Methods for predicting an individual's clinical treatment outcome from sampling a group of patient's biological profiles

Abstract

Methods, systems, and computer program products that predict an individual's treatment outcome from a sampling of a group of patients' biological profiles. Biological profile information is received from patients who had a medical condition and who received a treatment. Treatment outcome information regarding the patients who had the medical condition and who received the treatment is also received. A discriminant analysis-based pattern recognition process is then performed on the biological profile information and the treatment outcome information, thereby generating a model that correlates between the biological profile information and the treatment outcome information. The model can be used for, among other things, predicting treatment outcome for the new patient for the treatment.

1 - 81 . (canceled) 
     
     
         82 . A method for treating cancer, comprising obtaining the results of a correlation between patient biological profile information and the predictive information of post-treatment efficacy for a particular drug treatment selected from one or more treatments for the cancer, wherein the correlation is obtained by:
 i) identifying a group of patients who had the cancer and who underwent the particular treatment for the cancer's primary tumor;   ii) receiving multiple gene based pre-treatment biological profile information obtained through analysis of one or more of tissue and biological specimens obtained from the group of patients prior to the particular treatment;   iii) receiving post-treatment efficacy information from the group of patients indicative of an impact of the particular treatment on the primary tumor   iv) performing a discriminant analysis-based pattern recognition process on the multiple gene based pre-treatment biological profile information and the post-treatment efficacy information, including identifying discriminating features of the multiple gene based pre-treatment biological profile information that correlate to different post treatment efficacies, and including generating a prediction model for the particular treatment that maps the multiple gene based pre-treatment biological profile information, using the discriminating features, to the corresponding different post treatment efficacies for the cancer's primary tumor;   v) receiving multiple gene based pre-treatment biological profile information obtained through analysis of the one or more of tissue and biological specimens obtained from a new patient prior to the new patient receiving the particular treatment for the cancer; and   vi) processing the new patient multiple gene based pre-treatment biological profile information according to the model, including using the discriminating features of the new patient multiple gene based pre-treatment biological profile information to predict an efficacy of the particular treatment for the new patient prior to the new patient receiving the particular treatment; wherein the multiple gene based pre-treatment biologic profile information and the post-treatment efficacy information are received within a suitably programmed computer system, and wherein the discriminant analysis-based pattern recognition process is performed within the suitably programmed computer system,   
       and treating the new patient with the particular treatment when the model predicts efficacy of the particular treatment for the new patient. 
     
     
         83 . The method according to  claim 82 , wherein the performing a discriminant analysis-based pattern recognition process comprises reducing the multiple gene based pre-treatment biological profile information to a sub-set of genes that account for a substantial portion of diversity. 
     
     
         84 . The method according to  claim 83 , wherein the receiving pre-treatment biological profile information from a new patient comprises receiving genetic profile information from the new patient regarding only the sub-set of genes. 
     
     
         85 . The method according to  claim 82 , further comprising using the model to predict efficacy of a first line treatment for a cancer patient. 
     
     
         86 . The method according to  claim 82 , further comprising using the model to predict efficacy of a multiple combination drug treatment for the cancer. 
     
     
         87 . The method according to  claim 82 , further comprising using the model to predict efficacy of a later-line drug treatment for the cancer. 
     
     
         88 . The method according to  claim 82 , further comprising using the model to predict efficacy of treatment for a second cancer condition without having been trained by the second cancer condition. 
     
     
         89 . The method according to  claim 88 , wherein the cancer of part i) comprises colon cancer and the second cancer comprises ovarian cancer. 
     
     
         90 . The method according to  claim 88 , wherein the cancer of part i) comprises a first type of tumor and the second cancer comprises a second type of tumor related to the first type of tumor. 
     
     
         91 . The method according to  claim 90 , wherein the first type of tumor is a primary tumor and the second type of tumor is a metastatic tumor. 
     
     
         92 . The method according to  claim 82 , wherein the performing a discriminant analysis-based pattern recognition process of part iv) comprises:
 dividing the biological profile information and the treatment efficacy information into a training sub-set and a testing sub-set;   performing the discriminant analysis-based pattern recognition process on the training sub-set; and   testing the resultant model with the testing sub-set.   
     
     
         93 . The method according to  claim 82 , wherein the performing a discriminant analysis-based pattern recognition process comprises:
 dividing the biological profile information and the post-treatment efficacy information into a training sub-set of biological profile information and post-treatment efficacy information and a testing sub-set of biological profile information and post-treatment efficacy information;
 performing a plurality of different types of discriminant analysis-based pattern recognition processes on the training sub-set of biological profile information and treatment efficacy information, including generating a plurality of models that correlate between the training set of biological profile information and the training set of post-treatment efficacy information; 
 testing the plurality of models with the testing sub-set of biological profile information and treatment efficacy information; and 
   selecting the model that most accurately predicts the testing sub-set of treatment efficacy information from the testing sub-set of biological profile information.   
     
     
         94 . The method according to  claim 82 , wherein the multiple gene based pre-treatment biological profile information comprises one or more of the following:
 genetic profile information; DNA profile information; single nucleotide polymorphism profile information; RNA profile information; and protein profile information.   
     
     
         95 . A method for treating cancer, comprising obtaining the results of a correlation between patient multiple gene based biological profile information and the predictive information of post-treatment efficacy for a particular treatment selected from one or more treatments for a cancer, wherein the multiple gene based biological profile information comprises one or more of the following: genetic profile information, DNA profile information; single nucleotide polymorphism profile information, RNA profile information, and protein profile information, wherein the particular treatment comprises a radiotherapy treatment, wherein the correlation is obtained by:
 i) identifying a group of patients who had the cancer and who underwent the particular treatment for the cancer;   ii) receiving multiple gene based pre-treatment biological profile information obtained through analysis of one or more of tissue and biological specimens obtained from the group of patients prior to the particular treatment;   iii) receiving post-treatment efficacy information from the group of patients indicative of an impact of the particular treatment;   iv) performing a discriminant analysis-based pattern recognition process on the multiple gene based pre-treatment biological profile information and the post-treatment efficacy information, including identifying discriminating features of the multiple gene based pre-treatment biological profile information that correlate to different post treatment efficacies, and including generating a prediction model for the particular treatment that maps the multiple gene based pre-treatment biological profile information, using the discriminating features, to the corresponding different post treatment efficacies;   v) receiving multiple gene based pre-treatment biological profile information obtained through analysis of the one or more of tissue and biological specimens obtained from a new patient prior to the new patient receiving the particular treatment for the cancer; and   vi) processing the new patient multiple gene based pre-treatment biological profile information according to the model, including using the discriminating features of the new patient multiple gene based pre-treatment biological profile information to predict an efficacy of the particular treatment for the new patient prior to the new patient receiving the particular treatment; wherein the multiple gene based pre-treatment biologic profile information and the post-treatment efficacy information are received within a suitably programmed computer system, and wherein the discriminant analysis-based pattern recognition process is performed within the suitably programmed computer system,   
       and treating the new patient with the particular treatment when the model predicts efficacy of the particular treatment for the new patient. 
     
     
         96 . The method according to  claim 95 , wherein the performing a discriminant analysis-based pattern recognition process comprises reducing the multiple gene based pre-treatment biological profile information to a sub-set of genes that account for a substantial portion of diversity. 
     
     
         97 . The method according to  claim 96 , wherein the receiving pre-treatment biological profile information from a new patient comprises receiving genetic profile information from the new patient regarding only the sub-set of genes. 
     
     
         98 . The method according to  claim 95 , further comprising using the model to predict efficacy of treatment for a second cancer condition without having been trained by the second cancer condition.