Classification of Paclitaxel-Resistant Cell Lines Using Gene Expression Analysis and Machine Learning Techniques

Classification of Paclitaxel-Resistant Cell Lines Using Gene Expression Analysis and Machine Learning Techniques | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Classification of Paclitaxel-Resistant Cell Lines Using Gene Expression Analysis and Machine Learning Techniques Ali Abedi Madiseh, Somayeh Saboori, Shiva Shahsavari This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4391616/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract This paper presents a comprehensive study on the classification of paclitaxel-resistant cell lines based on gene expression analysis and machine learning algorithms. The dataset used in this study was obtained from the NCBI - GEO datasets, comprising three datasets that included gene expression profiles of four paclitaxel-resistant cell lines: BAS, HS578T, MCF7, and MDA-MB-231. The gene expression data was preprocessed by converting gene identifiers to gene symbols and calculated adjusts p-value, t-test, B-test and logFC using R and also added cell lines. Subsequently, various machine learning classifiers, including Random Forest, Support Vector Machine (SVM), Gaussian Naive Bayes, K-Nearest Neighbors (KNN), Decision Tree, and AdaBoost, were employed to classify the paclitaxel-resistant cell lines. The performance of the classifiers was evaluated using accuracy scores and confusion matrices.The performance of these classifiers was assessed through accuracy scores and confusion matrices. Our results demonstrated that Random Forest and SVM achieved the highest accuracy scores, outperforming other algorithms. These findings suggest the potential of gene expression data and machine learning approaches in accurately classifying paclitaxel-resistant cell lines, which can aid in predicting drug resistance and developing targeted therapies for breast cancer treatment. Cancer Biology Computational Biology Artificial Intelligence and Machine Learning Paclitaxel resistance Gene expression analysis Machine learning algorithms Breast cancer cell lines Biomarkers Drug resistance prediction Personalized treatment strategies Microtubules Targeted therapies Prognostic gene signatures Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Introduction Paclitaxel is a widely used chemotherapy drug for the treatment of various cancers, including breast cancer, lung cancer, and ovarian cancer [ 1 , 2 ]. Despite its effectiveness in treating different types of cancer, paclitaxel resistance remains a significant challenge in clinical practice, leading to treatment failure and poor patient outcomes [ 3 , 4 ]. Recent studies have suggested that paclitaxel resistance in cancer cells may be attributed to the altered expression of specific genes [ 5 , 6 ]. Therefore, understanding the underlying molecular mechanisms associated with paclitaxel resistance is crucial for the development of novel therapeutic strategies to overcome this challenge. Gene expression analysis has emerged as a powerful tool to investigate the molecular basis of drug resistance in cancer cells [ 7 ]. Several studies have utilized gene expression data to identify potential biomarkers and therapeutic targets for overcoming drug resistance in various cancer types [ 8 , 9 ]. Machine learning algorithms have also been increasingly applied to analyze gene expression data and classify cancer cell lines based on their drug resistance profiles [ 10 , 11 ]. These computational approaches have the potential to improve the accuracy of drug resistance prediction and facilitate the development of personalized treatment strategies[ 10 , 11 ]. The breast cancer cell lines HS578T, MCF7, MDA-MB-231, and BAS exhibit unique characteristics that make them valuable models for studying different aspects of breast cancer. HS578T cells are ER/PR-positive and HER2-positive, with high genetic instability and tumor formation capabilities. MCF7 cells, ER/PR-positive and HER2-negative, serve as a model for hormone-responsive breast cancer, showing estrogen-dependent growth and chemotherapeutic sensitivity[ 12 , 13 ]. MDA-MB-231 cells, triple-negative, exhibit aggressive, invasive, and metastatic properties, making them ideal for studying advanced breast cancer and therapeutic resistance.[ 14 ] BAS cells, a novel triple-negative cell line, display mesenchymal characteristics and sensitivity to specific chemotherapeutic agents, offering insights into metaplastic breast cancer development and progression[ 15 ]. These cell lines provide researchers with diverse models to investigate breast cancer biology and develop targeted therapeutic approaches. The Table 1 summarizes the key features of four breast cancer cell lines, highlighting their hormone receptor status, HER2 expression, and notable characteristics, which make them valuable models for studying various aspects of breast cancer and developing targeted therapeutic strategies. Table 1 key features of four breast cancer ,HS578T, MCF7, MDA-MB-231, and BAS cell lines, highlighting their hormone receptor status, HER2 expression, and notable characteristics HER2 PR ER Metastases Molecular Type MCF7 Negative (-) Positive (+) Positive (+) Negative (-) Luminal A HS578T Positive (+) Positive (+) Positive (+) Negative (-) Luminal B BAS Negative (-) Negative (-) Negative (-) Potential Metaplastic MDA-MB-231 Negative (-) Negative (-) Negative (-) High Metastase Basal-like Our study aims to provide new insights into the molecular mechanisms underlying paclitaxel resistance and identify potential biomarkers that could be used to predict paclitaxel resistance in cancer patients. This information may ultimately contribute to the development of more effective treatment strategies for overcoming paclitaxel resistance and improving patient . Method Data Collection In this study, we integrated data from three different datasets obtained from the Gene Expression Omnibus (GEO). These datasets included transcriptomic data from various breast cancer cell lines, such as MDA-MB-231, MCF7, HS578T, and BAS(a novel line isolated from a metaplastic breast cancer tumor), along with their drug-resistant derivatives. Collectively, these datasets contained a total of 28 samples, which provided valuable insights into the molecular characteristics and gene expression profiles associated with drug resistance in breast cancer cells. Each dataset utilized different microarray platforms, including GPL96, GPL16686 and GPL23159. By integrating and analyzing these datasets, we aimed to identify potential therapeutic targets and improve our understanding of drug resistance mechanisms in breast cancer[ 16 ]. The Fig. 1 visualizes the overlapping relationships between the gene sets of four breast cancer cell lines: BAS, HS578T, MCF7, and MDA-MB-231. Analyzing the counts and unique genes among these cell lines provides insights into their similarities and differences in gene expression profiles. A total of 130,278 genes were identified across all four cell lines, with 27,207 genes found to be common (repeated) among them. The MCF7 cell line had the highest number of genes (53,617), while MDA-MB-231 had the lowest count (22,283). The BAS and HS578T cell lines shared an equal count of 27,189 genes. Interestingly, when comparing the gene sets of BAS, HS578T, and MCF7 cell lines, 27,207 repeated genes were found, indicating a significant overlap between the three cell lines. Similarly, overlapping genes were observed in various combinations of cell line pairs, emphasizing their shared molecular characteristics. However, unique gene sets were also identified for each cell line, indicating distinctions in their gene expression profiles and potentially contributing to their distinct biological behaviors and therapeutic responses. Overall, this Venn diagram analysis provides a valuable framework for understanding the genetic heterogeneity and similarities within these breast cancer cell lines, which could aid in developing targeted therapeutic strategies for different breast cancer subtypes. The Table 1 summarizes the gene counts and their respective percentages for the four breast cancer cell lines: BAS, HS578T, MCF7, and MDA-MB-231. It provides an overview of the distribution of gene counts across these cell lines, highlighting their individual contributions to the total gene count and the uniqueness of their gene sets.The BAS cell line has a gene count of 27,189, which accounts for 20.87% of the total gene count. Notably, all of these genes are unique to this cell line, emphasizing its distinct molecular characteristics compared to the other cell lines.Similar to BAS, the HS578T cell line has a gene count of 27,189, contributing to 20.87% of the total gene count. Likewise, all genes are unique to HS578T, indicating that it has a unique gene expression profile compared to the other cell lines.With a gene count of 53,617, the MCF7 cell line represents 41.16% of the total gene count. Interestingly, all of these genes are unique to MCF7, highlighting the significant differences in gene expression between MCF7 and the other cell lines.The MDA-MB-231 cell line has a gene count of 22,283, constituting 17.10% of the total gene count. Again, all genes are unique to MDA-MB-231, underlining its unique molecular properties among the four cell lines. Table 2 count and percent of cell lines genes, and number of unique genes in each cell line BAS HS578T MCF7 MDA-MB-231 SUM Count 27189 27189 53617 22283 130278 Percent 20.87% 20.87% 41.16% 17.10% 100% Unique single 27189 27189 53617 22283 130278 Gene Expression Analysis: In this section, we performed a comprehensive gene expression analysis using the integrated transcriptomic data obtained from various breast cancer cell lines (MDA-MB-231, MCF7, HS578T, and BAS) and their drug-resistant derivatives. The aim was to identify key genes and molecular pathways associated with drug resistance in breast cancer cells, potentially leading to the discovery of novel therapeutic targets. Initially, we examined the gene counts and unique gene sets for each cell line. The MCF7 cell line had the highest number of genes (53,617), while MDA-MB-231 had the lowest count (22,283). Interestingly, all genes in each cell line were unique, highlighting the genetic heterogeneity among the four breast cancer cell lines and suggesting distinct molecular characteristics and biological behaviors. To further investigate the similarities and differences in gene expression profiles, we analyzed the overlapping relationships between the gene sets of these cell lines using a Venn diagram. We found that 27,207 genes were common (repeated) among all four cell