Integrative Proteomic Characterization of Human Lung Adenocarcinoma.

Genomic studies of lung adenocarcinoma (LUAD) have advanced our understanding of the disease's biology and accelerated targeted therapy. However, the proteomic characteristics of LUAD remain poorly understood. We carried out a comprehensive proteomics analysis of 103 cases of LUAD in Chinese patients. Integrative analysis of proteome, phosphoproteome, transcriptome, and whole-exome sequencing data revealed cancer-associated characteristics, such as tumor-associated protein variants, distinct proteomics features, and clinical outcomes in patients at an early stage or with EGFR and TP53 mutations. Proteome-based stratification of LUAD revealed three subtypes (S-I, S-II, and S-III) related to different clinical and molecular features. Further, we nominated potential drug targets and validated the plasma protein level of HSP 90ß as a potential prognostic biomarker for LUAD in an independent cohort. Our integrative proteomics analysis enables a more comprehensive understanding of the molecular landscape of LUAD and offers an opportunity for more precise diagnosis and treatment.

Genetic Diversity in Mycobacterium tuberculosis Clinical Isolates and Resulting Outcomes of Tuberculosis Infection and Disease.

Tuberculosis claims more human lives than any other bacterial infectious disease and represents a clear and present danger to global health as new tools for vaccination, treatment, and interruption of transmission have been slow to emerge. Additionally, tuberculosis presents with notable clinical heterogeneity, which complicates diagnosis, treatment, and the establishment of nonrelapsing cure. How this heterogeneity is driven by the diversity ofclinical isolates of the causative agent, Mycobacterium tuberculosis, has recently garnered attention. Herein, we review advances in the understanding of how naturally occurring variation in clinical isolates affects transmissibility, pathogenesis, immune modulation, and drug resistance. We also summarize how specific changes in transcriptional responses can modulate infection or disease outcome, together with strain-specific effects on gene essentiality. Further understanding of how this diversity of M. tuberculosis isolates affects disease and treatment outcomes will enable the development of more effective therapeutic options and vaccines for this dreaded disease.

The germ theory revisited: A noncentric view on infection outcome.

The germ theory states that pathogenic microorganisms are responsible for causing infectious diseases. The theory is inherently microbe-centric and does not account for variability in disease severity among individuals and asymptomatic carriership-two phenomena indicating an important role for host variability in infection outcome. The basic tenet of the germ theory was recently challenged, and a radically host-centric paradigm referred to as the "full-blown host theory" was proposed. According to this view, the pathogen is reduced to a passive environmental trigger, and the development of disease is instead due to pre-existing immunodeficiencies of the host. Here, we consider the factors that determine disease severity using established knowledge concerning evolutionary biology, microbial pathogenesis, and host-pathogen interactions. We note that the available data support a noncentric view that recognizes key roles for both the causative microbe and the host in dictating infection outcome.

An encoding generative modeling approach to dimension reduction and covariate adjustment in causal inference with observational studies.

In this article, we develop CausalEGM, a deep learning framework for nonlinear dimension reduction and generative modeling of the dependency among covariate features affecting treatment and response. CausalEGM can be used for estimating causal effects in both binary and continuous treatment settings. By learning a bidirectional transformation between the high-dimensional covariate space and a low-dimensional latent space and then modeling the dependencies of different subsets of the latent variables on the treatment and response, CausalEGM can extract the latent covariate features that affect both treatment and response. By conditioning on these features, one can mitigate the confounding effect of the high dimensional covariate on the estimation of the causal relation between treatment and response. In a series of experiments, the proposed method is shown to achieve superior performance over existing methods in both binary and continuous treatment settings. The improvement is substantial when the sample size is large and the covariate is of high dimension. Finally, we established excess risk bounds and consistency results for our method, and discuss how our approach is related to and improves upon other dimension reduction approaches in causal inference.

RepurposeDrugs: an interactive web-portal and predictive platform for repurposing mono- and combination therapies.

