Detecting tipping points of complex diseases by network information entropy.

The progression of complex diseases often involves abrupt and non-linear changes characterized by sudden shifts that trigger critical transformations. Identifying these critical states or tipping points is crucial for understanding disease progression and developing effective interventions. To address this challenge, we have developed a model-free method named Network Information Entropy of Edges (NIEE). Leveraging dynamic network biomarkers, sample-specific networks, and information entropy theories, NIEE can detect critical states or tipping points in diverse data types, including bulk, single-sample expression data. By applying NIEE to real disease datasets, we successfully identified critical predisease stages and tipping points before disease onset. Our findings underscore NIEE's potential to enhance comprehension of complex disease development.

SMURF: embedding single-cell RNA-seq data with matrix factorization preserving self-consistency.

The advance in single-cell RNA-sequencing (scRNA-seq) sheds light on cell-specific transcriptomic studies of cell developments, complex diseases and cancers. Nevertheless, scRNA-seq techniques suffer from 'dropout' events, and imputation tools are proposed to address the sparsity. Here, rather than imputation, we propose a tool, SMURF, to extract the low-dimensional embeddings from cells and genes utilizing matrix factorization with a mixture of Poisson-Gamma divergent as objective while preserving self-consistency. SMURF exhibits feasible cell subpopulation discovery efficacy with obtained cell embeddings on replicated in silico and eight web lab scRNA datasets with ground truth cell types. Furthermore, SMURF can reduce the cell embedding to a 1D-oval space to recover the time course of cell cycle. SMURF can also serve as an imputation tool; the in silico data assessment shows that SMURF parades the most robust gene expression recovery power with low root mean square error and high Pearson correlation. Moreover, SMURF recovers the gene distribution for the WM989 Drop-seq data. SMURF is available at https://github.com/deepomicslab/SMURF.

Quantitative annotations of T-Cell repertoire specificity.

The specificity of a T-cell receptor (TCR) repertoire determines personalized immune capacity. Existing methods have modeled the qualitative aspects of TCR specificity, while the quantitative aspects remained unaddressed. We developed a package, TCRanno, to quantify the specificity of TCR repertoires. We created deep-learning-based, epitope-aware vector embeddings to infer individual TCR specificity. Then we aggregated clonotype frequencies of TCRs to obtain a quantitative profile of repertoire specificity at epitope, antigen and organism levels. Applying TCRanno to 4195 TCR repertoires revealed quantitative changes in repertoire specificity upon infections, autoimmunity and cancers. Specifically, TCRanno found cytomegalovirus-specific TCRs in seronegative healthy individuals, supporting the possibility of abortive infections. TCRanno discovered age-accumulated fraction of severe acute respiratory syndrome coronavirus 2 specific TCRs in pre-pandemic samples, which may explain the aggressive symptoms and age-related severity of coronavirus disease 2019. TCRanno also identified the encounter of Hepatitis B antigens as a potential trigger of systemic lupus erythematosus. TCRanno annotations showed capability in distinguishing TCR repertoires of healthy and cancers including melanoma, lung and breast cancers. TCRanno also demonstrated usefulness to single-cell TCRseq+gene expression data analyses by isolating T-cells with the specificity of interest.

Incorporating cell hierarchy to decipher the functional diversity of single cells.

Cells possess functional diversity hierarchically. However, most single-cell analyses neglect the nested structures while detecting and visualizing the functional diversity. Here, we incorporate cell hierarchy to study functional diversity at subpopulation, club (i.e., sub-subpopulation), and cell layers. Accordingly, we implement a package, SEAT, to construct cell hierarchies utilizing structure entropy by minimizing the global uncertainty in cell-cell graphs. With cell hierarchies, SEAT deciphers functional diversity in 36 datasets covering scRNA, scDNA, scATAC, and scRNA-scATAC multiome. First, SEAT finds optimal cell subpopulations with high clustering accuracy. It identifies cell types or fates from omics profiles and boosts accuracy from 0.34 to 1. Second, SEAT detects insightful functional diversity among cell clubs. The hierarchy of breast cancer cells reveals that the specific tumor cell club drives AREG-EGFT signaling. We identify a dense co-accessibility network of cis-regulatory elements specified by one cell club in GM12878. Third, the cell order from the hierarchy infers periodic pseudo-time of cells, improving accuracy from 0.79 to 0.89. Moreover, we incorporate cell hierarchy layers as prior knowledge to refine nonlinear dimension reduction, enabling us to visualize hierarchical cell layouts in low-dimensional space.

