Targeted unsupervised features learning for gene expression data analysis to predict cancer stage

Zenbout, Imene; Bouramoul, Abdelkrim; Meshoul, Souham

doi:10.1145/3365953.3365958

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, (Yan and Han 2018) used SAE as a feature extraction method to enhance intrusion detection systems. Furthermore, Zenbout et al (2020) employed SAE for miRNA-based cancer classi cation. However, to the best of our knowledge, there have been limited recent investigations into the application of autoencoders speci cally for SDP tasks.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Feature Selection via Semi supervised denoising autoencoder and traditional approaches For Software Fault-prone Classification

Amara

Rabai

2023

Preprint

View full text Add to dashboard Cite

Software quality is the capability of a software process to produce software product satisfying the end user. The quality of process or product entities is described through a set of attributes that may be internal or external. For the product entity, especially, the source code, different internal attributes are defined to evaluate its quality like complexity and cohesion. Concerning external attributes related to the product environment like reliability, their assessment is more difficult. Thus, they are usually predicted by the development of prediction models based on software metrics as independent variables and other measurable attributes as dependent variables. For instance, reliability like other external attributes is generally measured and predicted based on other quality attributes like defect density, defect count and fault-proneness. The success of machine learning (ML) and deep learning (DL) approaches for software defect and faulty modules classification as crucial attributes for software reliability improvement is remarkable. In recent years, there has been growing interest in exploring the use of deep learning autoencoders, a type of neural network architecture, for software defect prediction. Therefore, we aim in this paper to explore the semi-supervised denoising DL autoencoder in order to capture relevant features. Then, we evaluate its performance in comparison to traditional ML supervised SVM technique for fault-prone modules classification. The performed experiments based on a set of software metrics extracted from NASA projects achieve promising results in terms of accuracy and show that denoising DL autoencoder outperforms traditional SVM technique.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison of Feature Selection via Semi supervised denoising autoencoder and traditional approaches For Software Fault-prone Classification

Amara

Rabai

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Shao W et al [28] proposed a multitasking multimodal feature selection method for joint cancer diagnosis and prognosis, and discovered the relationship between cancer diagnosis (e.g., TNM stage) and prognosis through a comprehensive analysis of histopathology images, genomic data, and clinical of squamous lung cancer. Zenbout I [29] used gene expression with histopathology imaging features to examine and directly compare simulated lung cancer overall survival.…”

Section: Introductionmentioning

confidence: 99%

A progressive phased attention model fusing histopathology and genomic features for lung cancer staging

Cai

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

Morphological information from histopathology slides and molecular profiles from genomic data are important for predicting the staging of lung cancer. However, most deep learning-based prediction results are based on histopathology or genomics alone, which do not fully utilize the complementary information of both and ignore staining differences in histopathology images due to different staining conditions. In this study, we propose a Multimodal Multi-scale Attention Model (MMAM) to predict patients’ lung cancer staging outcomes by end-to-end multimodal fusion of patients' multi-scale histopathology image features with genetic features by augmented attention. The proposed MMAM consists of two phases. In the first phase, a Staining Difference Elimination Network (SDEN) is proposed for stable detection of histopathology image features to eliminate differences arising from different hospital/specimen staining conditions. In the second phase, we design a Multimodal Multi-scale Fusion Network (MMFN) to efficiently fuse different modality features. We have validated our approach on the lung cancer dataset from The Cancer Genome Atlas (TCGA). The results show that the proposed MMAM improves the staging effectiveness of the fusion network of histopathological and genomic features, reduces the effect of appearance variability due to staining differences on blurred pictures, achieves an AUC of 88.51%, and outperforms other popular methods in predicting lung cancer staging.

show abstract

Prediction of Cancer Clinical Endpoints Using Deep Learning and RPPA Data

Zenbout

Bouramoul

Meshoul

2022

Artificial Intelligence and Its Applications

View full text Add to dashboard Cite

Targeted unsupervised features learning for gene expression data analysis to predict cancer stage

Cited by 3 publications

References 15 publications

Comparison of Feature Selection via Semi supervised denoising autoencoder and traditional approaches For Software Fault-prone Classification

Comparison of Feature Selection via Semi supervised denoising autoencoder and traditional approaches For Software Fault-prone Classification

A progressive phased attention model fusing histopathology and genomic features for lung cancer staging

Prediction of Cancer Clinical Endpoints Using Deep Learning and RPPA Data

Contact Info

Product

Resources

About