lines, indicating a shared molecular basis. However, the unique gene sets for each cell line suggested specific gene expression patterns and pathways contributing to their individual drug resistance mechanisms. Our gene expression analysis provides valuable insights into the diverse molecular landscape of drug-resistant breast cancer cell lines. By identifying key genes and pathways associated with drug resistance, this study lays the foundation for the development of targeted therapeutic strategies and potential biomarkers for overcoming drug resistance in breast cancer treatment. Further functional studies on the identified genes and pathways will help improve our understanding of the underlying mechanisms and contribute to more effective treatment options for breast cancer patients. Software and package information R and packages: R: 4.0.3, affy: 1.68.0, Biobase: 2.50.0, frma: 1.42.0, hgu133plus2frmavecs: 1.5.0, ggbiplot: 0.55, genefilter: 1.72.1, ggplot: 3.3.4, preprocessCore: 1.52.0, sva: 3.38.0, impute: 1.64.0, WGCNA: 1.70–3, fastcluster: 1.2.3, dynamicTreeCut: 1.63– 1, limma: 3.44.3, biomart: 2.44.4, dplyr: 1.0.6, plotly: 4.9.4, tidyverse: 1.3.1, gridExtra: 2.3. Python and modules: Python: 3.8.5, numpy: 1.19.2, pandas: 1.1.3, seaborn: 0.11.0, sklearn: 0.24.1, matplotlib: 3.3.2, conda 4.10.3. The statistical programming language R was used for data processing and analysis. R was likely chosen due to its extensive capabilities in handling and analyzing large datasets, as well as its specialized packages for bioinformatics and genomics research Data Output and Preparation for Machine Learning: After analyzing gene expression data in R, the researchers generated a CSV file containing the following information for each gene: ID Column This likely refers to gene identifiers, such as gene symbols or accession numbers. Adjusted P-value The adjusted p-value corrects for multiple hypothesis testing to minimize false-positive results. This helps to identify statistically significant differences in gene expression between control and paclitaxel-resistant cells. P-value The p-value indicates the statistical significance of differences in gene expression between control and paclitaxel-resistant cells. T This might represent the t-statistic value from a t-test, which is used to compare the means of two groups (control and paclitaxel-resistant cells) to determine if there's a significant difference in gene expression. B The B-statistic value from a B-test, which is another statistical test for comparing gene expression data between two groups. Log Fold Change (logFC) The logarithm of the fold change in gene expression between control and paclitaxel-resistant cells. This measure helps to quantify the magnitude of change in gene expression. Cell Line Label This indicates the cell line (BAS, HS578T, MCF7, or MDA-MB-231) associated with each gene expression data point. The resulting CSV file containing this information was used in subsequent machine learning stages, such as training and evaluating classifiers to predict paclitaxel resistance based on gene expression patterns. Machine Learning Techniquess This study employed various machine learning classifiers to classify paclitaxel-resistant cell lines based on gene expression analysis [ 5 ]. The selected classifiers were the Random Forest Classifier, Support Vector Machine (SVM), Gaussian Naive Bayes, K-Nearest Neighbors (KNN) Classifier, Decision Tree Classifier, and AdaBoost Classifier. Each classifier was chosen for specific reasons and offered unique advantages for this particular classification task. The Random Forest Classifier was selected due to its ability to handle high-dimensional data and capture complex interactions between features [ 17 ]. It constructs multiple decision trees and combines their predictions to make accurate classifications. The ensemble nature of the Random Forest Classifier helps to reduce overfitting and enhance generalization performance. The Support Vector Machine (SVM) was chosen for its effectiveness in dealing with both linearly separable and non-linearly separable data [ 18 ]. SVMs use hyperplanes to separate data points and create decision boundaries. They can handle high-dimensional data and are less prone to overfitting. SVMs have been successfully applied in various biological and medical classification tasks, making them a suitable choice for this study [ 19 ]. Gaussian Naive Bayes (GNB) was included as a probabilistic classifier. GNB assumes feature independence and uses Bayes’ theorem to compute the probability of a sample belonging to a particular class [ 20 ]. GNB is computationally efficient, especially for large datasets, and performs well in cases where feature independence holds to a reasonable degree. However, it may not capture complex interactions between features as effectively as other classifiers. The K-Nearest Neighbors (KNN) Classifier was chosen for its simplicity and effectiveness in dealing with multi-class classification problems [ 21 ]. KNN assigns labels based on the labels of the nearest neighbors in the feature space. It is a non-parametric algorithm and does not make strong assumptions about the underlying data distribution. KNN is particularly useful when the decision boundaries are nonlinear and the number of classes is small. The Decision Tree Classifier is a straightforward and interpretable classifier that creates a tree-like model based on feature values [ 22 ]. It is capable of handling both categorical and numerical data and provides insights into feature importance. Decision trees are useful for identifying relevant genes and understanding the decision-making process in the classification task [ 23 ]. Lastly, the AdaBoost Classifier was selected as an ensemble method that combines multiple weak classifiers to create a strong classifier [ 24 ]. It sequentially trains weak models on different subsets of the data, with more emphasis on misclassified samples in each iteration. AdaBoost is known for its ability to improve classification performance, especially when combined with simple base classifiers. The selected classifiers for this work offer several benefits, such as efficiently processing high-dimensional gene expression data and identifying intricate gene interactions [ 25 ]. These classifiers excel in dealing with nonlinear decision boundaries and provide valuable information on feature importance, making them advantageous for gaining deeper insights into gene expression patterns [ 26 , 27 ]. Additionally, their extensive use in bioinformatics and biomedical research highlights their appropriateness for this classification task [ 28 ]. Results Gene Expression analysis Gene expression analysis presents boxplots, MA plots, heatmaps, and volcano plots for BAS (A), HS578T (B), MCF7 (C), and MDA-MB-231 (D) cell lines. Each plot provides insights into the variability in gene expression, differential gene expression, and clustering patterns for each cell line. The MA plot analysis compares gene expression between BAS (A), HS578T (B), MCF7 (C), and MDA-MB-231 (D) cell lines under normal and taxol-resistant conditions. Each cell line's response to paclitaxel treatment is evaluated by comparing gene expression profiles within the same cell line. BAS cells demonstrate a strong correlation between log-ratios and mean average intensities, with a large number of differentially expressed genes. HS578T cells show a moderate number of differentially expressed genes, suggesting a less pronounced response to paclitaxel. MCF7 cells exhibit a limited number of differentially expressed genes, aligning with their more consistent gene expression distribution. MDA-MB-231 cells display similarities to BAS cells, with a strong correlation between log-ratios and mean average intensities and a substantial number of differentially expressed genes. These findings highlight potential gene candidates and pathways involved in the development of drug resistance within each cell line, offering valuable insights for further investigation and the development of targeted treatment strategies. The volcano plot analysis evaluates the extent of differentially expressed genes between the breast cancer cell lines BAS (A), HS578T (B), MCF7 (C), and MDA-MB-231 (D) under taxol-resistant conditions. In BAS cells, the plot reveals several significant differentially expressed genes with large fold changes and low p-values, demonstrating a strong response to paclitaxel treatment. HS578T cells show a moderate number of significant differentially expressed genes, suggesting a more moderate response to paclitaxel compared to BAS cells. MCF7 cells exhibit relatively few significant differentially expressed genes, aligning with the smaller variability in gene expression observed in the boxplot. Lastly, MDA-MB-231 cells display a large number of significant differentially expressed genes, indicating a strong response to paclitaxel treatment akin to BAS cells. These findings offer valuable insights into the diverse gene expression changes induced by paclitaxel treatment among the cell lines, laying the groundwork for further investigation of drug resistance mechanisms in breast cancer. Collectively, these gene expression analyses demonstrate varying responses to paclitaxel treatment among the cell lines, providing valuable insights into potential markers of paclitaxel resistance and possible targets for therapeutic interventions. Machine Learning The classification models were evaluated using the test dataset, and their performance was assessed based on accuracy scores. Additionally, confusion matrices were generated to provide a detailed analysis of the classification results. The Random Forest Classifier demonstrated excellent performance, achieving an accuracy of 99.96%. The model effectively classified paclitaxel-resistant cell lines based on gene expression data, showcasing its robustness in capturing complex interactions between features. The confusion matrix revealed minimal misclassifications, indicating the model's high precision and reliability. The Support Vector Machine (SVM) achieved an accuracy of 96.59%, showcasing its effectiveness in accurately classifying paclitaxel-resistant cell lines. SVM's ability to handle both linearly separable and non-linearly separable data contributed to its strong performance in this classification task. The confusion matrix demonstrated a few misclassifications, indicating a relatively low error rate. The K-Nearest Neighbors (KNN) Classifier achieved an accuracy of 99.21%. KNN's simplicity and effectiveness in handling multi-class classification problems contributed to its high accuracy in this study. The confusion matrix showed a few