TIMEDB: tumor immune micro-environment cell composition database with automatic analysis and interactive visualization.

Deciphering the cell-type composition in the tumor immune microenvironment (TIME) can significantly increase the efficacy of cancer treatment and improve the prognosis of cancer. Such a task has benefited from microarrays and RNA sequencing technologies, which have been widely adopted in cancer studies, resulting in extensive expression profiles with clinical phenotypes across multiple cancers. Current state-of-the-art tools can infer cell-type composition from bulk expression profiles, providing the possibility of investigating the inter-heterogeneity and intra-heterogeneity of TIME across cancer types. Much can be gained from these tools in conjunction with a well-curated database of TIME cell-type composition data, accompanied by the corresponding clinical information. However, currently available databases fall short in data volume, multi-platform dataset integration, and tool integration. In this work, we introduce TIMEDB (https://timedb.deepomics.org), an online database for human tumor immune microenvironment cell-type composition estimated from bulk expression profiles. TIMEDB stores manually curated expression profiles, cell-type composition profiles, and the corresponding clinical information of a total of 39,706 samples from 546 datasets across 43 cancer types. TIMEDB comes readily equipped with online tools for automatic analysis and interactive visualization, and aims to serve the community as a convenient tool for investigating the human tumor microenvironment.

CircPHKB decreases the sensitivity of liver cancer cells to sorafenib via miR-1234-3p/CYP2W1 axis.

Sorafenib is currently the first-line treatment for patients with advanced liver cancer, but its therapeutic efficacy declines significantly after a few months of treatment. Therefore, it is of great importance to investigate the regulatory mechanisms of sorafenib sensitivity in liver cancer cells. In this study, we provided initial evidence demonstrating that circPHKB, a novel circRNA markedly overexpressed in sorafenib-treated liver cancer cells, attenuated the sensitivity of liver cancer cells to sorafenib. Mechanically, circPHKB sequestered miR-1234-3p, resulting in the up-regulation of cytochrome P450 family 2 subfamily W member 1 (CYP2W1), thereby reducing the killing effect of sorafenib on liver cancer cells. Moreover, knockdown of circPHKB sensitized liver cancer cells to sorafenib in vivo. The findings reveal a novel circPHKB/miR-1234-3p/CYP2W1 pathway that decreases the sensitivity of liver cancer cells to sorafenib, suggesting that circPHKB and the axis may serve as promising targets to improve the therapeutic efficacy of sorafenib against liver cancer.

Somatic variant analysis suite: copy number variation clonal visualization online platform for large-scale single-cell genomics.

The recent advance of single-cell copy number variation (CNV) analysis plays an essential role in addressing intratumor heterogeneity, identifying tumor subgroups and restoring tumor-evolving trajectories at single-cell scale. Informative visualization of copy number analysis results boosts productive scientific exploration, validation and sharing. Several single-cell analysis figures have the effectiveness of visualizations for understanding single-cell genomics in published articles and software packages. However, they almost lack real-time interaction, and it is hard to reproduce them. Moreover, existing tools are time-consuming and memory-intensive when they reach large-scale single-cell throughputs. We present an online visualization platform, single-cell Somatic Variant Analysis Suite (scSVAS), for real-time interactive single-cell genomics data visualization. scSVAS is specifically designed for large-scale single-cell genomic analysis that provides an arsenal of unique functionalities. After uploading the specified input files, scSVAS deploys the online interactive visualization automatically. Users may conduct scientific discoveries, share interactive visualizations and download high-quality publication-ready figures. scSVAS provides versatile utilities for managing, investigating, sharing and publishing single-cell CNV profiles. We envision this online platform will expedite the biological understanding of cancer clonal evolution in single-cell resolution. All visualizations are publicly hosted at https://sc.deepomics.org.

Detecting TAD-like domains from RNA-associated interactions.