RepurposeDrugs (https://repurposedrugs.org/) is a comprehensive web-portal that combines a unique drug indication database with a machine learning (ML) predictor to discover new drug-indication associations for approved as well as investigational mono and combination therapies. The platform provides detailed information on treatment status, disease indications and clinical trials across 25 indication categories, including neoplasms and cardiovascular conditions. The current version comprises 4314 compounds (approved, terminated or investigational) and 161 drug combinations linked to 1756 indications/conditions, totaling 28 148 drug-disease pairs. By leveraging data on both approved and failed indications, RepurposeDrugs provides ML-based predictions for the approval potential of new drug-disease indications, both for mono- and combinatorial therapies, demonstrating high predictive accuracy in cross-validation. The validity of the ML predictor is validated through a number of real-world case studies, demonstrating its predictive power to accurately identify repurposing candidates with a high likelihood of future approval. To our knowledge, RepurposeDrugs web-portal is the first integrative database and ML-based predictor for interactive exploration and prediction of both single-drug and combination approval likelihood across indications. Given its broad coverage of indication areas and therapeutic options, we expect it accelerates many future drug repurposing projects.

Tools to facilitate communication during physician-patient consultations in cancer care: An overview of systematic reviews.

Tools have been developed to facilitate communication and support information exchange between people diagnosed with cancer and their physicians. Patient-reported outcome measures, question prompt lists, patient-held records, tape recordings of consultations, decision aids, and survivorship care plans have all been promoted as potential tools, and there is extensive literature exploring their impact on patient outcomes. Eleven systematic reviews of studies evaluating tools to facilitate patient-physician communication were reviewed and summarized in this overview of systematic reviews. Across the systematic reviews, 87 publications reported on 84 primary studies involving 15,381 participants. Routine use of patient-reported outcome measures and feedback of results to clinicians can improve pain management, physician-patient communication, and symptom detection and control; increase utilization of supportive care; and increase patient involvement in care. Question prompt lists can increase the number of questions asked by patients without increasing consultation length and may encourage them to reflect and plan questions before the consultation. There is limited benefit in audio recording consultations or using patient-held records during consultations. Physicians should be supported by adequately resourced health services to respond effectively to the range of clinical and broader patient needs identified through the routine use of tools to facilitate communication.

Sharing of misinformation is habitual, not just lazy or biased.

Why do people share misinformation on social media? In this research (N = 2,476), we show that the structure of online sharing built into social platforms is more important than individual deficits in critical reasoning and partisan bias-commonly cited drivers of misinformation. Due to the reward-based learning systems on social media, users form habits of sharing information that attracts others' attention. Once habits form, information sharing is automatically activated by cues on the platform without users considering response outcomes such as spreading misinformation. As a result of user habits, 30 to 40% of the false news shared in our research was due to the 15% most habitual news sharers. Suggesting that sharing of false news is part of a broader response pattern established by social media platforms, habitual users also shared information that challenged their own political beliefs. Finally, we show that sharing of false news is not an inevitable consequence of user habits: Social media sites could be restructured to build habits to share accurate information.

Noncanonical HPV carcinogenesis drives radiosensitization of head and neck tumors.

We analyzed transcriptional data from 104 HPV+ (Human papillomavirus) HNSCC (head and neck squamous cell carcinoma) tumors together with two publicly available sources to identify highly robust transcriptional programs (modules) which could be detected consistently despite heterogeneous sequencing and quantification methodologies. Among 22 modules identified, we found a single module that naturally subclassifies HPV+ HNSCC tumors based on a bimodal pattern of gene expression, clusters all atypical features of HPV+ HNSCC biology into a single subclass, and predicts patient outcome in four independent cohorts. The subclass-defining gene set was strongly correlated with Nuclear factor kappa B (NF-κB) target expression. Tumors with high expression of this NF-κB module were rarely associated with activating PIK3CA alterations or viral integration, and also expressed higher levels of HPHPV E2 and had decreased APOBEC mutagenesis. Alternatively, they harbored inactivating alterations of key regulators of NF-κB, TNF receptor associated factor 3 (TRAF3), and cylindromatosis (CYLD), as well as retinoblastoma protein (RB1). HPV+ HNSCC cells in culture with experimental depletion of TRAF3 or CYLD displayed increased expression of the subclass-defining genes, as well as robust radio-sensitization, thus recapitulating both the tumor transcriptional state and improved treatment response observed in patient data. Across all gene sets investigated, methylation to expression correlations were the strongest for the subclass-defining, NF-κB-related genes. Increased tumor-infiltrating CD4+ T cells and increased Estrogen receptors alpha (ERα) expression were identified in NF-κB active tumors. Based on the relatively high rates of cure in HPV+ HNSCC, deintensification of therapy to reduce treatment-related morbidity is being studied at many institutions. Tumor subclassification based on oncogenic subtypes may help guide the selection of therapeutic intensity or modality for patients with HPV+ HNSCC.