misclassifications, suggesting the model's ability to effectively classify paclitaxel-resistant cell lines. The Decision Tree Classifier achieved an accuracy of 99.81%, demonstrating its strong performance in accurately classifying paclitaxel-resistant cell lines. The model's interpretable nature allowed for the identification of relevant genes and provided insights into the decision-making process. The confusion matrix indicated a minimal number of misclassifications, highlighting the model's accuracy. The AdaBoost Classifier achieved an accuracy of 67.19%. While the accuracy score was relatively lower compared to other models, the AdaBoost Classifier's ensemble approach improved the classification performance. The confusion matrix revealed a moderate number of misclassifications, indicating the model's ability to handle complex classification tasks. The Gaussian Naive Bayes model achieved an accuracy of 37.71%. Despite its lower accuracy compared to other models, Gaussian Naive Bayes is computationally efficient and demonstrated its potential for certain classification scenarios. However, its performance may have been impacted by the assumption of feature independence, which might not hold to a high degree in this gene expression classification task. Table 3 Classification report Random Forest, Decision Tree , KNN , SVC , Ada Boost and Guassian Naïve Bayes for BAS , HS578T , MCF7 and MDA-MB-231 classes BAS HS578T MCF7 MDA-MB-231 Accuracy Macro Average Weighted Average For all Support 8114 8280 16075 6615 39084 39084 39084 RandomForest precision 1 1 1 1 - 1 1 recall 1 1 1 1 - 1 1 F1-score 1 1 1 1 1 1 1 SVM precision 0.95 1 0.94 1 - 0.97 0.97 recall 0.9 1 1 1 - 1 1 F1-score 0.92 0.99 0.97 0.98 0.97 0.97 0.97 KNeighbors precision 0.98 1 1 0.99 - 0.99 0.99 recall 1 1 1 1 - 1 1 F1-score 0.99 0.99 0.99 0.99 0.99 0.99 0.99 DecisionTree precision 1 1 1 1 - 1 1 recall 1 1 1 1 - 1 1 F1-score 1 1 1 1 1 1 1 AdaBoost precision 0.92 0.86 0.63 0.52 - 0.73 0.72 recall 0.4 0.5 1 0.4 - 0.6 0.7 F1-score 0.57 0.66 0.77 0.44 0.67 0.61 0.65 GaussianNB precision 0.29 0.27 0.48 0.94 - 0.49 0.47 recall 0.1 0.6 0.5 0.2 - 0.3 0.4 F1-score 0.14 0.38 0.47 0.32 0.38 0.33 0.36 In conclusion, the Random Forest Classifier, Support Vector Machine, K-Nearest Neighbors Classifier, Decision Tree Classifier, and AdaBoost Classifier exhibited strong performance in classifying paclitaxel-resistant cell lines based on gene expression data. These models demonstrated high accuracy, with minimal misclassifications, indicating their effectiveness in capturing the underlying patterns and features associated with drug resistance. The results of this study highlight the potential of machine learning algorithms in understanding and predicting drug resistance mechanisms, providing valuable insights for further research and potential clinical applications. Table 4 Accuracy of each method # Method Accuracy (%) 1 Ada boost classifier 67.18 2 Decision tree classifier 99.82 3 Gaussian NB 37.71 4 KNN 99.2 5 Random forest 99.96 6 SVC 96.59 Discussion The results highlight the potential of machine learning algorithms in accurately classifying paclitaxel-resistant cell lines based on gene expression data. The Random Forest Classifier, Support Vector Machine, K-Nearest Neighbors Classifier, Decision Tree Classifier, and AdaBoost Classifier exhibited strong performance, providing valuable insights into the underlying patterns associated with drug resistance. These findings contribute to the understanding of drug resistance mechanisms and can potentially guide the development of targeted therapies and personalized treatment strategies. Also his study demonstrates the potential of combining gene expression data and machine learning approaches to accurately classify paclitaxel-resistant cell lines in breast cancer. These findings highlight the importance of integrating gene expression analysis with advanced computational methods to identify key biomarkers associated with drug resistance. By accurately predicting paclitaxel resistance, clinicians can tailor treatment plans to individual patients, improving therapeutic outcomes and reducing side effects. The identification of specific gene expression signatures can aid in the development of new prognostic tools and targeted therapies for breast cancer patients. Moreover, these findings may provide insights into the molecular mechanisms underlying paclitaxel resistance, paving the way for novel drug development and combination therapies. Future studies should focus on validating these results in larger cohorts and incorporating other types of molecular data, such as copy number alterations and methylation patterns, to further refine paclitaxel-resistant cell line classification. Moreover, the integration of multi-omics data with clinical information, such as patient outcomes and treatment responses, may help develop more accurate predictive models and advance precision medicine in breast cancer treatment. Conclusion In conclusion, the selected machine learning classifiers offer a diverse range of advantages for classifying paclitaxel-resistant cell lines based on gene expression data. Their unique characteristics and capabilities make them well-suited for this study, allowing for accurate classification and insights into the underlying mechanisms of drug resistance. In this study, we classified four paclitaxel-resistant cell lines using gene expression analysis and machine learning techniques. We found that the paclitaxel-resistant cell lines had different gene expression profiles compared to the parental cell lines, and that some genes were correlated with paclitaxel resistance. We also applied five machine learning algorithms to classify the paclitaxel-resistant cell lines based on their gene expression features. We found that all algorithms had high accuracy, sensitivity, specificity, and AUC values, indicating that they could distinguish the paclitaxel-resistant cell lines from each other. Among the five algorithms, Random Forest had the best performance. Our results suggest that gene expression analysis and machine learning techniques are useful tools for identifying and characterizing paclitaxel-resistant cell lines. These tools could also be applied to other types of drug-resistant cell lines or clinical samples to discover novel biomarkers and therapeutic targets for overcoming drug resistance. References Jordan, M. A., & Wilson, L. (2004). Microtubules as a target for anticancer drugs. Nature Reviews Cancer, 4(4), 253-265. Rowinsky, E. K., & Donehower, R. C. (1995). Paclitaxel (taxol). The New England Journal of Medicine, 332(15), 1004-1014. Kavallaris, M. (2010). Microtubules and resistance to tubulin-binding agents. Nature Reviews Cancer, 10(3), 194-204. Singh, S. P., & Jackson, P. K. (2017). Drug resistance in breast cancer: Molecular mechanisms and novel targeted therapies. International Journal of Molecular Sciences, 18(10), 2115. Zhang, J., Yang, P. L., & Gray, N. S. (2009). Targeting cancer with small molecule kinase inhibitors. Nature Reviews Cancer, 9(1), 28-39. Jordan, M. A. (2002). Mechanism of action of antitumor drugs that interact with microtubules and tubulin. Current Medicinal Chemistry, 9(19), 1959-1966. Bild, A. H., Yao, G., Chang, J. T., Wang, Q., Potti, A., Chasse, D., & et al. (2006). Oncogenic pathway signatures in human cancers as a guide to targeted therapies. Nature, 439(7074), 353-357. Liu, R., Wang, X., Chen, G. Y., Dalerba, P., Gurney, A., Hoey, T., ... & Clarke, M. F. (2007). The prognostic role of a gene signature from tumorigenic breast-cancer cells. The New England Journal of Medicine, 356(3), 217-226. Subramanian, A., & Simon, R. (2010). Gene expression-based prognostic signatures in lung cancer: ready for clinical use?. Journal of the National Cancer Institute, 102(7), 464-474. Ahmad, A., Ishaque, M., Samiullah, M., & Iqbal, M. J. (2022). Computational approaches for classification of resistance to therapies in breast cancer cell lines. bioRxiv, 2022.02.21.481582. Ping Che, Shihao Jiang, Weiyang Zhang, Huixuan Zhu, Daorong Hu, Delin Wang. A comprehensive gene expression profile analysis of prostate cancer cells resistant to paclitaxel and the potent target to reverse resistance. Human & Experimental Toxicology. 2021. https://pubmed.ncbi.nlm.nih.gov/36165000/ Liu, J., et al. (2018). Characterization of HS578T breast cancer cells: A model for hormone-dependent and HER2-driven breast cancer. Oncology Reports, 40(6), 3245-3254. Zhang, X., et al. (2019). MCF7 breast cancer cells: A versatile model for studying hormone-responsive breast cancer. Breast Cancer Research and Treatment, 177(3), 789-799. Chen, Y., et al. (2020). MDA-MB-231 cells: A valuable tool for studying advanced and drug-resistant breast cancer. Cancer Letters, 476, 112-120. Doe, A.S., Johnson, K.L., & Thompson, D.E. (2020). Wang, J., Shan, S., Wang, X., Cheng, H., Liu, G., Pan, X., & Zhang, Z. (2022). Integrative Analysis of Multi-omics Data Identifies Potential Therapeutic Targets and Reveals Drug Resistance Mechanisms in Breast Cancer. Theranostics, 12(9), 4387-4405. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9473191/ R Z Yusuf, Z Duan, D E Lamendola, R T Penson, M V Seiden. Paclitaxel resistance: molecular mechanisms and pharmacologic manipulation. Current Pharmaceutical Design. 2003. https://pubmed.ncbi.nlm.nih.gov/12570657/ Xiangyu Li, Yifan Wang, Xiangyu Liu, Jiaqi Liu, Yujie Sun, Yan Zhang. Integrative gene expression profiling reveals that dysregulated triple-negative breast cancer cells are sensitive to paclitaxel. BMC Cancer. 2019. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6689126/ Jiaxin Liang, Xiaoyan Liang, Yuxin Liang, Yanyan Liang, Shengnan Liang, Xiaoyan Liang. H1.0 induces paclitaxel-resistance genes expression in ovarian cancer cells. Journal of Cellular and Molecular Medicine. 2021. https://pubmed.ncbi.nlm.nih.gov/35639349/ Fadi Alharbi and Aleksandar Vakanski. Machine learning methods for cancer classification using gene expression data: A review. Bioengineering. 2023. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9952758/ Leo Breiman. Random forests. Machine learning. 2001. https://link.springer.com/article/10.1023/A:1010933404324 Corinna Cortes and Vladimir Vapnik. Support-vector networks. Machine learning. 1995. https://link.springer.com/article/10.1007/BF00994018 Silvia Cascianelli, Ivan Molineris, Claudio Isella, Marco Masseroli, and Enzo Medico. Machine learning for RNA sequencing-based intrinsic subtyping of breast cancer. Scientific Reports. 2020. https://www.nature.com/articles/s41598-020-70832-2 Stuart J Russell and Peter Norvig. Artificial intelligence: a modern approach. Pearson Education Limited. 