Identification of key gene expression associated with quality of life after recovery from COVID-19

Ren, JingXin; Gao, Qian; Zhou, XianChao; Chen, Lei; Guo, Wei; Feng, KaiYan; Huang, Tao; Cai, Yu-Dong

doi:10.1007/s11517-023-02988-8

Cited by 7 publications

(2 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pertinent feature subsets, identified by algorithms such as Adaboost, CatBoost, ExtraTrees, LASSO, LightGBM, MCFS, RF_ZL, and XGBoost, were located at the maximum points. These subsets comprised 60, 70, 105, 75, 70, 140, 100, and 100 features for lung endothelial cells; 50, 125, 155, 125, 125, 170, 105, and 200 features for lung epithelial cells; 55, 55, 100, 100, 50, 180, 100, and 170 features for lung immune cells; and 125, 65,145,45,85,195,75, and 125 features for lung stroma cells, respectively. It can be found that several maximum points need no less than 100 features.…”

Section: Ifs Results and Feature Intersections For Finding Key Featur...mentioning

confidence: 99%

“…The weighted F1 score is a valuable metric used to assess a classifier's performance, especially in datasets with class imbalances. Unlike the macro F1 score, which averages the F1 scores [43][44][45][46][47][48][49][50][51][52] of each class, the weighted version allocates weights proportionate to each class's sample size. This ensures that larger classes have a more pronounced influence on the overall score.…”

Section: Performance Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Reveals Impacts of Smoking on Gene Profiles of Different Cell Types in Lung

Ma,

Shen,

Guo

et al. 2024

Life

Self Cite

View full text Add to dashboard Cite

Smoking significantly elevates the risk of lung diseases such as chronic obstructive pulmonary disease (COPD) and lung cancer. This risk is attributed to the harmful chemicals in tobacco smoke that damage lung tissue and impair lung function. Current research on the impact of smoking on gene expression in specific lung cells is limited. This study addresses this gap by analyzing gene expression profiles at the single-cell level from 43,539 lung endothelial cells, 234,349 lung epithelial cells, 189,843 lung immune cells, and 16,031 lung stromal cells using advanced machine learning techniques. The data, categorized by different lung cell types, were classified into three smoking states: active smoker, former smoker, and never smoker. Each cell sample encompassed 28,024 feature genes. Employing an incremental feature selection method within a computational framework, several specific genes have been identified as potential markers of smoking status in different lung cell types. These include B2M, EEF1A1, and TPT1 in lung endothelial cells; FTL and MT-ATP8 in lung epithelial cells; HLA-B and HLA-C in lung immune cells; and HSP90B1 and LCN2 in lung stroma cells. Additionally, this study developed quantitative rules for representing the gene expression patterns related to smoking. This research highlights the potential of machine learning in oncology, enhancing our molecular understanding of smoking’s harm and laying the groundwork for future mechanism-based studies.

show abstract

Section: Ifs Results and Feature Intersections For Finding Key Featur...mentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

Machine Learning Reveals Impacts of Smoking on Gene Profiles of Different Cell Types in Lung

Ma,

Shen,

Guo

et al. 2024

Life

Self Cite

View full text Add to dashboard Cite

show abstract

Identification of Key Genes in Fetal Gut Development at Single‐Cell Level by Exploiting Machine Learning Techniques

Ma,

Meng,

Zhou

et al. 2024

Proteomics

View full text Add to dashboard Cite

The study of fetal gut development is critical due to its substantial influence on immediate neonatal and long‐term adult health. Current research largely focuses on microbiome colonization, gut immunity, and barrier function, alongside the impact of external factors on these phenomena. Limited research has been dedicated to the categorization of developing fetal gut cells. Our study aimed to enhance our understanding of fetal gut development by employing advanced machine‐learning techniques on single‐cell sequencing data. This dataset consisted of 62,849 samples, each characterized by 33,694 distinct gene features. Four feature ranking algorithms were utilized to sort features according to their significance, resulting in four feature lists. Then, these lists were fed into an incremental feature selection method to extract essential genes, classification rules, and build efficient classifiers. Several important genes were recognized by multiple feature ranking algorithms, such as FGG, MDK, RBP1, RBP2, IGFBP7, and SPON2. These features were key in differentiating specific developing intestinal cells, including epithelial, immune, mesenchymal, and vasculature cells of the colon, duo jejunum, and ileum cells. The classification rules showed special gene expression patterns on some intestinal cell types and the efficient classifiers can be useful tools for identifying intestinal cells.

show abstract

Prediction of Solubility of Proteins in Escherichia coli Based on Functional and Structural Features Using Machine Learning Methods

Huang,

Gao,

Zhou

et al. 2024

Protein J

View full text Add to dashboard Cite

Identification of key gene expression associated with quality of life after recovery from COVID-19

Cited by 7 publications

References 70 publications

Machine Learning Reveals Impacts of Smoking on Gene Profiles of Different Cell Types in Lung

Machine Learning Reveals Impacts of Smoking on Gene Profiles of Different Cell Types in Lung

Identification of Key Genes in Fetal Gut Development at Single‐Cell Level by Exploiting Machine Learning Techniques

Prediction of Solubility of Proteins in Escherichia coli Based on Functional and Structural Features Using Machine Learning Methods

Contact Info

Product

Resources

About