Gene Selection Method Research Articles

A novel and innovative cancer classification framework through a consecutive utilization of hybrid feature selection

Cancer prediction in the early stage is a topic of major interest in medicine since it allows accurate and efficient actions for successful medical treatments of cancer. Mostly cancer datasets contain various gene expression levels as features with less samples, so firstly there is a need to eliminate similar features to permit faster convergence rate of classification algorithms. These features (genes) enable us to identify cancer disease, choose the best prescription to prevent cancer and discover deviations amid different techniques. To resolve this problem, we proposed a hybrid novel technique CSSMO-based gene selection for cancer classification. First, we made alteration of the fitness of spider monkey optimization (SMO) with cuckoo search algorithm (CSA) algorithm viz., CSSMO for feature selection, which helps to combine the benefit of both metaheuristic algorithms to discover a subset of genes which helps to predict a cancer disease in early stage. Further, to enhance the accuracy of the CSSMO algorithm, we choose a cleaning process, minimum redundancy maximum relevance (mRMR) to lessen the gene expression of cancer datasets. Next, these subsets of genes are classified using deep learning (DL) to identify different groups or classes related to a particular cancer disease. Eight different benchmark microarray gene expression datasets of cancer have been utilized to analyze the performance of the proposed approach with different evaluation matrix such as recall, precision, F1-score, and confusion matrix. The proposed gene selection method with DL achieves much better classification accuracy than other existing DL and machine learning classification models with all large gene expression dataset of cancer.

A differential diagnosis between uterine leiomyoma and leiomyosarcoma using transcriptome analysis

BackgroundThe objective of this study was to estimate the accuracy of transcriptome-based classifier in differential diagnosis of uterine leiomyoma and leiomyosarcoma. We manually selected 114 normal uterine tissue and 31 leiomyosarcoma samples from publicly available transcriptome data in UCSC Xena as training/validation sets. We developed pre-processing procedure and gene selection method to sensitively find genes of larger variance in leiomyosarcoma than normal uterine tissues. Through our method, 17 genes were selected to build transcriptome-based classifier. The prediction accuracies of deep feedforward neural network (DNN), support vector machine (SVM), random forest (RF), and gradient boosting (GB) models were examined. We interpret the biological functionality of selected genes via network-based analysis using GeneMANIA. To validate the performance of trained model, we additionally collected 35 clinical samples of leiomyosarcoma and leiomyoma as a test set (18 + 17 as 1st and 2nd test sets).ResultsWe discovered genes expressed in a highly variable way in leiomyosarcoma while these genes are expressed in a conserved way in normal uterine samples. These genes were mainly associated with DNA replication. As gene selection and model training were made in leiomyosarcoma and uterine normal tissue, proving discriminant of ability between leiomyosarcoma and leiomyoma is necessary. Thus, further validation of trained model was conducted in newly collected clinical samples of leiomyosarcoma and leiomyoma. The DNN classifier performed sensitivity 0.88, 0.77 (8/9, 7/9) while the specificity 1.0 (8/8, 8/8) in two test data set supporting that the selected genes in conjunction with DNN classifier are well discriminating the difference between leiomyosarcoma and leiomyoma in clinical sample.ConclusionThe transcriptome-based classifier accurately distinguished uterine leiomyosarcoma from leiomyoma. Our method can be helpful in clinical practice through the biopsy of sample in advance of surgery. Identification of leiomyosarcoma let the doctor avoid of laparoscopic surgery, thus it minimizes un-wanted tumor spread.

A Gene Selection Method Considering Measurement Errors.

The analysis of gene expression data has made significant contributions to understanding disease mechanisms and developing new drugs and therapies. In such analysis, gene selection is often required for identifying informative and relevant genes and removing redundant and irrelevant ones. However, this is not an easy task as gene expression data have inherent challenges such as ultra-high dimensionality, biological noise, and measurement errors. This study focuses on the measurement errors in gene selection problems. Typically, high-throughput experiments have their own intrinsic measurement errors, which can result in an increase of falsely discovered genes. To alleviate this problem, this study proposes a gene selection method that takes into account measurement errors using generalized liner measurement error models. The method consists of iterative filtering and selection steps until convergence, leading to fewer false positives and providing stable results under measurement errors. The performance of the proposed method is demonstrated through simulation studies and applied to a lung cancer data set.