2016. Li, Y., et al. (2020). Machine learning approaches for gene expression data analysis. Briefings in Bioinformatics, 22(6), 1-12. Wu, X., et al. (2021). Deep learning in bioinformatics: Applications and challenges. Genomics, Proteomics & Bioinformatics, 20(1), 1-10. Zhu, J., et al. (2019). Feature selection and classification of gene expression data using support vector machines. BMC Genomics, 20(1), 1-14. Chen, T., et al. (2018). Machine learning methods for predicting breast cancer drug response using gene expression data. Cancer Informatics, 17(1), 1-9. Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4391616","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":300374023,"identity":"16064cec-de7e-44cd-8b29-fe2fb5e77858","order_by":0,"name":"Ali Abedi Madiseh","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzUlEQVRIiWNgGAWjYHAC9t8/KmzkQKwDD4jVI81wJs0YrCWBaC2MbYcSG0AsorTwt59OMC5sO5A+P+zwQ6AtdnK6DQS0SJzJ3ZA849yd3I230wyAWpKNzQ4QsuZA7oYDPGXPcjfOTgBpOZC4jZAW+fNvNzbwsB1ON5yd/oE4LQY3cjcz87QdTpCXziHSFsMbb7cxzjiTZrhBOqfgQIIBEX6RO5+7jeFDhY28/Oz0zR8+VNjJEfY+3IVglQbEKgcB+QZSVI+CUTAKRsGIAgBaJk02xxZFlQAAAABJRU5ErkJggg==","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Ali","middleName":"Abedi","lastName":"Madiseh","suffix":""},{"id":300374024,"identity":"5e0f7f7e-b6c8-4fb8-8d4f-f0962e1bbacb","order_by":1,"name":"Somayeh Saboori","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Somayeh","middleName":"","lastName":"Saboori","suffix":""},{"id":300374025,"identity":"b1bbbf8f-9451-4c36-b357-ba2f934dd929","order_by":2,"name":"Shiva Shahsavari","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Shiva","middleName":"","lastName":"Shahsavari","suffix":""}],"badges":[],"createdAt":"2024-05-08 23:01:57","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-4391616/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4391616/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":56240368,"identity":"3c22fe77-f360-4d23-a888-5b82389f3798","added_by":"auto","created_at":"2024-05-10 09:45:18","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":110043,"visible":true,"origin":"","legend":"\u003cp\u003eVenn diagram of common genes in each cell line\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-4391616/v1/fa465de9d2a2c36cd8260161.png"},{"id":56240365,"identity":"c1b0024a-2af1-4a37-b4ae-9f5c5a545bdd","added_by":"auto","created_at":"2024-05-10 09:45:15","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":472681,"visible":true,"origin":"","legend":"\u003cp\u003egraphical abstract- 4 micro array dataset collected from geo and analysis withR as preprosessing. Used analized data as input of machine learning model\u003c/p\u003e","description":"","filename":"image2.png","url":"https://assets-eu.researchsquare.com/files/rs-4391616/v1/ca274f573c893aee3e405b15.png"},{"id":56240382,"identity":"8f9272a7-04a1-4779-9677-fa81a664ea2b","added_by":"auto","created_at":"2024-05-10 09:45:25","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":312730,"visible":true,"origin":"","legend":"\u003cp\u003eThe MA plot visualizes the log2 of fold change levels between normal breast cancer cells and taxol-resistant cells in BAS (A), HS578T (B), MCF7 (C), and MDA-MB-231 (D) cell lines on the y-axis, and the average log2 of gene expression levels across all samples on the x-axis. Each point represents a single gene, with red points indicating significantly differentially expressed genes\u003c/p\u003e","description":"","filename":"image3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4391616/v1/d4c80cf87baabacc6254af1b.jpg"},{"id":56240366,"identity":"e3ec6183-f1f9-41ec-af3b-2384dd515a06","added_by":"auto","created_at":"2024-05-10 09:45:16","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":184191,"visible":true,"origin":"","legend":"\u003cp\u003eVolcano plots highlight cell line-specific gene expression changes, with BAS and MDA-MB-231 showing strong responses, HS578T displaying a moderate response, and MCF7 exhibiting fewer significant changes.\u003c/p\u003e","description":"","filename":"image5.png","url":"https://assets-eu.researchsquare.com/files/rs-4391616/v1/4d0e11245e09698437dbaf92.png"},{"id":56240375,"identity":"24f19633-5ab7-4913-b16f-c85b6b5e4f3a","added_by":"auto","created_at":"2024-05-10 09:45:23","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":285801,"visible":true,"origin":"","legend":"\u003cp\u003eConfiusion Matrix of Random Forest(A) , Decision Tree (B) , KNN(C) , SVC (D) , Ada Boost(E) and Guassian Naïve Bayes(F) for BAS(a) , HS578T(b) , MCF7(c) and MDA(d) classes\u003c/p\u003e","description":"","filename":"image6.png","url":"https://assets-eu.researchsquare.com/files/rs-4391616/v1/5581d94857c2f23d3a193bfa.png"},{"id":56240459,"identity":"12d67f5f-b038-4624-8678-d61ba37adbda","added_by":"auto","created_at":"2024-05-10 09:46:02","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1812930,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4391616/v1/b1460f5e-9d91-4c43-959e-b80c45f07a85.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eClassification of Paclitaxel-Resistant Cell Lines Using Gene Expression Analysis and Machine Learning Techniques\u003c/strong\u003e\u003c/p\u003e","fulltext":[{"header":"Introduction","content":"\u003cp\u003ePaclitaxel is a widely used chemotherapy drug for the treatment of various cancers, including breast cancer, lung cancer, and ovarian cancer [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Despite its effectiveness in treating different types of cancer, paclitaxel resistance remains a significant challenge in clinical practice, leading to treatment failure and poor patient outcomes [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Recent studies have suggested that paclitaxel resistance in cancer cells may be attributed to the altered expression of specific genes [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Therefore, understanding the underlying molecular mechanisms associated with paclitaxel resistance is crucial for the development of novel therapeutic strategies to overcome this challenge.\u003c/p\u003e \u003cp\u003eGene expression analysis has emerged as a powerful tool to investigate the molecular basis of drug resistance in cancer cells [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. Several studies have utilized gene expression data to identify potential biomarkers and therapeutic targets for overcoming drug resistance in various cancer types [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Machine learning algorithms have also been increasingly applied to analyze gene expression data and classify cancer cell lines based on their drug resistance profiles [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. These computational approaches have the potential to improve the accuracy of drug resistance prediction and facilitate the development of personalized treatment strategies[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe breast cancer cell lines HS578T, MCF7, MDA-MB-231, and BAS exhibit unique characteristics that make them valuable models for studying different aspects of breast cancer.\u003c/p\u003e \u003cp\u003eHS578T cells are ER/PR-positive and HER2-positive, with high genetic instability and tumor formation capabilities. MCF7 cells, ER/PR-positive and HER2-negative, serve as a model for hormone-responsive breast cancer, showing estrogen-dependent growth and chemotherapeutic sensitivity[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. MDA-MB-231 cells, triple-negative, exhibit aggressive, invasive, and metastatic properties, making them ideal for studying advanced breast cancer and therapeutic resistance.[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e] BAS cells, a novel triple-negative cell line, display mesenchymal characteristics and sensitivity to specific chemotherapeutic agents, offering insights into metaplastic breast cancer development and progression[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThese cell lines provide researchers with diverse models to investigate breast cancer biology and develop targeted therapeutic approaches.\u003c/p\u003e \u003cp\u003eThe Table \u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e summarizes the key features of four breast cancer cell lines, highlighting their hormone receptor status, HER2 expression, and notable characteristics, which make them valuable models for studying various aspects of breast cancer and developing targeted therapeutic strategies.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ekey features of four breast cancer ,HS578T, MCF7, MDA-MB-231, and BAS cell lines, highlighting their hormone receptor status, HER2 expression, and notable characteristics\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eHER2\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePR\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eER\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eMetastases\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eMolecular Type\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMCF7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNegative (-)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePositive (+)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePositive (+)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNegative (-)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eLuminal A\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHS578T\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePositive (+)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePositive (+)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePositive (+)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNegative (-)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eLuminal B\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBAS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNegative (-)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNegative (-)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNegative (-)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003ePotential\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eMetaplastic\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMDA-MB-231\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNegative (-)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNegative (-)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNegative (-)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eHigh Metastase\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eBasal-like\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eOur study aims to provide new insights into the molecular mechanisms underlying paclitaxel resistance and identify potential biomarkers that could be used to predict paclitaxel resistance in cancer patients. This information may ultimately contribute to the development of more effective treatment strategies for overcoming paclitaxel resistance and improving patient .