Topologically associated domains (TADs) are crucial chromatin structural units. Evidence has illustrated that RNA-chromatin and RNA-RNA spatial interactions, so-called RNA-associated interactions (RAIs), may be associated with TAD-like domains (TLDs). To decode hierarchical TLDs from RAIs, we proposed SuperTLD, a domain detection algorithm incorporating imputation. We applied SuperTLD on four RAI data sets and compared TLDs with the TADs identified from the corresponding Hi-C datasets. The TLDs and TADs share a moderate similarity of hierarchies ≥ 0.5312 and the finest structures ≥ 0.8295. Comparison between boundaries and domains further demonstrated the novelty of TLDs. Enrichment analysis of epigenetic characteristics illustrated that the novel TLDs exhibit an enriched CTCF by 0.6245 fold change and H3 histone marks enriched within domains. GO analysis on the TLD novel boundaries exhibited enriched diverse terms, revealing TLDs' formation mechanism related closely to gene regulation.

Symptom management experiences of Chinese individuals with Crohn's disease: A longitudinal descriptive qualitative study.

Individuals diagnosed with Crohn's disease, a chronic lifelong condition, experience a dynamic or fluctuating process of developing symptom management behavior. However, less clear is how these individuals respond to and manage their symptoms over time. The aim of this study was to longitudinally explore the symptom management experiences of individuals with Crohn's disease in China. A longitudinal qualitative design was used. Eighteen individuals with newly diagnosed Crohn's disease were purposely selected. Semi-structured interviews were conducted on four occasions over a 12-month period. Interviews at each time point were transcribed and coded using conventional content analysis. Afterward, data analyses of each time point were compared longitudinally to form a holistic understanding. Three themes and eight subthemes emerged from the analysis: (1) disclosing symptoms strategically: voluntary disclosure, reluctance to disclose, no need to disclose; (2) decreasing vigilance in symptom prevention: preventing symptoms stringently, preventing symptoms discriminatively, preventing symptoms with decreased diligence; and (3) increasing autonomy in symptom treatment: actively seeking medical advice, self-treatment and self-observation. The participants were inclined to keep symptoms hidden from relatives and friends and showed a downward trend in actively disclosing physical discomfort to medical staff within the course of 1 year. The participants' attention to symptom prevention declined, but the enthusiasm and independence to eliminate symptoms on their own increased over time. Nurses could implement targeted interventions according to the characteristics of different periods to assist individuals with Crohn's disease in managing symptoms effectively, reducing symptom burden and improving their quality of life.

SpecHap: a diploid phasing algorithm based on spectral graph theory.

Haplotype phasing plays an important role in understanding the genetic data of diploid eukaryotic organisms. Different sequencing technologies (such as next-generation sequencing or third-generation sequencing) produce various genetic data that require haplotype assembly. Although multiple diploid haplotype phasing algorithms exist, only a few will work equally well across all sequencing technologies. In this work, we propose SpecHap, a novel haplotype assembly tool that leverages spectral graph theory. On both in silico and whole-genome sequencing datasets, SpecHap consumed less memory and required less CPU time, yet achieved comparable accuracy with state-of-art methods across all the test instances, which comprises sequencing data from next-generation sequencing, linked-reads, high-throughput chromosome conformation capture, PacBio single-molecule real-time, and Oxford Nanopore long-reads. Furthermore, SpecHap successfully phased an individual Ambystoma mexicanum, a species with gigantic diploid genomes, within 6 CPU hours and 945MB peak memory usage, while other tools failed to yield results either due to memory overflow (40GB) or time limit exceeded (5 days). Our results demonstrated that SpecHap is scalable, efficient, and accurate for diploid phasing across many sequencing platforms.

The symptom experience of newly diagnosed Chinese patients with Crohn's disease: A longitudinal qualitative study.

AIMS: To longitudinally explore the symptom experience of Chinese patients with Crohn's disease within the first year following their diagnosis. DESIGN: A longitudinal qualitative study. METHOD: Eighteen newly diagnosed Chinese patients with Crohn's disease were recruited through purposive sampling. Semi-structured interviews were conducted at four time points: soon after diagnosis, 3, 6 and 12 months post-diagnosis. Data were collected between January 2021 and February 2022. Conventional content analysis was used for data analysis of each time point. Afterwards, the data of each time point were compared longitudinally. COREQ checklist was followed. RESULTS: Three themes and eight sub-themes were formed through analysis: feelings towards symptoms (symptoms make me feel uneasy, symptoms make me feel inferior and symptoms make me feel helpless); acceptability of symptoms (difficult to accept, have to accept, be able to accept); functions of symptoms (assessing disease conditions and treatment effects, warning of disease management). CONCLUSIONS: Overall, the negative emotions related to symptoms gradually decreased over time, and the patient's acceptance of symptoms increased within the first year following diagnosis. In addition, when the disease was in remission after treatment, the warning function of symptoms gradually weakened. IMPACT: The process of how patients accept their symptoms found in this study provides a basis for nurses to improve patients' acceptance of symptoms and reduce their symptom-related negative emotions. This study also emphasizes the phenomenon that patients gradually ignore some symptoms with their increased acceptance level, which warrants additional health education to strengthen their awareness of self-management. PATIENT OR PUBLIC CONTRIBUTION: No patient or public contribution was required to design or undertake this study. Patients contributed only to the data collection and member checking.

