Identifying diagnostic biomarkers for cancer is crucial in the field of personalized medicine. The available transcriptome and interactome provide unprecedented opportunities and challenges for biomarker screening. From a systematic perspective, network-based medicine methods provide alternative approaches to organizing the available high-throughput omics data for deciphering molecular interactions and their associations with phenotypic states. In this work, we propose a bioinformatics strategy named TopMarker for discovering diagnostic biomarkers by comparing the network topology differences in control and disease samples. Specifically, we build up gene-gene interaction networks in the two states of control and disease respectively. The network rewiring status across the two networks results in differential network topologies reflecting dynamics and changes in normal samples when compared with those in disease. Thus, we identify the potential biomarker genes with differential network topological parameters between the control and disease gene networks. For a proof-of-concept study, we introduce the computational pipeline of biomarker discovery in hepatocellular carcinoma (HCC). We prove the effectiveness of the proposed TopMarker method using these candidate biomarkers in classifying HCC samples and validate its signature capability across numerous independent datasets. We also compare the discriminant power of biomarker genes identified by TopMarker with those identified by other baseline methods. The higher classification performances and functional implications indicate the advantages of our proposed method for discovering biomarkers from differential network topology.

OBJECTIVE: This study aimed to identify significantly differentially expressed genes (DEGs) related to cervical cancer by exploring extensive gene expression datasets to unveil new therapeutic targets.
METHODS: Gene expression profiles were extracted from the Gene Expression Omnibus, The Cancer Genome Atlas, and the Genotype-Tissue Expression platforms. A differential expression analysis identified DEGs in cervical cancer cases. Weighted gene co-expression network analysis (WGCNA) was implemented to locate genes closely linked to the clinical traits of diseases. Machine learning algorithms, including LASSO regression and the random forest algorithm, were applied to pinpoint key genes.
RESULTS: The investigation successfully isolated DEGs pertinent to cervical cancer. Interleukin-24 was recognized as a pivotal gene via WGCNA and machine learning techniques. Experimental validations demonstrated that human interleukin (hIL)-24 inhibited proliferation, migration, and invasion, while promoting apoptosis, in SiHa and HeLa cervical cancer cells, affirming its role as a therapeutic target.
CONCLUSIONS: The multi-database analysis strategy employed herein emphasized hIL-24 as a principal gene in cervical cancer pathogenesis. The findings suggest hIL-24 as a promising candidate for targeted therapy, offering a potential avenue for innovative treatment modalities. This study enhances the understanding of molecular mechanisms of cervical cancer and aids in the pursuit of novel oncological therapies.

BACKGROUND: There is a great need to develop a computational approach to analyze and exploit the information contained in gene expression data. The recent utilization of nonnegative matrix factorization (NMF) in computational biology has demonstrated the capability to derive essential details from a high amount of data in particular gene expression microarrays. A common problem in NMF is finding the proper number rank (r) of factors of the degraded demonstration, but no agreement exists on which technique is most appropriate to utilize for this purpose. Thus, various techniques have been suggested to select the optimal value of rank factorization (r).
OBJECTIVE: In this work, a new metric for rank selection is proposed based on the elbow method, which was methodically compared against the cophenetic metric.
METHODS: To decide the optimum number rank (r), this study focused on the unit invariant knee (UIK) method of the NMF on gene expression data sets. Since the UIK method requires an extremum distance estimator that is eventually employed for inflection and identification of a knee point, the proposed method finds the first inflection point of the curvature of the residual sum of squares of the proposed algorithms using the UIK method on gene expression data sets as a target matrix.
RESULTS: Computation was conducted for the UIK task using gene expression data of acute lymphoblastic leukemia and acute myeloid leukemia samples. Consequently, the distinct results of NMF were subjected to comparison on different algorithms. The proposed UIK method is easy to perform, fast, free of a priori rank value input, and does not require initial parameters that significantly influence the model\'s functionality.
CONCLUSIONS: This study demonstrates that the elbow method provides a credible prediction for both gene expression data and for precisely estimating simulated mutational processes data with known dimensions. The proposed UIK method is faster than conventional methods, including metrics utilizing the consensus matrix as a criterion for rank selection, while achieving significantly better computational efficiency without visual inspection on the curvatives. Finally, the suggested rank tuning method based on the elbow method for gene expression data is arguably theoretically superior to the cophenetic measure.