Identification of gene expression biomarkers to predict clinical response to methotrexate in patients with rheumatoid arthritis

ObjectivesTo identify biomarkers at the gene expression level to predict response to methotrexate (MTX) in patients with rheumatoid arthritis (RA).MethodsMTX-naïve patients with RA were started on MTX and followed up over three months. The disease activity score 28 (DAS28) was used to classify patients into responders and non-responders. Genome-wide gene expression analysis was performed in CD4 + and CD14 + mononuclear cells sampled from whole blood at baseline to identify differentially expressed genes in responders versus non-responders. Gene selection methods and prediction modelling obtained the most relevant differentially expressed genes. A logistic regression prediction model was subsequently constructed and validated via bootstrapping. The area under the receiver operating characteristic (AUC) curve was calculated to judge model quality.ResultsSeventy-nine patients with RA (53.4 ± 13.9 years, 74.7% females) were enrolled, and 70 finished the study with a documented treatment EULAR response (77.1% responders). Forty-six differentially expressed genes were found. The most promising genes were KRTAP4-11, LOC101927584, and PECAM1 in CD4 + cells and PSMD5 and ID1 in CD14 + cells. The final prediction model using these genes reached an AUC of 90%; the validation set’s AUC was 82%.ConclusionsOur prediction model constructed via genome-wide gene expression analysis in CD4 + and CD14 + mononuclear cells yielded excellent predictions. Our findings necessitate confirmation in other cohorts of MTX-naïve RA patients. Especially if used in conjunction with previously identified clinical and laboratory (bio)markers, our results could help predict response to MTX in RA to guide treatment decisions.Key Points• Patients with rheumatoid arthritis may or may not respond to treatment with methotrexate, which is the recommended first-line drug in guidelines around the world.• In non-responders, valuable time is lost until second-line treatments are started.• This study aimed at predicting response to methotrexate by identifying differentially expressed genes from peripheral blood samples.• The final prediction model yielded excellent prognostic values, but validation in other cohorts is necessary to corroborate these findings.

Gene selection and tumor identification based on a hybrid of the multi-filter embedded recursive mountain gazelle algorithm

Microarray gene expression data are useful for identifying gene expression patterns associated with cancer outcomes; however, their high dimensionality make it difficult to extract meaningful information and accurately classify tumors. Hence, developing effective methods for reducing dimensionality while preserving relevant information is a crucial task. Hybrid-based gene selection methods are widely proposed in the gene expression analysis domain and can still be enhanced in terms of efficiency and reliability. This study proposes a new hybrid-based gene selection method, called multi-filter embedded mountain gazelle optimizer (MUL-MGO), which utilizes two filters and an embedded method to remove irrelevant genes, followed by selecting the most relevant genes using recently developed MGO algorithm. To the best of our knowledge, this is the first work to exploit MGO as a gene or feature selection method. A new version of MGO, called recursive mountain gazelle optimizer (RMGO), which implements MGO algorithm recursively to avoid local optima, minimize search space, and obtain minimum gene count without decreasing the classifier’s performance, is developed. The proposed RMGO is used to develop a new hybrid gene selection method employing similar filters and embedded methods as MUL-MGO, but with a recursive MGO algorithm version. The resulting method is called multi-filter embedded recursive mountain gazelle optimizer (MUL-RMGO). Several classifiers are used for cancer classification. Accordingly, several experimental studies are performed on eight microarray gene expression datasets to demonstrate the proficiencies of MUL-MGO and MUL-RMGO methods. The experimental findings indicate the efficiency and productivity of the suggested MUL-MGO and MUL-RMGO methods for gene selection. The methods outperform cutting-edge methods in the literature, with MUL-RMGO exceeding MUL-MGO in terms of accuracy and selected gene count.