The Illness Experiences of Chinese Adolescent Patients Living with Crohn Disease: A Descriptive Qualitative Study.

The purpose of this qualitative study was to explore the illness experience of adolescent patients with Crohn disease and describe the impact of the disease on the everyday lives of these individuals within the Chinese social and cultural context to provide references for targeted interventions for the healthcare team. A descriptive qualitative design was adopted. Purposive sampling was used to select Chinese adolescent patients with Crohn disease to participate in face-to-face in-depth interviews. Data analysis was performed using the conventional content analysis method. Through the analysis of data from 14 adolescent patients with Crohn disease, four themes were formed: (1) I am different from others, (2) I am a burden to my parents, (3) I want to be the master of my own body, and (4) I grow up suffering from illness. Healthcare providers should offer more psychological support to adolescent Crohn disease patients and advise parents to shift more attention to the mental health of their children.

SCSilicon: a tool for synthetic single-cell DNA sequencing data generation.

BACKGROUND: Single-cell DNA sequencing is getting indispensable in the study of cell-specific cancer genomics. The performance of computational tools that tackle single-cell genome aberrations may be nevertheless undervalued or overvalued, owing to the insufficient size of benchmarking data. In silicon simulation is a cost-effective approach to generate as many single-cell genomes as possible in a controlled manner to make reliable and valid benchmarking. RESULTS: This study proposes a new tool, SCSilicon, which efficiently generates single-cell in silicon DNA reads with minimum manual intervention. SCSilicon automatically creates a set of genomic aberrations, including SNP, SNV, Indel, and CNV. Besides, SCSilicon yields the ground truth of CNV segmentation breakpoints and subclone cell labels. We have manually inspected a series of synthetic variations. We conducted a sanity check of the start-of-the-art single-cell CNV callers and found SCYN was the most robust one. CONCLUSIONS: SCSilicon is a user-friendly software package for users to develop and benchmark single-cell CNV callers. Source code of SCSilicon is available at https://github.com/xikanfeng2/SCSilicon .

eSMC: a statistical model to infer admixture events from individual genomics data.

BACKGROUND: Inferring historical population admixture events yield essential insights in understanding a species demographic history. Methods are available to infer admixture events in demographic history with extant genetic data from multiple sources. Due to the deficiency in ancient population genetic data, there lacks a method for admixture inference from a single source. Pairwise Sequentially Markovian Coalescent (PSMC) estimates the historical effective population size from lineage genomes of a single individual, based on the distribution of the most recent common ancestor between the diploid's alleles. However, PSMC does not infer the admixture event. RESULTS: Here, we proposed eSMC, an extended PSMC model for admixture inference from a single source. We evaluated our model's performance on both in silico data and real data. We simulated population admixture events at an admixture time range from 5 kya to 100 kya (5 years/generation) with population admix ratio at 1:1, 2:1, 3:1, and 4:1, respectively. The root means the square error is [Formula: see text] kya for all experiments. Then we implemented our method to infer the historical admixture events in human, donkey and goat populations. The estimated admixture time for both Han and Tibetan individuals range from 60 kya to 80 kya (25 years/generation), while the estimated admixture time for the domesticated donkeys and the goats ranged from 40 kya to 60 kya (8 years/generation) and 40 kya to 100 kya (6 years/generation), respectively. The estimated admixture times were concordance to the time that domestication occurred in human history. CONCLUSION: Our eSMC effectively infers the time of the most recent admixture event in history from a single individual's genomics data. The source code of eSMC is hosted at https://github.com/zachary-zzc/eSMC .

Dichloroacetate enhances the anti-tumor effect of sorafenib via modulating the ROS-JNK-Mcl-1 pathway in liver cancer cells.

