Cancer Subtype Classification Research Articles

HyperTMO: a trusted multi-omics integration framework based on hypergraph convolutional network for patient classification.

The rapid development of high-throughput biomedical technologies can provide researchers with detailed multi-omics data. The multi-omics integrated analysis approach based on machine learning contributes a more comprehensive perspective to human disease research. However, there are still significant challenges in representing single-omics data and integrating multi-omics information. This article presents HyperTMO, a Trusted Multi-Omics integration framework based on Hypergraph convolutional network for patient classification. HyperTMO constructs hypergraph structures to represent the association between samples in single-omics data, then evidence extraction is performed by hypergraph convolutional network, and multi-omics information is integrated at an evidence level. Last, we experimentally demonstrate that HyperTMO outperforms other state-of-the-art methods in breast cancer subtype classification and Alzheimer's disease classification tasks using multi-omics data from TCGA (BRCA) and ROSMAP datasets. Importantly, HyperTMO is the first attempt to integrate hypergraph structure, evidence theory, and multi-omics integration for patient classification. Its accurate and robust properties bring great potential for applications in clinical diagnosis. HyperTMO and datasets are publicly available at https://github.com/ippousyuga/HyperTMO.

A novel machine learning algorithm selects proteome signature to specifically identify cancer exosomes

Non-invasive early cancer diagnosis remains challenging due to the low sensitivity and specificity of current diagnostic approaches. Exosomes are membrane-bound nanovesicles secreted by all cells that contain DNA, RNA, and proteins that are representative of the parent cells. This property, along with the abundance of exosomes in biological fluids makes them compelling candidates as biomarkers. However, a rapid and flexible exosome-based diagnostic method to distinguish human cancers across cancer types in diverse biological fluids is yet to be defined. Here, we describe a novel machine learning-based computational method to distinguish cancers using a panel of proteins associated with exosomes. Employing datasets of exosome proteins from human cell lines, tissue, plasma, serum, and urine samples from a variety of cancers, we identify Clathrin Heavy Chain (CLTC), Ezrin, (EZR), Talin-1 (TLN1), Adenylyl cyclase-associated protein 1 (CAP1), and Moesin (MSN) as highly abundant universal biomarkers for exosomes and define three panels of pan-cancer exosome proteins that distinguish cancer exosomes from other exosomes and aid in classifying cancer subtypes employing random forest models. All the models using proteins from plasma, serum, or urine-derived exosomes yield AUROC scores higher than 0.91 and demonstrate superior performance compared to Support Vector Machine, K Nearest Neighbor Classifier and Gaussian Naive Bayes. This study provides a reliable protein biomarker signature associated with cancer exosomes with scalable machine learning capability for a sensitive and specific non-invasive method of cancer diagnosis.

A novel machine learning algorithm selects proteome signature to specifically identify cancer exosomes.

Non-invasive early cancer diagnosis remains challenging due to the low sensitivity and specificity of current diagnostic approaches. Exosomes are membrane-bound nanovesicles secreted by all cells that contain DNA, RNA, and proteins that are representative of the parent cells. This property, along with the abundance of exosomes in biological fluids makes them compelling candidates as biomarkers. However, a rapid and flexible exosome-based diagnostic method to distinguish human cancers across cancer types in diverse biological fluids is yet to be defined. Here, we describe a novel machine learning-based computational method to distinguish cancers using a panel of proteins associated with exosomes. Employing datasets of exosome proteins from human cell lines, tissue, plasma, serum, and urine samples from a variety of cancers, we identify Clathrin Heavy Chain (CLTC), Ezrin, (EZR), Talin-1 (TLN1), Adenylyl cyclase-associated protein 1 (CAP1), and Moesin (MSN) as highly abundant universal biomarkers for exosomes and define three panels of pan-cancer exosome proteins that distinguish cancer exosomes from other exosomes and aid in classifying cancer subtypes employing random forest models. All the models using proteins from plasma, serum, or urine-derived exosomes yield AUROC scores higher than 0.91 and demonstrate superior performance compared to Support Vector Machine, K Nearest Neighbor Classifier and Gaussian Naive Bayes. This study provides a reliable protein biomarker signature associated with cancer exosomes with scalable machine learning capability for a sensitive and specific non-invasive method of cancer diagnosis.