Gene selection with Game Shapley Harris hawks optimizer for cancer classification

Cancer disease has been classified as a perilous disease for humans, being the second leading cause of death globally. Even advanced-stage diagnosis may not be effective in preventing patient mortality. Therefore, it is important to establish a sustainable framework that predicts reliable estimates for an early cancer diagnosis. In this paper, a new two-phase feature (gene) selection approach is presented. In the first phase, the kernel Shapley value (kSV) that is based on the cooperative game-theoretic feature extraction approach is utilized to extract the important feature from the high dimensional gene expression data. In the second phase, Harris hawks optimizer (HHO) algorithm is utilized to further optimize the most effective feature extracted by kSV. Next, to evaluate the effectiveness of our proposed algorithm, we conduct extensive experiments on eight benchmark high-dimensional gene expression datasets, comparing them with other state-of-the-art techniques. We employ three classifiers, namely support vector machines (SVM), Naive Bayes (NB), and K-nearest neighbors (KNN), to assess the selected genes efficacy and their impact on classification accuracy. The experimental results demonstrate that the proposed method, particularly when combined with the SVM classifier, outperforms other gene selection methods. The evaluation metrics, including accuracy, precision, recall, F1-score, ROC-AUC, box plot, and radar plot, consistently indicate the superiority of kSV-HHO across all tested datasets. Moreover, the comparative and statistical analysis reveals that our proposed method excels in identifying the most relevant features for cancer diagnosis compared to other gene selection approaches. This makes our framework a valuable tool for cancer research and clinical practice, potentially enhancing the accuracy of early cancer diagnosis using high-dimensional gene expression biomedical data.

A Novel Machine-Learning Approach to Predict Stress-Responsive Genes in Arabidopsis

This study proposes a hybrid gene selection method to identify and predict key genes in Arabidopsis associated with various stresses (including salt, heat, cold, high-light, and flagellin), aiming to enhance crop tolerance. An open-source microarray dataset (GSE41935) comprising 207 samples and 30,380 genes was analyzed using several machine learning tools including the synthetic minority oversampling technique (SMOTE), information gain (IG), ReliefF, and least absolute shrinkage and selection operator (LASSO), along with various classifiers (BayesNet, logistic, multilayer perceptron, sequential minimal optimization (SMO), and random forest). We identified 439 differentially expressed genes (DEGs), of which only three were down-regulated (AT3G20810, AT1G31680, and AT1G30250). The performance of the top 20 genes selected by IG and ReliefF was evaluated using the classifiers mentioned above to classify stressed versus non-stressed samples. The random forest algorithm outperformed other algorithms with an accuracy of 97.91% and 98.51% for IG and ReliefF, respectively. Additionally, 42 genes were identified from all 30,380 genes using LASSO regression. The top 20 genes for each feature selection were analyzed to determine three common genes (AT5G44050, AT2G47180, and AT1G70700), which formed a three-gene signature. The efficiency of these three genes was evaluated using random forest and XGBoost algorithms. Further validation was performed using an independent RNA_seq dataset and random forest. These gene signatures can be exploited in plant breeding to improve stress tolerance in a variety of crops.

GeNetOntology: identifying affected gene ontology terms via grouping, scoring, and modeling of gene expression data utilizing biological knowledge-based machine learning.

