Patent US6789069B1 successfully refreshed from Google Patents.
US6789069B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method for enhancing knowledge discovered from biological data using a learning machine
Assignee: Health Discovery Corp
•
Filing: 2000-08-07
•
Granted: 2004-09-07
•
Expires: 2020-08-07
Abstract
Abstract A learning machine is used to extract useful information from vast quantities of biological data. The method includes pre-processing of training data and test data to add dimensionality or to identify missing or erroneous data points. The training data is used to train the learning machine after which the success of the training is tested using the test data. The test output is pre-processed to determine whether the knowledge discovered from the pre-processed test data set is desirable. After the training has been confirmed, live biological data can be pre-processed then input into the trained learning machine for extraction of useful information. In the preferred embodiment, the learning machine is one or more support vector machines.
Inventors
- 👤 Stephen Barnhill
- 👤 Isabelle Guyon
- 👤 Jason Weston
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 11:08
CPC Classifications
G; G06; G06N; G06N20/00; G06F; G06F18/00; G06F18/20; G06F18/21; G06F18/211; G06F18/2113; G06F18/24; G06F18/241; G06F18/2411; G06N20/10; G16; G16B; G16B25/00; G16B25/20; G16B25/30; G16B40/00; G16B40/20
Claims Analysis
Total Claims: 55
Claim 1
Independent Claim
113 words
A method for enhancing knowledge discovered from biological data using a learning machine comprising the steps of: a) pre-processing a training data set derived from biological data to expand each of a plurality of training data points; training the learning machine using the pre-processed training data set; pre-processing a test data set derived from biological data to expand each of a plurality of test data points; testing the trained learning machine using the pre-processed test data set to generate a test output; and in response to receiving the test output of the trained learning machine, post-processing the test output to determine if the knowledge discovered from the pre-processed test data set is desirable.
Claim 2
Independent Claim
113 words
A method for enhancing knowledge discovered from biological data using a learning machine comprising the steps of: a) pre-processing a training data set derived from biological data to expand each of a plurality of training data points; training the learning machine using the pre-processed training data set; pre-processing a test data set derived from biological data to expand each of a plurality of test data points; testing the trained learning machine using the pre-processed test data set to generate a test output; and in response to receiving the test output of the trained learning machine, post-processing the test output to determine if the knowledge discovered from the pre-processed test data set is desirable.
Claim 3
Dependent Claim
34 words
The method of claim 1 , wherein pre-processing the training data set to expand each of the plurality of training data points comprises adding dimensionality to each of the plurality of training data points.
Claim 4
Dependent Claim
39 words
The method of claim 2 , wherein each training data point comprises a vector having one or more original coordinates; and wherein adding dimensionality to each training data point comprises adding one or more new coordinates to the vector.
Claim 5
Dependent Claim
26 words
The method of claim 3 , wherein the new coordinate added to the vector is derived by applying a transformation to one of the original coordinates.
Claim 6
Dependent Claim
14 words
The method of claim 4 , wherein the transformation is based on expert knowledge.
Claim 7
Dependent Claim
12 words
The method of claim 4 , wherein the transformation is computationally derived.
Claim 8
Dependent Claim
29 words
The method of claim 4 , wherein the training data set comprises a continuous variable; and wherein the transformation comprises optimally categorizing the continuous variable of training data set.
Claim 9
Dependent Claim
30 words
The method of claim 1 , wherein post-processing the test output comprises interpreting the test output into a format that may be compared with the plurality of test data points.
Claim 10
Dependent Claim
42 words
The method of claim 1 , wherein the knowledge to be discovered from the data relates to a regression or density estimation; and wherein post-processing the test output comprises optimally categorizing the test output to derive cutoff points in the continuous variable.
Claim 11
Dependent Claim
73 words
The method of claim 1 , wherein the knowledge to be discovered from the data relates to a regression or density estimation; wherein the training output comprises a continuous variable; and wherein the method further comprises the steps of: in response to training the learning machine, receiving a training output from the learning machine, and post-processing the training output by optimally categorizing the test output to derive cutoff points in the continuous variable.
Claim 12
Dependent Claim
21 words
The method of claim 1 , wherein the knowledge discovered from biological data comprises diagnosis or prognosis of a disease state.
Claim 13
Dependent Claim
21 words
The method of claim 1 , wherein the knowledge discovered from biological data comprises efficacy of treatment of a disease state.
Claim 14
Independent Claim
114 words
A method for enhancing knowledge discovered from biological data using a support vector machine comprising the steps of: pre-processing a training data set derived from biological data to add meaning to each of a plurality of training data points; training the support vector machine using the pre-processed training data set; pre-processing a test data set derived from biological data to expand each of a plurality of test data points; testing the trained support vector machine using the pre-processed test data set to generate a test output; and in response to receiving the test output of the trained support vector machine, post-processing the test output to determine if the test output is an optimal solution.