Severity-Dependent Interhemispheric White Matter Connectivity Predicts Poststroke Neglect Recovery.

Left-sided spatial neglect is a very common and challenging issue after right-hemispheric stroke, which strongly and negatively affects daily living behavior and recovery of stroke survivors. The mechanisms underlying recovery of spatial neglect remain controversial, particularly regarding the involvement of the intact, contralesional hemisphere, with potential contributions ranging from maladaptive to compensatory. In the present prospective, observational study, we assessed neglect severity in 54 right-hemispheric stroke patients (32 male; 22 female) at admission to and discharge from inpatient neurorehabilitation. We demonstrate that the interaction of initial neglect severity and spared white matter (dis)connectivity resulting from individual lesions (as assessed by diffusion tensor imaging, DTI) explains a significant portion of the variability of poststroke neglect recovery. In mildly impaired patients, spared structural connectivity within the lesioned hemisphere is sufficient to attain good recovery. Conversely, in patients with severe impairment, successful recovery critically depends on structural connectivity within the intact hemisphere and between hemispheres. These distinct patterns, mediated by their respective white matter connections, may help to reconcile the dichotomous perspectives regarding the role of the contralesional hemisphere as exclusively compensatory or not. Instead, they suggest a unified viewpoint wherein the contralesional hemisphere can - but must not necessarily - assume a compensatory role. This would depend on initial impairment severity and on the available, spared structural connectivity. In the future, our findings could serve as a prognostic biomarker for neglect recovery and guide patient-tailored therapeutic approaches.

Structured testing of genetic association with mixed clinical outcomes.

Genetic factors play a fundamental role in disease development. Studying the genetic association with clinical outcomes is critical for understanding disease biology and devising novel treatment targets. However, the frequencies of genetic variations are often low, making it difficult to examine the variants one-by-one. Moreover, the clinical outcomes are complex, including patients' survival time and other binary or continuous outcomes such as recurrences and lymph node count, and how to effectively analyze genetic association with these outcomes remains unclear. In this article, we proposed a structured test statistic for testing genetic association with mixed types of survival, binary, and continuous outcomes. The structured testing incorporates known biological information of variants while allowing for their heterogeneous effects and is a powerful strategy for analyzing infrequent genetic factors. Simulation studies show that the proposed test statistic has correct type I error and is highly effective in detecting significant genetic variants. We applied our approach to a uterine corpus endometrial carcinoma study and identified several genetic pathways associated with the clinical outcomes.

Randomized Trial for Evaluation in Secondary Prevention Efficacy of Combination Therapy-Statin and Eicosapentaenoic Acid (RESPECT-EPA).

BACKGROUND: Low plasma levels of eicosapentaenoic acid (EPA) are associated with cardiovascular events. This trial aimed to assess the clinical benefits of icosapent ethyl in patients with coronary artery disease, a low EPA/arachidonic acid (AA) ratio, and statin treatment. METHODS: In this prospective, multicenter, randomized, open-label, blinded end-point study, patients with stable coronary artery disease and a low EPA/AA ratio (<0.4) were randomized to EPA (1800 of icosapent ethyl administered daily) or control group. The primary end point was a composite of cardiovascular death, nonfatal myocardial infarction, nonfatal ischemic stroke, unstable angina pectoris, and coronary revascularization. The secondary composite end points of coronary events included sudden cardiac death, fatal and nonfatal myocardial infarction, unstable angina requiring emergency hospitalization and coronary revascularization, or coronary revascularization. RESULTS: Overall, 3884 patients were enrolled at 95 sites in Japan. Among them, 2506 patients had a low EPA/AA ratio, and 1249 and 1257 patients were randomized to the EPA and control group, respectively. The median EPA/AA ratio was 0.243 (interquartile range, 0.180-0.314) and 0.235 (interquartile range, 0.163-0.310) in the EPA and control group, respectively. Over a median period of 5 years, the primary end point occurred in 112 of 1225 patients (9.1%) and 155 of 1235 patients (12.6%) in the EPA and control group, respectively (hazard ratio, 0.79 [95% CI, 0.62-1.00]; P=0.055). Meanwhile, the secondary composite end point of coronary events in the EPA group was significantly lower (81/1225 [6.6%] versus 120/1235 [9.7%] patients; hazard ratio, 0.73 [95% CI, 0.55-0.97]). Adverse events did not differ between the groups, but the rate of new-onset atrial fibrillation was significantly higher in the EPA group (3.1% versus 1.6%; P=0.017). CONCLUSIONS: Icosapent ethyl treatment resulted in a numerically lower risk of cardiovascular events that did not reach statistical significance in patients with chronic coronary artery disease, a low EPA/AA ratio, and statin treatment. REGISTRATION: URL: https://www.umin.ac.jp/ctr/; Unique identifier: UMIN000012069.