Introduction: Identifying significant sets of genes that are up/downregulated under specific conditions is vital to understand disease development mechanisms at the molecular level. Along this line, in order to analyze transcriptomic data, several computational feature selection (i.e., gene selection) methods have been proposed. On the other hand, uncovering the core functions of the selected genes provides a deep understanding of diseases. In order to address this problem, biological domain knowledge-based feature selection methods have been proposed. Unlike computational gene selection approaches, these domain knowledge-based methods take the underlying biology into account and integrate knowledge from external biological resources. Gene Ontology (GO) is one such biological resource that provides ontology terms for defining the molecular function, cellular component, and biological process of the gene product. Methods: In this study, we developed a tool named GeNetOntology which performs GO-based feature selection for gene expression data analysis. In the proposed approach, the process of Grouping, Scoring, and Modeling (G-S-M) is used to identify significant GO terms. GO information has been used as the grouping information, which has been embedded into a machine learning (ML) algorithm to select informative ontology terms. The genes annotated with the selected ontology terms have been used in the training part to carry out the classification task of the ML model. The output is an important set of ontologies for the two-class classification task applied to gene expression data for a given phenotype. Results: Our approach has been tested on 11 different gene expression datasets, and the results showed that GeNetOntology successfully identified important disease-related ontology terms to be used in the classification model. Discussion: GeNetOntology will assist geneticists and scientists to identify a range of disease-related genes and ontologies in transcriptomic data analysis, and it will also help doctors design diagnosis platforms and improve patient treatment plans.

Utilization of Computer Classification Methods for Exposure Prediction and Gene Selection in Daphnia magna Toxicogenomics.

Zinc (Zn) is an essential element that influences many cellular functions. Depending on bioavailability, Zn can cause both deficiency and toxicity. Zn bioavailability is influenced by water hardness. Therefore, water quality analysis for health-risk assessment should consider both Zn concentration and water hardness. However, exposure media selection for traditional toxicology tests are set to defined hardness levels and do not represent the diverse water chemistry compositions observed in nature. Moreover, these tests commonly use whole organism endpoints, such as survival and reproduction, which require high numbers of test animals and are labor intensive. Gene expression stands out as a promising alternative to provide insight into molecular events that can be used for risk assessment. In this work, we apply machine learning techniques to classify the Zn concentrations and water hardness from Daphnia magna gene expression by using quantitative PCR. A method for gene ranking was explored using techniques from game theory, namely, Shapley values. The results show that standard machine learning classifiers can classify both Zn concentration and water hardness simultaneously, and that Shapley values are a versatile and useful alternative for gene ranking that can provide insight about the importance of individual genes.

MSC based gene delivery methods and strategies improve the therapeutic efficacy of neurological diseases.

Mesenchymal stem cells (MSCs) are promising seed cells for neural regeneration therapy owing to their plasticity and accessibility. They possess several inherent characteristics advantageous for the transplantation-based treatment of neurological disorders, including neural differentiation, immunosuppression, neurotrophy, and safety. However, the therapeutic efficacy of MSCs alone remains unsatisfactory in most cases. To improve some of their abilities, many studies have employed genetic engineering to transfer key genes into MSCs. Both viral and nonviral methods can be used to overexpress therapeutic proteins that complement the inherent properties. However, to date, different modes of gene transfer have specific drawbacks and advantages. In addition, MSCs can be functionalized through targeted gene modification to facilitate neural repair by promoting neural differentiation, enhancing neurotrophic and neuroprotective functions, and increasing survival and homing abilities. The methods of gene transfer and selection of delivered genes still need to be optimized for improved therapeutic and targeting efficacies while minimizing the loss of MSC function. In this review, we focus on gene transport technologies for engineering MSCs and the application of strategies for selecting optimal delivery genes. Further, we describe the prospects and challenges of their application in animal models of different neurological lesions to broaden treatment alternatives for neurological diseases.

AAFL: automatic association feature learning for gene signature identification of cancer subtypes in single-cell RNA-seq data.

