XGBLC: an improved survival prediction model based on XGBoost

GNNs and ensemble models enhance the prediction of new sRNA-mRNA interactions in unseen conditions

Bacterial small RNAs (sRNAs) are pivotal in post-transcriptional regulation, affecting functions like virulence, metabolism, and gene expression by binding specific mRNA targets. Identifying these targets is crucial to understanding sRNA regulation across species. Despite advancements in high-throughput (HT) experimental methods, they remain technically challenging and are limited to detecting sRNA-target interactions under specific environmental conditions. Therefore, computational approaches, especially machine learning (ML), are essential for identifying strong candidates for biological validation. In this paper, we hypothesize that ML models trained on large-scale interaction data from specific conditions can accurately predict new interactions in unseen conditions within the same bacterial strain. To test this, we developed models from two families: (1) graph neural networks (GNNs), including GraphRNA and kGraphRNA, that learn transformed representations of interacting sRNA-mRNA pairs via graph relationships, and (2) decision forests, sInterRF (Random Forest) and sInterXGB (XGBoost), which use various interaction features for prediction. We also proposed Summation Ensemble Models (SEM) that combine scores from multiple models. Across three seen-to-unseen conditions evaluations, our models -particularly kGraphRNA- significantly improved the area under the ROC curve (AUC) and Precision-Recall curve (PR-AUC) compared to sRNARFTarget, CopraRNA, and RNAup. The SEM model combining GraphRNA and CopraRNA outperformed CopraRNA alone on a low-throughput (LT) interactions test set (HT-to-LT evaluation). Beyond enhanced performance, our models enable target prediction for species-specific sRNAs, a capability lacking in some existing tools. Furthermore, GNN models remove the dependency on external tools like RNAplex or RNAup to compute hybridization duplex or energy features, enhancing scalability and runtime efficiency. While this study focuses on E. coli K12 MG1655 interactions, our methods are fully adaptable to predict interactions in other bacterial strains, given sufficient data for training. Our comprehensive feature importance analysis revealed the complexity of sRNA-mRNA interactions across environmental conditions, underscoring the significance of RNA sequence composition and duplex structure characteristics, like base pairing and energy factors; findings that align with biological evidence from previous studies. As HT experiments expand sRNA-target interaction data across conditions in various bacteria, our ML methods with features analysis offer promising advances in sRNA-target prediction and deeper insights into sRNA regulatory mechanisms across diverse species.

Identification of a gene signature and prediction of overall survival of patients with stage IV colorectal cancer using a novel machine learning approach

OBJECTIVE

We sought to characterize unique gene signature patterns associated with worse overall survival (OS) among patients with stage IV colorectal cancer (CRC) using a machine learning (ML) approach.

METHODS

Data from the AACR GENIE registry were analyzed for genetic variations (somatic mutations, structural variants and copy number alterations) among patients with CRC. Adult patients (≥18 years) with histologically confirmed stage IV CRC who underwent next-generation sequencing were included. An eXtreme Gradient Boosting (XGBoost) model was developed to predict OS and the relative importance of different genetic alterations was determined using SHapley Additive exPlanations (SHAP) algorithm.

RESULTS

Among 688 patients with stage IV CRC, 54.4 % were male (n = 374) with a median age of 55 years (IQR, 46-64). An XGBoost model developed using the 200 most frequent genetic alterations demonstrated good performance to predict OS with a c-index of 0.701 (95 % CI: 0.675-0.726) on 5-fold cross-validation. The model achieved time-dependent AUC of 0.742, 0.757 and 0.793 at 12-, 24- and 36-months, respectively. The SHAP algorithm identified the top 20 genetic alterations most strongly predictive of worse OS among stage IV CRC patients. Based on the 20-gene signature, individuals at high risk had worse 12- and 36-month OS versus low-risk patients (82.6 % vs. 97.1 % and 30.1 % vs. 72.6 %, respectively; p < 0.001).

CONCLUSION

The XGBoost ML model identified a unique gene signature that accurately risk stratified stage IV CRC patients. ML models that incorporate molecular information represent an opportunity to predict long-term outcomes and potentially identify novel therapeutic targets for stage IV CRC patients.