Clinical Impact of Routine Assessment of Patient-Reported Health Status in Heart Failure Clinic: The PRO-HF Trial.

BACKGROUND: The impact of routine clinic use of patient-reported outcome (PRO) measures on clinical outcomes in patients with heart failure (HF) has not been well-characterized. We tested if clinic-based use of a disease-specific PRO improves patient-reported quality of life at 1 year. METHODS: The PRO-HF trial (Patient-Reported Outcome Measurement in Heart Failure Clinic) was an open-label, parallel, patient-level randomized clinical trial of routine PRO assessment or usual care at an academic HF clinic between August 30, 2021, and June 30, 2022, with 1 year of follow-up. In the PRO assessment arm, participants completed the Kansas City Cardiomyopathy Questionnaire-12 (KCCQ-12) at each HF clinic visit, and results were shared with their treating clinician. The usual care arm completed the KCCQ-12 at randomization and 1 year later, which was not shared with the treating clinician. The primary outcome was the KCCQ-12 overall summary score (OSS) between 12 and 15 months after randomization. Secondary outcomes included domains of the KCCQ-12, hospitalization and emergency department visit rates, HF medication therapy, clinic visit frequency, and testing rates. RESULTS: Across 17 clinicians, 1248 participants were enrolled and randomized to PRO assessment (n=624) or usual care (n=624). The median age was 63.9 years (interquartile range [IQR], 51.8-72.8), 38.9% were women, and the median baseline KCCQ-12 OSS was 82.3 (IQR, 58.3-94.8). Final KCCQ-12 (available in 87.9% of the PRO arm and 85.1% in usual care; P=0.16) median OSS were 87.5 (IQR, 68.8-96.9) in the PRO arm and 87.6 (IQR, 69.7-96.9) in the usual care arm with a baseline-adjusted mean difference of 0.2 ([95% CI, -1.7 to 2.0]; P=0.85). The results were consistent across prespecified subgroups. A post hoc analysis demonstrated a significant interaction with greater benefit among participants with a baseline KCCQ-12 OSS of 60 to 80 but not in less or more symptomatic participants. No significant differences were found in 1-year mortality, hospitalizations, emergency department visits, medication therapy, clinic follow-up, or testing rates between arms. CONCLUSIONS: Routine PRO assessment in HF clinic visits did not impact patient-reported quality of life or other clinical outcomes. Alternate strategies and settings for embedding PROs into routine clinical care should be tested. REGISTRATION: URL: https://www.clinicaltrials.gov; Unique identifier: NCT04164004.

Estimated Lifetime Cardiovascular, Kidney, and Mortality Benefits of Combination Treatment With SGLT2 Inhibitors, GLP-1 Receptor Agonists, and Nonsteroidal MRA Compared With Conventional Care in Patients With Type 2 Diabetes and Albuminuria.