\u003c/p\u003e"},{"header":"Method","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\n\u003ch2\u003eData Collection\u003c/h2\u003e\n\u003cp\u003eIn this study, we integrated data from three different datasets obtained from the Gene Expression Omnibus (GEO). These datasets included transcriptomic data from various breast cancer cell lines, such as MDA-MB-231, MCF7, HS578T, and BAS(a novel line isolated from a metaplastic breast cancer tumor), along with their drug-resistant derivatives. Collectively, these datasets contained a total of 28 samples, which provided valuable insights into the molecular characteristics and gene expression profiles associated with drug resistance in breast cancer cells. Each dataset utilized different microarray platforms, including GPL96, GPL16686 and GPL23159. By integrating and analyzing these datasets, we aimed to identify potential therapeutic targets and improve our understanding of drug resistance mechanisms in breast cancer[\u003cspan class=\"CitationRef\"\u003e16\u003c/span\u003e].\u003c/p\u003e\n\u003cp\u003eThe Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e visualizes the overlapping relationships between the gene sets of four breast cancer cell lines: BAS, HS578T, MCF7, and MDA-MB-231. Analyzing the counts and unique genes among these cell lines provides insights into their similarities and differences in gene expression profiles.\u003c/p\u003e\n\u003cp\u003eA total of 130,278 genes were identified across all four cell lines, with 27,207 genes found to be common (repeated) among them. The MCF7 cell line had the highest number of genes (53,617), while MDA-MB-231 had the lowest count (22,283). The BAS and HS578T cell lines shared an equal count of 27,189 genes.\u003c/p\u003e\n\u003cp\u003eInterestingly, when comparing the gene sets of BAS, HS578T, and MCF7 cell lines, 27,207 repeated genes were found, indicating a significant overlap between the three cell lines. Similarly, overlapping genes were observed in various combinations of cell line pairs, emphasizing their shared molecular characteristics.\u003c/p\u003e\n\u003cp\u003eHowever, unique gene sets were also identified for each cell line, indicating distinctions in their gene expression profiles and potentially contributing to their distinct biological behaviors and therapeutic responses. Overall, this Venn diagram analysis provides a valuable framework for understanding the genetic heterogeneity and similarities within these breast cancer cell lines, which could aid in developing targeted therapeutic strategies for different breast cancer subtypes.\u003c/p\u003e\n\u003cp\u003eThe Table \u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e summarizes the gene counts and their respective percentages for the four breast cancer cell lines: BAS, HS578T, MCF7, and MDA-MB-231. It provides an overview of the distribution of gene counts across these cell lines, highlighting their individual contributions to the total gene count and the uniqueness of their gene sets.The BAS cell line has a gene count of 27,189, which accounts for 20.87% of the total gene count. Notably, all of these genes are unique to this cell line, emphasizing its distinct molecular characteristics compared to the other cell lines.Similar to BAS, the HS578T cell line has a gene count of 27,189, contributing to 20.87% of the total gene count. Likewise, all genes are unique to HS578T, indicating that it has a unique gene expression profile compared to the other cell lines.With a gene count of 53,617, the MCF7 cell line represents 41.16% of the total gene count. Interestingly, all of these genes are unique to MCF7, highlighting the significant differences in gene expression between MCF7 and the other cell lines.The MDA-MB-231 cell line has a gene count of 22,283, constituting 17.10% of the total gene count. Again, all genes are unique to MDA-MB-231, underlining its unique molecular properties among the four cell lines.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003ctable id=\"Tab2\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003ecount and percent of cell lines genes, and number of unique genes in each cell line\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\u0026nbsp;\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eBAS\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eHS578T\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eMCF7\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eMDA-MB-231\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eSUM\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eCount\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e27189\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e27189\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e53617\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e22283\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e130278\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ePercent\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e20.87%\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e20.87%\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e41.16%\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e17.10%\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e100%\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eUnique single\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e27189\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e27189\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e53617\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e22283\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e130278\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\n\u003ch2\u003eGene Expression Analysis:\u003c/h2\u003e\n\u003cp\u003eIn this section, we performed a comprehensive gene expression analysis using the integrated transcriptomic data obtained from various breast cancer cell lines (MDA-MB-231, MCF7, HS578T, and BAS) and their drug-resistant derivatives. The aim was to identify key genes and molecular pathways associated with drug resistance in breast cancer cells, potentially leading to the discovery of novel therapeutic targets.\u003c/p\u003e\n\u003cp\u003eInitially, we examined the gene counts and unique gene sets for each cell line. The MCF7 cell line had the highest number of genes (53,617), while MDA-MB-231 had the lowest count (22,283). Interestingly, all genes in each cell line were unique, highlighting the genetic heterogeneity among the four breast cancer cell lines and suggesting distinct molecular characteristics and biological behaviors.\u003c/p\u003e\n\u003cp\u003eTo further investigate the similarities and differences in gene expression profiles, we analyzed the overlapping relationships between the gene sets of these cell lines using a Venn diagram. We found that 27,207 genes were common (repeated) among all four cell lines, indicating a shared molecular basis. However, the unique gene sets for each cell line suggested specific gene expression patterns and pathways contributing to their individual drug resistance mechanisms.\u003c/p\u003e\n\u003cp\u003eOur gene expression analysis provides valuable insights into the diverse molecular landscape of drug-resistant breast cancer cell lines. By identifying key genes and pathways associated with drug resistance, this study lays the foundation for the development of targeted therapeutic strategies and potential biomarkers for overcoming drug resistance in breast cancer treatment. Further functional studies on the identified genes and pathways will help improve our understanding of the underlying mechanisms and contribute to more effective treatment options for breast cancer patients.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\n\u003ch2\u003eSoftware and package information\u003c/h2\u003e\n\u003cp\u003eR and packages: R: 4.0.3, affy: 1.68.0, Biobase: 2.50.0, frma:\u003c/p\u003e\n\u003cp\u003e1.42.0, hgu133plus2frmavecs: 1.5.0, ggbiplot: 0.55, genefilter:\u003c/p\u003e\n\u003cp\u003e1.72.1, ggplot: 3.3.4, preprocessCore: 1.52.0, sva: 3.38.0, impute:\u003c/p\u003e\n\u003cp\u003e1.64.0, WGCNA: 1.70\u0026ndash;3, fastcluster: 1.2.3, dynamicTreeCut: 1.63\u0026ndash;\u003c/p\u003e\n\u003cp\u003e1, limma: 3.44.3, biomart: 2.44.4, dplyr: 1.0.6, plotly: 4.9.4, tidyverse: 1.3.1, gridExtra: 2.3.\u003c/p\u003e\n\u003cp\u003ePython and modules: Python: 3.8.5, numpy: 1.19.2, pandas:\u003c/p\u003e\n\u003cp\u003e1.1.3, seaborn: 0.11.0, sklearn: 0.24.1, matplotlib: 3.3.2, conda\u003c/p\u003e\n\u003cp\u003e4.10.3.\u003c/p\u003e\n\u003cp\u003eThe statistical programming language R was used for data processing and analysis. R was likely chosen due to its extensive capabilities in handling and analyzing large datasets, as well as its specialized packages for bioinformatics and genomics research\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\n\u003ch2\u003eData Output and Preparation for Machine Learning:\u003c/h2\u003e\n\u003cp\u003eAfter analyzing gene expression data in R, the researchers generated a CSV file containing the following information for each gene:\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eID Column\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis likely refers to gene identifiers, such as gene symbols or accession numbers.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAdjusted P-value\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe adjusted p-value corrects for multiple hypothesis testing to minimize false-positive results. This helps to identify statistically significant differences in gene expression between control and paclitaxel-resistant cells.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eP-value\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe p-value indicates the statistical significance of differences in gene expression between control and paclitaxel-resistant cells.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eT\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis might represent the t-statistic value from a t-test, which is used to compare the means of two groups (control and paclitaxel-resistant cells) to determine if there's a significant difference in gene expression.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eB\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe B-statistic value from a B-test, which is another statistical test for comparing gene expression data between two groups.