A Machine Learning Model for Predicting Intensive Care Unit Admission in Inpatients with COVID-19 Using Clinical Data and Laboratory Biomarkers

Background: Artificial intelligence tools can help improve the clinical management of patients with severe COVID-19. The aim of this study was to validate a machine learning model to predict admission to the Intensive Care Unit (ICU) in individuals with COVID-19. Methods: A total of 201 hospitalized patients with COVID-19 were included. Sociodemographic and clinical data as well as laboratory biomarker results were obtained from medical records and the clinical laboratory information system. Three machine learning models were generated, trained, and internally validated: logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost). The models were evaluated for sensitivity (Sn), specificity (Sp), area under the curve (AUC), precision (P), SHapley Additive exPlanation (SHAP) values, and the clinical utility of predictive models using decision curve analysis (DCA). Results: The predictive model included the following variables: type 2 diabetes mellitus (T2DM), obesity, absolute neutrophil and basophil counts, the neutrophil-to-lymphocyte ratio (NLR), and D-dimer levels on the day of hospital admission. LR showed an Sn of 0.67, Sp of 0.65, AUC of 0.74, and P of 0.66. RF achieved an Sn of 0.87, Sp of 0.83, AUC of 0.96, and P of 0.85. XGBoost demonstrated an Sn of 0.87, Sp of 0.85, AUC of 0.95, and P of 0.86. Conclusions: Among the evaluated models, XGBoost showed robust predictive performance (Sn = 0.87, Sp = 0.85, AUC = 0.95, P = 0.86) and a favorable net clinical benefit in the decision curve analysis, confirming its suitability for predicting ICU admission in COVID-19 and aiding clinical decision-making.

Assessing the prognostic and therapeutic value of cuproptosis-related genes in colon adenocarcinoma patients

Background

Colon adenocarcinoma (COAD) remains a major global health challenge with poor prognosis despite advances in treatment, underscoring the need for new biomarkers. As a novel mode of cell death, cuproptosis is thought to be potentially involved in the development of cancer. However, the particularly as the role of cuproptosis-related genes (CRGs) in COAD prognosis and therapy remains unclear.

Methods

We analyzed RNA sequencing data from The Cancer Genome Atlas for COAD, focusing on CRG expression patterns and their clinicopathological correlations. Using the Weighted Gene Co-expression Network Analysis (WGCNA) method, we identified the gene module most strongly linked to cuproptosis and conducted functional enrichment analysis to explore the roles of genes within this module in COAD tumorigenesis. A novel prognostic risk model based on four CRGs (ORC1, PTTG1, DLAT, PDHB) was developed to stratify COAD patients into high-risk and low-risk groups, assessing overall survival, tumor microenvironment, and mutational landscape differences. We also evaluated the therapeutic effects of ferredoxin 1 (FDX1) and elesclomol in promoting cuproptosis in HCT116 and LoVo cell lines through various experiments, including cell proliferation, apoptosis assessment, mitochondrial membrane potential evaluation, and DLAT lipoylation detection via Western blot.

Results

Certain CRGs showed different expressions in COAD versus normal tissues. WGCNA identified a gene module linked to cuproptosis, crucial for pathways like cell cycle regulation, citrate cycle (TCA cycle), and DNA replication. The novel risk model stratified patients into high and low-risk groups based on risk scores, revealing that high-risk COAD patients had shorter overall survival and distinct immune cell infiltration, while low-risk patients were more sensitive to immunotherapy. Experimental results indicated that FDX1 exerted an inhibitory effect on COAD, and its combination with elesclomol significantly reduced proliferation, promoted apoptosis, increased DLAT lipoylation, and lowered mitochondrial membrane potential in COAD cells.

Conclusion

The findings of this study provided a new perspective for the research on biomarkers and therapeutic strategies in COAD, evaluated the prognostic and therapeutic value of CRGs in COAD patients, and laid a theoretical foundation for the future clinical application of CRGs.