UNASSIGNED: Selecting an appropriate similarity measurement method is crucial for obtaining biologically meaningful clustering modules. Commonly used measurement methods are insufficient in capturing the complexity of biological systems and fail to accurately represent their intricate interactions.
UNASSIGNED: This study aimed to obtain biologically meaningful gene modules by using the clustering algorithm based on a similarity measurement method.
UNASSIGNED: A new algorithm called the Dual-Index Nearest Neighbor Similarity Measure (DINNSM) was proposed. This algorithm calculated the similarity matrix between genes using Pearson\'s or Spearman\'s correlation. It was then used to construct a nearest-neighbor table based on the similarity matrix. The final similarity matrix was reconstructed using the positions of shared genes in the nearest neighbor table and the number of shared genes.
UNASSIGNED: Experiments were conducted on five different gene expression datasets and compared with five widely used similarity measurement techniques for gene expression data. The findings demonstrate that when utilizing DINNSM as the similarity measure, the clustering results performed better than using alternative measurement techniques.
UNASSIGNED: DINNSM provided more accurate insights into the intricate biological connections among genes, facilitating the identification of more accurate and biological gene co-expression modules.

High-throughput technologies are becoming increasingly important in discovering prognostic biomarkers and in identifying novel drug targets. With Mammaprint, Oncotype DX, and many other prognostic molecular signatures breast cancer is one of the paradigmatic examples of the utility of high-throughput data to deliver prognostic biomarkers, that can be represented in a form of a rather short gene list. Such gene lists can be obtained as a set of features (genes) that are important for the decisions of a Machine Learning (ML) method applied to high-dimensional gene expression data. Several studies have identified predictive gene lists for patient prognosis in breast cancer, but these lists are unstable and have only a few genes in common. Instability of feature selection impedes biological interpretability: genes that are relevant for cancer pathology should be members of any predictive gene list obtained for the same clinical type of patients. Stability and interpretability of selected features can be improved by including information on molecular networks in ML methods. Graph Convolutional Neural Network (GCNN) is a contemporary deep learning approach applicable to gene expression data structured by a prior knowledge molecular network. Layer-wise Relevance Propagation (LRP) and SHapley Additive exPlanations (SHAP) are methods to explain individual decisions of deep learning models. We used both GCNN+LRP and GCNN+SHAP techniques to construct feature sets by aggregating individual explanations. We suggest a methodology to systematically and quantitatively analyze the stability, the impact on the classification performance, and the interpretability of the selected feature sets. We used this methodology to compare GCNN+LRP to GCNN+SHAP and to more classical ML-based feature selection approaches. Utilizing a large breast cancer gene expression dataset we show that, while feature selection with SHAP is useful in applications where selected features have to be impactful for classification performance, among all studied methods GCNN+LRP delivers the most stable (reproducible) and interpretable gene lists.

BACKGROUND: Helicobacter pylori is considered a true human pathogen for which rising drug resistance constitutes a drastic concern globally. The present study aimed to reconstruct a genome-scale metabolic model (GSMM) to decipher the metabolic capability of H. pylori strains in response to clarithromycin and rifampicin along with identification of novel drug targets.
METHODS: The iIT341 model of H. pylori was updated based on genome annotation data, and biochemical knowledge from literature and databases. Context-specific models were generated by integrating the transcriptomic data of clarithromycin and rifampicin resistance into the model. Flux balance analysis was employed for identifying essential genes in each strain, which were further prioritized upon being nonhomologs to humans, virulence factor analysis, druggability, and broad-spectrum analysis. Additionally, metabolic differences between sensitive and resistant strains were also investigated based on flux variability analysis and pathway enrichment analysis of transcriptomic data.
RESULTS: The reconstructed GSMM was named as HpM485 model. Pathway enrichment and flux variability analyses demonstrated reduced activity in the ribosomal pathway in both clarithromycin- and rifampicin-resistant strains. Also, a significant decrease was detected in the activity of metabolic pathways of clarithromycin-resistant strain. Moreover, 23 and 16 essential genes were exclusively detected in clarithromycin- and rifampicin-resistant strains, respectively. Based on prioritization analysis, cyclopropane fatty acid synthase and phosphoenolpyruvate synthase were identified as putative drug targets in clarithromycin- and rifampicin-resistant strains, respectively.
CONCLUSIONS: We present a robust and reliable metabolic model of H. pylori. This model can predict novel drug targets to combat drug resistance and explore the metabolic capability of H. pylori in various conditions.

