A Machine Learning Approach for Identifying Gene Biomarkers Guiding the Treatment of Breast Cancer

Can Gut Microbiota Be a Good Predictor for Parkinson's Disease? A Machine Learning Approach

The involvement of the gut microbiota in Parkinson's disease (PD), investigated in several studies, identified some common alterations of the microbial community, such as a decrease in Lachnospiraceae and an increase in Verrucomicrobiaceae families in PD patients. However, the results of other bacterial families are often contradictory. Machine learning is a promising tool for building predictive models for the classification of biological data, such as those produced in metagenomic studies. We tested three different machine learning algorithms (random forest, neural networks and support vector machines), analyzing 846 metagenomic samples (472 from PD patients and 374 from healthy controls), including our published data and those downloaded from public databases. Prediction performance was evaluated by the area under curve, accuracy, precision, recall and F-score metrics. The random forest algorithm provided the best results. Bacterial families were sorted according to their importance in the classification, and a subset of 22 families has been identified for the prediction of patient status. Although the results are promising, it is necessary to train the algorithm with a larger number of samples in order to increase the accuracy of the procedure.

Flexible Data Trimming Improves Performance of Global Machine Learning Methods in Omics-Based Personalized Oncology

(1) Background: Machine learning (ML) methods are rarely used for an omics-based prescription of cancer drugs, due to shortage of case histories with clinical outcome supplemented by high-throughput molecular data. This causes overtraining and high vulnerability of most ML methods. Recently, we proposed a hybrid global-local approach to ML termed floating window projective separator (FloWPS) that avoids extrapolation in the feature space. Its core property is data trimming, i.e., sample-specific removal of irrelevant features. (2) Methods: Here, we applied FloWPS to seven popular ML methods, including linear SVM, k nearest neighbors (kNN), random forest (RF), Tikhonov (ridge) regression (RR), binomial naïve Bayes (BNB), adaptive boosting (ADA) and multi-layer perceptron (MLP). (3) Results: We performed computational experiments for 21 high throughput gene expression datasets (41–235 samples per dataset) totally representing 1778 cancer patients with known responses on chemotherapy treatments. FloWPS essentially improved the classifier quality for all global ML methods (SVM, RF, BNB, ADA, MLP), where the area under the receiver-operator curve (ROC AUC) for the treatment response classifiers increased from 0.61–0.88 range to 0.70–0.94. We tested FloWPS-empowered methods for overtraining by interrogating the importance of different features for different ML methods in the same model datasets. (4) Conclusions: We showed that FloWPS increases the correlation of feature importance between the different ML methods, which indicates its robustness to overtraining. For all the datasets tested, the best performance of FloWPS data trimming was observed for the BNB method, which can be valuable for further building of ML classifiers in personalized oncology.

Identification of LCN1 as a Potential Biomarker for Breast Cancer by Bioinformatic Analysis

The biological functions of lipocalin-1 (LCN1) are involved in innate immune responses and act as a physiological scavenger of potentially harmful lipophilic molecules. However, the relevance of LCN1 with cancer is rarely concerned currently. The aim of this study is to address the relevance of LCN1 with BRCA by bioinformatics. In this study, we found that the expressions of LCN1 increased significantly in various cancerous tissues, including BRCA, compared with their adjacent normal tissues through the TIMER database. Furthermore, UALCAN database analysis showed that the expression of LCN1 increased gradually from stage 1 to stage 4 and was upregulated in BRCA patients with different races and subtypes compared with that in the normal. In addition, those patients with perimenopause and postmenopause status displayed higher LCN1 expression. Importantly, LCN1 genetic alterations, including copy number amplification, deep deletion, and missense mutation, could be found, and the alteration frequency showed difference in various invasive BRCA through cBioPortal database. Moreover, a positive correlation between LCN1 somatic copy number alterations and immune cell enrichments was revealed in basal like BRCA by GISTIC 2.0. Finally, analysis on prognostic value of LCN1 by Kaplan-Meier plotter showed that low LCN1 expression correlated with poor prognosis for relapse-free survival in all types of BRCA, overall survival in luminal B BRCA, distant metastasis free survival in human epithelial growth factor receptor-2 (HER2) positive BRCA, and postprogression survival (PPS) in luminal A BRCA. But high LCN1 expression also displayed poor prognosis for PPS in HER2 positive BRCA. The results together verified the significance of LCN1 in BRCA, suggesting that it may be a potential biomarker for BRCA diagnosis.