Metabolic marker-assisted genomic prediction improves hybrid breeding

Hybrid breeding is widely acknowledged as the most effective method for increasing crop yield, particularly in maize and rice. However, a major challenge in hybrid breeding is the selection of desirable combinations from the vast pool of potential crosses. Genomic selection (GS) has emerged as a powerful tool to tackle this challenge, but its success in practical breeding depends on prediction accuracy. Several strategies have been explored to enhance prediction accuracy for complex traits, such as the incorporation of functional markers and multi-omics data. Metabolome-wide association studies (MWAS) help to identify metabolites that are closely linked to phenotypes, known as metabolic markers. However, the use of preselected metabolic markers from parental lines to predict hybrid performance has not yet been explored. In this study, we developed a novel approach called metabolic marker-assisted genomic prediction (MM_GP), which incorporates significant metabolites identified from MWAS into GS models to improve the accuracy of genomic hybrid prediction. In maize and rice hybrid populations, MM_GP outperformed genomic prediction (GP) for all traits, regardless of the method used (genomic best linear unbiased prediction or eXtreme gradient boosting). On average, MM_GP demonstrated 4.6% and 13.6% higher predictive abilities than GP for maize and rice, respectively. MM_GP could also match or even surpass the predictive ability of M_GP (integrated genomic-metabolomic prediction) for most traits. In maize, the integration of only six metabolic markers significantly associated with multiple traits resulted in 5.0% and 3.1% higher average predictive ability compared with GP and M_GP, respectively. With advances in high-throughput metabolomics technologies and prediction models, this approach holds great promise for revolutionizing genomic hybrid breeding by enhancing its accuracy and efficiency.

A hybrid machine learning approach for the personalized prognostication of aggressive skin cancers

Accurate prognostication guides optimal clinical management in skin cancer. Merkel cell carcinoma (MCC) is the most aggressive form of skin cancer that often presents in advanced stages and is associated with poor survival rates. There are no personalized prognostic tools in use in MCC. We employed explainability analysis to reveal new insights into mortality risk factors for this highly aggressive cancer. We then combined deep learning feature selection with a modified XGBoost framework, to develop a web-based prognostic tool for MCC termed 'DeepMerkel'. DeepMerkel can make accurate personalised, time-dependent survival predictions for MCC from readily available clinical information. It demonstrated generalizability through high predictive performance in an international clinical cohort, out-performing current population-based prognostic staging systems. MCC and DeepMerkel provide the exemplar model of personalised machine learning prognostic tools in aggressive skin cancers.

Prediction of Survival in Patients With Esophageal Cancer After Immunotherapy Based on Small-Size Follow-Up Data

Esophageal cancer (EC) poses a significant health concern, particularly among the elderly, warranting effective treatment strategies. While immunotherapy holds promise in activating the immune response against tumors, its specific impact and associated reactions in EC patients remain uncertain. Precise prognosis prediction becomes crucial for guiding appropriate interventions. This study, based on data from the First Affiliated Hospital of Xiamen University (January 2017 to May 2021), focuses on 113 EC patients undergoing immunotherapy. The primary objectives are to elucidate the effectiveness of immunotherapy in EC treatment and to introduce a stacking ensemble learning method for predicting the survival of EC patients who have undergone immunotherapy, in the context of small sample sizes, addressing the imperative of supporting clinical decision-making for healthcare professionals. Our method incorporates five sub-learners and one meta-learner. Leveraging optimal features from the training dataset, this approach achieved compelling accuracy (89.13%) and AUC (88.83%) in predicting three-year survival status, surpassing conventional techniques. The model proves efficient in guiding clinical decisions, especially in scenarios with small-size follow-up data.

Survival prediction landscape: an in-depth systematic literature review on activities, methods, tools, diseases, and databases

Survival prediction integrates patient-specific molecular information and clinical signatures to forecast the anticipated time of an event, such as recurrence, death, or disease progression. Survival prediction proves valuable in guiding treatment decisions, optimizing resource allocation, and interventions of precision medicine. The wide range of diseases, the existence of various variants within the same disease, and the reliance on available data necessitate disease-specific computational survival predictors. The widespread adoption of artificial intelligence (AI) methods in crafting survival predictors has undoubtedly revolutionized this field. However, the ever-increasing demand for more sophisticated and effective prediction models necessitates the continued creation of innovative advancements. To catalyze these advancements, it is crucial to bring existing survival predictors knowledge and insights into a centralized platform. The paper in hand thoroughly examines 23 existing review studies and provides a concise overview of their scope and limitations. Focusing on a comprehensive set of 90 most recent survival predictors across 44 diverse diseases, it delves into insights of diverse types of methods that are used in the development of disease-specific predictors. This exhaustive analysis encompasses the utilized data modalities along with a detailed analysis of subsets of clinical features, feature engineering methods, and the specific statistical, machine or deep learning approaches that have been employed. It also provides insights about survival prediction data sources, open-source predictors, and survival prediction frameworks.

