Background:Lung adenocarcinoma(LUAD)is a highly heterogeneous cancer type with a poor prognosis.Accurate subtype identification can help guide its treatment.The traditional subtype identification methods using a singl...Background:Lung adenocarcinoma(LUAD)is a highly heterogeneous cancer type with a poor prognosis.Accurate subtype identification can help guide its treatment.The traditional subtype identification methods using a single-omics approach make it difficult to comprehensively characterize the molecular features of LUAD.Identification of subtypes through multi-omics association strategies can effectively supplement the shortcomings of single-omics information.Methods:In this study,we used the Generative Adversarial Network(GAN)to mine transcriptomic,proteomic,and epigenomic information and generate an integrated data set.The newly integrated data were then used to identify LUAD immune subtypes.In the improved GAN(MOGAN)method,we not only integrated multiple omics datasets but also included the interactions between proteins and genes and between methylation and genes.Thus,we achieved effective complementarity of multi-omics information.Results:Two subtypes,MOGANTPM_S1 and MOGANTPM_S2,were identified using immune cell infiltration analysis and the integrated multi-omics data.MOGANTPM_S1 patients displayed higher immune cell infiltration,better prognosis,and sensitivity to immune checkpoint inhibitors(ICIs),while MOGANTPM_S2 had lower immune cell infiltration,poorer prognosis,and were insensitive to ICIs.Therefore,immunotherapy was more suitable for MOGANTPM_S1 patients in clinical practice.In addition,this study developed a LUAD subtype diagnostic model using the transcriptomic and proteomic features of five genes,which can be used to guide clinical subtype diagnosis.Conclusions:In summary,the MOGAN method was applied to integrate three omics data types and successfully identify two LUAD immune subtypes with significant survival differences.This classification method may be useful for LUAD treatment decisions.展开更多
Background:Accurate classification of normal blood cells is a critical foundation for automated hematological analysis,including the detection of pathological conditions like leukemia.While convolutional neural networ...Background:Accurate classification of normal blood cells is a critical foundation for automated hematological analysis,including the detection of pathological conditions like leukemia.While convolutional neural networks(CNNs)excel in local feature extraction,their ability to capture global contextual relationships in complex cellular morphologies is limited.This study introduces a hybrid CNN-Transformer framework to enhance normal blood cell classification,laying the groundwork for future leukemia diagnostics.Methods:The proposed architecture integrates pre-trained CNNs(ResNet50,EfficientNetB3,InceptionV3,CustomCNN)with Vision Transformer(ViT)layers to combine local and global feature modeling.Four hybrid models were evaluated on the publicly available Blood Cell Images dataset from Kaggle,comprising 17,092 annotated normal blood cell images across eight classes.The models were trained using transfer learning,fine-tuning,and computational optimizations,including cross-model parameter sharing to reduce redundancy by reusing weights across CNN backbones and attention-guided layer pruning to eliminate low-contribution layers based on attention scores,improving efficiency without sacrificing accuracy.Results:The InceptionV3-ViT model achieved a weighted accuracy of 97.66%(accounting for class imbalance by weighting each class’s contribution),a macro F1-score of 0.98,and a ROC-AUC of 0.998.The framework excelled in distinguishing morphologically similar cell types demonstrating robustness and reliable calibration(ECE of 0.019).The framework addresses generalization challenges,including class imbalance and morphological similarities,ensuring robust performance across diverse cell types.Conclusion:The hybrid CNN-Transformer framework significantly improves normal blood cell classification by capturing multi-scale features and long-range dependencies.Its high accuracy,efficiency,and generalization position it as a strong baseline for automated hematological analysis,with potential for extension to leukemia subtype classification through future validation on pathological samples.展开更多
The proposition of cancer cells in a tumor sample,named as tumor purity,is an intrinsic factor of tumor samples and has potentially great influence in variety of analyses including differential methylation,subclonal d...The proposition of cancer cells in a tumor sample,named as tumor purity,is an intrinsic factor of tumor samples and has potentially great influence in variety of analyses including differential methylation,subclonal deconvolution and subtype clustering.Infinium-Purify is an integrated R package for estimating and accounting for tumor purity based on DNA methylation Infinium 450 k array data.InfiniumPurify has three main functions getPurity,InfiniumDMC and InfiniumClust,which could infer tumor purity,differential methylation analysis and tumor sample cluster accounting for estimated or user-provided tumor purities,respectively.The InfiniumPurify package provides a comprehensive analysis of tumor purity in cancer methylation research.展开更多
