Systems and methods for detecting biological features

Abstract

A computer having a memory stores instructions for receiving data. The data comprises one or more characteristics for each cellular constituent in a plurality of cellular constituents that have been measured in a test organism of a species or a test biological specimen from an organism of the species. The memory further stores instructions for computing a model in a plurality of models, wherein the model is characterized by a model score that represents the likelihood of a biological feature in the test organism or the test biological specimen. Computation of the model comprises determining the model score using one or more characteristics for one or more cellular constituents in the plurality of cellular constituents. The memory also stores instructions for repeating the instructions for computing one or more times, thereby computing the plurality of models. The memory also stores instructions for communicating computed model scores.

Description

1. FIELD OF THE INVENTION The field of this invention relates to computer systems and methods for identifying biological features, such as disease, in biological specimens. 2. BACKGROUND OF THE INVENTION A first step in rationally treating disease is to assess the patient against a classification of diseases, the results being used to determine what kind of disease the patient has and to predict the person's response to various therapies. The effectiveness of the process depends on the quality of the classification. At least in the case of cancer, the advent of microarray methods to analyze DNA, RNA or proteins from tumor cells has started to refine and improve the classification of cancer cells. See, for example, Golub et al., 1999, Science 286, p. 531. Further, van't Veer et al., 2002, Nature 415, p. 530, illustrates how such “molecular profiling” is improving cancer classification. Van't Veer et al. shows that the results of gene-expression profiling of breast tumors, carried ...

AI Technical Summary

Benefits of technology

Another aspect of the present invention provides a computer comprising a central processing unit and a memory coupled to the central processing unit. The memory stores instructions for receiving data, wherein the data comprises one or more aspects of the biological state of each cellular constituent in a plurality of cellular constituents that have been measured in a test organism of a species or a test biological specimen from an organism of the species. The memory further stores instructions for computing a model in a plurality of models. The instructions for computing produce a model characterization for the model that indicates whether the test organism of the species or the test biological specimen from the organism of the species is a member of a biological sample class. The instructions for computing the model comprise characterizing the model using one or more aspects of the biological state of one or more cellular constituents in the plurality of cellular constituents. The memory further stores instructions for repeating the instructions for computing one or more times, thereby computing the plurality of models. The memory also stores instructions for communicating each model characterization computed in an instance of the instructions for computing. In some embodiments, the instructions for receiving data comprise instructions for receiving the data from a remote computer over a wide area network, such as the Internet. In some embodiments, the biological sample class is a disease such as cancer.

Another aspect of the invention provides a computer comprising a central processing unit and a memory, coupled to the central processing unit. The memory stores instructions for receiving data. The data comprises one or more aspects of the biological state of each cellular constituent in a plurality of cellular constituents that have been measured in a test organism of a species or a test biological specimen from an organism of the species. The memory further stores instructions for computing a plurality of models. This computing produces a model characterization for each model in the plurality of models that indicates whether the test organism of the species or the test biological specimen from the organism of the species is a member of a biological sample class. The computing comprises characterizing each model in the plurality of models using one or more aspects of the biological state of one or more cellular constituents in the plurality of cellular constituents. The memory further stores instructions for communicating each model characterization computed by the instructions for computing.

Still another aspect of the invention provides a computer program product for use in conjunction with a computer system. The computer program product comprises a computer readable storage medium and a computer program mechanism embedded therein. The computer program mechanism further comprises instructions for receiving data. Such data comprises one or more aspects of the biological state of each cellular constituent in a plurality of cellular constituents that have been measured in a test organism of a species or a test biological specimen from an organism of the species. The computer program mechanism further comprises instructions for computing a model in a plurality of models. Such computing produces a model characterization for the model that indicates whether the test organism of the species or the test biological specimen from the organism of the species is a member of a biological sample class. The computation of the model comprises characterizing the model using one or more aspects of the biological state of one or more cellular constituents in the plurality of cellular constituents. The computer program mechanism further comprises instructions for repeating the instructions for computing one or more times, thereby computing the plurality of models. The computer program mechanism also comprises instructions for communicating each model characterization computed in an instance of the instructions for computing.

Still another aspect of the invention comprises a computer program product for use in conjunction with a computer system. The computer program product comprises a computer readable storage medium and a computer program mechanism embedded therein. The computer program mechanism comprises instructions for receiving data. The data comprises one or more aspects of the biological state of each cellular constituent in a plurality of cellular constituents that have been measured in a test organism of a species or a test biological specimen from an organism of the species. The computer program mechanism further comprises instructions for computing a plurality of models. The computing produces a model characterization for each model in the plurality of models that indicates whether the test organism of the species or the test biological specimen from the organism of the species is a member of a biological sample class. The computing comprises characterizing each model in the plurality of models using one or more aspects of the biological state of one or more cellular constituents in the plurality of cellular constituents. The computer program mechanism further comprises instructions for communicating each model characterization computed by the instructions for computing.

Another aspect of the invention provides a method that comprises receiving data. Such data comprises one or more aspects of the biological state of each cellular constituent in a plurality of cellular constituents that have been measured in a test organism of a species or a test biological specimen from an organism of the species. A model in a plurality of models is computed. The computing produces a model characterization for the model that indicates whether the test organism of the species or the test biological specimen from the organism of the species is a member of a biological sample class. The computing of the model comprises characterizing the model using one or more aspects of the biological state of one or more cellular constituents in the plurality of cellular constituents. The computing is repeated one or more times thereby computing the plurality of models. Each of the model characterization computed in an instance of the computing is then communicated.

Still another aspect of the invention comprises receiving data. The data comprises one or more aspects of the biological state of each cellular constituent in a plurality of cellular constituents that have been measured in a test organism of a species or a test biological specimen from an organism of the species. A plurality of models is computed. Such computing produces a model characterization for each model in the plurality of models that indicates whether the test organism of the species or the test biological specimen from the organism of the species is a member of a biological sample class. The computing comprises characterizing each model in the plurality of models using one or more aspects of the biological state of one or more cellular constituents in the plurality of cellular constituents. Each computed model characterization communicated.

Problems solved by technology

Unfortunately some of these patients later develop clinical metastasis.

Such treatments frequently have toxic side effects.

Even taken together, however, these indicators are only poorly predictive.

One problem with each of these aforementioned biological classification schemes is that they each require specialized input (e.g., formatted microarray data).

Because of such obstacles, medical care professionals typically use only a limited subset, at most, of such biological classification schemes.

Images