SELECTOR: Heterogeneous graph network with convolutional masked autoencoder for multimodal robust prediction of cancer survival

Accurately predicting the survival rate of cancer patients is crucial for aiding clinicians in planning appropriate treatment, reducing cancer-related medical expenses, and significantly enhancing patients' quality of life. Multimodal prediction of cancer patient survival offers a more comprehensive and precise approach. However, existing methods still grapple with challenges related to missing multimodal data and information interaction within modalities. This paper introduces SELECTOR, a heterogeneous graph-aware network based on convolutional mask encoders for robust multimodal prediction of cancer patient survival. SELECTOR comprises feature edge reconstruction, convolutional mask encoder, feature cross-fusion, and multimodal survival prediction modules. Initially, we construct a multimodal heterogeneous graph and employ the meta-path method for feature edge reconstruction, ensuring comprehensive incorporation of feature information from graph edges and effective embedding of nodes. To mitigate the impact of missing features within the modality on prediction accuracy, we devised a convolutional masked autoencoder (CMAE) to process the heterogeneous graph post-feature reconstruction. Subsequently, the feature cross-fusion module facilitates communication between modalities, ensuring that output features encompass all features of the modality and relevant information from other modalities. Extensive experiments and analysis on six cancer datasets from TCGA demonstrate that our method significantly outperforms state-of-the-art methods in both modality-missing and intra-modality information-confirmed cases. Our codes are made available at https://github.com/panliangrui/Selector.

Predicting Glaucoma Progression to Surgery with Artificial Intelligence Survival Models

Purpose

Prior artificial intelligence (AI) models for predicting glaucoma progression have used traditional classifiers that do not consider the longitudinal nature of patients' follow-up. In this study, we developed survival-based AI models for predicting glaucoma patients' progression to surgery, comparing performance of regression-, tree-, and deep learning-based approaches.

Design

Retrospective observational study.

Subjects

Patients with glaucoma seen at a single academic center from 2008 to 2020 identified from electronic health records (EHRs).

Methods

From the EHRs, we identified 361 baseline features, including demographics, eye examinations, diagnoses, and medications. We trained AI survival models to predict patients' progression to glaucoma surgery using the following: (1) a penalized Cox proportional hazards (CPH) model with principal component analysis (PCA); (2) random survival forests (RSFs); (3) gradient-boosting survival (GBS); and (4) a deep learning model (DeepSurv). The concordance index (C-index) and mean cumulative/dynamic area under the curve (mean AUC) were used to evaluate model performance on a held-out test set. Explainability was investigated using Shapley values for feature importance and visualization of model-predicted cumulative hazard curves for patients with different treatment trajectories.

Main Outcome Measures

Progression to glaucoma surgery.

Results

Of the 4512 patients with glaucoma, 748 underwent glaucoma surgery, with a median follow-up of 1038 days. The DeepSurv model performed best overall (C-index, 0.775; mean AUC, 0.802) among the models studied in this article (CPH with PCA: C-index, 0.745; mean AUC, 0.780; RSF: C-index, 0.766; mean AUC, 0.804; GBS: C-index, 0.764; mean AUC, 0.791). Predicted cumulative hazard curves demonstrate how models could distinguish between patient who underwent early surgery and patients who underwent surgery after > 3000 days of follow-up or no surgery.

Conclusions

Artificial intelligence survival models can predict progression to glaucoma surgery using structured data from EHRs. Tree-based and deep learning-based models performed better at predicting glaucoma progression to surgery than the CPH regression model, potentially because of their better suitability for high-dimensional data sets. Future work predicting ophthalmic outcomes should consider using tree-based and deep learning-based survival AI models. Additional research is needed to develop and evaluate more sophisticated deep learning survival models that can incorporate clinical notes or imaging.

Financial Disclosures

Proprietary or commercial disclosure may be found after the references.

Weighted gene coexpression network analysis and machine learning reveal oncogenome associated microbiome plays an important role in tumor immunity and prognosis in pan-cancer

BACKGROUND

For many years, the role of the microbiome in tumor progression, particularly the tumor microbiome, was largely overlooked. The connection between the tumor microbiome and the tumor genome still requires further investigation.