DiffRS-net: A Novel Framework for Classifying Breast Cancer Subtypes on Multi-Omics Data

The precise classification of breast cancer subtypes is crucial for clinical diagnosis and treatment, yet early symptoms are often subtle. The use of multi-omics data from high-throughput sequencing can improve the classification accuracy. However, most research primarily focuses on the association between individual omics data and breast cancer, neglecting the interactions between different omics. This may fail to provide a comprehensive understanding of the biological processes of breast cancer. Here, we propose a novel framework called DiffRS-net for classifying breast cancer subtypes by identifying the association among different omics. DiffRS-net performs a differential analysis on each omics datum to identify differentially expressed genes (DE-genes) and adopts a robustness-aware Sparse Multi-View Canonical Correlation Analysis to detect multi-way association among DE-genes. These DE-genes with high levels of correlation are then used to train an attention learning network, thereby enhancing the prediction accuracy of breast cancer subtypes. The experimental results show that, by mining the associations between multi-omics data, DiffRS-net achieves a more accurate classification of breast cancer subtypes than the existing methods.

Abstract 3505: Classification of cancer subtypes by cfDNA fragmentomics analysis

Abstract Introduction Fragmentation patterns of cell-free DNA (cfDNA) from whole genome sequencing offer insights into nucleosome occupancy, providing a tool to infer epigenomic and transcriptomic information. The nucleosome complex, the primary protector of cfDNA, is reflected in the size distribution of cfDNA fragments, with a mode fragment size of 167 bp corresponding to the wrapping of DNA around a single nucleosome. Nucleosome occupancy patterns at transcription factor binding sites (TFBS) exhibit differences between circulating tumor DNA in cancer patients and normal plasma controls, as well as among different tumor subtypes. Therefore, cfDNA fragmentomics can be employed for cancer subtyping analysis. Methods We utilized the Griffin framework to classify tumor subtypes based on nucleosome profiling of cancer-specific TFBS and tumor subtype-specific chromatin accessibility regions from low-pass whole genome sequencing data of cfDNA. For prostate cancer subtyping, AR and ASCL1 binding sites were used to distinguish between androgen receptor-dependent prostate cancer (ARPC) and neuroendocrine prostate cancer (NEPC). ER and ERBB2 were employed for breast cancer subtyping to differentiate between ER-positive and ER-negative tumor subtypes. Results Nucleosome profiling patterns at AR binding sites (ARBS) were compared among over 500 prostate cancer plasma samples and 42 normal plasma backgrounds. The ARBS nucleosome profiling abnormality score (ARBS score) was quantified by comparing its GC-corrected fragment central coverage with the normal background using a standard Z-score.Majority of prostate cancer samples with a high ARBS score could be classified as ARPC. For 12 samples with high tumor fraction but low ARBS score and no AR copy number amplification, we found that 8 had a high ASCL1 nucleosome profiling abnormality score. All these samples also exhibited RB1 copy number loss, suggesting that these 8 samples likely belong to NEPC. Nucleosome profiling of 171 breast cancer plasma samples at breast cancer-specific ER binding sites revealed that majority of samples had a high ERBS abnormality score, indicating likely ER-positive breast cancer. Conclusion Our results demonstrate that nucleosome profiling of tumor cfDNA exhibits distinct patterns across different tumor types. Integrating nucleosome profiling at cancer-specific transcription factor binding sites can facilitate cancer subtyping, highlighting its potential clinical utility for patient stratification. Citation Format: Lisha Zhu, Chao Dai, Shuang Gan, Shidong Jia, Pan Du. Classification of cancer subtypes by cfDNA fragmentomics analysis [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3505.