Claim 15
Independent Claim
114 words
A method for enhancing knowledge discovered from biological data using a support vector machine comprising the steps of: pre-processing a training data set derived from biological data to add meaning to each of a plurality of training data points; training the support vector machine using the pre-processed training data set; pre-processing a test data set derived from biological data to expand each of a plurality of test data points; testing the trained support vector machine using the pre-processed test data set to generate a test output; and in response to receiving the test output of the trained support vector machine, post-processing the test output to determine if the test output is an optimal solution.
Claim 16
Dependent Claim
60 words
The method of claim 13 , wherein each training data point comprises a vector having one or more coordinates; and wherein pre-processing the training data set to add meaning to each training data point comprises: determining that the training data point is dirty; and in response to determining that the training data point is dirty, cleaning the training data point.
Claim 17
Dependent Claim
20 words
The method of claim 14 , wherein cleaning the training data point comprises deleting, repairing or replacing the data point.
Claim 18
Dependent Claim
53 words
The method of claim 13 , wherein each training data point comprises a vector having one or more original coordinates; and wherein pre-processing the training data set to add meaning to each training data point comprises adding dimensionality to each training data point by adding one or more new coordinates to the vector.
Claim 19
Dependent Claim
31 words
The method of claim 16 , wherein the one or more new coordinates added to the vector are derived by applying a transformation to one or more of the original coordinates.
Claim 20
Dependent Claim
14 words
The method of claim 17 , wherein the transformation is based on expert knowledge.
Claim 21
Dependent Claim
12 words
The method of claim 17 , wherein the transformation is computationally derived.
Claim 22
Dependent Claim
30 words
The method of claim 17 , wherein the training data set comprises a continuous variable; and wherein the transformation comprises optimally categorizing the continuous variable of the training data set.
Claim 23
Dependent Claim
28 words
The method of claim 13 , wherein post-processing the test output comprises interpreting the test output into a format that may be compared with the test data set.
Claim 24
Dependent Claim
57 words
The method of claim 13 , wherein the knowledge to be discovered from the data relates to a regression or density estimation; wherein a training output comprises a continuous variable; and wherein the method further comprises the step of post-processing the training output by optimally categorizing the training output to derive cutoff points in the continuous variable.
Claim 25
Dependent Claim
66 words
The method of claim 13 , further comprising the steps of: selecting a kernel for the support vector machine prior to training the support vector machine; in response to post-processing the test output, determining that the test output is not the optimal solution; adjusting the selection of the kernel; and in response to adjusting the selection of the kernel, retraining and retesting the support vector machine.
Claim 26
Dependent Claim
41 words
The method of claim 23 , wherein the selection of a kernel is based on prior performance or historical data and is dependent on the nature of the knowledge to be discovered from the data or the nature of the data.
Claim 27
Dependent Claim
71 words
The method of claim 13 , further comprising the steps of: in response to post-processing the test output, determining that the test output is the optimal solution; collecting a live data set; pre-processing the live data set to expand each of a plurality of live data points; inputting the pre-processed live data set to the support vector machine for processing; and receiving the live output of the trained support vector machine.
Claim 28
Dependent Claim
25 words
The method of claim 25 , further comprising the step post-processing the live output by interpreting the live output into a computationally derived alphanumerical classifier.
Claim 29
Dependent Claim
21 words
The method of claim 13 , wherein the knowledge discovered from biological data comprises diagnosis or prognosis of a disease state.
Claim 30
Dependent Claim
21 words
The method of claim 13 , wherein the knowledge discovered from biological data comprises efficacy of treatment of a disease state.
Claim 31
Independent Claim
154 words
A system for enhancing knowledge discovered from biological data using a support vector machine comprising: a storage device for storing a training data set and a test data set; a processor for executing a support vector machine; the processor further operable for: collecting the training data set from the database, pre-processing the training data set to add meaning to each of a plurality of training data points, training the support vector machine using the pre-processed training data set; in response to training the support vector machine, collecting the test data set from the database, pre-processing the test data set to expand each of a plurality of test data points, testing the trained support vector machine using the pre-processed test data set to generate a test output, and in response to receiving the test output of the trained support vector machine, post-processing the test output to determine if the test output is an optimal solution.
Claim 32
Independent Claim
154 words
A system for enhancing knowledge discovered from biological data using a support vector machine comprising: a storage device for storing a training data set and a test data set; a processor for executing a support vector machine; the processor further operable for: collecting the training data set from the database, pre-processing the training data set to add meaning to each of a plurality of training data points, training the support vector machine using the pre-processed training data set; in response to training the support vector machine, collecting the test data set from the database, pre-processing the test data set to expand each of a plurality of test data points, testing the trained support vector machine using the pre-processed test data set to generate a test output, and in response to receiving the test output of the trained support vector machine, post-processing the test output to determine if the test output is an optimal solution.
Claim 33
Dependent Claim
74 words
The system of claim 29 , further comprising a communications device for receiving the test data set and the training data set from a remote source; and wherein the processor is further operable to store the training data set in the storage device prior to collection and pre-processing of the training data set and to store the test data set in the storage device prior to collection and pre-processing of the test data set.
Claim 34
Dependent Claim
17 words
The system of claim 29 , further comprising a display device for displaying the post-processed test data.