BACKGROUND: Sodium glucose cotransporter 2 inhibitors (SGLT2i), glucagon-like peptide-1 receptor agonists (GLP-1 RA), and the nonsteroidal mineralocorticoid receptor antagonist (ns-MRA) finerenone all individually reduce cardiovascular, kidney, and mortality outcomes in patients with type 2 diabetes and albuminuria. However, the lifetime benefits of combination therapy with these medicines are not known. METHODS: We used data from 2 SGLT2i trials (CANVAS [Canagliflozin Cardiovascular Assessment] and CREDENCE [Canagliflozin and Renal Events in Diabetes with Established Nephropathy Clinical Evaluation]), 2 ns-MRA trials (FIDELIO-DKD [Finerenone in Reducing Kidney Failure and Disease Progression in Diabetic Kidney Disease] and FIGARO-DKD [Efficacy and Safety of Finerenone in Subjects With Type 2 Diabetes Mellitus and the Clinical Diagnosis of Diabetic Kidney Disease]), and 8 GLP-1 RA trials to estimate the relative effects of combination therapy versus conventional care (renin-angiotensin system blockade and traditional risk factor control) on cardiovascular, kidney, and mortality outcomes. Using actuarial methods, we then estimated absolute risk reductions with combination SGLT2i, GLP-1 RA, and ns-MRA in patients with type 2 diabetes and at least moderately increased albuminuria (urinary albumin:creatinine ratio ≥30 mg/g) by applying estimated combination treatment effects to participants receiving conventional care in CANVAS and CREDENCE. RESULTS: Compared with conventional care, the combination of SGLT2i, GLP-1 RA, and ns-MRA was associated with a hazard ratio of 0.65 (95% CI, 0.55-0.76) for major adverse cardiovascular events (nonfatal myocardial infarction, nonfatal stroke, or cardiovascular death). The corresponding estimated absolute risk reduction over 3 years was 4.4% (95% CI, 3.0-5.7), with a number needed to treat of 23 (95% CI, 18-33). For a 50-year-old patient commencing combination therapy, estimated major adverse cardiovascular event-free survival was 21.1 years compared with 17.9 years for conventional care (3.2 years gained [95% CI, 2.1-4.3]). There were also projected gains in survival free from hospitalized heart failure (3.2 years [95% CI, 2.4-4.0]), chronic kidney disease progression (5.5 years [95% CI, 4.0-6.7]), cardiovascular death (2.2 years [95% CI, 1.2-3.0]), and all-cause death (2.4 years [95% CI, 1.4-3.4]). Attenuated but clinically relevant gains in event-free survival were observed in analyses assuming 50% additive effects of combination therapy, including for major adverse cardiovascular events (2.4 years [95% CI, 1.1-3.5]), chronic kidney disease progression (4.5 years [95% CI, 2.8-5.9]), and all-cause death (1.8 years [95% CI, 0.7-2.8]). CONCLUSIONS: In patients with type 2 diabetes and at least moderately increased albuminuria, combination treatment of SGLT2i, GLP-1 RA, and ns-MRA has the potential to afford relevant gains in cardiovascular and kidney event-free and overall survival.

Patient-Reported Outcomes in Disorders of Gut-Brain Interaction.

Disorders of gut-brain interaction are characterized by chronic gastrointestinal symptoms in the absence of abnormal endoscopic or radiologic findings or objective biomarkers that can be identified during routine clinical evaluation. The assessment of the symptom pattern and severity, therefore, is the key modality to evaluate the presence, impact, and evolution of these conditions, for both clinical and regulatory purposes. Patient-reported outcomes are structured symptom assessment questionnaires designed to evaluate symptom patterns, quantify severity of symptoms, and evaluate response to treatment at follow-up. This review provides an overview of currently available patient-reported outcomes for evaluating the main disorders of gut-brain interaction, specifically, functional dyspepsia; irritable bowel syndrome; and chronic constipation. It summarizes their content, level of validation for clinical practice and for research, and the regulatory approach to these conditions. Expected future developments and need for further research on patient-reported outcomes for these and other disorders of gut-brain interaction are highlighted.

Influence of Procedural Volume on the Outcome of Gastric Endoscopic Submucosal Dissection: A Nationwide Population-Based Study Using Administrative Data.