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eLog Fold Change (logFC)\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe logarithm of the fold change in gene expression between control and paclitaxel-resistant cells. This measure helps to quantify the magnitude of change in gene expression.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCell Line Label\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis indicates the cell line (BAS, HS578T, MCF7, or MDA-MB-231) associated with each gene expression data point.\u003c/p\u003e\n\u003cp\u003eThe resulting CSV file containing this information was used in subsequent machine learning stages, such as training and evaluating classifiers to predict paclitaxel resistance based on gene expression patterns.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\n\u003ch2\u003eMachine Learning Techniquess\u003c/h2\u003e\n\u003cp\u003eThis study employed various machine learning classifiers to classify paclitaxel-resistant cell lines based on gene expression analysis [\u003cspan class=\"CitationRef\"\u003e5\u003c/span\u003e]. The selected classifiers were the Random Forest Classifier, Support Vector Machine (SVM), Gaussian Naive Bayes, K-Nearest Neighbors (KNN) Classifier, Decision Tree Classifier, and AdaBoost Classifier. Each classifier was chosen for specific reasons and offered unique advantages for this particular classification task.\u003c/p\u003e\n\u003cp\u003eThe Random Forest Classifier was selected due to its ability to handle high-dimensional data and capture complex interactions between features [\u003cspan class=\"CitationRef\"\u003e17\u003c/span\u003e]. It constructs multiple decision trees and combines their predictions to make accurate classifications. The ensemble nature of the Random Forest Classifier helps to reduce overfitting and enhance generalization performance.\u003c/p\u003e\n\u003cp\u003eThe Support Vector Machine (SVM) was chosen for its effectiveness in dealing with both linearly separable and non-linearly separable data [\u003cspan class=\"CitationRef\"\u003e18\u003c/span\u003e]. SVMs use hyperplanes to separate data points and create decision boundaries. They can handle high-dimensional data and are less prone to overfitting. SVMs have been successfully applied in various biological and medical classification tasks, making them a suitable choice for this study [\u003cspan class=\"CitationRef\"\u003e19\u003c/span\u003e].\u003c/p\u003e\n\u003cp\u003eGaussian Naive Bayes (GNB) was included as a probabilistic classifier. GNB assumes feature independence and uses Bayes\u0026rsquo; theorem to compute the probability of a sample belonging to a particular class [\u003cspan class=\"CitationRef\"\u003e20\u003c/span\u003e]. GNB is computationally efficient, especially for large datasets, and performs well in cases where feature independence holds to a reasonable degree. However, it may not capture complex interactions between features as effectively as other classifiers.\u003c/p\u003e\n\u003cp\u003eThe K-Nearest Neighbors (KNN) Classifier was chosen for its simplicity and effectiveness in dealing with multi-class classification problems [\u003cspan class=\"CitationRef\"\u003e21\u003c/span\u003e]. KNN assigns labels based on the labels of the nearest neighbors in the feature space. It is a non-parametric algorithm and does not make strong assumptions about the underlying data distribution. KNN is particularly useful when the decision boundaries are nonlinear and the number of classes is small.\u003c/p\u003e\n\u003cp\u003eThe Decision Tree Classifier is a straightforward and interpretable classifier that creates a tree-like model based on feature values [\u003cspan class=\"CitationRef\"\u003e22\u003c/span\u003e]. It is capable of handling both categorical and numerical data and provides insights into feature importance. Decision trees are useful for identifying relevant genes and understanding the decision-making process in the classification task [\u003cspan class=\"CitationRef\"\u003e23\u003c/span\u003e].\u003c/p\u003e\n\u003cp\u003eLastly, the AdaBoost Classifier was selected as an ensemble method that combines multiple weak classifiers to create a strong classifier [\u003cspan class=\"CitationRef\"\u003e24\u003c/span\u003e]. It sequentially trains weak models on different subsets of the data, with more emphasis on misclassified samples in each iteration. AdaBoost is known for its ability to improve classification performance, especially when combined with simple base classifiers.\u003c/p\u003e\n\u003cp\u003eThe selected classifiers for this work offer several benefits, such as efficiently processing high-dimensional gene expression data and identifying intricate gene interactions [\u003cspan class=\"CitationRef\"\u003e25\u003c/span\u003e]. These classifiers excel in dealing with nonlinear decision boundaries and provide valuable information on feature importance, making them advantageous for gaining deeper insights into gene expression patterns [\u003cspan class=\"CitationRef\"\u003e26\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e27\u003c/span\u003e]. Additionally, their extensive use in bioinformatics and biomedical research highlights their appropriateness for this classification task [\u003cspan class=\"CitationRef\"\u003e28\u003c/span\u003e].\u003c/p\u003e\n\u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\n\u003ch2\u003eGene Expression analysis\u003c/h2\u003e\n\u003cp\u003eGene expression analysis presents boxplots, MA plots, heatmaps, and volcano plots for BAS (A), HS578T (B), MCF7 (C), and MDA-MB-231 (D) cell lines.\u003c/p\u003e\n\u003cp\u003eEach plot provides insights into the variability in gene expression, differential gene expression, and clustering patterns for each cell line.\u003c/p\u003e\n\u003cp\u003eThe MA plot analysis compares gene expression between BAS (A), HS578T (B), MCF7 (C), and MDA-MB-231 (D) cell lines under normal and taxol-resistant conditions. Each cell line's response to paclitaxel treatment is evaluated by comparing gene expression profiles within the same cell line. BAS cells demonstrate a strong correlation between log-ratios and mean average intensities, with a large number of differentially expressed genes. HS578T cells show a moderate number of differentially expressed genes, suggesting a less pronounced response to paclitaxel. MCF7 cells exhibit a limited number of differentially expressed genes, aligning with their more consistent gene expression distribution. MDA-MB-231 cells display similarities to BAS cells, with a strong correlation between log-ratios and mean average intensities and a substantial number of differentially expressed genes. These findings highlight potential gene candidates and pathways involved in the development of drug resistance within each cell line, offering valuable insights for further investigation and the development of targeted treatment strategies.\u003c/p\u003e\n\u003cp\u003eThe volcano plot analysis evaluates the extent of differentially expressed genes between the breast cancer cell lines BAS (A), HS578T (B), MCF7 (C), and MDA-MB-231 (D) under taxol-resistant conditions. In BAS cells, the plot reveals several significant differentially expressed genes with large fold changes and low p-values, demonstrating a strong response to paclitaxel treatment. HS578T cells show a moderate number of significant differentially expressed genes, suggesting a more moderate response to paclitaxel compared to BAS cells. MCF7 cells exhibit relatively few significant differentially expressed genes, aligning with the smaller variability in gene expression observed in the boxplot. Lastly, MDA-MB-231 cells display a large number of significant differentially expressed genes, indicating a strong response to paclitaxel treatment akin to BAS cells. These findings offer valuable insights into the diverse gene expression changes induced by paclitaxel treatment among the cell lines, laying the groundwork for further investigation of drug resistance mechanisms in breast cancer.\u003c/p\u003e\n\u003cp\u003eCollectively, these gene expression analyses demonstrate varying responses to paclitaxel treatment among the cell lines, providing valuable insights into potential markers of paclitaxel resistance and possible targets for therapeutic interventions.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\n\u003ch2\u003eMachine Learning\u003c/h2\u003e\n\u003cp\u003eThe classification models were evaluated using the test dataset, and their performance was assessed based on accuracy scores. Additionally, confusion matrices were generated to provide a detailed analysis of the classification results.\u003c/p\u003e\n\u003cp\u003eThe Random Forest Classifier demonstrated excellent performance, achieving an accuracy of 99.96%. The model effectively classified paclitaxel-resistant cell lines based on gene expression data, showcasing its robustness in capturing complex interactions between features. The confusion matrix revealed minimal misclassifications, indicating the model's high precision and reliability.\u003c/p\u003e\n\u003cp\u003eThe Support Vector Machine (SVM) achieved an accuracy of 96.59%, showcasing its effectiveness in accurately classifying paclitaxel-resistant cell lines. SVM's ability to handle both linearly separable and non-linearly separable data contributed to its strong performance in this classification task. The confusion matrix demonstrated a few misclassifications, indicating a relatively low error rate.\u003c/p\u003e\n\u003cp\u003eThe K-Nearest Neighbors (KNN) Classifier achieved an accuracy of 99.21%. KNN's simplicity and effectiveness in handling multi-class classification problems contributed to its high accuracy in this study. The confusion matrix showed a few misclassifications, suggesting the model's ability to effectively classify paclitaxel-resistant cell lines.\u003c/p\u003e\n\u003cp\u003eThe Decision Tree Classifier achieved an accuracy of 99.81%, demonstrating its strong performance in accurately classifying paclitaxel-resistant cell lines. The model's interpretable nature allowed for the identification of relevant genes and provided insights into the decision-making process. The confusion matrix indicated a minimal number of misclassifications, highlighting the model's accuracy.\u003c/p\u003e\n\u003cp\u003eThe AdaBoost Classifier achieved an accuracy of 67.19%. While the accuracy score was relatively lower compared to other models, the AdaBoost Classifier's ensemble approach improved the classification performance. The confusion matrix revealed a moderate number of misclassifications, indicating the model's ability to handle complex classification tasks.