Claim 35
Dependent Claim
53 words
The system of claim 29 , wherein each training data point comprises a vector having one or more original coordinates; and wherein pre-processing the training data set to add meaning to each training data point comprises adding dimensionality to each training data point by adding one or more new coordinates to the vector.
Claim 36
Dependent Claim
31 words
The system of claim 32 , wherein the one or more new coordinates added to the vector are derived by applying a transformation to one or more of the original coordinates.
Claim 37
Dependent Claim
14 words
The system of claim 33 , wherein the transformation is based on expert knowledge.
Claim 38
Dependent Claim
12 words
The system of claim 33 , wherein the transformation is computationally derived.
Claim 39
Dependent Claim
30 words
The system of claim 33 , wherein the training data set comprises a continuous variable; and wherein the transformation comprises optimally categorizing the continuous variable of the training data set.
Claim 40
Dependent Claim
31 words
The system of claim 29 , wherein the test output comprises a continuous variable; and wherein post-processing the test output comprises optimally categorizing the continuous variable of the test data set.
Claim 41
Dependent Claim
52 words
The system of claim 29 , wherein the knowledge to be discovered from the data relates to a regression or density estimation; wherein a training output comprises a continuous variable; and wherein the processor is further operable for post-processing the training output by optimally categorizing the continuous variable of the training output.
Claim 42
Dependent Claim
25 words
The system of claim 38 , wherein optimally categorizing the training output comprises determining optimal cutoff points in the continuous variable based on entropy calculations.
Claim 43
Dependent Claim
68 words
The system of claim 29 , wherein the processor is further operable for: selecting a kernel for the support vector machine prior to training the support vector machine; in response to post-processing the test output, determining that the test output is not the optimal solution; adjusting the selection of the kernel; and in response to adjusting the selection of the kernel, retraining and retesting the support vector machine.
Claim 44
Dependent Claim
41 words
The system of claim 40 , wherein the selection of a kernel is based on prior performance or historical data and is dependant on the nature of the knowledge to be discovered from the data or the nature of the data.
Claim 45
Dependent Claim
93 words
The system of claim 29 , wherein a live data set is stored in the storage device; and wherein the processor is further operable for: in response to post-processing the test output, determining that the test output is the optimal solution, collecting the live data set from the storage device; pre-processing the live data set to expand each of a plurality of live data points; inputting the pre-processed live data set to the support vector machine for processing to generate live output; and receiving the live output of the trained support vector machine.
Claim 46
Dependent Claim
28 words
The system of claim 42 , wherein the processor is further operable for post-processing the live output by interpreting the live output into a computationally derived alphanumerical classifier.
Claim 47
Dependent Claim
26 words
The system of claim 43 , wherein the communications device is further operable to send the alphanumerical classifier to the remote source or another remote source.
Claim 48
Dependent Claim
21 words
The system of claim 29 , wherein the knowledge discovered from biological data comprises diagnosis or prognosis of a disease state.
Claim 49
Dependent Claim
21 words
The system of claim 29 , wherein the knowledge discovered from biological data comprises efficacy of treatment of a disease state.
Claim 50
Independent Claim
107 words
A method for diagnosing disease, comprising, using a learning machine comprising, a) pre-processing a training data set derived from biological data to expand each of a plurality of training data points; training the learning machine using the pre-processed training data set; pre-processing a test data set derived from biological data to expand each of a plurality of test data points; testing the trained learning machine using the pre-processed test data set to generate a test output; and in response to receiving the test output of the trained learning machine, post-processing the test output to determine if the knowledge discovered from the pre-processed test data set is desirable.
Claim 51
Independent Claim
107 words
A method for diagnosing disease, comprising, using a learning machine comprising, a) pre-processing a training data set derived from biological data to expand each of a plurality of training data points; training the learning machine using the pre-processed training data set; pre-processing a test data set derived from biological data to expand each of a plurality of test data points; testing the trained learning machine using the pre-processed test data set to generate a test output; and in response to receiving the test output of the trained learning machine, post-processing the test output to determine if the knowledge discovered from the pre-processed test data set is desirable.
Claim 52
Dependent Claim
11 words
The method of claim 47 , wherein the disease is cancer.
Claim 53
Dependent Claim
12 words
The method of claim 48 , wherein the cancer is colon cancer.
Claim 54
Dependent Claim
12 words
The method of claim 48 , wherein the cancer is breast cancer.
Claim 55
Dependent Claim
21 words
The method of claim 47 , wherein the knowledge discovered from the test data set comprises genes associated with the disease.
References Cited (Backward Citations)
US4881178A
Cited
US5138694A
Cited
US5649068A
Cited
US5627945A
Cited
US5809144A
Cited
US5950146A
Cited
US6112195A
Cited
US6134344A
Cited
US6128608A
Cited
US6157921A
Cited
US6427141B1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2007-09-07 | 2008-03-08 | 2008-09-07 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2011-09-07 | 2012-03-08 | 2012-09-07 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2015-09-07 | 2016-03-08 | 2016-09-07 | $7700.00 | Window Closed / Lapsed |