Liver cancer is one of the most common and high recurrence malignancies. Besides radiotherapy and surgery, chemotherapy also plays an essential role in the treatment of liver cancer. Sorafenib and sorafenib-based combination therapies have been proven efficacy against tumors. However, previous clinical studies have indicated that some patients with liver cancer are resistant to sorafenib treatment and the existing strategies are not satisfactory in the clinic. Therefore, it is urgent to investigate strategies to improve the effectiveness of sorafenib for liver cancer and to explore effective drug combinations. In the present study, we found that dichloroacetate (DCA) could significantly enhance the anti-tumor effect of sorafenib on liver cancer cells, including reduced viability and dramatically promoted apoptosis in liver cancer cells. Moreover, compared to sorafenib alone, the combination of DCA and sorafenib markedly increased the degradation of anti-apoptotic protein Mcl-1 by enhancing its phosphorylation. Overexpression of Mcl-1 could significantly attenuate the synergetic effect of DCA and sorafenib on apoptosis induction in liver cancer cells. Furthermore, we found that the ROS-JNK pathway was obviously activated in the DCA combined sorafenib group. The levels of ROS and p-JNK were dramatically up-regulated in the two drug combination groups. Antioxidant NAC could alleviate the synergetic effects of DCA and sorafenib on ROS generation, JNK activation, Mcl-1 degradation, and cell apoptosis. Moreover, DCA and sorafenib's effects on Mcl-1 degradation and apoptosis could also be inhibited by JNK inhibitor 'SP'600125. Finally, the synergetic effects of DCA and sorafenib on tumor growth suppression, Mcl-1 degradation and induction of apoptosis were also validated in liver cancer xenograft in vivo. These findings indicate that DCA enhances the anti-tumor effect of sorafenib via the ROS-JNK-Mcl-1 pathway in liver cancer cells. This study may provide new insights to improve the chemotherapeutic effect of sorafenib, which may be beneficial for further clinical application of sorafenib in liver cancer treatment.

Oviz-Bio: a web-based platform for interactive cancer genomics data visualization.

Genetics data visualization plays an important role in the sharing of knowledge from cancer genome research. Many types of visualization are widely used, most of which are static and require sufficient coding experience to create. Here, we present Oviz-Bio, a web-based platform that provides interactive and real-time visualizations of cancer genomics data. Researchers can interactively explore visual outputs and export high-quality diagrams. Oviz-Bio supports a diverse range of visualizations on common cancer mutation types, including annotation and signatures of small scale mutations, haplotype view and focal clusters of copy number variations, split-reads alignment and heatmap view of structural variations, transcript junction of fusion genes and genomic hotspot of oncovirus integrations. Furthermore, Oviz-Bio allows landscape view to investigate multi-layered data in samples cohort. All Oviz-Bio visual applications are freely available at https://bio.oviz.org/.

SCYN: single cell CNV profiling method using dynamic programming.

BACKGROUND: Copy number variation is crucial in deciphering the mechanism and cure of complex disorders and cancers. The recent advancement of scDNA sequencing technology sheds light upon addressing intratumor heterogeneity, detecting rare subclones, and reconstructing tumor evolution lineages at single-cell resolution. Nevertheless, the current circular binary segmentation based approach proves to fail to efficiently and effectively identify copy number shifts on some exceptional trails. RESULTS: Here, we propose SCYN, a CNV segmentation method powered with dynamic programming. SCYN resolves the precise segmentation on in silico dataset. Then we verified SCYN manifested accurate copy number inferring on triple negative breast cancer scDNA data, with array comparative genomic hybridization results of purified bulk samples as ground truth validation. We tested SCYN on two datasets of the newly emerged 10x Genomics CNV solution. SCYN successfully recognizes gastric cancer cells from 1% and 10% spike-ins 10x datasets. Moreover, SCYN is about 150 times faster than state of the art tool when dealing with the datasets of approximately 2000 cells. CONCLUSIONS: SCYN robustly and efficiently detects segmentations and infers copy number profiles on single cell DNA sequencing data. It serves to reveal the tumor intra-heterogeneity. The source code of SCYN can be accessed in https://github.com/xikanfeng2/SCYN .

Prognostic implications of tumour-infiltrating lymphocytes for recurrence in epithelial ovarian cancer.