Abstract 3526: GAIN-BRCA: A graphical explainable AI-net framework for breast cancer subtype classification using multiomics data

Abstract Higher standards for precise distinction and classification among the four breast cancer subtypes, i.e., Luminal A. Luminal B, HER-2-enriched, and Basal, are essential to delivering customized treatment in precision oncology. The effective integration of readily accessible multi-omics datasets from the same patient may improve the accuracy of subtype prediction algorithms and help decipher reliable molecular features for the prediction and prognosis of breast cancer. Previous models for predicting breast cancer subtypes relied mostly on concatenation and autoencoder methods but rarely utilized graph-based integration to leverage the biological associations among omics datatypes. To overcome these limitations, we developed a graph-based multi-omics integration method using features from mRNA, DNA methylation, and miRNA data and synthesized features from their interactions. GAIN-BRCA computes weightage scores from miRNA-mRNA and DNA methylation-mRNA interactions to derive a new transformed feature vector without compromising biological information. The neural network architecture was designed and trained on the transformed features to classify breast cancer subtypes. Neural network prediction accuracies were compared using concatenated, autoencoder, and GAIN-BRCA-based integrated datasets. GAIN-BRCA outperforms the existing similar models MOGONET (Acc: 0.72) and moBRCA-net (Acc: 0.86) with an accuracy of 0.91. These transformed features were then processed using SHAP, and the top 357 features were selected for functional characterization and pathway analysis. We identified specific pathways and genes related to each breast cancer subtype separately. The most enriched pathways found in each subtype are ribonucleotide reductase signaling and glucocorticoid signaling pathways in luminal A, PFKB4 signaling pathway in luminal B, adipogenesis and DNA methylation and transcriptional signaling in HER2+, and the role of OCT4 in mammalian embryonic stem cell pluripotency in basal. Similarly, the most discriminated gene features are BRAF, ESR1, KRAS, MAPK1, SMARCE1, PPP3CA, and TGFBR2 in luminal A, TGFB3 and NCOA3 in luminal B, HNF4A, SIN3A, and SOX9 in HER2+, and POU5F1 and FOXA2 in basal subtypes. The GAIN-BRCA framework, combined with SHAP, weighs independent omics as cross-disciplinary rather than multidisciplinary and presents a distinctive picture for each subtype. As a result, the framework presents the importance of features about the corresponding subtype, which might lead to a greater understanding of the molecular basis of breast cancer subtypes. Citation Format: Jai Chand Patel, Sushil Kumar Shakyawar, Sahil Sethi, Chittibabu Guda. GAIN-BRCA: A graphical explainable AI-net framework for breast cancer subtype classification using multiomics data [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 3526.

Cell‐free DNA‐associated multi‐feature applications in cancer diagnosis and treatment

AbstractMalignant tumours pose significant challenges in terms of high morbidity and mortality rates, primarily due to the lack of large‐scale applicable screening methods and efficient treatment strategies. However, the development of liquid biopsies, particularly circulating cell‐free DNA (cfDNA), offers promising solutions characterised by their non‐invasiveness and cost‐effectiveness, providing comprehensive tumour information on a global scale. The release of cfDNA is predominantly associated with cell death and turnover, while its elimination occurs through nuclease digestion, renal excretion into the urine and uptake by the liver and spleen. Extensive research into the biological properties of cfDNA has led to the identification of novel applications, including non‐invasive cancer screening, cancer subtype classification, tissue‐of‐origin detection and monitoring of treatment efficacy. Additionally, emerging fields such as methylation‐omics, fragment‐omics and nucleosome‐omics show immense potential as tissue‐ and disease‐specific markers. Therefore, this review aims to comprehensively introduce the latest detection techniques of cfDNA, along with detailed information on its characteristics and applications, providing valuable insights for cancer diagnosis and monitoring, which will assist us in purposefully enhancing relevant features for a more comprehensive application in clinical practice.

Few-shot genes selection: subset of PAM50 genes for breast cancer subtypes classification

BackgroundIn recent years, researchers have made significant strides in understanding the heterogeneity of breast cancer and its various subtypes. However, the wealth of genomic and proteomic data available today necessitates efficient frameworks, instruments, and computational tools for meaningful analysis. Despite its success as a prognostic tool, the PAM50 gene signature’s reliance on many genes presents challenges in terms of cost and complexity. Consequently, there is a need for more efficient methods to classify breast cancer subtypes using a reduced gene set accurately.ResultsThis study explores the potential of achieving precise breast cancer subtype categorization using a reduced gene set derived from the PAM50 gene signature. By employing a “Few-Shot Genes Selection” method, we randomly select smaller subsets from PAM50 and evaluate their performance using metrics and a linear model, specifically the Support Vector Machine (SVM) classifier. In addition, we aim to assess whether a more compact gene set can maintain performance while simplifying the classification process. Our findings demonstrate that certain reduced gene subsets can perform comparable or superior to the full PAM50 gene signature.ConclusionsThe identified gene subsets, with 36 genes, have the potential to contribute to the development of more cost-effective and streamlined diagnostic tools in breast cancer research and clinical settings.