Single-cell RNA-sequencing (scRNA-seq) technologies have enabled the study of human cancers in individual cells, which explores the cellular heterogeneity and the genotypic status of tumors. Gene signature identification plays an important role in the precise classification of cancer subtypes. However, most existing gene selection methods only select the same informative genes for each subtype. In this study, we propose a novel gene selection method, automatic association feature learning (AAFL), which automatically identifies different gene signatures for different cell subpopulations (cancer subtypes) at the same time. The proposed AAFL method combines the residual network with the low-rank network, which selects genes that are most associated with the corresponding cell subpopulations. Moreover, the differential expression genes are acquired before gene selection to filter the redundant genes. We apply the proposed feature learning method to the real cancer scRNA-seq data sets (melanoma) to identify cancer subtypes and detect gene signatures of identified cancer subtypes. The experimental results demonstrate that the proposed method can automatically identify different gene signatures for identified cancer subtypes. Gene ontology enrichment analysis shows that the identified gene signatures of different subtypes reveal the key biological processes and pathways. These gene signatures are expected to bring important implications for understanding cellular heterogeneity and the complex ecosystem of tumors.

A New Multi-objective Hybrid Gene Selection Algorithm for Tumor Classification Based on Microarray Gene Expression Data

Tumor classification based on microarray gene expression data is easy to fall into overfitting because such data are composed of many irrelevant, redundant, and noisy genes. Traditional gene selection methods cannot achieve satisfactory classification results. In this study, we propose a novel multi-target hybrid gene selection method named RMOGA (ReliefF Multi-Objective Genetic Algorithm), which aims to select a few genes and obtain good tumor recognition accuracy. RMOGA consists of two phases. Firstly, ReliefF is used to select the top 5% subset of genes from the original datasets. Secondly, a multi-objective genetic algorithm searches for the optimal gene subset from the gene subset obtained by the ReliefF method. To verify the validity of RMOGA, we conducted extensive experiments on 11 available microarray datasets and compared the proposed method with other previous methods. Two classical classifiers including Naive Bayes and Support Vector Machine were used to measure the classification performance of all comparison methods. Experimental results show that the RMOGA algorithm can yield significantly better results than previous state-of-the-art methods in terms of classification accuracy and the number of selected genes.

Transcriptomic-based selection of reference genes for quantitative real-time PCR in an insect endosymbiotic model

Reference genes are a fundamental tool for analyses of gene expression by real-time quantitative PCR (qRT-PCR), in that they ensure the correct comparison between conditions, stages, or treatments. Because of this, selection of appropriate genes to use as references is crucial for proper application of the technique. Nevertheless, efforts to find appropriate, stably expressed transcripts are still lacking, in particular in the field of insect science. Here, we took advantage of a massive transcriptomic high-throughput analysis of various developmental stages of the gut and associated-bacteriomes of the cereal weevil Sitophilus oryzae and identified a subset of stably expressed genes with the potential to be used as housekeeping genes from the larva to the adult stage. We employed several normalization techniques to select the most suitable genes among our subset. Our final selection includes two genes–TAO, and YTH3–which can also be used to compare transcript abundance at various developmental stages in symbiotic insects, and in insects devoid of endosymbionts (aposymbiotic). Since they are well conserved, these genes have the potential to be useful for many other insect species. This work confirms the interest in using large-scale, unbiased methods for reference gene selection.

Genetic algorithm-based feature selection with manifold learning for cancer classification using microarray data

BackgroundMicroarray data have been widely utilized for cancer classification. The main characteristic of microarray data is “large p and small n” in that data contain a small number of subjects but a large number of genes. It may affect the validity of the classification. Thus, there is a pressing demand of techniques able to select genes relevant to cancer classification.ResultsThis study proposed a novel feature (gene) selection method, Iso-GA, for cancer classification. Iso-GA hybrids the manifold learning algorithm, Isomap, in the genetic algorithm (GA) to account for the latent nonlinear structure of the gene expression in the microarray data. The Davies–Bouldin index is adopted to evaluate the candidate solutions in Isomap and to avoid the classifier dependency problem. Additionally, a probability-based framework is introduced to reduce the possibility of genes being randomly selected by GA. The performance of Iso-GA was evaluated on eight benchmark microarray datasets of cancers. Iso-GA outperformed other benchmarking gene selection methods, leading to good classification accuracy with fewer critical genes selected.ConclusionsThe proposed Iso-GA method can effectively select fewer but critical genes from microarray data to achieve competitive classification performance.

