Small cell lung cancer (SCLC) is a highly aggressive high-grade neuroendocrine carcinoma with a poor prognosis. Molecular subtyping of transcription factors (SCLC-A, -N, -P, and -Y) shows great potential for guiding treatment decisions. However, its clinical application are limited by insufficient samples and the complexity of molecular testing. In this study, we developed DeepTFtyper, a graph neural network-based deep learning model for automatically classifying SCLC molecular subtypes from hematoxylin and eosin-stained whole-slide images. DeepTFtyper was trained and tested on the Cancer Hospital, Chinese Academy of Medical Science cohort (n = 389) with 4-fold cross-validation, and achieved high performance with an area under the receiver operating characteristic curve above 0.70 for all four molecular subtypes identified by immunohistochemistry (IHC). Furthermore, the digital H-scores predicted by DeepTFtyper showed a significant correlation with IHC-based H-scores. Patch-level visualization and morphological analysis revealed that DeepTFtyper identifies interpretable and generalizable features corresponding to areas of relevant transcription factor expression as revealed by IHC staining and correlates well with morphological features. This study represents the first deep learning framework for predicting SCLC molecular subtypes from hematoxylin and eosin-stained histology slides, providing a scalable, accurate, and clinically relevant tool to improve patient management and guide personalized treatment decisions.

Homologous recombination deficiency (HRD) is a well-recognized important biomarker in determining the clinical benefits of platinum-based chemotherapy and PARP inhibitor therapy for patients diagnosed with gynecologic cancers. Accurate prediction of HRD phenotype remains challenging. Here, we proposed a novel Multi-Omics integrative Deep-learning framework named MODeepHRD for detecting HRD-positive phenotype. MODeepHRD utilizes a convolutional attention autoencoder that effectively leverages omics-specific and cross-omics complementary knowledge learning. We trained MODeepHRD on 351 ovarian cancer (OV) patients using transcriptomic, DNA methylation and mutation data, and validated it in 2133 OV samples of 22 datasets. The predicted HRD-positive tumors were significantly associated with improved survival (HR = 0.68; 95% CI, 0.60-0.77; log-rank p < 0.001 for meta-cohort; HR = 0.5; 95% CI, 0.29-0.86; log-rank p = 0.01 for ICGC-OV cohort) and higher response to platinum-based chemotherapy compared to predicted HRD-negative tumors. The translational potential of MODeepHRDs was further validated in multicenter breast and endometrial cancer cohorts. Furthermore, MODeepHRD outperforms conventional machine-learning methods and other similar task approaches. In conclusion, our study demonstrates the promising value of deep learning as a solution for HRD testing in the clinical setting. MODeepHRD holds potential clinical applicability in guiding patient risk stratification and therapeutic decisions, providing valuable insights for precision oncology and personalized treatment strategies.

Multi-omics data integration is a complex and challenging task in biomedical research. Consensus clustering, also known as meta-clustering or cluster ensembles, has become an increasingly popular downstream tool for phenotyping and endotyping using multiple omics and clinical data. However, current consensus clustering methods typically rely on ensembling clustering outputs with similar sample coverages (mathematical replicates), which may not reflect real-world data with varying sample coverages (biological replicates). To address this issue, we propose a new consensus clustering with missing labels (ccml) strategy termed ccml, an R protocol for two-step consensus clustering that can handle unequal missing labels (i.e. multiple predictive labels with different sample coverages). Initially, the regular consensus weights are adjusted (normalized) by sample coverage, then a regular consensus clustering is performed to predict the optimal final cluster. We applied the ccml method to predict molecularly distinct groups based on 9-omics integration in the Karolinska COSMIC cohort, which investigates chronic obstructive pulmonary disease, and 24-omics handprint integrative subgrouping of adult asthma patients of the U-BIOPRED cohort. We propose ccml as a downstream toolkit for multi-omics integration analysis algorithms such as Similarity Network Fusion and robust clustering of clinical data to overcome the limitations posed by missing data, which is inevitable in human cohorts consisting of multiple data modalities. The ccml tool is available in the R language (https://CRAN.R-project.org/package=ccml, https://github.com/pulmonomics-lab/ccml, or https://github.com/ZhoulabCPH/ccml).

