Using Machine Learning and Natural Language Processing to Review and Classify the Medical Literature on Cancer Susceptibility Genes.

PURPOSE: The medical literature relevant to germline genetics is growing exponentially. Clinicians need tools that help to monitor and prioritize the literature to understand the clinical implications of pathogenic genetic variants. We developed and evaluated two machine learning models to classify abstracts as relevant to the penetrance-risk of cancer for germline mutation carriers-or prevalence of germline genetic mutations. MATERIALS AND METHODS: We conducted literature searches in PubMed and retrieved paper titles and abstracts to create an annotated data set for training and evaluating the two machine learning classification models. Our first model is a support vector machine (SVM) which learns a linear decision rule on the basis of the bag-of-ngrams representation of each title and abstract. Our second model is a convolutional neural network (CNN) which learns a complex nonlinear decision rule on the basis of the raw title and abstract. We evaluated the performance of the two models on the classification of papers as relevant to penetrance or prevalence. RESULTS: For penetrance classification, we annotated 3,740 paper titles and abstracts and evaluated the two models using 10-fold cross-validation. The SVM model achieved 88.93% accuracy-percentage of papers that were correctly classified-whereas the CNN model achieved 88.53% accuracy. For prevalence classification, we annotated 3,753 paper titles and abstracts. The SVM model achieved 88.92% accuracy and the CNN model achieved 88.52% accuracy. CONCLUSION: Our models achieve high accuracy in classifying abstracts as relevant to penetrance or prevalence. By facilitating literature review, this tool could help clinicians and researchers keep abreast of the burgeoning knowledge of gene-cancer associations and keep the knowledge bases for clinical decision support tools up to date.

Artificial Anti-Tumor Opsonizing Proteins with Fibronectin Scaffolds Engineered for Specificity to Each of the Murine FcγR Types.

We have engineered a panel of novel Fn3 scaffold-based proteins that bind with high specificity and affinity to each of the individual mouse Fcγ receptors (mFcγR). These binders were expressed as fusions to anti-tumor antigen single-chain antibodies and mouse serum albumin, creating opsonizing agents that invoke only a single mFcγR response rather than the broader activity of natural Fc isotypes, as well as all previously reported Fc mutants. This panel isolated the capability of each of the four mFcγRs to contribute to macrophage phagocytosis of opsonized tumor cells and in vivo tumor growth control with these monospecific opsonizing fusion proteins. All activating receptors (mFcγRI, mFcγRIII, and mFcγRIV) were capable of driving specific tumor cell phagocytosis to an equivalent extent, while mFcγRII, the inhibitory receptor, did not drive phagocytosis. Monospecific opsonizing fusion proteins that bound mFcγRI alone controlled tumor growth to an extent similar to the most active IgG2a murine isotype. As expected, binding to the inhibitory mFcγRII did not delay tumor growth, but unexpectedly, mFcγRIII also failed to control tumor growth. mFcγRIV exhibited detectable but lesser tumor-growth control leading to less overall survival compared to mFcγRI. Interestingly, in vivo macrophage depletion demonstrates their importance in tumor control with mFcγRIV engagement, but not with mFcγRI. This panel of monospecific mFcγR-binding proteins provides a toolkit for isolating the functional effects of each mFcγR in the context of an intact immune system.