The multi-stage hypothesis suggests that cancers develop through a single defined series of genetic alterations. This hypothesis was first suggested over 50 years ago based upon age-specific incidence data. However, recent molecular studies of tumors indicate that multiple routes exist to the formation of cancer, not a single route. This parallel route hypothesis has not been tested with age-specific incidence data.

To test the parallel route hypothesis, I formulated it in terms of a mathematical equation and then tested whether this equation was consistent with age-specific incidence data compiled by the Surveillance Epidemiology and End Results (SEER) cancer registries since 1973. I used the chi-squared goodness of fit test to measure consistency. The age-specific incidence data from most human carcinomas, including those of the colon, lung, prostate, and breast were consistent with the parallel route hypothesis. However, this hypothesis is only consistent if an immune sub-population exists, one that will never develop carcinoma. Furthermore, breast carcinoma has two distinct forms of the disease, and one of these occurs at significantly different rates in different racial groups.

I conclude that the parallel route hypothesis is consistent with the age-specific incidence data only if carcinoma occurs in a distinct sub population, while the multi-stage hypothesis is inconsistent with this data.

Colorectal cancer is the third most common type of cancer in the world. Colorectal cancer begins with small, noncancerous clumps of cells (polyps). Early screening, with colonoscopies, and surgical removal of polyps can prevent the cancer from ever developing. However, colonoscopies are expensive and painful, and the lifetime risk of colon cancer is only 5%. A test to identify people who are likely to develop colon cancer could eliminate needless colonoscopies.

We obtained germline genetic data for 1309 patients diagnosed with colon cancer and compared this to 7517 others who have never been diagnosed with colon cancer. This dataset was collected as part of the Cancer Genome Atlas Program. We used supervised machine learning on this dataset to answer two questions. First, what fraction of these colon cancer patients should be predictable from germline data? Second, how well could such a test perform. We evaluated the performance of five different machine-learning algorithms (gradient boost machine, wide neuron networks, deep neuron networks, dense-sparse neuron networks, and pairwise neuron networks) to answer these questions.

We found that about 78% of colon cancer cases in the dataset should be predictable from germline genetic data. We measured the receiver operating characteristic curve, which quantifies the tradeoff between sensitivity and specificity, for a germline genetic test that could predict a future diagnosis of colon cancer. We measured the area under the receiver operating characteristic curve to be about 0.80. We found that the gradient boost machine and pairwise neuron network algorithms perform equally well, and these two models were significantly better than the others. We conclude that a germline genetic test to predict a future diagnosis of colon cancer could be useful to focus screening on appropriate populations.

Introduction

Methods

Results

Conclusion

Glioblastoma multiforme (GBM) is the most common form of brain cancer. The exact cause of GBM is not well understood. In this thesis, we tested whether germline genetic information could predict who will develop GBM and when will they develop it. We first extracted copy number variation (CNV) data from germline DNA in the peripheral blood samples of 8826 patients in the The Cancer Genome Atlas (TCGA) database. We compared that to 8338 patients in the database who did not develop GBM. We used several machine learning algorithms: deep learning, gradient boosting machine and random forest methods to test whether the germ line genetic data could predict who would develop GBM. The gradient boosting machine algorithm achieved the best results with an 0.82 AUC. We then used this gradient boosting method to test whether germ line DNA information could predict the age of diagnosis of GBM patients. We compared the correlation coefficient between the predicted age and actual age for GBM patients to the predicted correlation coefficient measured for randomized control groups and found a significantly better prediction in the GBM patient group (p-value 0.0004). These results suggest that who develops glioblastoma and when they are diagnosed with glioblastoma is influenced by germline genetics.

Introduction

Methods

Results

Conclusion

Introduction

Methods

Results

Conclusion

Introduction

Methods

Results

Conclusion