The rapid development of single-cell RNA-sequencing (scRNA-seq) technology has raised significant computational and analytical challenges. The application of deep learning to scRNA-seq data analysis is rapidly evolving and can overcome the unique challenges in upstream (quality control and normalization) and downstream (cell-, gene- and pathway-level) analysis of scRNA-seq data. In the present study, recent advances and applications of deep learning-based methods, together with specific tools for scRNA-seq data analysis, were summarized. Moreover, the future perspectives and challenges of deep-learning techniques regarding the appropriate analysis and interpretation of scRNA-seq data were investigated. The present study aimed to provide evidence supporting the biomedical application of deep learning-based tools and may aid biologists and bioinformaticians in navigating this exciting and fast-moving area.

The coronavirus disease 2019 (COVID-19) pandemic, caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), rapidly became a global health challenge, leading to unprecedented social and economic consequences. The mechanisms behind the pathogenesis of SARS-CoV-2 are both unique and complex. Omics-scale studies are emerging rapidly and offer a tremendous potential to unravel the puzzle of SARS-CoV-2 pathobiology, as well as moving forward with diagnostics, potential drug targets, risk stratification, therapeutic responses, vaccine development and therapeutic innovation. This review summarizes various aspects of understanding multiomics integration-based molecular characterizations of COVID-19, which to date include the integration of transcriptomics, proteomics, genomics, lipidomics, immunomics and metabolomics to explore virus targets and developing suitable therapeutic solutions through systems biology tools. Furthermore, this review also covers an abridgment of omics investigations related to disease pathogenesis and virulence, the role of host genetic variation and a broad array of immune and inflammatory phenotypes contributing to understanding COVID-19 traits. Insights into this review, which combines existing strategies and multiomics integration profiling, may help further advance our knowledge of COVID-19.

Uveal melanoma (UVM) is the most common primary intraocular human malignancy with a high mortality rate. Aberrant DNA methylation has rapidly emerged as a diagnostic and prognostic signature in many cancers. However, such DNA methylation signature available in UVM remains limited. In this study, we performed a genome-wide integrative analysis of methylome and transcriptome and identified 40 methylation-driven prognostic genes (MDPGs) associated with the tumorigenesis and progression of UVM. Then, we proposed a machine-learning-based discovery and validation strategy to identify a DNA methylation-driven signature (10MeSig) composing of 10 MDPGs (AZGP1, BAI1, CCDC74A, FUT3, PLCD1, S100A4, SCN8A, SEMA3B, SLC25A38 and SLC44A3), which stratified 80 patients of the discovery cohort into two risk subtypes with significantly different overall survival (HR = 29, 95% CI: 6.7-126, P < 0.001). The 10MeSig was validated subsequently in an independent cohort with 57 patients and yielded a similar prognostic value (HR = 2.1, 95% CI: 1.2-3.7, P = 0.006). Multivariable Cox regression analysis showed that the 10MeSig is an independent predictive factor for the survival of patients with UVM. With a prospective validation study, this 10MeSig will improve clinical decisions and provide new insights into the pathogenesis of UVM.

Tumor-infiltrating immune cells (TIICs) have been recognized as crucial components of the tumor microenvironment (TME) and induced both beneficial and adverse consequences for tumorigenesis as well as outcome and therapy (particularly immunotherapy). Computer-aided investigation of immune cell components in the TME has become a promising avenue to better understand the interplay between the immune system and tumors. In this study, we presented an overview of data sources, computational methods and software tools, as well as their application in inferring the composition of tumor-infiltrating immune cells in the TME. In parallel, we explored the future perspectives and challenges that may be faced with more accurate quantitative infiltration of immune cells in the future. Together, our study provides a little guide for scientists in the field of clinical and experimental immunology to look for dedicated resources and more competent tools for accelerating the unraveling of tumor-immune interactions with the implication in precision immunotherapy.

An accurate prognosis assessment for cancer patients could aid in guiding clinical decision-making. Reliance on traditional clinical features alone in a complex clinical environment is challenging and unsatisfactory in the era of precision medicine; thus, reliable prognostic biomarkers are urgently required to improve a patient staging system. In this study, we proposed a patient-level computational framework from mechanistic and translational perspectives to establish a personalized prognostic signature (named PLPPS) in high-grade serous ovarian carcinoma (HGSOC). The PLPPS composed of 68 immune genes achieved accurate prognostic risk stratification for 1190 patients in the meta-training cohort and was rigorously validated in multiple cross-platform independent cohorts comprising 792 HGSOC patients. Furthermore, the PLPPS was shown to be the better prognostic factor compared with clinical parameters in the univariate analysis and retained a significant independent association with prognosis after adjusting for clinical parameters in the multivariate analysis. In benchmark comparisons, the performance of PLPPS (hazard ratio (HR), 1.371; concordance index (C-index), 0.604 and area under the curve (AUC), 0.637) is comparable to or better than other published gene signatures (HR, 0.972 to 1.340; C-index, 0.495 to 0.592 and AUC, 0.48-0.624). With further validation in prospective clinical trials, we hope that the PLPPS might become a promising genomic tool to guide personalized management and decision-making of HGSOC in clinical practice.