METHODS

The TCGA microbiome and genome data were obtained from Haziza et al.'s article and UCSC Xena database, respectively. Separate WGCNA networks were constructed for the tumor microbiome and genomic data after filtering the datasets. Correlation analysis between the microbial and mRNA modules was conducted to identify oncogenome associated microbiome module (OAM) modules, with three microbial modules selected for each tumor type. Reactome analysis was used to enrich biological processes. Machine learning techniques were implemented to explore the tumor type-specific enrichment and prognostic value of OAM, as well as the ability of the tumor microbiome to differentiate TP53 mutations.

RESULTS

We constructed a total of 182 tumor microbiome and 570 mRNA WGCNA modules. Our results show that there is a correlation between tumor microbiome and tumor genome. Gene enrichment analysis results suggest that the genes in the mRNA module with the highest correlation with the tumor microbiome group are mainly enriched in infection, transcriptional regulation by TP53 and antigen presentation. The correlation analysis of OAM with CD8+ T cells or TAM1 cells suggests the existence of many microbiota that may be involved in tumor immune suppression or promotion, such as Williamsia in breast cancer, Biostraticola in stomach cancer, Megasphaera in cervical cancer and Lottiidibacillus in ovarian cancer. In addition, the results show that the microbiome-genome prognostic model has good predictive value for short-term prognosis. The analysis of tumor TP53 mutations shows that tumor microbiota has a certain ability to distinguish TP53 mutations, with an AUROC value of 0.755. The tumor microbiota with high importance scores are Corallococcus, Bacillus and Saezia. Finally, we identified a potential anti-cancer microbiota, Tissierella, which has been shown to be associated with improved prognosis in tumors including breast cancer, lung adenocarcinoma and gastric cancer.

CONCLUSION

There is an association between the tumor microbiome and the tumor genome, and the existence of this association is not accidental and could change the landscape of tumor research.

Diagnosis of neurosyphilis in HIV-negative patients with syphilis: development, validation, and clinical utility of a suite of machine learning models

Background

The ability to accurately identify the absolute risk of neurosyphilis diagnosis for patients with syphilis would allow preventative and therapeutic interventions to be delivered to patients at high-risk, sparing patients at low-risk from unnecessary care. We aimed to develop, validate, and evaluate the clinical utility of simplified clinical diagnostic models for neurosyphilis diagnosis in HIV-negative patients with syphilis.

Methods

We searched PubMed, China National Knowledge Infrastructure and UpToDate for publications about neurosyphilis diagnostic guidelines in English or Chinese from database inception until March 15, 2023. We developed and validated machine learning models with a uniform set of predictors based on six authoritative diagnostic guidelines across four continents to predict neurosyphilis using routinely collected data from real-world clinical practice in China and the United States (through the Dermatology Hospital of Southern Medical University in Guangzhou [659 recruited between August 2012 and March 2022, treated as Development cohort], the Beijing Youan Hospital of Capital Medical University in Beijng [480 recruited between December 2013 and April 2021, treated as External cohort 1], the Zhongshan Hospital of Xiamen University in Xiamen [493 recruited between November 2005 and November 2021, treated as External cohort 2] from China, and University of Washington School of Medicine in Seattle [16 recruited between September 2002 and April 2014, treated as External cohort 3] from United States). We included all these patients with syphilis into our analysis, and no patients were further excluded. We trained eXtreme gradient boosting (XGBoost) models to predict the diagnostic outcome of neurosyphilis according to each diagnostic guideline in two scenarios, respectively. Model performance was measured through both internal and external validation in terms of discrimination and calibration, and clinical utility was evaluated using decision curve analysis.

Findings

The final simplified clinical diagnostic models included neurological symptoms, cerebrospinal fluid (CSF) protein, CSF white blood cell, and CSF venereal disease research laboratory test/rapid plasma reagin. The models showed good calibration with rescaled Brier score of 0.99 (95% CI 0.98-1.00) and excellent discrimination (the minimum value of area under the receiver operating characteristic curve, 0.84; 95% CI 0.81-0.88) when externally validated. Decision curve analysis demonstrated that the models were useful across a range of neurosyphilis probability thresholds between 0.33 and 0.66 compared to the alternatives of managing all patients with syphilis as if they do or do not have neurosyphilis.

Interpretation

The simplified clinical diagnostic models comprised of readily available data show good performance, are generalisable across clinical settings, and have clinical utility over a broad range of probability thresholds. The models with a uniform set of predictors can simplify the sophisticated clinical diagnosis of neurosyphilis, and guide decisions on delivery of neurosyphilis health-care, ultimately, support accurate diagnosis and necessary treatment.

