A Novel Epigenetic Machine Learning Model to Define Risk of Progression for Hepatocellular Carcinoma Patients.

Although extensive advancements have been made in treatment against hepatocellular carcinoma (HCC), the prognosis of HCC patients remains unsatisfied. It is now clearly established that extensive epigenetic changes act as a driver in human tumors. This study exploits HCC epigenetic deregulation to define a novel prognostic model for monitoring the progression of HCC. We analyzed the genome-wide DNA methylation profile of 374 primary tumor specimens using the Illumina 450 K array data from The Cancer Genome Atlas. We initially used a novel combination of Machine Learning algorithms (Recursive Features Selection, Boruta) to capture early tumor progression features. The subsets of probes obtained were used to train and validate Random Forest models to predict a Progression Free Survival greater or less than 6 months. The model based on 34 epigenetic probes showed the best performance, scoring 0.80 accuracy and 0.51 Matthews Correlation Coefficient on testset. Then, we generated and validated a progression signature based on 4 methylation probes capable of stratifying HCC patients at high and low risk of progression. Survival analysis showed that high risk patients are characterized by a poorer progression free survival compared to low risk patients. Moreover, decision curve analysis confirmed the strength of this predictive tool over conventional clinical parameters. Functional enrichment analysis highlighted that high risk patients differentiated themselves by the upregulation of proliferative pathways. Ultimately, we propose the oncogenic MCM2 gene as a methylation-driven gene of which the representative epigenetic markers could serve both as predictive and prognostic markers. Briefly, our work provides several potential HCC progression epigenetic biomarkers as well as a new signature that may enhance patients surveillance and advances in personalized treatment.

Machine Learning Application Identifies Germline Markers of Hypertension in Patients With Ovarian Cancer Treated With Carboplatin, Taxane, and Bevacizumab.

Pharmacogenomics studies how genes influence a person's response to treatment. When complex phenotypes are influenced by multiple genetic variations with little effect, a single piece of genetic information is often insufficient to explain this variability. The application of machine learning (ML) in pharmacogenomics holds great potential - namely, it can be used to unravel complicated genetic relationships that could explain response to therapy. In this study, ML techniques were used to investigate the relationship between genetic variations affecting more than 60 candidate genes and carboplatin-induced, taxane-induced, and bevacizumab-induced toxicities in 171 patients with ovarian cancer enrolled in the MITO-16A/MaNGO-OV2A trial. Single-nucleotide variation (SNV, formerly SNP) profiles were examined using ML to find and prioritize those associated with drug-induced toxicities, specifically hypertension, hematological toxicity, nonhematological toxicity, and proteinuria. The Boruta algorithm was used in cross-validation to determine the significance of SNVs in predicting toxicities. Important SNVs were then used to train eXtreme gradient boosting models. During cross-validation, the models achieved reliable performance with a Matthews correlation coefficient ranging from 0.375 to 0.410. A total of 43 SNVs critical for predicting toxicity were identified. For each toxicity, key SNVs were used to create a polygenic toxicity risk score that effectively divided individuals into high-risk and low-risk categories. In particular, compared with low-risk individuals, high-risk patients were 28-fold more likely to develop hypertension. The proposed method provided insightful data to improve precision medicine for patients with ovarian cancer, which may be useful for reducing toxicities and improving toxicity management.

Machine Learning Application in a Phase I Clinical Trial Allows for the Identification of Clinical-Biomolecular Markers Significantly Associated With Toxicity.

Machine learning (ML) algorithms have been used to forecast clinical outcomes or drug adverse effects by analyzing different data sets such as electronic health records, diagnostic data, and molecular data. However, ML implementation in phase I clinical trial is still an unexplored strategy that implies challenges such as the selection of the best development strategy when dealing with limited sample size. In the attempt to better define prechemotherapy baseline clinical and biomolecular predictors of drug toxicity, we trained and compared five ML algorithms starting from clinical, blood biochemistry, and genotype data derived from a previous phase Ib study aimed to define the maximum tolerated dose of irinotecan (FOLFIRI (folinic acid, fluorouracil, and irinotecan) plus bevacizumab regimen) in patients with metastatic colorectal cancer. During cross-validation the Random Forest algorithm achieved the best performance with a mean Matthews correlation coefficient of 0.549 and a mean accuracy of 80.4%; the best predictors of dose-limiting toxicity at baseline were hemoglobin, serum glutamic oxaloacetic transaminase (SGOT), and albumin. The feasibility of a prediction model prototype was in principle assessed using the two distinct dose escalation cohorts, where in the validation cohort the model scored a Matthews correlation coefficient of 0.59 and an accuracy of 82.0%. Moreover, we found a strong relationship between SGOT and irinotecan pharmacokinetics, suggesting its role as surrogates' estimators of the irinotecan metabolism equilibrium. In conclusion, the potential application of ML techniques to phase I study could provide clinicians with early prediction tools useful both to ameliorate the management of clinical trials and to make more adequate treatment decisions.

An online tool for fetal fraction prediction based on direct size distribution analysis of maternal cell-free DNA.

The discovery of circulating fetal DNA in the plasma of pregnant women has greatly promoted advances in noninvasive prenatal testing. Screening performance is enhanced with higher fetal fraction and analysis of samples whose fetal DNA fraction is lower than 4% are unreliable. Although current approaches to fetal fraction measurement are accurate, most of them are expensive and time consuming. Here we present a simple and cost-effective solution that provides a quick and reasonably accurate fetal fraction by directly evaluating the size distribution of circulating DNA fragments in the extracted maternal cell-free DNA. The presented approach could be useful in the presequencing stage of noninvasive prenatal testing to evaluate whether the sample is suitable for the test or a repeat blood draw is recommended.

A New Epigenetic Model to Stratify Glioma Patients According to Their Immunosuppressive State.

Gliomas are the most common primary neoplasm of the central nervous system. A promising frontier in the definition of glioma prognosis and treatment is represented by epigenetics. Furthermore, in this study, we developed a machine learning classification model based on epigenetic data (CpG probes) to separate patients according to their state of immunosuppression. We considered 573 cases of low-grade glioma (LGG) and glioblastoma (GBM) from The Cancer Genome Atlas (TCGA). First, from gene expression data, we derived a novel binary indicator to flag patients with a favorable immune state. Then, based on previous studies, we selected the genes related to the immune state of tumor microenvironment. After, we improved the selection with a data-driven procedure, based on Boruta. Finally, we tuned, trained, and evaluated both random forest and neural network classifiers on the resulting dataset. We found that a multi-layer perceptron network fed by the 338 probes selected by applying both expert choice and Boruta results in the best performance, achieving an out-of-sample accuracy of 82.8%, a Matthews correlation coefficient of 0.657, and an area under the ROC curve of 0.9. Based on the proposed model, we provided a method to stratify glioma patients according to their epigenomic state.