Long noncoding RNAs (lncRNAs) have been associated with cancer immunity regulation and the tumor microenvironment (TME). However, functions of lncRNAs of tumor-infiltrating B lymphocytes (TIL-Bs) and their clinical significance have not yet been fully elucidated. In the present study, a machine learning-based computational framework is presented for the identification of lncRNA signature of TIL-Bs (named 'TILBlncSig') through integrative analysis of immune, lncRNA and clinical profiles. The TILBlncSig comprising eight lncRNAs (TNRC6C-AS1, WASIR2, GUSBP11, OGFRP1, AC090515.2, PART1, MAFG-DT and LINC01184) was identified from the list of 141 B-cell-specific lncRNAs. The TILBlncSig was capable of distinguishing worse compared with improved survival outcomes across different independent patient datasets and was also independent of other clinical covariates. Functional characterization of TILBlncSig revealed it to be an indicator of infiltration of mononuclear immune cells (i.e. natural killer cells, B-cells and mast cells), and it was associated with hallmarks of cancer, as well as immunosuppressive phenotype. Furthermore, the TILBlncSig revealed predictive value for the survival outcome and immunotherapy response of patients with anti-programmed death-1 (PD-1) therapy and added significant predictive power to current immune checkpoint gene markers. The present study has highlighted the value of the TILBlncSig as an indicator of immune cell infiltration in the TME from a noncoding RNA perspective and strengthened the potential application of lncRNAs as predictive biomarkers of immunotherapy response, which warrants further investigation.

Emerging evidence revealed the critical roles of long non-coding RNAs (lncRNAs) in maintaining genomic instability. However, identification of genome instability-associated lncRNAs and their clinical significance in cancers remain largely unexplored. Here, we developed a mutator hypothesis-derived computational frame combining lncRNA expression profiles and somatic mutation profiles in a tumor genome and identified 128 novel genomic instability-associated lncRNAs in breast cancer as a case study. We then identified a genome instability-derived two lncRNA-based gene signature (GILncSig) that stratified patients into high- and low-risk groups with significantly different outcome and was further validated in multiple independent patient cohorts. Furthermore, the GILncSig correlated with genomic mutation rate in both ovarian cancer and breast cancer, indicating its potential as a measurement of the degree of genome instability. The GILncSig was able to divide TP53 wide-type patients into two risk groups, with the low-risk group showing significantly improved outcome and the high-risk group showing no significant difference compared with those with TP53 mutation. In summary, this study provided a critical approach and resource for further studies examining the role of lncRNAs in genome instability and introduced a potential new avenue for identifying genomic instability-associated cancer biomarkers.

An increasing number of functional studies shows that long noncoding RNAs (lncRNAs) are involved in many aspects of cellular physiology and fulfills a wide variety of regulatory roles at almost every stage of gene expression. A major feature of lncRNAs is the highly folded modular domains in transcripts. With improved modeling and definition, it is now feasible to explore and gain novel insights into the structural-functional relationship of lncRNAs and their association with complex human diseases. In this study, we utilized an automatic computational pipeline to scan lncRNA architecture at the genome-wide scale and to obtain a landscape of functional domains. An accurate alignment algorithm was performed to identify 40 triple pairs between single-nucleotide polymorphisms (SNPs), lncRNAs and diseases. In order to detect the potential contribution of a lncRNA's modular character, we estimated and evaluated structural rearrangements, which were derived from disease-associated SNPs. In addition, we focused on annotating and comparing the global and local heterogeneity of the wild-type and mutant lncRNAs. Assessing lncRNA architecture has yielded how variations in structured regions impact the molecular mechanisms of lncRNAs and how SNPs disturb binding and recruiting ability. These observations are the first glimpse of the 'lncRNA structurome' and make it possible to robustly explore and assemble intricate space conformation and their stress variation. This result also successfully demonstrates that lncRNA transcripts contain a complex structural landscape and highlights the proposed contribution of lncRNA structure in controlling RNA functions and disease mechanisms.