The Association of Calcium Signaling Pathway Gene Variants, Bone Mineral Density and Mild Cognitive Impairment in Elderly People.

The association of calcium signaling pathway gene variants, bone mineral density (BMD) and mild cognitive impairment (MCI) is poorly understood so far. A total of 878 participants from Qingdao city were recruited in this study. According to the candidate gene selection method, 58 single nucleotide polymorphisms (SNPs) in eight calcium signaling genes were selected. The association between gene polymorphisms and MCI was revealed by using multiple genetic models. Polygenic risk scores (PRS) were used to summarize the effects of the whole gene. Logistic regression was used to analyze the association between each PRS and MCI. The multiplicative interaction term in the regression models was used to estimate the interaction effects between the PRS and BMD. We observed significant associations of rs6877893 (NR3C1), rs6448456 (CCKAR), and rs723672 (CACNA1C) polymorphisms with MCI. The PRSs of NR3C1 (OR = 4.012, 95% CI = 1.722-9.347, p < 0.001), PRKCA (OR = 1.414, 95% CI = 1.083-1.845, p = 0.011) and TRPM1 (OR = 3.253, 95% CI = 1.116-9.484, p = 0.031) were associated with an increased risk of developing MCI, and the PRS of total genes (OR = 0.330, 95% CI = 0.224-0.485, p < 0.001) was associated with a decreased risk of developing MCI. In interaction effect analysis, the interaction effect of PRKCA and BMD was significant. Genetic variations of the calcium signaling pathway were associated with MCI in older people. There was an interaction effect between PRKCA gene variants and BMD on MCI.

Breast Cancer Classification by Gene Expression Analysis using Hybrid Feature Selection and Hyper-heuristic Adaptive Universum Support Vector Machine

Comprehensive assessments of the molecular characteristics of breast cancer from gene expression patterns can aid in the early identification and treatment of tumor patients. The enormous scale of gene expression data obtained through microarray sequencing increases the difficulty of training the classifier due to large-scale features. Selecting pivotal gene features can minimize high dimensionality and the classifier complexity with improved breast cancer detection accuracy. However, traditional filter and wrapper-based selection methods have scalability and adaptability issues in handling complex gene features. This paper presents a hybrid feature selection method of Mutual Information Maximization - Improved Moth Flame Optimization (MIM-IMFO) for gene selection along with an advanced Hyper-heuristic Adaptive Universum Support classification model Vector Machine (HH-AUSVM) to improve cancer detection rates. The hybrid gene selection method is developed by performing filter-based selection using MIM in the first stage followed by the wrapper method in the second stage, to obtain the pivotal features and remove the inappropriate ones. This method improves standard MFO by a hybrid exploration/exploitation phase to accomplish a better trade-off between exploration and exploitation phases. The classifier HH-AUSVM is formulated by integrating the Adaptive Universum learning approach to the hyper- heuristics-based parameter optimized SVM to tackle the class samples imbalance problem. Evaluated on breast cancer gene expression datasets from Mendeley Data Repository, this proposed MIM-IMFO gene selection-based HH-AUSVM classification approach provided better breast cancer detection with high accuracies of 95.67%, 96.52%, 97.97% and 95.5% and less processing time of 4.28, 3.17, 9.45 and 6.31 seconds, respectively.

A new hybrid algorithm for three-stage gene selection based on whale optimization

In biomedical data mining, the gene dimension is often much larger than the sample size. To solve this problem, we need to use a feature selection algorithm to select feature gene subsets with a strong correlation with phenotype to ensure the accuracy of subsequent analysis. This paper presents a new three-stage hybrid feature gene selection method, that combines a variance filter, extremely randomized tree, and whale optimization algorithm. First, a variance filter is used to reduce the dimension of the feature gene space, and an extremely randomized tree is used to further reduce the feature gene set. Finally, the whale optimization algorithm is used to select the optimal feature gene subset. We evaluate the proposed method with three different classifiers in seven published gene expression profile datasets and compare it with other advanced feature selection algorithms. The results show that the proposed method has significant advantages in a variety of evaluation indicators.