The recurrence of patients with epithelial ovarian cancer (EOC) is largely attributed to tumour cells escaping from the surveillance of immune cells. However, to date there is a lack of studies that have systematically evaluated the associations between the infiltration fraction of immune cells and the recurrence risk of EOC. Based on the micro-ribonucleic acid (microRNA) expression profiles of 441 EOC patients, we constructed a microRNA-based panel with recurrence prediction potential using non-negative matrix factorization consensus clustering. Then, we evaluated the association between recurrence risk and infiltration proportions among 10 immune cell types by CIBERSORT and a multivariable Cox regression model. As a result, we identified a 72-microRNA-based panel that could stratify patients into high and low risk of recurrence. The infiltration of plasma cells and M1 macrophages was consistently significantly associated with the risk of recurrence in patients with EOC. Plasma cells were significantly associated with a decreased risk of relapse [hazard ratio (HR) = 0.58, p = 0.006), while M1 macrophages were associated with an increased risk of relapse (HR = 1.59, p = 0.003). Therefore, the 72-microRNA-based panel, M1 macrophages and plasma cells may hold potential to serve as recurrence predictors of EOC patients in clinical practice.

I-Impute: a self-consistent method to impute single cell RNA sequencing data.

BACKGROUND: Single-cell RNA-sequencing (scRNA-seq) is becoming indispensable in the study of cell-specific transcriptomes. However, in scRNA-seq techniques, only a small fraction of the genes are captured due to "dropout" events. These dropout events require intensive treatment when analyzing scRNA-seq data. For example, imputation tools have been proposed to estimate dropout events and de-noise data. The performance of these imputation tools are often evaluated, or fine-tuned, using various clustering criteria based on ground-truth cell subgroup labels. This limits their effectiveness in the cases where we lack cell subgroup knowledge. We consider an alternative strategy which requires the imputation to follow a "self-consistency" principle; that is, the imputation process is to refine its results until there is no internal inconsistency or dropouts from the data. RESULTS: We propose the use of "self-consistency" as a main criteria in performing imputation. To demonstrate this principle we devised I-Impute, a "self-consistent" method, to impute scRNA-seq data. I-Impute optimizes continuous similarities and dropout probabilities, in iterative refinements until a self-consistent imputation is reached. On the in silico data sets, I-Impute exhibited the highest Pearson correlations for different dropout rates consistently compared with the state-of-art methods SAVER and scImpute. Furthermore, we collected three wetlab datasets, mouse bladder cells dataset, embryonic stem cells dataset, and aortic leukocyte cells dataset, to evaluate the tools. I-Impute exhibited feasible cell subpopulation discovery efficacy on all the three datasets. It achieves the highest clustering accuracy compared with SAVER and scImpute. CONCLUSIONS: A strategy based on "self-consistency", captured through our method, I-Impute, gave imputation results better than the state-of-the-art tools. Source code of I-Impute can be accessed at https://github.com/xikanfeng2/I-Impute .

DeepMF: deciphering the latent patterns in omics profiles with a deep learning method.

BACKGROUND: With recent advances in high-throughput technologies, matrix factorization techniques are increasingly being utilized for mapping quantitative omics profiling matrix data into low-dimensional embedding space, in the hope of uncovering insights in the underlying biological processes. Nevertheless, current matrix factorization tools fall short in handling noisy data and missing entries, both deficiencies that are often found in real-life data. RESULTS: Here, we propose DeepMF, a deep neural network-based factorization model. DeepMF disentangles the association between molecular feature-associated and sample-associated latent matrices, and is tolerant to noisy and missing values. It exhibited feasible cancer subtype discovery efficacy on mRNA, miRNA, and protein profiles of medulloblastoma cancer, leukemia cancer, breast cancer, and small-blue-round-cell cancer, achieving the highest clustering accuracy of 76%, 100%, 92%, and 100% respectively. When analyzing data sets with 70% missing entries, DeepMF gave the best recovery capacity with silhouette values of 0.47, 0.6, 0.28, and 0.44, outperforming other state-of-the-art MF tools on the cancer data sets Medulloblastoma, Leukemia, TCGA BRCA, and SRBCT. Its embedding strength as measured by clustering accuracy is 88%, 100%, 84%, and 96% on these data sets, which improves on the current best methods 76%, 100%, 78%, and 87%. CONCLUSION: DeepMF demonstrated robust denoising, imputation, and embedding ability. It offers insights to uncover the underlying biological processes such as cancer subtype discovery. Our implementation of DeepMF can be found at https://github.com/paprikachan/DeepMF.