Funding

The Natural Science Foundation of China General Program, Health Appropriate Technology Promotion Project of Guangdong Medical Research Foundation, Department of Science and technology of Guangdong Province Xinjiang Rural Science and Technology（Special Commissioner）Project, Southern Medical University Clinical Research Nursery Garden Project, Beijing Municipal Administration of Hospitals Incubating Program.

Orchestrating information across tissues via a novel multitask GAT framework to improve quantitative gene regulation relation modeling for survival analysis

Survival analysis is critical to cancer prognosis estimation. High-throughput technologies facilitate the increase in the dimension of genic features, but the number of clinical samples in cohorts is relatively small due to various reasons, including difficulties in participant recruitment and high data-generation costs. Transcriptome is one of the most abundantly available OMIC (referring to the high-throughput data, including genomic, transcriptomic, proteomic and epigenomic) data types. This study introduced a multitask graph attention network (GAT) framework DQSurv for the survival analysis task. We first used a large dataset of healthy tissue samples to pretrain the GAT-based HealthModel for the quantitative measurement of the gene regulatory relations. The multitask survival analysis framework DQSurv used the idea of transfer learning to initiate the GAT model with the pretrained HealthModel and further fine-tuned this model using two tasks i.e. the main task of survival analysis and the auxiliary task of gene expression prediction. This refined GAT was denoted as DiseaseModel. We fused the original transcriptomic features with the difference vector between the latent features encoded by the HealthModel and DiseaseModel for the final task of survival analysis. The proposed DQSurv model stably outperformed the existing models for the survival analysis of 10 benchmark cancer types and an independent dataset. The ablation study also supported the necessity of the main modules. We released the codes and the pretrained HealthModel to facilitate the feature encodings and survival analysis of transcriptome-based future studies, especially on small datasets. The model and the code are available at http://www.healthinformaticslab.org/supp/.

Using machine learning to realize genetic site screening and genomic prediction of productive traits in pigs

Genomic prediction, which is based on solving linear mixed-model (LMM) equations, is the most popular method for predicting breeding values or phenotypic performance for economic traits in livestock. With the need to further improve the performance of genomic prediction, nonlinear methods have been considered as an alternative and promising approach. The excellent ability to predict phenotypes in animal husbandry has been demonstrated by machine learning (ML) approaches, which have been rapidly developed. To investigate the feasibility and reliability of implementing genomic prediction using nonlinear models, the performances of genomic predictions for pig productive traits using the linear genomic selection model and nonlinear machine learning models were compared. Then, to reduce the high-dimensional features of genome sequence data, different machine learning algorithms, including the random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost) and convolutional neural network (CNN) algorithms, were used to perform genomic feature selection as well as genomic prediction on reduced feature genome data. All of the analyses were processed on two real pig datasets: the published PIC pig dataset and a dataset comprising data from a national pig nucleus herd in Chifeng, North China. Overall, the accuracies of predicted phenotypic performance for traits T1, T2, T3 and T5 in the PIC dataset and average daily gain (ADG) in the Chifeng dataset were higher using the ML methods than the LMM method, while those for trait T4 in the PIC dataset and total number of piglets born (TNB) in the Chifeng dataset were slightly lower using the ML methods than the LMM method. Among all the different ML algorithms, SVM was the most appropriate for genomic prediction. For the genomic feature selection experiment, the most stable and most accurate results across different algorithms were achieved using XGBoost in combination with the SVM algorithm. Through feature selection, the number of genomic markers can be reduced to 1 in 20, while the predictive performance on some traits can even be improved compared to using the full genome data. Finally, we developed a new tool that can be used to execute combined XGBoost and SVM algorithms to realize genomic feature selection and phenotypic prediction.

A Combined Risk Score Model to Assess Prognostic Value in Patients with Soft Tissue Sarcomas

A study by Tsvetkov et al. recently published a proposed novel form of copper-induced cell death in Science; however, few studies have looked into the possible mechanism in soft tissue sarcoma (STS). Herein, this study sought to investigate the function of cuproptosis-related genes (CRGs) in the development of tumor-associated immune cells and the prognosis of sarcoma. Herein, this study aimed to explore the role of cuproptosis-related genes (CRGs) in the development, tumor-associated immune cells, and the prognosis of sarcoma.

