Uncovering the prognostic gene signatures for the improvement of risk stratification in cancers by using deep learning algorithm coupled with wavelet transform

Zhao, Yijia; Zhou, Yifan; Liu, Yuan; Hao, Yinyi; Li, Menglong; Pu, Xuemei; Li, Chuan; Wen, Zhining

doi:10.1186/s12859-020-03544-z

Cited by 4 publications

(2 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the traditional LASSO method and the latest method SWT-CNN, the predictive ability of the proposed deep learning method is significantly higher than that of LASSO [18] and SWT-CNN [19].…”

Section: Methodsmentioning

confidence: 92%

A Wavelet-Based Learning Model Enhances Molecular Prognosis in Pancreatic Adenocarcinoma

Tang

Chen

Wang

et al. 2021

BioMed Research International

View full text Add to dashboard Cite

Genome-wide omics technology boosts deep interrogation into the clinical prognosis and inherent mechanism of pancreatic oncology. Classic LASSO methods coequally treat all candidates, ignoring individual characteristics, thus frequently deteriorating performance with comparatively more predictors. Here, we propose a wavelet-based deep learning method in variable selection and prognosis formulation for PAAD with small samples and multisource information. With the genomic, epigenomic, and clinical cohort information from The Cancer Genome Atlas, the constructed five-molecule model is validated via Kaplan-Meier survival estimate, rendering significant prognosis capability on high- and low-risk subcohorts ( p value < 0.0001), together with three predictors manifesting the individual prognosis significance ( p value: 0.0012~0.024). Moreover, the performance of the prognosis model has been benchmarked against the traditional LASSO and wavelet-based methods in the 3- and 5-year prediction AUC items, respectively. Specifically, the proposed model with discrete stationary wavelet base (bior1.5) overwhelmingly outperformed traditional LASSO and wavelet-based methods (AUC: 0.787 vs. 0.782 and 0.721 for the 3-year case; AUC: 0.937 vs. 0.802 and 0.859 for the 5-year case). Thus, the proposed model provides a more accurate perspective, but with less predictor burden for clinical prognosis in the pancreatic carcinoma study.

show abstract

Section: Methodsmentioning

confidence: 92%

A Wavelet-Based Learning Model Enhances Molecular Prognosis in Pancreatic Adenocarcinoma

Tang

Chen

Wang

et al. 2021

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…In breast cancer research, there are several gene expression panels to classify and/or predict subtypes, outcomes, or patient survival such as PAM50, which used mRNA expression values of 50 preselected genes ( 15 ), while MammaPrint using 70-gene signatures ( 16 ), BluePrint using 80-gene signatures ( 17 ), and Oncotype DX using 21-gene signatures ( 18 ). Recently, there is a growing number of literatures regarding the applications of machine learning and deep learning to predict the mRNA gene expression values using hematoxylin and eosin staining ( 19 ) or (synthetic) gene signature prediction using RNA sequencing and clinical information ( 20 ). The capacity in predicting gene expression signature taxonomy is extremely important due to the high correlation between these gene panels and patient outcomes or subtypes.…”

Section: Introductionmentioning

confidence: 99%

Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images

et al. 2021

View full text Add to dashboard Cite

We proposed a highly versatile two-step transfer learning pipeline for predicting the gene signature defining the intrinsic breast cancer subtypes using unannotated pathological images. Deciphering breast cancer molecular subtypes by deep learning approaches could provide a convenient and efficient method for the diagnosis of breast cancer patients. It could reduce costs associated with transcriptional profiling and subtyping discrepancy between IHC assays and mRNA expression. Four pretrained models such as VGG16, ResNet50, ResNet101, and Xception were trained with our in-house pathological images from breast cancer patient with recurrent status in the first transfer learning step and TCGA-BRCA dataset for the second transfer learning step. Furthermore, we also trained ResNet101 model with weight from ImageNet for comparison to the aforementioned models. The two-step deep learning models showed promising classification results of the four breast cancer intrinsic subtypes with accuracy ranging from 0.68 (ResNet50) to 0.78 (ResNet101) in both validation and testing sets. Additionally, the overall accuracy of slide-wise prediction showed even higher average accuracy of 0.913 with ResNet101 model. The micro- and macro-average area under the curve (AUC) for these models ranged from 0.88 (ResNet50) to 0.94 (ResNet101), whereas ResNet101_imgnet weighted with ImageNet archived an AUC of 0.92. We also show the deep learning model prediction performance is significantly improved relatively to the common Genefu tool for breast cancer classification. Our study demonstrated the capability of deep learning models to classify breast cancer intrinsic subtypes without the region of interest annotation, which will facilitate the clinical applicability of the proposed models.