Identification of breast cancer subtypes based on graph convolutional network

Identification of molecular subtypes of malignant tumors plays a vital role in individualized diagnosis, personalized treatment, and prognosis prediction of cancer patients. The continuous improvement of comprehensive tumor genomics database and the ongoing breakthroughs in deep learning technology have driven further advancements in computer-aided tumor classification. Although the existing classification methods based on gene expression omnibus database take the complexity of cancer molecular classification into account, they ignore the internal correlation and synergism of genes. To solve this problem, we propose a multi-layer graph convolutional network model for breast cancer subtype classification combined with hierarchical attention network. This model constructs the graph embedding datasets of patients' genes, and develops a new end-to-end multi-classification model, which can effectively recognize molecular subtypes of breast cancer. A large number of test data prove the good performance of this new model in the classification of breast cancer subtypes. Compared to the original graph convolutional neural networks and two mainstream graph neural network classification algorithms, the new model has remarkable advantages. The accuracy, weight-F1-score, weight-recall, and weight-precision of our model in seven-category classification has reached 0.851 7, 0.823 5, 0.851 7 and 0.793 6 respectively. In the four-category classification, the results are 0.928 5, 0.894 9, 0.928 5 and 0.865 0 respectively. In addition, compared with the latest breast cancer subtype classification algorithms, the method proposed in this paper also achieved the highest classification accuracy. In summary, the model proposed in this paper may serve as an auxiliary diagnostic technology, providing a reliable option for precise classification of breast cancer subtypes in the future and laying the theoretical foundation for computer-aided tumor classification.

Supervised graph contrastive learning for cancer subtype identification through multi-omics data integration.

Cancer is one of the most deadly diseases in the world. Accurate cancer subtype classification is critical for patient diagnosis, treatment, and prognosis. Ever-increasing multi-omics data describes the characteristics of the patients from different views and serves as complementary information to promote cancer subtype identification. However, omics data generally have different distributions and high dimensions. How to effectively integrate multiple omics data to classify cancer subtypes accurately is a challenge for researchers. This work proposes a method integrating multi-omics data based on supervised graph contrast learning (MCRGCN) to classify cancer subtypes. The method considers the unique feature distribution of each omics data and the interaction of different omics data features to improve the accuracy of cancer subtype classification. To achieve this, MCRGCN first constructs different sample networks based on the multi-omics data of the samples. Then, it puts the omics data and adjacency matrix of the sample into different residual graph convolution models to get multi-omics features of the samples, which are trained with a supervised comparison loss to maintain that the sample features of each omics should be as consistent as possible. Finally, we input the sample features combining multi-omics features into a classifier to obtain the cancer subtypes. We applied MCRGCN to the invasive breast carcinoma (BRCA) and glioblastoma multiforme (GBM) datasets, integrating gene expression, miRNA expression, and DNA methylation data. The results demonstrate that our model is superior to other methods in integrating multi-omics data. Moreover, the results of survival analysis experiments demonstrate that the cancer subtypes identified by our model have significant clinical features. Furthermore, our model can help to identify potential biomarkers and pathways associated with cancer subtypes.

Classifying breast cancer using multi-view graph neural network based on multi-omics data.

