Developing liver cancer drug response prediction system using late fusion of reduced deep features

Hassan, Mehdi; Ali, Safdar; Alquhayz, Hani; Kim, Jin Young; Sanaullah, Muhammad

doi:10.1016/j.jksuci.2022.07.024

Cited by 5 publications

(7 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, only a small amount of annotated data is available for medical diagnosis. Therefore, it is recommended to use certain statistical approaches to estimate sample size for study justification and experimentation [11]. For this purpose, G * Power statistical tool is adopted to estimate the sample size for DL model training and validation in the context of TL concept.…”

Section: Sample Size Selectionmentioning

confidence: 99%

“…The ResNet model architecture contains stacking of several convolutional and pooling layers to perform image feature extraction followed by classification layers. Moreover, the ResNet deep learning architecture has a skip connection or residual learning capability, enabling the network to explore and learn hidden image patterns better than other networks, such as AlexNet, GoogLeNet, and VGG [11,20,21]. In this study, ResNet50, ResNet101, InceptionV3, GoogLeNet, and MobileNetV2 models are customized and trained to determine the best network for the current classification task.…”

Section: Customized Resnet101 Deep Learning Modelmentioning

confidence: 99%

“…In TL, the weight-sharing mechanism is achieved by freezing the weights of some layers in the existing network and then retraining for newly introduced layers. This procedure is successfully being adopted to solve several problems, such as human liver cancer drug response, HBV, skin cancer diagnosis, and plant disease predictions [11,[22][23][24][25].…”

Section: The Resnet101 Transfer Learningmentioning

confidence: 99%

“…These DFs are further used for LDA classification. Similarly, several real-world problems are solved by the TL-based deep feature extraction model followed by classification [11,21]. A feature vector x DF 1 , x DF 2 , .…”

Section: Deep Tl-resnet101 Bcrp Feature Extractionmentioning

confidence: 99%

“…In another study, Sasahara et al [10] proposed a drug metabolism prediction model by adopting different conventional classification techniques and reported an accuracy of 79.9% on the test dataset. Hassan et al [11] proposed a drug response prediction model for in-vitro human liver cancer cell lines using reduced features and a quadratic discriminant analysis (QDA) algorithm. The study reported an accuracy of 98.0% on the test dataset for HepG2 cancer cell line classification.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Developing a Breast Cancer Resistance Protein Substrate Prediction System Using Deep Features and LDA

Hassan,

Ali,

Young Kim

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Breast cancer resistance protein (BCRP) is an important resistance protein that significantly impacts anticancer drug discovery, treatment, and rehabilitation. Early identification of BCRP substrates is quite a challenging task. This study aims to predict early substrate structure, which can help to optimize anticancer drug development and clinical diagnosis. For this study, a novel intelligent approach-based methodology is developed by modifying the ResNet101 model using transfer learning (TL) for automatic deep feature (DF) extraction followed by classification with linear discriminant analysis algorithm (TLRNDF-LDA). This study utilized structural fingerprints, which are exploited by DF contrary to conventional molecular descriptors. The proposed in silico model achieved an outstanding accuracy performance of 98.56% on test data compared to other state-of-the-art approaches using standard quality measures. Furthermore, the model's efficacy is validated via a statistical analysis ANOVA test. It is demonstrated that the developed model can be used effectively for early prediction of the substrate structure. The pipeline of this study is flexible and can be extended for in vitro assessment efficacy of anticancer drug response, identification of BCRP functions in transport experiments, and prediction of prostate or lung cancer cell lines.

show abstract

Section: Sample Size Selectionmentioning

confidence: 99%

Section: Customized Resnet101 Deep Learning Modelmentioning

confidence: 99%

Section: The Resnet101 Transfer Learningmentioning

confidence: 99%

Section: Deep Tl-resnet101 Bcrp Feature Extractionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Developing a Breast Cancer Resistance Protein Substrate Prediction System Using Deep Features and LDA

Hassan,

Ali,

Young Kim

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

A review of cancer data fusion methods based on deep learning

Zhao,

Li,

Zhou

et al. 2024

Information Fusion

View full text Add to dashboard Cite

Optimal fusion of genotype and drug embeddings in predicting cancer drug response

Nguyen,

Campbell,

Kumar

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

Predicting cancer drug response using both genomics and drug features has shown some success compared to using genomics features alone. However, there has been limited research done on how best to combine or fuse the two types of features. Using a visible neural network with two deep learning branches for genes and drug features as the base architecture, we experimented with different fusion functions and fusion points. Our experiments show that injecting multiplicative relationships between gene and drug latent features into the original concatenation-based architecture DrugCell significantly improved the overall predictive performance and outperformed other baseline models. We also show that different fusion methods respond differently to different fusion points, indicating that the relationship between drug features and different hierarchical biological level of gene features is optimally captured using different methods. Considering both predictive performance and runtime speed, tensor product partial is the best-performing fusion function to combine late-stage representations of drug and gene features to predict cancer drug response.

show abstract

Developing liver cancer drug response prediction system using late fusion of reduced deep features

Cited by 5 publications

References 40 publications

Developing a Breast Cancer Resistance Protein Substrate Prediction System Using Deep Features and LDA

Developing a Breast Cancer Resistance Protein Substrate Prediction System Using Deep Features and LDA

A review of cancer data fusion methods based on deep learning

Optimal fusion of genotype and drug embeddings in predicting cancer drug response

Contact Info

Product

Resources

About