METHODS

The prognostic model was established via the least absolute shrinkage and selection operator (LASSO) algorithm as well as multivariate Cox regression analysis. The stromal scores, immune scores, ESTIMA scores, and tumor purity of sarcoma patients were evaluated by the ESTIMATE algorithm. Functional analyses were performed to investigate the underlying mechanisms of immune cell infiltration and the prognosis of CRGs in sarcoma.

RESULTS

Two molecular subgroups with different CRG expression patterns were recognized, which showed that patients with a higher immune score and more active immune status were prone to have better prognostic survival. Moreover, GO and KEGG analyses showed that these differentially expressed CRGs were mainly enriched in metabolic/ions-related signaling pathways, indicating that CRGs may have impacts on the immune cell infiltration and prognosis of sarcoma via regulating the bioprocess of mitochondria and consequently affecting the immune microenvironment. The expression levels of CRGs were closely correlated to the immunity condition and prognostic survival of sarcoma patients.

CONCLUSIONS

The interaction between cuproptosis and immunity in sarcoma may provide a novel insight into the study of molecular mechanisms and candidate biomarkers for the prognosis, resulting in effective treatments for sarcoma patients.

Survival prediction model for right-censored data based on improved composite quantile regression neural network

With the development of the field of survival analysis, statistical inference of right-censored data is of great importance for the study of medical diagnosis. In this study, a right-censored data survival prediction model based on an improved composite quantile regression neural network framework, called rcICQRNN, is proposed. It incorporates composite quantile regression with the loss function of a multi-hidden layer feedforward neural network, combined with an inverse probability weighting method for survival prediction. Meanwhile, the hyperparameters involved in the neural network are adjusted using the WOA algorithm, integer encoding and One-Hot encoding are implemented to encode the classification features, and the BWOA variable selection method for high-dimensional data is proposed. The rcICQRNN algorithm was tested on a simulated dataset and two real breast cancer datasets, and the performance of the model was evaluated by three evaluation metrics. The results show that the rcICQRNN-5 model is more suitable for analyzing simulated datasets. The One-Hot encoding of the WOA-rcICQRNN-30 model is more applicable to the NKI70 data. The model results are optimal for k=15 after feature selection for the METABRIC dataset. Finally, we implemented the method for cross-dataset validation. On the whole, the Cindex results using One-Hot encoding data are more stable, making the proposed rcICQRNN prediction model flexible enough to assist in medical decision making. It has practical applications in areas such as biomedicine, insurance actuarial and financial economics.

Deep learning methods may not outperform other machine learning methods on analyzing genomic studies

Deep Learning (DL) has been broadly applied to solve big data problems in biomedical fields, which is most successful in image processing. Recently, many DL methods have been applied to analyze genomic studies. However, genomic data usually has too small a sample size to fit a complex network. They do not have common structural patterns like images to utilize pre-trained networks or take advantage of convolution layers. The concern of overusing DL methods motivates us to evaluate DL methods' performance versus popular non-deep Machine Learning (ML) methods for analyzing genomic data with a wide range of sample sizes. In this paper, we conduct a benchmark study using the UK Biobank data and its many random subsets with different sample sizes. The original UK Biobank data has about 500k participants. Each patient has comprehensive patient characteristics, disease histories, and genomic information, i.e., the genotypes of millions of Single-Nucleotide Polymorphism (SNPs). We are interested in predicting the risk of three lung diseases: asthma, COPD, and lung cancer. There are 205,238 participants have recorded disease outcomes for these three diseases. Five prediction models are investigated in this benchmark study, including three non-deep machine learning methods (Elastic Net, XGBoost, and SVM) and two deep learning methods (DNN and LSTM). Besides the most popular performance metrics, such as the F1-score, we promote the hit curve, a visual tool to describe the performance of predicting rare events. We discovered that DL methods frequently fail to outperform non-deep ML in analyzing genomic data, even in large datasets with over 200k samples. The experiment results suggest not overusing DL methods in genomic studies, even with biobank-level sample sizes. The performance differences between DL and non-deep ML decrease as the sample size of data increases. This suggests when the sample size of data is significant, further increasing sample sizes leads to more performance gain in DL methods. Hence, DL methods could be better if we analyze genomic data bigger than this study.