Introduction: As the evaluation indices, cancer grading and subtyping have diverse clinical, pathological, and molecular characteristics with prognostic and therapeutic implications. Although researchers have begun to study cancer differentiation and subtype prediction, most of relevant methods are based on traditional machine learning and rely on single omics data. It is necessary to explore a deep learning algorithm that integrates multi-omics data to achieve classification prediction of cancer differentiation and subtypes. Methods: This paper proposes a multi-omics data fusion algorithm based on a multi-view graph neural network (MVGNN) for predicting cancer differentiation and subtype classification. The model framework consists of a graph convolutional network (GCN) module for learning features from different omics data and an attention module for integrating multi-omics data. Three different types of omics data are used. For each type of omics data, feature selection is performed using methods such as the chi-square test and minimum redundancy maximum relevance (mRMR). Weighted patient similarity networks are constructed based on the selected omics features, and GCN is trained using omics features and corresponding similarity networks. Finally, an attention module integrates different types of omics features and performs the final cancer classification prediction. Results: To validate the cancer classification predictive performance of the MVGNN model, we conducted experimental comparisons with traditional machine learning models and currently popular methods based on integrating multi-omics data using 5-fold cross-validation. Additionally, we performed comparative experiments on cancer differentiation and its subtypes based on single omics data, two omics data, and three omics data. Discussion: This paper proposed the MVGNN model and it performed well in cancer classification prediction based on multiple omics data.

A Hybrid Attention-based Deep Model for Lung Cancer Subtype Classification from Multimodality Images

Lung cancer is a deadly type of malignancy that poses a significant threat to human health. Accurately identifying the subtypes of lung cancer is critical for effective treatment. However, conventional methods for determining subtypes, such as histological examination, are invasive and time-consuming. In order to overcome this problem, a non-invasive approach for predicting lung cancer subtypes using multi-modality images with a hybrid model is proposed in this study. The model combines attention-based Convolutional Neural Networks (CNNs) and machine learning classifiers to achieve this objective. The model employs a soft-attention mechanism to focus on the pathological areas and extract both global and local features from the images. The stack-based ensemble classifier employs logistic regression as a meta-learner and four machine learning classifiers, including Support Vector Machine (SVM), Naive Bayes, Random Forest, and J48. The classifier categorizes lung cancer into Adenocarcinoma (ADC), Squamous Cell Carcinoma (SQC), and Small Cell Carcinoma (SCC). The suggested model validated using publically accessible datasets (Lung-PET-CT-DX, Lung1, and Lung3) achieved superior performance, with a validation accuracy of 98.8%, an F1-score of 0.986, and a Matthews Correlation Coefficient (MCC) of 0.988.

A multimodal graph neural network framework for cancer molecular subtype classification

BackgroundThe recent development of high-throughput sequencing has created a large collection of multi-omics data, which enables researchers to better investigate cancer molecular profiles and cancer taxonomy based on molecular subtypes. Integrating multi-omics data has been proven to be effective for building more precise classification models. Most current multi-omics integrative models use either an early fusion in the form of concatenation or late fusion with a separate feature extractor for each omic, which are mainly based on deep neural networks. Due to the nature of biological systems, graphs are a better structural representation of bio-medical data. Although few graph neural network (GNN) based multi-omics integrative methods have been proposed, they suffer from three common disadvantages. One is most of them use only one type of connection, either inter-omics or intra-omic connection; second, they only consider one kind of GNN layer, either graph convolution network (GCN) or graph attention network (GAT); and third, most of these methods have not been tested on a more complex classification task, such as cancer molecular subtypes.ResultsIn this study, we propose a novel end-to-end multi-omics GNN framework for accurate and robust cancer subtype classification. The proposed model utilizes multi-omics data in the form of heterogeneous multi-layer graphs, which combine both inter-omics and intra-omic connections from established biological knowledge. The proposed model incorporates learned graph features and global genome features for accurate classification. We tested the proposed model on the Cancer Genome Atlas (TCGA) Pan-cancer dataset and TCGA breast invasive carcinoma (BRCA) dataset for molecular subtype and cancer subtype classification, respectively. The proposed model shows superior performance compared to four current state-of-the-art baseline models in terms of accuracy, F1 score, precision, and recall. The comparative analysis of GAT-based models and GCN-based models reveals that GAT-based models are preferred for smaller graphs with less information and GCN-based models are preferred for larger graphs with extra information.

Modern Subtype Classification and Outlier Detection Using the Attention Embedder to Transform Ovarian Cancer Diagnosis.