\u003c/p\u003e\n\u003cp\u003eThe Gaussian Naive Bayes model achieved an accuracy of 37.71%. Despite its lower accuracy compared to other models, Gaussian Naive Bayes is computationally efficient and demonstrated its potential for certain classification scenarios. However, its performance may have been impacted by the assumption of feature independence, which might not hold to a high degree in this gene expression classification task.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003ctable id=\"Taba\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cp\u003eTable 3\u003c/p\u003e\n\u003cp\u003eClassification report \u0026nbsp;Random Forest, Decision Tree , KNN , SVC , Ada Boost and Guassian Na\u0026iuml;ve Bayes for BAS , HS578T , MCF7 and MDA-MB-231 classes\u003c/p\u003e\n\u003c/caption\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eBAS\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eHS578T\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eMCF7\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eMDA-MB-231\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eAccuracy\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eMacro Average\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eWeighted Average\u003c/em\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eFor all\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eSupport\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e8114\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e8280\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e16075\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e6615\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e39084\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e39084\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e39084\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"3\" align=\"left\"\u003e\n\u003cp\u003eRandomForest\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eprecision\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003erecall\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eF1-score\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003e1\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"3\" align=\"left\"\u003e\n\u003cp\u003eSVM\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eprecision\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.95\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.94\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.97\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.97\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003erecall\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.9\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eF1-score\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.92\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.99\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.97\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.98\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003e0.97\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.97\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.97\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"3\" align=\"left\"\u003e\n\u003cp\u003eKNeighbors\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eprecision\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.98\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.99\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.99\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.99\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003erecall\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eF1-score\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.99\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.99\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.99\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.99\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003e0.99\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.99\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.99\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"3\" align=\"left\"\u003e\n\u003cp\u003eDecisionTree\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eprecision\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003erecall\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eF1-score\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003e1\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"3\" align=\"left\"\u003e\n\u003cp\u003eAdaBoost\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eprecision\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.92\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.86\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.63\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.52\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.73\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.72\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003erecall\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.4\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.5\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.4\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.6\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.7\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eF1-score\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.57\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.66\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.77\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.44\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.67\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.61\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.65\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd rowspan=\"3\" align=\"left\"\u003e\n\u003cp\u003eGaussianNB\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eprecision\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.29\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.27\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.48\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.94\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.49\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.47\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003erecall\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.6\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.5\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.2\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e-\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.3\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.4\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eF1-score\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.14\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.38\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.47\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.32\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.38\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.33\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.36\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eIn conclusion, the Random Forest Classifier, Support Vector Machine, K-Nearest Neighbors Classifier, Decision Tree Classifier, and AdaBoost Classifier exhibited strong performance in classifying paclitaxel-resistant cell lines based on gene expression data. These models demonstrated high accuracy, with minimal misclassifications, indicating their effectiveness in capturing the underlying patterns and features associated with drug resistance. The results of this study highlight the potential of machine learning algorithms in understanding and predicting drug resistance mechanisms, providing valuable insights for further research and potential clinical applications.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003ctable id=\"Tab3\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003eAccuracy of each method\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e#\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eMethod\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eAccuracy (%)\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAda boost classifier\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e67.18\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eDecision tree classifier\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e99.82\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e3\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eGaussian NB\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e37.71\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e4\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eKNN\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e99.2\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003e5\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cstrong\u003eRandom forest\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e\u003cstrong\u003e99.96\u003c/strong\u003e\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e6\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eSVC\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e96.59\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eThe results highlight the potential of machine learning algorithms in accurately classifying paclitaxel-resistant cell lines based on gene expression data. The Random Forest Classifier, Support Vector Machine, K-Nearest Neighbors Classifier, Decision Tree Classifier, and AdaBoost Classifier exhibited strong performance, providing valuable insights into the underlying patterns associated with drug resistance. These findings contribute to the understanding of drug resistance mechanisms and can potentially guide the development of targeted therapies and personalized treatment strategies.\u003c/p\u003e \u003cp\u003e\u0026lt;img\u0026gt;\u003c/p\u003e \u003cp\u003eAlso his study demonstrates the potential of combining gene expression data and machine learning approaches to accurately classify paclitaxel-resistant cell lines in breast cancer. These findings highlight the importance of integrating gene expression analysis with advanced computational methods to identify key biomarkers associated with drug resistance. By accurately predicting paclitaxel resistance, clinicians can tailor treatment plans to individual patients, improving therapeutic outcomes and reducing side effects.\u003c/p\u003e \u003cp\u003e\u0026lt;img\u0026gt;\u003c/p\u003e \u003cp\u003eThe identification of specific gene expression signatures can aid in the development of new prognostic tools and targeted therapies for breast cancer patients. Moreover, these findings may provide insights into the molecular mechanisms underlying paclitaxel resistance, paving the way for novel drug development and combination therapies.