基金Chongqing Municipal Human Resources and Social Security Bureau(Grant No:2023C0BSHTB1001)Science and Technology Research Program of Chongqing Municipal Education(Grant No:KJ202200678822935)。
文摘Background:Lung adenocarcinoma(LUAD)is a highly heterogeneous cancer type with a poor prognosis.Accurate subtype identification can help guide its treatment.The traditional subtype identification methods using a single-omics approach make it difficult to comprehensively characterize the molecular features of LUAD.Identification of subtypes through multi-omics association strategies can effectively supplement the shortcomings of single-omics information.Methods:In this study,we used the Generative Adversarial Network(GAN)to mine transcriptomic,proteomic,and epigenomic information and generate an integrated data set.The newly integrated data were then used to identify LUAD immune subtypes.In the improved GAN(MOGAN)method,we not only integrated multiple omics datasets but also included the interactions between proteins and genes and between methylation and genes.Thus,we achieved effective complementarity of multi-omics information.Results:Two subtypes,MOGANTPM_S1 and MOGANTPM_S2,were identified using immune cell infiltration analysis and the integrated multi-omics data.MOGANTPM_S1 patients displayed higher immune cell infiltration,better prognosis,and sensitivity to immune checkpoint inhibitors(ICIs),while MOGANTPM_S2 had lower immune cell infiltration,poorer prognosis,and were insensitive to ICIs.Therefore,immunotherapy was more suitable for MOGANTPM_S1 patients in clinical practice.In addition,this study developed a LUAD subtype diagnostic model using the transcriptomic and proteomic features of five genes,which can be used to guide clinical subtype diagnosis.Conclusions:In summary,the MOGAN method was applied to integrate three omics data types and successfully identify two LUAD immune subtypes with significant survival differences.This classification method may be useful for LUAD treatment decisions.
基金the Deanship of Graduate Studies and Scientific Research at Najran University,Saudi Arabia,for their financial support through the Easy Track Research program,grant code(NU/EFP/MRC/13).
文摘Background:Accurate classification of normal blood cells is a critical foundation for automated hematological analysis,including the detection of pathological conditions like leukemia.While convolutional neural networks(CNNs)excel in local feature extraction,their ability to capture global contextual relationships in complex cellular morphologies is limited.This study introduces a hybrid CNN-Transformer framework to enhance normal blood cell classification,laying the groundwork for future leukemia diagnostics.Methods:The proposed architecture integrates pre-trained CNNs(ResNet50,EfficientNetB3,InceptionV3,CustomCNN)with Vision Transformer(ViT)layers to combine local and global feature modeling.Four hybrid models were evaluated on the publicly available Blood Cell Images dataset from Kaggle,comprising 17,092 annotated normal blood cell images across eight classes.The models were trained using transfer learning,fine-tuning,and computational optimizations,including cross-model parameter sharing to reduce redundancy by reusing weights across CNN backbones and attention-guided layer pruning to eliminate low-contribution layers based on attention scores,improving efficiency without sacrificing accuracy.Results:The InceptionV3-ViT model achieved a weighted accuracy of 97.66%(accounting for class imbalance by weighting each class’s contribution),a macro F1-score of 0.98,and a ROC-AUC of 0.998.The framework excelled in distinguishing morphologically similar cell types demonstrating robustness and reliable calibration(ECE of 0.019).The framework addresses generalization challenges,including class imbalance and morphological similarities,ensuring robust performance across diverse cell types.Conclusion:The hybrid CNN-Transformer framework significantly improves normal blood cell classification by capturing multi-scale features and long-range dependencies.Its high accuracy,efficiency,and generalization position it as a strong baseline for automated hematological analysis,with potential for extension to leukemia subtype classification through future validation on pathological samples.
基金This project was partially supported by the National Natural Science Foundation of China(61702325 and 61572327)Shanghai Science and Technology Innovation Action Plan(16391902900)National Institute of Health(R01GM122083).
文摘The proposition of cancer cells in a tumor sample,named as tumor purity,is an intrinsic factor of tumor samples and has potentially great influence in variety of analyses including differential methylation,subclonal deconvolution and subtype clustering.Infinium-Purify is an integrated R package for estimating and accounting for tumor purity based on DNA methylation Infinium 450 k array data.InfiniumPurify has three main functions getPurity,InfiniumDMC and InfiniumClust,which could infer tumor purity,differential methylation analysis and tumor sample cluster accounting for estimated or user-provided tumor purities,respectively.The InfiniumPurify package provides a comprehensive analysis of tumor purity in cancer methylation research.