Ovarian cancer, a deadly female reproductive system disease, is a significant challenge in medical research due to its notorious lethality. Addressing ovarian cancer in the current medical landscape has become more complex than ever. This research explores the complex field of Ovarian Cancer Subtype Classification and the crucial task of Outlier Detection, driven by a progressive automated system, as the need to fight this unforgiving illness becomes critical. This study primarily uses a unique dataset painstakingly selected from 20 esteemed medical institutes. The dataset includes a wide range of images, such as tissue microarray (TMA) images at 40× magnification and whole-slide images (WSI) at 20× magnification. The research is fully committed to identifying abnormalities within this complex environment, going beyond the classification of subtypes of ovarian cancer. We proposed a new Attention Embedder, a state-of-the-art model with effective results in ovarian cancer subtype classification and outlier detection. Using images magnified WSI, the model demonstrated an astonishing 96.42% training accuracy and 95.10% validation accuracy. Similarly, with images magnified via a TMA, the model performed well, obtaining a validation accuracy of 94.90% and a training accuracy of 93.45%. Our fine-tuned hyperparameter testing resulted in exceptional performance on independent images. At 20× magnification, we achieved an accuracy of 93.56%. Even at 40× magnification, our testing accuracy remained high, at 91.37%. This study highlights how machine learning can revolutionize the medical field's ability to classify ovarian cancer subtypes and identify outliers, giving doctors a valuable tool to lessen the severe effects of the disease. Adopting this novel method is likely to improve the practice of medicine and give people living with ovarian cancer worldwide hope.

Clinical impact of ampulla of Vater cancer subtype classification based on immunohistochemical staining

BackgroundThe histological subtype is an important prognostic factor for ampulla of Vater (AoV) cancer. This study proposes a classification system for the histological subtyping of AoV cancer based on immunohistochemical (IHC) staining and its prognostic significance.MethodsSeventy-five AoV cancers were analyzed for cytokeratin 7 (CK7), CK20, and causal-type homeobox transcription factor 2 (CDX2) expression by IHC staining. We differentiated the subtypes (INT, intestinal; PB, pancreatobiliary; MIX, mixed; NOS, not otherwise specified) into classification I: CK7/CK20, classification II: CK7/CK20 or CDX2, classification III: CK7/CDX2 and examined their associations with clinicopathological factors.ResultsClassifications I, II, and III subtypes were INT (7, 10, and 10 cases), PB (43, 37, and 38 cases), MIX (13, 19, and 18 cases), and NOS (12, 9, and 9 cases). Significant differences in disease-free survival among the subtypes were observed in classifications II and III using CDX2; the PB and NOS subtype exhibited shorter survival time compared with INT subtype. In classification III, an association was revealed between advanced T/N stage, poor differentiation, lymphovascular invasion (LVI), the PB and NOS subtypes, and recurrence risk. In classification III, the subtypes differed significantly in T/N stage and LVI. Patients with the PB subtype had advanced T and N stages and a higher incidence of LVI.ConclusionsClassification using CDX2 revealed subtypes with distinct prognostic significance. Combining CK7 and CDX2 or adding CDX2 to CK7/CK20 is useful for distinguishing subtypes, predicting disease outcomes, and impacting the clinical management of patients with AoV cancer.

Empowering Ovarian Cancer Subtype Classification with Parallel Swin Transformers and WSI Imaging

Ovarian cancer constitutes a notable proportion of cancer-related mortalities among women. The diagnostic classification of ovarian cancer subtypes has demonstrated complexity, characterized by limited concordance among pathologists. Vision Transformer (ViT) models have emerged as the predominant architecture in numerous computer vision applications, encompassing tasks such as image classification and cancer detection. Their success stems primarily from their capacity to integrate global contextual information through self-attention mechanisms during the learning process. However, the key issue with ViT is its compatibility with high-res images. Computation grows quadratically with image size, resulting in a large number of tokens and significant computational demands for self-attention. Swin Transformer (Swin-T) addresses this challenge by introducing two main concepts: hierarchical feature mapping and windowed attention transformation. This work presents a parallel implementation of Swin Transformers (Swin-Ts) that leverages the powerful feature extraction capabilities and aimed at classifying five subtypes within ovarian cancer utilizing Whole Slide Imaging (WSI) and it yielded average precision, recall, and F1-score metrics of 0.958, 0.964, and 0.96 correspondingly. The findings show that the proposed parallel Swin-Ts reduce the misclassification errors and improve medical image analysis robustness. Additionally, the suggested technique is promising for accurate and efficient ovarian carcinoma subtype categorization, with possible applicability to other cancers. Future research will integrate other data sources and validate the technique in various clinical contexts