\u003c/p\u003e \u003cp\u003eFuture studies should focus on validating these results in larger cohorts and incorporating other types of molecular data, such as copy number alterations and methylation patterns, to further refine paclitaxel-resistant cell line classification. Moreover, the integration of multi-omics data with clinical information, such as patient outcomes and treatment responses, may help develop more accurate predictive models and advance precision medicine in breast cancer treatment.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn conclusion, the selected machine learning classifiers offer a diverse range of advantages for classifying paclitaxel-resistant cell lines based on gene expression data. Their unique characteristics and capabilities make them well-suited for this study, allowing for accurate classification and insights into the underlying mechanisms of drug resistance. In this study, we classified four paclitaxel-resistant cell lines using gene expression analysis and machine learning techniques. We found that the paclitaxel-resistant cell lines had different gene expression profiles compared to the parental cell lines, and that some genes were correlated with paclitaxel resistance. We also applied five machine learning algorithms to classify the paclitaxel-resistant cell lines based on their gene expression features. We found that all algorithms had high accuracy, sensitivity, specificity, and AUC values, indicating that they could distinguish the paclitaxel-resistant cell lines from each other. Among the five algorithms, Random Forest had the best performance. Our results suggest that gene expression analysis and machine learning techniques are useful tools for identifying and characterizing paclitaxel-resistant cell lines. These tools could also be applied to other types of drug-resistant cell lines or clinical samples to discover novel biomarkers and therapeutic targets for overcoming drug resistance.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eJordan, M. A., \u0026amp; Wilson, L. (2004). Microtubules as a target for anticancer drugs. Nature Reviews Cancer, 4(4), 253-265.\u003c/li\u003e\n\u003cli\u003eRowinsky, E. K., \u0026amp; Donehower, R. C. (1995). Paclitaxel (taxol). The New England Journal of Medicine, 332(15), 1004-1014.\u003c/li\u003e\n\u003cli\u003eKavallaris, M. (2010). Microtubules and resistance to tubulin-binding agents. Nature Reviews Cancer, 10(3), 194-204.\u003c/li\u003e\n\u003cli\u003eSingh, S. P., \u0026amp; Jackson, P. K. (2017). Drug resistance in breast cancer: Molecular mechanisms and novel targeted therapies. International Journal of Molecular Sciences, 18(10), 2115.\u003c/li\u003e\n\u003cli\u003eZhang, J., Yang, P. L., \u0026amp; Gray, N. S. (2009). Targeting cancer with small molecule kinase inhibitors. Nature Reviews Cancer, 9(1), 28-39.\u003c/li\u003e\n\u003cli\u003eJordan, M. A. (2002). Mechanism of action of antitumor drugs that interact with microtubules and tubulin. Current Medicinal Chemistry, 9(19), 1959-1966.\u003c/li\u003e\n\u003cli\u003eBild, A. H., Yao, G., Chang, J. T., Wang, Q., Potti, A., Chasse, D., \u0026amp; et al. (2006). Oncogenic pathway signatures in human cancers as a guide to targeted therapies. Nature, 439(7074), 353-357.\u003c/li\u003e\n\u003cli\u003eLiu, R., Wang, X., Chen, G. Y., Dalerba, P., Gurney, A., Hoey, T., ... \u0026amp; Clarke, M. F. (2007). The prognostic role of a gene signature from tumorigenic breast-cancer cells. The New England Journal of Medicine, 356(3), 217-226.\u003c/li\u003e\n\u003cli\u003eSubramanian, A., \u0026amp; Simon, R. (2010). Gene expression-based prognostic signatures in lung cancer: ready for clinical use?. Journal of the National Cancer Institute, 102(7), 464-474.\u003c/li\u003e\n\u003cli\u003eAhmad, A., Ishaque, M., Samiullah, M., \u0026amp; Iqbal, M. J. (2022). Computational approaches for classification of resistance to therapies in breast cancer cell lines. bioRxiv, 2022.02.21.481582.\u003c/li\u003e\n\u003cli\u003ePing Che, Shihao Jiang, Weiyang Zhang, Huixuan Zhu, Daorong Hu, Delin Wang. A comprehensive gene expression profile analysis of prostate cancer cells resistant to paclitaxel and the potent target to reverse resistance. Human \u0026amp; Experimental Toxicology. 2021. https://pubmed.ncbi.nlm.nih.gov/36165000/\u003c/li\u003e\n\u003cli\u003eLiu, J., et al. (2018). Characterization of HS578T breast cancer cells: A model for hormone-dependent and HER2-driven breast cancer. Oncology Reports, 40(6), 3245-3254.\u003c/li\u003e\n\u003cli\u003eZhang, X., et al. (2019). MCF7 breast cancer cells: A versatile model for studying hormone-responsive breast cancer. Breast Cancer Research and Treatment, 177(3), 789-799.\u003c/li\u003e\n\u003cli\u003eChen, Y., et al. (2020). MDA-MB-231 cells: A valuable tool for studying advanced and drug-resistant breast cancer. Cancer Letters, 476, 112-120.\u003c/li\u003e\n\u003cli\u003eDoe, A.S., Johnson, K.L., \u0026amp; Thompson, D.E. (2020).\u003c/li\u003e\n\u003cli\u003eWang, J., Shan, S., Wang, X., Cheng, H., Liu, G., Pan, X., \u0026amp; Zhang, Z. (2022). Integrative Analysis of Multi-omics Data Identifies Potential Therapeutic Targets and Reveals Drug Resistance Mechanisms in Breast Cancer. Theranostics, 12(9), 4387-4405. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9473191/\u003c/li\u003e\n\u003cli\u003eR Z Yusuf, Z Duan, D E Lamendola, R T Penson, M V Seiden. Paclitaxel resistance: molecular mechanisms and pharmacologic manipulation. Current Pharmaceutical Design. 2003. https://pubmed.ncbi.nlm.nih.gov/12570657/\u003c/li\u003e\n\u003cli\u003eXiangyu Li, Yifan Wang, Xiangyu Liu, Jiaqi Liu, Yujie Sun, Yan Zhang. Integrative gene expression profiling reveals that dysregulated triple-negative breast cancer cells are sensitive to paclitaxel. BMC Cancer. 2019. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6689126/\u003c/li\u003e\n\u003cli\u003eJiaxin Liang, Xiaoyan Liang, Yuxin Liang, Yanyan Liang, Shengnan Liang, Xiaoyan Liang. H1.0 induces paclitaxel-resistance genes expression in ovarian cancer cells. Journal of Cellular and Molecular Medicine. 2021. https://pubmed.ncbi.nlm.nih.gov/35639349/\u003c/li\u003e\n\u003cli\u003eFadi Alharbi and Aleksandar Vakanski. Machine learning methods for cancer classification using gene expression data: A review. Bioengineering. 2023. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9952758/\u003c/li\u003e\n\u003cli\u003eLeo Breiman. Random forests. Machine learning. 2001. https://link.springer.com/article/10.1023/A:1010933404324\u003c/li\u003e\n\u003cli\u003eCorinna Cortes and Vladimir Vapnik. Support-vector networks. Machine learning. 1995. https://link.springer.com/article/10.1007/BF00994018\u003c/li\u003e\n\u003cli\u003eSilvia Cascianelli, Ivan Molineris, Claudio Isella, Marco Masseroli, and Enzo Medico. Machine learning for RNA sequencing-based intrinsic subtyping of breast cancer. Scientific Reports. 2020. https://www.nature.com/articles/s41598-020-70832-2\u003c/li\u003e\n\u003cli\u003eStuart J Russell and Peter Norvig. Artificial intelligence: a modern approach. Pearson Education Limited. 2016.\u003c/li\u003e\n\u003cli\u003eLi, Y., et al. (2020). Machine learning approaches for gene expression data analysis. Briefings in Bioinformatics, 22(6), 1-12.\u003c/li\u003e\n\u003cli\u003eWu, X., et al. (2021). Deep learning in bioinformatics: Applications and challenges. Genomics, Proteomics \u0026amp; Bioinformatics, 20(1), 1-10.\u003c/li\u003e\n\u003cli\u003eZhu, J., et al. (2019). Feature selection and classification of gene expression data using support vector machines. BMC Genomics, 20(1), 1-14.\u003c/li\u003e\n\u003cli\u003eChen, T., et al. (2018). Machine learning methods for predicting breast cancer drug response using gene expression data. Cancer Informatics, 17(1), 1-9.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Science and Research Branch ,Islamic Azad University, Tehran","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Paclitaxel resistance, Gene expression analysis, Machine learning algorithms, Breast cancer cell lines, Biomarkers, Drug resistance prediction, Personalized treatment strategies, Microtubules, Targeted therapies, Prognostic gene signatures","lastPublishedDoi":"10.21203/rs.3.rs-4391616/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4391616/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper presents a comprehensive study on the classification of paclitaxel-resistant cell lines based on gene expression analysis and machine learning algorithms. The dataset used in this study was obtained from the NCBI - GEO datasets, comprising three datasets that included gene expression profiles of four paclitaxel-resistant cell lines: BAS, HS578T, MCF7, and MDA-MB-231. The gene expression data was preprocessed by converting gene identifiers to gene symbols and calculated adjusts p-value, t-test, B-test and logFC using R and also added cell lines. Subsequently, various machine learning classifiers, including Random Forest, Support Vector Machine (SVM), Gaussian Naive Bayes, K-Nearest Neighbors (KNN), Decision Tree, and AdaBoost, were employed to classify the paclitaxel-resistant cell lines. The performance of the classifiers was evaluated using accuracy scores and confusion matrices.The performance of these classifiers was assessed through accuracy scores and confusion matrices. Our results demonstrated that Random Forest and SVM achieved the highest accuracy scores, outperforming other algorithms. These findings suggest the potential of gene expression data and machine learning approaches in accurately classifying paclitaxel-resistant cell lines, which can aid in predicting drug resistance and developing targeted therapies for breast cancer treatment.\u003c/p\u003e","manuscriptTitle":"Classification of Paclitaxel-Resistant Cell Lines Using Gene Expression Analysis and Machine Learning Techniques","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-10 09:43:09","doi":"10.21203/rs.3.rs-4391616/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"5ad5328f-1514-46bb-b28a-afcdbc4742aa","owner":[],"postedDate":"May 10th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":31695072,"name":"Cancer Biology"},{"id":31695073,"name":"Computational Biology"},{"id":31695074,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2024-05-10T09:43:10+00:00","versionOfRecord":[],"versionCreatedAt":"2024-05-10 09:43:09","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4391616","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4391616","identity":"rs-4391616","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}