Support vector machines (SVMs) are widely employed in molecular diagnosis of disease for their efficiency and robustness. However, there is no previous research to analyze their overfitting in high-dimensional omics data based disease diagnosis, which is essential to avoid deceptive diagnostic results and enhance clinical decision making. In this work, we comprehensively investigate this problem from both theoretical and practical standpoints to unveil the special characteristics of SVM overfitting. We found that disease diagnosis under an SVM classifier would inevitably encounter overfitting under a Gaussian kernel because of the large data variations generated from high-throughput profiling technologies. Furthermore, we propose a novel sparse-coding kernel approach to overcome SVM overfitting in disease diagnosis. Unlike traditional ad-hoc parametric tuning approaches, it not only robustly conquers the overfitting problem, but also achieves good diagnostic accuracy. To our knowledge, it is the first rigorous method proposed to overcome SVM overfitting. Finally, we propose a novel biomarker discovery algorithm: Gene-Switch-Marker (GSM) to capture meaningful biomarkers by taking advantage of SVM overfitting on single genes.

MicroRNAs (miRNAs) are a class of important non-coding RNAs, which play important roles in tumorigenesis and development by targeting oncogenes or tumor suppressor genes. One miRNA can regulate multiple genes, and one gene can be regulated by multiple miRNAs. To promote the clinical application of miRNAs, two fundamental questions should be answered: what's the regulatory mechanism of a miRNA to a gene, and which miRNAs are important for a specific type of cancer. In this study, we propose a miRNA influence capturing (miRNAInf) to decipher regulation relations of miRNAs on target genes and identify critical miRNAs in cancers in a systematic approach. With the pair-wise miRNA/gene expression profiles data, we consider the assigning problem of a miRNA on target genes and determine the regulatory mechanisms by computing the Pearson correlation coefficient between the expression changes of a miRNA and that of its target gene. Furthermore, we compute the relative local influence strength of a miRNA on its target gene. Finally, integrate the local influence strength and target gene's importance to determine the critical miRNAs involved in specific cancer. Results on breast, liver and prostate cancers show that positive regulations are as common as negative regulations. The top-ranked miRNAs show great potential as therapeutic targets driving cancer to a normal state, and they are demonstrated to be closely related to cancers based on biological functional analysis, drug sensitivity/resistance analysis and survival analysis. This study will be helpful for the discovery of critical miRNAs and development of miRNAs-based clinical therapeutics.

Artificial intelligence (AI) is revolutionizing biomedical data science at an unprecedented pace, transforming various aspects of the field with remarkable speed and depth. However, a critical issue remains unclear: how reproducible are the AI models and systems employed in biomedical data science? In this study, we examine the challenges of AI reproducibility by analyzing the factors influenced by data, model, and learning complexities, as well as through a game-theoretical perspective. While adherence to reproducibility standards is essential for the long-term advancement of AI, the conflict between following these standards and aligning with researchers’ personal goals remains a significant hurdle in achieving AI reproducibility.

The utilization of both constrained and unconstrained-based optimization for solving constrained multi-objective optimization problems (CMOPs) has become prevalent among recently proposed constrained multiobjective evolutionary algorithms (CMOEAs). However, the constrained-based optimization which adopted by many CMOEAs typically gives priority to feasible solutions over infeasible ones regardless of their objective values, potentially leading to degraded performance due to the elimination of promising infeasible solutions with strong convergence and diversity. Furthermore, many existing CMOEAs have difficulty in maintaining diversity while focusing on feasibility, thereby hindering their ability to effectively address CMOPs characterized by complex feasible regions. To tackle these challenges, a constraint-Pareto dominance relationship is proposed in this paper to evaluate solutions based on both objectives and feasibility, to improve the optimization potential by reduce the elimination probability of promising infeasible solutions. A diversity enhancement strategy is also designed to enable simultaneously focus on both diversity and feasibility, thus effectively ensuring the diversity of the feasible solutions obtained. Empirical results from benchmark suites and real-world problems demonstrate that our proposed algorithm surpasses state-of-the-art CMOEAs.

Speech emotion recognition is a substantial component of natural language processing (NLP). It has strict requirements for the effectiveness of feature extraction and that of the acoustic model. With that in mind, a Heterogeneous Parallel Convolution Bi-LSTM model is proposed to address the challenges. It consists of two heterogeneous branches: the left one contains two dense layers and a Bi-LSTM layer, while the right one contains a dense layer, a convolution layer, and a Bi-LSTM layer. It can exploit the spatiotemporal information more effectively, and achieves 84.65%, 79.67%, and 56.50% unweighted average recalls on the benchmark databases EMODB, CASIA, and SAVEE, respectively. Compared with the previous research results, the proposed model achieves better performance stably.