OVANet: Dual Attention Mechanism Based New Deep Learning Framework for Diagnosis and Classification of Ovarian Cancer Subtypes From Histopathological Images

OVANet: Dual Attention Mechanism Based New Deep Learning Framework for Diagnosis and Classification of Ovarian Cancer Subtypes From Histopathological Images

A Novel Feature Engineering Method Based on Latent Representation Learning for Radiomics: Application in NSCLC Subtype Classification.

Radiomics refers to the high-throughput extraction of quantitative features from medical images, and is widely used to construct machine learning models for the prediction of clinical outcomes, while feature engineering is the most important work in radiomics. However, current feature engineering methods fail to fully and effectively utilize the heterogeneity of features when dealing with different kinds of radiomics features. In this work, latent representation learning is first presented as a novel feature engineering approach to reconstruct a set of latent space features from original shape, intensity and texture features. This proposed method projects features into a subspace called latent space, in which the latent space features are obtained by minimizing a unique hybrid loss function including a clustering-like loss and a reconstruction loss. The former one ensures the separability among each class while the latter one narrows the gap between the original features and latent space features. Experiments were performed on a multi-center non-small cell lung cancer (NSCLC) subtype classification dataset from 8 international open databases. Results showed that compared with four traditional feature engineering methods (baseline, PCA, Lasso and L2,1-norm minimization), latent representation learning could significantly improve the classification performance of various machine learning classifiers on the independent test set (all p<0.001). Further on two additional test sets, latent representation learning also showed a significant improvement in generalization performance. Our research shows that latent representation learning is a more effective feature engineering method, which has the potential to be used as a general technology in a wide range of radiomics researches.

A comprehensive evaluation framework for benchmarking multi-objective feature selection in omics-based biomarker discovery.

Machine learning algorithms have been extensively used for accurate classification of cancer subtypes driven by gene expression-based biomarkers. However, biomarker models combining multiple gene expression signatures are often not reproducible in external validation datasets and their feature set size is often not optimized, jeopardizing their translatability into cost-effective clinical tools. We investigated how to solve the multi-objective problem of finding the best trade-offs between classification performance and set size applying seven algorithms for machine learning-driven feature subset selection and analyse how they perform in a benchmark with eight large-scale transcriptome datasets of cancer, covering both training and external validation sets. The benchmark includes evaluation metrics assessing the performance of the individual biomarkers and the solution sets, according to their accuracy, diversity, and stability of the composing genes. Moreover, a new evaluation metric for cross-validation studies is proposed that generalizes the hypervolume, which is commonly used to assess the performance of multi-objective optimization algorithms. Biomarkers exhibiting 0.8 of balanced accuracy on the external dataset for breast, kidney and ovarian cancer using respectively 4, 2 and 7 features, were obtained. Genetic algorithms often provided better performance than other considered algorithms, and the recently proposed NSGA2-CH and NSGA2-CHS were the best performing methods in most cases.

Identification of protein signatures for lung cancer subtypes based on BPSO method

The objective of this study was to identify protein biomarkers that can distinguish between LUAD and LUSC, critical for personalized treatment plans. The proteomic profiling data of LUAD and LUSC samples from TCPA database, along with phenotype and survival information from TCGA database were downloaded and preprocessed for analysis. We used BPSO feature selection method and identified 10 candidate protein biomarkers that have better classifying performance, as analyzed by t-SNE and PCA algorithms. To explore the causalities among these proteins and their associations with tumor subtypes, we conducted the PCStable algorithm to construct a regulatory network. Results indicated that 4 proteins, MIG6, CD26, NF2, and INPP4B, were directly linked to the lung cancer subtypes and may be useful in guiding therapeutic decision-making. Besides, spearman correlation, Cox proportional hazard model and Kaplan-Meier curve was employed to validate the biological significance of the candidate proteins. In summary, our study highlights the importance of protein biomarkers in the classification of lung cancer subtypes and the potential of computational methods for identifying key biomarkers and understanding their underlying biological mechanisms.