Methods and systems for determination of an effective therapeutic regimen and drug discovery
The present invention relates to the discovery of a method for identifying a treatment regimen for a patient diagnosed with cancer, predicting patient resistance to therapeutic agents and identifying new therapeutic agents. Specifically, the present invention relates to the use of an algorithm to identify a mutation in a kinase, determine if the mutation is an activation or resistance mutation and then to suggest an appropriate therapeutic regimen. The invention also relates to the use of a pattern matching algorithm and a crystal structure library to predict the functionality of a gene mutation, predict the specificity of small molecule kinase inhibitors and for the identification of new therapeutic agents.
1. A method of treating a subject with cancer comprising:
a) obtaining a biologic sample from the subject;
b) identifying at least one mutation in a gene sequence from the sample;
c) executing with a computer at least one program embodied on a computer-readable medium, the at least one program including at least one pattern matching machine learning algorithm to determine if the at least one mutation is a cancer associated activation mutation or a therapeutic agent resistance mutation, and to search a crystal structure library to select at least one therapeutic agent to target the activation mutation or the resistance mutation, the pattern matching machine learning algorithm being trained on a collection of patterns of known cancer associated activation mutations, patterns of known therapeutic agent resistance mutations and patterns of known therapeutic agents, the pattern matching machine algorithm also classifying mutations based on a plurality of kinase DFG patterns; and
d) treating the subject with the at least one therapeutic agent.
2. The method of claim 1 , wherein the at least one mutation is identified by sequence analysis.
3. The method of claim 1 , wherein the at least one mutation is in the gene sequence of a receptor or a kinase.
4. The method of claim 3 , wherein the at least one mutation is in the catalytic domain of a kinase.
5. The method of claim 4 , wherein the at least one mutation results in a novel kinase conformation.
6. The method of claim 3 , wherein the receptor is the estrogen receptor.
7. The method of claim 3 , wherein the receptor is an estrogen receptor 1 or estrogen receptor 2.
8. The method of claim 1 , wherein the crystal structure library comprises a kinase crystal structure database, receptor crystal structure database and/or a therapeutic agent crystal structure database.
9. The method of claim 1 , wherein the biological sample is selected from the group consisting of blood, saliva, urine, bone marrow, serum, lymph, cerebrospinal fluid, sputum, stool, organ tissue and ejaculate sample.
10. The method of claim 1 , wherein the at least one mutation comprises an activation mutation or a resistance mutation.
11. The method of claim 1 , wherein the therapeutic agent is a kinase inhibitor and/or a chemotherapeutic agent.
12. The method of claim 1 , further comprising applying the at least one algorithm to test known patterns, different than the collections of patterns, to determine the accuracy of the at least one algorithm.
13. The method of claim 1 , wherein the plurality of kinase DFG patterns include an IN conformation, an OUT conformation and an INTERMEDIATE conformation.
14. A method for identifying a therapeutic regimen or predicting resistance to a therapeutic regimen for a subject with cancer comprising:
a) obtaining a biologic sample from the subject;
b) identifying at least one mutation in a gene sequence from the sample;
c) executing with a computer at least one program embodied on a computer-readable medium, the at least one program including at least one pattern matching machine learning algorithm to determine if the at least one mutation is a cancer associated activation mutation or a therapeutic agent resistance mutation, and to search a crystal structure library to select at least one therapeutic agent to target the activation mutation or the resistance mutation, the pattern matching machine learning algorithm being trained on a collection of patterns of known cancer associated activation mutations, patterns of known therapeutic agent resistance mutations and patterns of known therapeutic agents, the pattern matching machine algorithm also classifying mutations based on a plurality of kinase DFG patterns,
thereby identifying a therapeutic regimen or predicting resistance to a therapeutic regimen.
15. The method of claim 14 , further comprising applying the at least one algorithm to test known patterns, different than the collections of patterns, to determine the accuracy of the at least one algorithm.
16. The method of claim 14 , wherein the plurality of kinase DFG patterns include an IN conformation, an OUT conformation and an INTERMEDIATE conformation.