BACKGROUND & AIMS: Endoscopic submucosal dissection (ESD) is a well-established treatment modality for gastric neoplasms. We aimed to investigate the effect of procedural volume on the outcome of ESD for gastric cancer or adenoma. METHODS: In this population-based cohort study, patients who underwent ESD for gastric cancer or adenoma from November 2011 to December 2017 were identified using the Korean National Health Insurance Service database. Operational definitions to identify the target population and post-procedural complications were created using diagnosis and procedure codes and were validated using hospital medical record data. Outcomes included hemorrhage, perforation, pneumonia, 30-day mortality, a composite outcome comprising all of these adverse outcomes, and additional resection. Hospital volume was categorized into 3 groups based on the results of the threshold analysis: high-, medium-, low-volume centers (HVCs, MVCs, and LVCs, respectively). Inverse probability of treatment weighting analysis was applied to enhance comparability across the volume groups. RESULTS: There were 94,246 procedures performed in 88,687 patients during the study period. There were 5886 composite events including 4925 hemorrhage, 447 perforation, and 703 pneumonia cases. There were significant differences in ESD-related adverse outcomes among the 3 hospital volume categories, showing that HVCs and MVCs were associated with a lower risk of a composite outcome than LVCs (inverse probability of treatment-weighted odds ratio [OR], 0.651; 95% CI, 0.521-0.814; inverse probability of treatment-weighted OR, 0.641; 95% CI, 0.534-0.769). Similar tendencies were also shown for hemorrhage, perforation, and pneumonia; however, these were not evident for additional resection. CONCLUSIONS: Procedural volume was closely associated with clinical outcome in patients undergoing ESD for gastric cancer or adenoma.

Dysbiosis and Associated Stool Features Improve Prediction of Response to Biological Therapy in Inflammatory Bowel Disease.

BACKGROUND & AIMS: Dysbiosis of the gut microbiota is considered a key contributor to inflammatory bowel disease (IBD) etiology. Here, we investigated potential associations between microbiota composition and the outcomes to biological therapies. METHODS: The study prospectively recruited 296 patients with active IBD (203 with Crohn's disease, 93 with ulcerative colitis) initiating biological therapy. Quantitative microbiome profiles of pretreatment and posttreatment fecal samples were obtained combining flow cytometry with 16S amplicon sequencing. Therapeutic response was assessed by endoscopy, patient-reported outcomes, and changes in fecal calprotectin. The effect of therapy on microbiome variation was evaluated using constrained ordination methods. Prediction of therapy outcome was performed using logistic regression with 5-fold cross-validation. RESULTS: At baseline, 65.9% of patients carried the dysbiotic Bacteroides2 (Bact2) enterotype, with a significantly higher prevalence among patients with ileal involvement (76.8%). Microbiome variation was associated with the choice of biological therapy rather than with therapeutic outcome. Only anti-tumor necrosis factor-α treatment resulted in a microbiome shift away from Bact2, concomitant with an increase in microbial load and butyrogen abundances and a decrease in potentially opportunistic Veillonella. Remission rates for patients hosting Bact2 at baseline were significantly higher with anti-tumor necrosis factor-α than with vedolizumab (65.1% vs 35.2%). A prediction model, based on anthropometrics and clinical data, stool features (microbial load, moisture, and calprotectin), and Bact2 detection predicted treatment outcome with 73.9% accuracy for specific biological therapies. CONCLUSION: Fecal characterization based on microbial load, moisture content, calprotectin concentration, and enterotyping may aid in the therapeutic choice of biological therapy in IBD.

Identification of complier and noncomplier average causal effects in the presence of latent missing-at-random (LMAR) outcomes: a unifying view and choices of assumptions.

The study of treatment effects is often complicated by noncompliance and missing data. In the one-sided noncompliance setting where of interest are the complier and noncomplier average causal effects, we address outcome missingness of the latent missing at random type (LMAR, also known as latent ignorability). That is, conditional on covariates and treatment assigned, the missingness may depend on compliance type. Within the instrumental variable (IV) approach to noncompliance, methods have been proposed for handling LMAR outcome that additionally invoke an exclusion restriction-type assumption on missingness, but no solution has been proposed for when a non-IV approach is used. This article focuses on effect identification in the presence of LMAR outcomes, with a view to flexibly accommodate different principal identification approaches. We show that under treatment assignment ignorability and LMAR only, effect nonidentifiability boils down to a set of two connected mixture equations involving unidentified stratum-specific response probabilities and outcome means. This clarifies that (except for a special case) effect identification generally requires two additional assumptions: a specific missingness mechanism assumption and a principal identification assumption. This provides a template for identifying effects based on separate choices of these assumptions. We consider a range of specific missingness assumptions, including those that have appeared in the literature and some new ones. Incidentally, we find an issue in the existing assumptions, and propose a modification of the assumptions to avoid the issue. Results under different assumptions are illustrated using data from the Baltimore Experience Corps Trial.