show abstract

Lösemi hastalığının temel türlerinden ALL ve KML malignitelerinin grafik sinir ağları ve bulanık mantık algoritması ile sınıflandırılması

AKALIN

Yumuşak

2022

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

Beyaz kan hücresi kanseri olan lösemi, yaşam kalitesini düşüren ve ilerleyen aşamalarda ölüme sebep olabilen maliyeti yüksek bir malignitedir. Farklı yaş gruplarında görülebilen bu hastalığın erken ve doğru teşhisinin sağlanması tedavi sürecini etkilemekte ve hastalığın ilerlemesini engellemektedir. Bu çalışmada löseminin temel türlerinden olan ALL ve KML malignitelerinin sınıflandırılması amaçlanmıştır. Genetik temelli maligniteler olan bu türlerin ayırt edilmesinde DNA’da bir mutasyon sonucunda beliren BCR-ABL geni analiz edilmiştir. Tıp dünyasında BCR-ABL geni üzerinden mevcut türlerin ayırt edilmesi hususunda PCR tekniği kullanılarak değerlendirmeler yapılabilmektedir. Teşhis ve tedavi sürecindeki maliyetin ve zamanın indirgenmesi amacıyla disiplinlerarası çalışmalar da mevcuttur . İki aşamadan oluşan bu çalışmanın ilk aşamasında farklı nükleotit uzunluklarına sahip ALL ve KML DNA dizilimlerinin spektral yoğunluk bilgisi sinyal işleme teknikleri kullanılarak spektogramlara yansıtılmıştır. Ardından CNN ve GNN teknolojilerinin hibrit yaklaşımı olan DGCNN teknolojisi ile ALL ve KML malignitelerine ait spektogramlar sınıflandırılmıştır. Ancak nükleotitlerin farklı uzunluklarda olmasından dolayı spektogramlar üzerinde net ifadeler elde edilememiştir. Çalışmanın ikinci aşamasında farklı uzunluklara sahip DNA dizilimleri, kodon dağılımlarının esas alındığı entropi temelli haritalama tekniği ile sayısallaştırılmıştır. Sayısallaştırılan bu dizilimler üzerinden çıkarılan istatiktiksel ve yapısal özellikler uyarlanabilir bulanık mantık algoritması ile sınıflandırılarak nükleotit uzunluğundan bağımsız bir çalışma gerçekleştirilmiştir. Böylece KML ve ALL malignitelerinin sınıflandırılmasında %80’lik bir başarı düzeyi yakalanmıştır.

show abstract

Uncovering the prognostic gene signatures for the improvement of risk stratification in cancers by using deep learning algorithm coupled with wavelet transform

Cited by 4 publications

References 84 publications

A Wavelet-Based Learning Model Enhances Molecular Prognosis in Pancreatic Adenocarcinoma

A Wavelet-Based Learning Model Enhances Molecular Prognosis in Pancreatic Adenocarcinoma

Predicting Breast Cancer Gene Expression Signature by Applying Deep Convolutional Neural Networks From Unannotated Pathological Images

Lösemi hastalığının temel türlerinden ALL ve KML malignitelerinin grafik sinir ağları ve bulanık mantık algoritması ile sınıflandırılması

Contact Info

Product

Resources

About