Machine Learning Analysis of RNA-seq Data for Diagnostic and Prognostic Prediction of Colon Cancer

Abstract

Data from omics studies have been used for prediction and classification of various diseases in biomedical and bioinformatics research. In recent years, Machine Learning (ML) algorithms have been used in many different fields related to healthcare systems, especially for disease prediction and classification tasks. Integration of molecular omics data with ML algorithms has offered a great opportunity to evaluate clinical data. RNA sequence (RNA-seq) analysis has been emerged as the gold standard for transcriptomics analysis. Currently, it is being used widely in clinical research. In our present work, RNA-seq data of extracellular vesicles (EV) from healthy and colon cancer patients are analyzed. Our aim is to develop models for prediction and classification of colon cancer stages. Five different canonical ML and Deep Learning (DL) classifiers are used to predict colon cancer of an individual with processed RNA-seq data. The classes of data are formed on the basis of both colon cancer stages and cancer presence (healthy or cancer). The canonical ML classifiers, which are k-Nearest Neighbor (kNN), Logistic Model Tree (LMT), Random Tree (RT), Random Committee (RC), and Random Forest (RF), are tested with both forms of the data. In addition, to compare the performance with canonical ML models, One-Dimensional Convolutional Neural Network (1-D CNN), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM) DL models are utilized. Hyper-parameter optimizations of DL models are constructed by using genetic meta-heuristic optimization algorithm (GA). The best accuracy in cancer prediction is obtained with RC, LMT, and RF canonical ML algorithms as 97.33%. However, RT and kNN show 95.33% performance. The best accuracy in cancer stage classification is achieved with RF as 97.33%. This result is followed by LMT, RC, kNN, and RT with 96.33%, 96%, 94.66%, and 94%, respectively. According to the results of the experiments with DL algorithms, the best accuracy in cancer prediction is obtained with 1-D CNN as 97.67%. BiLSTM and LSTM show 94.33% and 93.67% performance, respectively. In classification of the cancer stages, the best accuracy is achieved with BiLSTM as 98%. 1-D CNN and LSTM show 97% and 94.33% performance, respectively. The results reveal that both canonical ML and DL models may outperform each other for different numbers of features.

Personalized Plasma Medicine for Cancer: Transforming Treatment Strategies with Mathematical Modeling and Machine Learning Approaches

“…The evolution of AI, particularly with the integration of ML, has opened new possibilities in oncology, revolutionizing every facet of cancer care. It has significantly enhanced cancer diagnosis [90][91][92][93], prognosis [94][95][96][97][98], and the prediction of metastasis [99][100][101].…”

“…The evolution of AI, particularly with the integration of ML, has opened new possibilities in oncology, revolutionizing every facet of cancer care. It has significantly enhanced cancer diagnosis [90][91][92][93], prognosis [94][95][96][97][98], and the prediction of metastasis [99][100][101]. Treatment selection [102], efficacy [103][104][105], response assessment [106][107][108][109][110], and outcome prediction [111][112][113][114][115] have also seen remarkable enhancements.…”

Predicting Phenotypic Traits Using a Massive RNA-seq Dataset

“…Random Forest models were created using the RandomForestClassifier class for classification of tissues and the RandomForestRegression class was used for age prediction. In both cases, the parameter search space iterated over the following grid: ‘bootstrap’: [True, False], ‘n_estimators’: [100, 300, 500, 1000, 1500, 2000], ‘n_estimators’: [3, 5, 10, 20], ‘max_depth’: 3 to 100 at an interval of 3), ‘min_samples_split’: [1,2,4], ‘min_samples_leaf’: [3, 5, 10, 20, 30], ‘max_features’: [’sqrt’, ‘log2’]. These parameters were sampled 100 times for each of the four filtered GEMs (NoNo, and three GEMs normalized by TMM, MRN, and TPM respectively).…”

“…This means that transcriptomic biomarkers can be used for monitoring and prediction of difficult-tomeasure phenotypic traits. Transcriptomic biomarkers are used in medical research with an emphasis on predicting cancer type and stage [1][2][3][4]. However, recent research has branched into high-value agricultural crops, where researchers are interested in predicting traits such as flowering time [5], flesh quality traits in apples, pears, and potatoes [6][7][8][9], and apple maturity [10].…”

Computational approaches in rheumatic diseases – Deciphering complex spatio-temporal cell interactions

“…Further studies in the selection of relevant hyperparameters are needed. [162] Classification of patients with multiple myeloma for three different chemotherapy treatment regimens to responders or non-responders by applying ML to RNAseq data. LR, RF, SVN No universal model.…”