UNASSIGNED: Gene expression data is typically high dimensional with a limited number of samples and contain many features that are unrelated to the disease of interest. Existing unsupervised feature selection algorithms primarily focus on the significance of features in maintaining the data structure while not taking into account the redundancy among features. Determining the appropriate number of significant features is another challenge.
UNASSIGNED: In this paper, we propose a clustering-guided unsupervised feature selection (CGUFS) algorithm for gene expression data that addresses these problems. Our proposed algorithm introduces three improvements over existing algorithms. For the problem that existing clustering algorithms require artificially specifying the number of clusters, we propose an adaptive k-value strategy to assign appropriate pseudo-labels to each sample by iteratively updating a change function. For the problem that existing algorithms fail to consider the redundancy among features, we propose a feature grouping strategy to group highly redundant features. For the problem that the existing algorithms cannot filter the redundant features, we propose an adaptive filtering strategy to determine the feature combinations to be retained by calculating the potentially effective features and potentially redundant features of each feature group.
UNASSIGNED: Experimental results show that the average accuracy (ACC) and matthews correlation coefficient (MCC) indexes of the C4.5 classifier on the optimal features selected by the CGUFS algorithm reach 74.37% and 63.84%, respectively, significantly superior to the existing algorithms.
UNASSIGNED: Similarly, the average ACC and MCC indexes of the Adaboost classifier on the optimal features selected by the CGUFS algorithm are significantly superior to the existing algorithms. In addition, statistical experiment results show significant differences between the CGUFS algorithm and the existing algorithms.

Cancer is one of the leading causes of deaths worldwide. Survival analysis and prediction of cancer patients is of great significance for their precision medicine. The robustness and interpretability of the survival prediction models are important, where robustness tells whether a model has learned the knowledge, and interpretability means if a model can show human what it has learned. In this paper, we propose a robust and interpretable model SurvConvMixer, which uses pathways customized gene expression images and ConvMixer for cancer short-term, mid-term and long-term overall survival prediction. With ConvMixer, the representation of each pathway can be learned respectively. We show the robustness of our model by testing the trained model on absolutely untrained external datasets. The interpretability of SurvConvMixer depends on gradient-weighted class activation mapping (Grad-Cam), by which we can obtain the pathway-level activation heat map. Then wilcoxon rank-sum tests are conducted to obtain the statistically significant pathways, thereby revealing which pathways the model focuses on more. SurvConvMixer achieves remarkable performance on the short-term, mid-term and long-term overall survival of lung adenocarcinoma, lung squamous cell carcinoma and skin cutaneous melanoma, and the external validation tests show that SurvConvMixer can generalize to external datasets so that it is robust. Finally, we investigate the activation maps generated by Grad-Cam, after wilcoxon rank-sum test and Kaplan-Meier estimation, we find that some survival-related pathways play important role in SurvConvMixer.

Enrichment analysis (EA) is a common approach to gain functional insights from genome-scale experiments. As a consequence, a large number of EA methods have been developed, yet it is unclear from previous studies which method is the best for a given dataset. The main issues with previous benchmarks include the complexity of correctly assigning true pathways to a test dataset, and lack of generality of the evaluation metrics, for which the rank of a single target pathway is commonly used. We here provide a generalized EA benchmark and apply it to the most widely used EA methods, representing all four categories of current approaches. The benchmark employs a new set of 82 curated gene expression datasets from DNA microarray and RNA-Seq experiments for 26 diseases, of which only 13 are cancers. In order to address the shortcomings of the single target pathway approach and to enhance the sensitivity evaluation, we present the Disease Pathway Network, in which related Kyoto Encyclopedia of Genes and Genomes pathways are linked. We introduce a novel approach to evaluate pathway EA by combining sensitivity and specificity to provide a balanced evaluation of EA methods. This approach identifies Network Enrichment Analysis methods as the overall top performers compared with overlap-based methods. By using randomized gene expression datasets, we explore the null hypothesis bias of each method, revealing that most of them produce skewed P-values.

A multiscale method proposed elsewhere for reconstructing plausible 3D configurations of the chromatin in cell nuclei is recalled, based on the integration of contact data from Hi-C experiments and additional information coming from ChIP-seq, RNA-seq and ChIA-PET experiments. Provided that the additional data come from independent experiments, this kind of approach is supposed to leverage them to complement possibly noisy, biased or missing Hi-C records. When the different data sources are mutually concurrent, the resulting solutions are corroborated; otherwise, their validity would be weakened. Here, a problem of reliability arises, entailing an appropriate choice of the relative weights to be assigned to the different informational contributions. A series of experiments is presented that help to quantify the advantages and the limitations offered by this strategy. Whereas the advantages in accuracy are not always significant, the case of missing Hi-C data demonstrates the effectiveness of additional information in reconstructing the highly packed segments of the structure.