Benchmarking of analytical combinations for COVID-19 outcome prediction using single-cell RNA sequencing data.

The advances of single-cell transcriptomic technologies have led to increasing use of single-cell RNA sequencing (scRNA-seq) data in large-scale patient cohort studies. The resulting high-dimensional data can be summarized and incorporated into patient outcome prediction models in several ways; however, there is a pressing need to understand the impact of analytical decisions on such model quality. In this study, we evaluate the impact of analytical choices on model choices, ensemble learning strategies and integrate approaches on patient outcome prediction using five scRNA-seq COVID-19 datasets. First, we examine the difference in performance between using single-view feature space versus multi-view feature space. Next, we survey multiple learning platforms from classical machine learning to modern deep learning methods. Lastly, we compare different integration approaches when combining datasets is necessary. Through benchmarking such analytical combinations, our study highlights the power of ensemble learning, consistency among different learning methods and robustness to dataset normalization when using multiple datasets as the model input.

Attention-based generative adversarial networks improve prognostic outcome prediction of cancer from multimodal data.

The prediction of prognostic outcome is critical for the development of efficient cancer therapeutics and potential personalized medicine. However, due to the heterogeneity and diversity of multimodal data of cancer, data integration and feature selection remain a challenge for prognostic outcome prediction. We proposed a deep learning method with generative adversarial network based on sequential channel-spatial attention modules (CSAM-GAN), a multimodal data integration and feature selection approach, for accomplishing prognostic stratification tasks in cancer. Sequential channel-spatial attention modules equipped with an encoder-decoder are applied for the input features of multimodal data to accurately refine selected features. A discriminator network was proposed to make the generator and discriminator learning in an adversarial way to accurately describe the complex heterogeneous information of multiple modal data. We conducted extensive experiments with various feature selection and classification methods and confirmed that the CSAM-GAN via the multilayer deep neural network (DNN) classifier outperformed these baseline methods on two different multimodal data sets with miRNA expression, mRNA expression and histopathological image data: lower-grade glioma and kidney renal clear cell carcinoma. The CSAM-GAN via the multilayer DNN classifier bridges the gap between heterogenous multimodal data and prognostic outcome prediction.

Clinical outcomes of patients with mut-type methylmalonic acidemia identified through expanded newborn screening in China.

BACKGROUND: Isolated methylmalonic acidemia, an autosomal recessive disorder of propionate metabolism, is usually caused by mutations in the methylmalonyl-CoA mutase gene (mut-type). Because no universal consensus was made on whether mut-type methylmalonic acidemia should be included in newborn screening (NBS), we aimed to compare the outcome of this disorder detected by NBS with that detected clinically and investigate the influence of NBS on the disease course. DESIGN & METHODS: In this study, 168 patients with mut-type methylmalonic acidemia diagnosed by NBS were compared to 210 patients diagnosed after disease onset while NBS was not performed. Clinical data of these patients from 7 metabolic centers in China were analyzed retrospectively, including initial manifestations, biochemical metabolites, the responsiveness of vitamin B12 therapy, and gene variation, to explore different factors on the long-term outcome. RESULTS: By comparison of the clinically-diagnosed patients, NBS-detected patients showed younger age at diagnosis, less incidence of disease onset, better responsiveness of vitamin B12, younger age at start of treatment, lower levels of biochemical features before and after treatment, and better long-term prognosis (P < 0.01). Onset of disease, blood C3/C2 ratio and unresponsiveness of vitamin B12 were more positively associated with poor outcomes of patients whether identified by NBS. Moreover, the factors above as well as older age at start of treatment were positively associated with mortality. CONCLUSIONS: This research highly demonstrated NBS could prevent major disease-related events and allow an earlier treatment initiation. As a key prognostic factor, NBS is beneficial for improving the overall survival of infants with mut-type methylmalonic acidemia.