MOTIVATION: At present, a fundamental challenge in single-cell RNA-sequencing data analysis is functional interpretation and annotation of cell clusters. Biological pathways in distinct cell types have different activation patterns, which facilitates the understanding of cell functions using single-cell transcriptomics. However, no effective web tool has been implemented for single-cell transcriptome data analysis based on prior biological pathway knowledge. RESULTS: Here, we present scTPA, a web-based platform for pathway-based analysis of single-cell RNA-seq data in human and mouse. scTPA incorporates four widely-used gene set enrichment methods to estimate the pathway activation scores of single cells based on a collection of available biological pathways with different functional and taxonomic classifications. The clustering analysis and cell-type-specific activation pathway identification were provided for the functional interpretation of cell types from a pathway-oriented perspective. An intuitive interface allows users to conveniently visualize and download single-cell pathway signatures. Overall, scTPA is a comprehensive tool for the identification of pathway activation signatures for the analysis of single cell heterogeneity. AVAILABILITY AND IMPLEMENTATION: http://sctpa.bio-data.cn/sctpa. CONTACT: [email protected] or [email protected] or [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Complex diseases cannot be understood only on the basis of single gene, single mRNA transcript or single protein but the effect of their collaborations. The combination consequence in molecular level can be captured by the alterations of metabolites. With the rapidly developing of biomedical instruments and analytical platforms, a large number of metabolite signatures of complex diseases were identified and documented in the literature. Biologists' hardship in the face of this large amount of papers recorded metabolic signatures of experiments' results calls for an automated data repository. Therefore, we developed MetSigDis aiming to provide a comprehensive resource of metabolite alterations in various diseases. MetSigDis is freely available at http://www.bio-annotation.cn/MetSigDis/. By reviewing hundreds of publications, we collected 6849 curated relationships between 2420 metabolites and 129 diseases across eight species involving Homo sapiens and model organisms. All of these relationships were used in constructing a metabolite disease network (MDN). This network displayed scale-free characteristics according to the degree distribution (power-law distribution with R2 = 0.909), and the subnetwork of MDN for interesting diseases and their related metabolites can be visualized in the Web. The common alterations of metabolites reflect the metabolic similarity of diseases, which is measured using Jaccard index. We observed that metabolite-based similar diseases are inclined to share semantic associations of Disease Ontology. A human disease network was then built, where a node represents a disease, and an edge indicates similarity of pair-wise diseases. The network validated the observation that linked diseases based on metabolites should have more overlapped genes.

Increasing evidence has revealed the multiple roles of long noncoding RNAs (lncRNAs) in neurodevelopment, brain function and aging, and their dysregulation was implicated in many types of neurological diseases. However, expression pattern and diagnostic role of lncRNAs in Alzheimer's disease (AD) remain largely unknown and has gained significant attention. In this study, we performed a comparative analysis for lncRNA expression profiles in four brain regions in brain aging and AD. Our analysis revealed age- and disease-dependent region-specific lncRNA expression patterns in aging and AD. Moreover, we identified a panel of nine lncRNAs (termed LncSigAD9) in a discovery cohort of 114 samples using supervised machine learning and stepwise selection method. The LncSigAD9 was able to differentiate between AD and healthy controls with high diagnostic sensitivity and specificity both in the discovery cohort (86.3 and 89.5%) and the additional independent AD cohort (90.8 and 83.8%). The receiver operating characteristic curves for the LncSigAD9 were 0.863 and 0.939 for discovery and independent cohorts, respectively. Furthermore, the LncSigAD9 demonstrated higher diagnostic performance than nine-minus-one lncRNA signature and mRNA-based signature with a similar number of genes. In silico functional analysis indicated the involvement of lncRNA expression variation in brain development- and metabolism-related biological processes. Taken together, our study highlights the importance of lncRNAs in brain aging and AD, and demonstrated the utility of lncRNAs as a promising biomarker for early AD diagnosis and treatment.

