Personalized medicine provides more safe and effective treatment by individualizing the choice of drug and dose based on an individual's genetic profile. Cancer patients' response to anti-cancer treatments (drugs) is one of the foremost challenges in personalized medicine that releases the target treatment. Both size and availability of drug sensitivity data have motivated researchers to develop Artificial Intelligence (AI), based models, for predicting drug response to advance cancer treatment. The concerned AI models include Machine Learning (ML) and the recently advanced Deep Learning (DL) based models. This paper introduces both; a data federation method and a DL-based model for predicting drug response. The fundamental goal is to generalize the predictor so it will be able to predict the response to different drugs accurately. As the data has a considerable effect on any AI model, the data federation is utilized to consolidate the data. The proposed consolidation process is carried out to make each cell line contains gene expression data, its mutation profile, and drug response data. ML models such as Support Vector Machine (SVM) and Linear Regression (LR) are used along with Principal Component Analysis (PCA) for feature reduction, and the AI models have been tested with and without data federation. The results show that data federation enhanced the accuracy and decreased the Mean Square Error (MSE) by almost 25%. The proposed DL model uses dimension reduction encoders. The encoder is a DL model that uses unsupervised learning. It is trained by integrating an encoder with a decoder to achieve equality between the input and output. The proposed model has achieved the best accuracy compared to some other recent models in terms of the Pearson correlation coefficient (PCC) as a performance measure. In addition, the results show that the Enhanced Deep Drug Response prediction (Enhanced Deep-DR) model has achieved the best PCC value even with the largest number of genes and drugs, which proves the high capacity and efficiency of the proposed model. Convolutional Neural Network (CNN) based-model is also implemented; it achieves higher accuracy in predicting the drug response than in some other DL-based models but less than the Enhanced Deep learning. The Enhanced Deep-DR achieves better accuracy within the range of 5% to 12% than other DL-models.
This chapter proposed different hybrid clustering methods based on combining particle swarm optimization (PSO), gravitational search algorithm (GSA) and free parameters central force optimization (CFO) with each other and with the k-means algorithm. The proposed methods were applied on 5 real datasets from the university of California, Irvine (UCI) machine learning repository. Comparative analysis was done in terms of three measures; the sum of intra cluster distances, the running time and the distances between the clusters centroids. The initial population for the used algorithms were enhanced to minimize the sum of intra cluster distances. Experimental results show that, increasing the number of iterations doesn't have a noticeable impact on the sum of intra cluster distances while it has a negative impact on the running time. K-means combined with GSA (KM-GSA), PSO combined with GSA (PSO-GSA) gave the best performance according to the sum of intra cluster distances while K-means combined with PSO (KM-PSO) and KM-GSA were the best in terms of the running time. Finally, KM-GSA and GSA have the best performance.
Recently, efforts are exerted on cancer treatment prediction based on the biomarkers related to the tumor. Gene expression and mutation profiles are the most used biomarkers for cancer prediction. Machine learning and deep learning algorithms have been used to predict drug response. The recent research show that the performance of deep learning models is better than the performance of machine learning based one. In this paper, Convolutional Neural Network (CNN) models use are introduced to predict different drugs response. DeepInsight algorithm used to convert the input data to images to be more suitable as input to the CNN. Three different pretrained CNNs-models (InceptionV3, Xception, EfficientNetB7) are introduced with alternatives in their settings of the training process and modification in their architectures to be able to predict the drug response using IC50 regression values. Those models are selected due to their efficiency for ImageNet applications.the proposed modified Xception model achieves the best accuracy over the 2 others. At first, the whole data input passes through DeepInsight which converts the gene expression data and mutation data to images. Dimension reduction is then applied using the helper technique inside the DeepIsignt. Comparative analysis with other Deep models, shows that the proposed approach improve the prediction accuracy in a range between 14% and 22% as a reduction in mean squared error (MSE).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.