AucPR: an AUC-based approach using penalized regression for disease prediction with high-dimensional omics data

A classification for complex imbalanced data in disease screening and early diagnosis

Imbalanced classification has drawn considerable attention in the statistics and machine learning literature. Typically, traditional classification methods often perform poorly when a severely skewed class distribution is observed, not to mention under a high-dimensional longitudinal data structure. Given the ubiquity of big data in modern health research, it is expected that imbalanced classification in disease diagnosis may encounter an additional level of difficulty that is imposed by such a complex data structure. In this article, we propose a nonparametric classification approach for imbalanced data in longitudinal and high-dimensional settings. Technically, the functional principal component analysis is first applied for feature extraction under the longitudinal structure. The univariate exponential loss function coupled with group LASSO penalty is then adopted into the classification procedure in high-dimensional settings. Along with a good improvement in imbalanced classification, our approach provides a meaningful feature selection for interpretation while enjoying a remarkably lower computational complexity. The proposed method is illustrated on the real data application of Alzheimer's disease early detection and its empirical performance in finite sample size is extensively evaluated by simulations.

A Modified AUC for Training Convolutional Neural Networks: Taking Confidence Into Account

Receiver operating characteristic (ROC) curve is an informative tool in binary classification and Area Under ROC Curve (AUC) is a popular metric for reporting performance of binary classifiers. In this paper, first we present a comprehensive review of ROC curve and AUC metric. Next, we propose a modified version of AUC that takes confidence of the model into account and at the same time, incorporates AUC into Binary Cross Entropy (BCE) loss used for training a Convolutional neural Network for classification tasks. We demonstrate this on three datasets: MNIST, prostate MRI, and brain MRI. Furthermore, we have published GenuineAI, a new python library, which provides the functions for conventional AUC and the proposed modified AUC along with metrics including sensitivity, specificity, recall, precision, and F1 for each point of the ROC curve.

Comparative Analysis of Unsupervised Protein Similarity Prediction Based on Graph Embedding

The study of protein-protein interaction and the determination of protein functions are important parts of proteomics. Computational methods are used to study the similarity between proteins based on Gene Ontology (GO) to explore their functions and possible interactions. GO is a series of standardized terms that describe gene products from molecular functions, biological processes, and cell components. Previous studies on assessing the similarity of GO terms were primarily based on Information Content (IC) between GO terms to measure the similarity of proteins. However, these methods tend to ignore the structural information between GO terms. Therefore, considering the structural information of GO terms, we systematically analyze the performance of the GO graph and GO Annotation (GOA) graph in calculating the similarity of proteins using different graph embedding methods. When applied to the actual Human and Yeast datasets, the feature vectors of GO terms and proteins are learned based on different graph embedding methods. To measure the similarity of the proteins annotated by different GO numbers, we used Dynamic Time Warping (DTW) and cosine to calculate protein similarity in GO graph and GOA graph, respectively. Link prediction experiments were then performed to evaluate the reliability of protein similarity networks constructed by different methods. It is shown that graph embedding methods have obvious advantages over the traditional IC-based methods. We found that random walk graph embedding methods, in particular, showed excellent performance in calculating the similarity of proteins. By comparing link prediction experiment results from GO(DTW) and GOA(cosine) methods, it is shown that GO(DTW) features provide highly effective information for analyzing the similarity among proteins.

Large-Scale Automatic Feature Selection for Biomarker Discovery in High-Dimensional OMICs Data

The identification of biomarker signatures in omics molecular profiling is usually performed to predict outcomes in a precision medicine context, such as patient disease susceptibility, diagnosis, prognosis, and treatment response. To identify these signatures, we have developed a biomarker discovery tool, called BioDiscML. From a collection of samples and their associated characteristics, i.e., the biomarkers (e.g., gene expression, protein levels, clinico-pathological data), BioDiscML exploits various feature selection procedures to produce signatures associated to machine learning models that will predict efficiently a specified outcome. To this purpose, BioDiscML uses a large variety of machine learning algorithms to select the best combination of biomarkers for predicting categorical or continuous outcomes from highly unbalanced datasets. The software has been implemented to automate all machine learning steps, including data pre-processing, feature selection, model selection, and performance evaluation. BioDiscML is delivered as a stand-alone program and is available for download at https://github.com/mickaelleclercq/BioDiscML.