Summary: DincRNA aims to provide a comprehensive web-based bioinformatics toolkit to elucidate the entangled relationships among diseases and non-coding RNAs (ncRNAs) from the perspective of disease similarity. The quantitative way to illustrate relationships of pair-wise diseases always depends on their molecular mechanisms, and structures of the directed acyclic graph of Disease Ontology (DO). Corresponding methods for calculating similarity of pair-wise diseases involve Resnik's, Lin's, Wang's, PSB and SemFunSim methods. Recently, disease similarity was validated suitable for calculating functional similarities of ncRNAs and prioritizing ncRNA-disease pairs, and it has been widely applied for predicting the ncRNA function due to the limited biological knowledge from wet lab experiments of these RNAs. For this purpose, a large number of algorithms and priori knowledge need to be integrated. e.g. 'pair-wise best, pairs-average' (PBPA) and 'pair-wise all, pairs-maximum' (PAPM) methods for calculating functional similarities of ncRNAs, and random walk with restart (RWR) method for prioritizing ncRNA-disease pairs. To facilitate the exploration of disease associations and ncRNA function, DincRNA implemented all of the above eight algorithms based on DO and disease-related genes. Currently, it provides the function to query disease similarity scores, miRNA and lncRNA functional similarity scores, and the prioritization scores of lncRNA-disease and miRNA-disease pairs. Availability and implementation: http://bio-annotation.cn:18080/DincRNAClient/. Contact: [email protected] or [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

Similar diseases are often caused by their similar molecular origins, such as disease-related protein-coding genes (PCGs). And nowadays, the function of PCGs has been widely studied on a gene function network, where each node represents a gene and each edge indicates an interaction between pair-wise genes. Therefore, functional interaction between disease-related PCGs should be exploited to measure disease similarity. Actually, functional interaction of pair-wise PCGs has been introduced to calculate disease similarity recently. However, existing method ignores that genes could also be associated based on intermediate nodes in the gene functional network. Here, in this article, we proposed a novel method, InfDisSim, to infer disease similarity. InfDisSim models the information flow to the network based on random walk with damping, in which the entire network could be fully utilized. The performance of InfDisSim was evaluated by a benchmark set of similar disease pairs. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the performance. As a result, InfDisSim achieves a very high AUC (0.9786), which shows it performs well. Furthermore, based on the disease similarity computed by the infDisSim, we re-validated that similar diseases tend to have common therapeutic drugs (Pearson correlation γ2=0.1315, p=2.2e-16). Finally, InfDisSim disease similarity was exploited to construct a lncRNA similarity network (LSN), which was further applied to predict potential associations between diseases and lncRNAs. High AUC (0.9893) based on leave-one-out cross validation shows the LSN is very suitable for identifying novel disease-related lncRNAs.

MOTIVATION: Recent studies on human disease have revealed that aberrant interaction between proteins probably underlies a substantial number of human genetic diseases. This suggests a need to investigate disease inheritance mode using interaction, and based on which to refresh our conceptual understanding of a series of properties regarding inheritance mode of human disease. RESULTS: We observed a strong correlation between the number of protein interactions and the likelihood of a gene causing any dominant diseases or multiple dominant diseases, whereas no correlation was observed between protein interaction and the likelihood of a gene causing recessive diseases. We found that dominant diseases are more likely to be associated with disruption of important interactions. These suggest inheritance mode should be understood using protein interaction. We therefore reviewed the previous studies and refined an interaction model of inheritance mode, and then confirmed that this model is largely reasonable using new evidences. With these findings, we found that the inheritance mode of human genetic diseases can be predicted using protein interaction. By integrating the systems biology perspectives with the classical disease genetics paradigm, our study provides some new insights into genotype-phenotype correlations. CONTACT: [email protected] or [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: In the functional genomic era, a large number of gene sets have been identified via high-throughput genomic and proteomic technologies. These gene sets of interest are often related to the same or similar disorders or phenotypes, and are commonly presented as differentially expressed gene lists, co-expressed gene modules, protein complexes or signaling pathways. However, biologists are still faced by the challenge of comparing gene sets and interpreting the functional relationships between gene sets into an understanding of the underlying biological mechanisms. RESULTS: We introduce a novel network-based method, designated corrected cumulative rank score (CCRS), which analyzes the functional communication and physical interaction between genes, and presents an easy-to-use web-based toolkit called GsNetCom to quantify the functional relationship between two gene sets. To evaluate the performance of our method in assessing the functional similarity between two gene sets, we analyzed the functional coherence of complexes in functional catalog and identified protein complexes in the same functional catalog. The results suggested that CCRS can offer a significant advance in addressing the functional relationship between different gene sets compared with several other available tools or algorithms with similar functionality. We also conducted the case study based on our method, and succeeded in prioritizing candidate leukemia-associated protein complexes and expanding the prioritization and analysis of cancer-related complexes to other cancer types. In addition, GsNetCom provides a new insight into the communication between gene modules, such as exploring gene sets from the perspective of well-annotated protein complexes. AVAILABILITY AND IMPLEMENTATION: GsNetCom is a freely available web accessible toolkit at http://bioinfo.hrbmu.edu.cn/GsNetCom.