A novel hybrid algorithm based on Harris Hawks for tumor feature gene selection.

Gene expression data are often used to classify cancer genes. In such high-dimensional datasets, however, only a few feature genes are closely related to tumors. Therefore, it is important to accurately select a subset of feature genes with high contributions to cancer classification. In this article, a new three-stage hybrid gene selection method is proposed that combines a variance filter, extremely randomized tree and Harris Hawks (VEH). In the first stage, we evaluated each gene in the dataset through the variance filter and selected the feature genes that meet the variance threshold. In the second stage, we use extremely randomized tree to further eliminate irrelevant genes. Finally, we used the Harris Hawks algorithm to select the gene subset from the previous two stages to obtain the optimal feature gene subset. We evaluated the proposed method using three different classifiers on eight published microarray gene expression datasets. The results showed a 100% classification accuracy for VEH in gastric cancer, acute lymphoblastic leukemia and ovarian cancer, and an average classification accuracy of 95.33% across a variety of other cancers. Compared with other advanced feature selection algorithms, VEH has obvious advantages when measured by many evaluation criteria.

ScMAGS: Marker gene selection from scRNA-seq data for spatial transcriptomics studies

Single-Cell RNA sequencing (scRNA-seq) has provided unprecedented opportunities for exploring gene expression and thus uncovering regulatory relationships between genes at the single-cell level. However, scRNA-seq relies on isolating cells from tissues. Therefore, the spatial context of the regulatory processes is lost. A recent technological innovation, spatial transcriptomics, allows for the measurement of gene expression while preserving spatial information. An initial step in the spatial transcriptomic analysis is to identify the cell type, which requires a careful selection of cell-specific marker genes. For this purpose, currently, scRNA-seq data is used to select a limited number of marker genes from among all genes that distinguish cell types from each other. This study proposes scMAGS (single-cell MArker Gene Selection), a novel method for marker gene selection from scRNA-seq data for spatial transcriptomics studies. scMAGS uses a filtering step in which the candidate genes are identified before the marker gene selection step. For the selection of marker genes, cluster validity indices, the Silhouette index, or the Calinski-Harabasz index (for large datasets) are utilized. Experimental results showed that, in comparison to the existing methods, scMAGS is scalable, fast, and accurate. Even for large datasets with millions of cells, scMAGS could find the required number of marker genes in a reasonable amount of time with fewer memory requirements. scMAGS is made freely available at https://github.com/doganlab/scmags and can be downloaded from the Python Package Directory (PyPI) software repository with the command pip install scmags.

Multilevel Feature Selection Method for Improving Classification of Microarray Gene Expression Data

Microarray gene expression profiles provide valuable answers to a variety of problems, and contributes to advances in clinical medicine. Gene expression data typically has a high dimension and a small sample size. Gene selection from microarray gene expression data is a challenge due to high dimensionality of the data. The number of samples in the microarray dataset is much smaller compared to the number of genes as features. To extract useful gene information from cancer microarray data and reduce dimensionality, selection of significant genes is necessary. An effective method of gene feature selection helps in dimensionality reduction and improves the classification performance. Experimental results suggest that appropriate combination of filter gene selection methods is more effective than individual techniques for microarray data classification. In this paper, we propose a two-layered feature selection method. In the first layer, t-test statistical method is used to remove the features that have little correlation with the classification results. In the second layer, line segment approximation method is used to transform the feature subset into a less dimensional feature space. Four well known classifiers kNN, SVM, NBC, DT were used to verify the performance of the proposed feature selection algorithm on binary class microarray data. The experimental results show that the proposed method can effectively select relevant gene subsets, and achieves higher classification accuracy.