectra. The methods are generally applicable and emphasize the importance of acquiring and using as much image and absorption, transmittance, or reflectance spectral information as possible, based on objective criteria. The present invention allows automated selection of embryos most suitable for further culture and rejection of those seen as less suitable.

1 . A method for classifying plant embryos according to their germination potential comprising: 
 (a) developing a single metric classification model by 
 (i) acquiring raw digital image data of reference samples of whole plant embryos or any portion thereof of known germination potential;  
 (ii) calculating a metric value from the acquired raw digital image data of each embryo of known germination potential;  
 (iii) dividing the metric values obtained in step (a)(ii) into two sets of metric values according to their known germination potential;  
 (iv) calculating a Lorenz curve from the two sets of metric values;  
 (v) using any point on the Lorenz curve calculated in step (a)(iv) as a threshold value to arrive at a single metric classification model for classifying plant embryos by their germination potential;  
   (b) acquiring raw digital image data of a whole plant embryo or any portion thereof of unknown germination potential; and    (c) applying the developed single metric classification model to the raw digital image data of step (b) in order to classify the plant embryo of unknown germination potential according to its presumed germination potential.    
     
     
         2 . A method according to  claim 1 , wherein two or more single metric classification models derived from different metrics are combined using one or more classification algorithms to develop a classification model for classifying plant embryos.  
     
     
         3 . A method according to  claim 1 , wherein the raw digital image data acquired in step (a)(i) is preprocessed using one or more preprocessing algorithms before step (a)(ii); the raw digital image data acquired in step (b) is preprocessed using one or more preprocessing algorithms; and step (c) is carried out using the preprocessed raw digital image data.  
     
     
         4 . A method according to  claim 3 , wherein the preprocessing algorithm removes raw image data that is not from the plant embryo or plant embryo organ.  
     
     
         5 . A method according to  claim 3 , wherein the preprocessing algorithm reduces the amount of raw image data.  
     
     
         6 . A method according to  claim 1 , wherein the raw digital image data is acquired from more than one view of the plant embryo or plant embryo organ.  
     
     
         7 . A method according to  claim 1 , wherein the plant embryo is a plant somatic embryo.  
     
     
         8 . A method according to  claim 7 , wherein the plant is a tree.  
     
     
         9 . A method according to  claim 8 , wherein the tree is a member of the order Coniferales.  
     
     
         10 . A method according to  claim 8 , wherein the tree is a member of the family Pinaceae.  
     
     
         11 . A method according to  claim 8 , wherein the tree is selected from the group consisting of genera  Pseudotsuga  and  Pinus.