Machine learning models identify predictive features of patient mortality across dementia types.

BACKGROUND: Dementia care is challenging due to the divergent trajectories in disease progression and outcomes. Predictive models are needed to flag patients at risk of near-term mortality and identify factors contributing to mortality risk across different dementia types. METHODS: Here, we developed machine-learning models predicting dementia patient mortality at four different survival thresholds using a dataset of 45,275 unique participants and 163,782 visit records from the U.S. National Alzheimer's Coordinating Center (NACC). We built multi-factorial XGBoost models using a small set of mortality predictors and conducted stratified analyses with dementiatype-specific models. RESULTS: Our models achieved an area under the receiver operating characteristic curve (AUC-ROC) of over 0.82 utilizing nine parsimonious features for all 1-, 3-, 5-, and 10-year thresholds. The trained models mainly consisted of dementia-related predictors such as specific neuropsychological tests and were minimally affected by other age-related causes of death, e.g., stroke and cardiovascular conditions. Notably, stratified analyses revealed shared and distinct predictors of mortality across eight dementia types. Unsupervised clustering of mortality predictors grouped vascular dementia with depression and Lewy body dementia with frontotemporal lobar dementia. CONCLUSIONS: This study demonstrates the feasibility of flagging dementia patients at risk of mortality for personalized clinical management. Parsimonious machine-learning models can be used to predict dementia patient mortality with a limited set of clinical features, and dementiatype-specific models can be applied to heterogeneous dementia patient populations.

Dementia has emerged as a major cause of death in societies with increasingly aging populations. However, predicting the exact timing of death in dementia cases is challenging, due to variations in the gradual process where cognitive decline interferes with the body's normal functions. In our study, we build machine-learning models to predict whether a patient diagnosed with dementia will survive or die within 1, 3, 5, or 10 years. We found that the prediction models can work well across patients from different parts of the US and across patients with different types of dementia. The key predictive factor was the information that is already used to diagnose and stage dementia, such as the results of memory tests. Interestingly, broader risk factors related to other causes of death, such as heart conditions, were less significant for predicting death in dementia patients. The ability of these models to identify dementia patients at a heightened risk of mortality could aid clinical practices, potentially allowing for earlier interventions and tailored treatment strategies to improve patient outcomes.

Multiscale protein networks systematically identify aberrant protein interactions and oncogenic regulators in seven cancer types.

Global proteomic data generated by advanced mass spectrometry (MS) technologies can help bridge the gap between genome/transcriptome and functions and hold great potential in elucidating unbiased functional models of pro-tumorigenic pathways. To this end, we collected the high-throughput, whole-genome MS data and conducted integrative proteomic network analyses of 687 cases across 7 cancer types including breast carcinoma (115 tumor samples; 10,438 genes), clear cell renal carcinoma (100 tumor samples; 9,910 genes), colorectal cancer (91 tumor samples; 7,362 genes), hepatocellular carcinoma (101 tumor samples; 6,478 genes), lung adenocarcinoma (104 tumor samples; 10,967 genes), stomach adenocarcinoma (80 tumor samples; 9,268 genes), and uterine corpus endometrial carcinoma UCEC (96 tumor samples; 10,768 genes). Through the protein co-expression network analysis, we identified co-expressed protein modules enriched for differentially expressed proteins in tumor as disease-associated pathways. Comparison with the respective transcriptome network models revealed proteome-specific cancer subnetworks associated with heme metabolism, DNA repair, spliceosome, oxidative phosphorylation and several oncogenic signaling pathways. Cross-cancer comparison identified highly preserved protein modules showing robust pan-cancer interactions and identified endoplasmic reticulum-associated degradation (ERAD) and N-acetyltransferase activity as the central functional axes. We further utilized these network models to predict pan-cancer protein regulators of disease-associated pathways. The top predicted pan-cancer regulators including RSL1D1, DDX21 and SMC2, were experimentally validated in lung, colon, breast cancer and fetal kidney cells. In summary, this study has developed interpretable network models of cancer proteomes, showcasing their potential in unveiling novel oncogenic regulators, elucidating underlying mechanisms, and identifying new therapeutic targets.

Mutation Impact on mRNA Versus Protein Expression across Human Cancers.

Cancer mutations are often assumed to alter proteins, thus promoting tumorigenesis. However, how mutations affect protein expression has rarely been systematically investigated. We conduct a comprehensive analysis of mutation impacts on mRNA- and protein-level expressions of 953 cancer cases with paired genomics and global proteomic profiling across six cancer types. Protein-level impacts are validated for 47.2% of the somatic expression quantitative trait loci (seQTLs), including mutations from likely "long-tail" driver genes. Devising a statistical pipeline for identifying somatic protein-specific QTLs (spsQTLs), we reveal several gene mutations, including NF1 and MAP2K4 truncations and TP53 missenses showing disproportional influence on protein abundance not readily explained by transcriptomics. Cross-validating with data from massively parallel assays of variant effects (MAVE), TP53 missenses associated with high tumor TP53 proteins were experimentally confirmed as functional. Our study demonstrates the importance of considering protein-level expression to validate mutation impacts and identify functional genes and mutations.

Calsarcin-2 May Play a Compensatory Role in the Development of Obese Sarcopenia.

Although obese sarcopenia is a major public health problem with increasing prevalence worldwide, the factors that contribute to the development of obese sarcopenia are still obscure. In order to clarify this issue, a high-fat-diet-induced obese sarcopenia mouse model was utilized. After being fed with a high-fat diet for 24 weeks, decreased motor functions and muscle mass ratios were found in the C57BL/6 mice. In addition, the expression of calsarcin-2 was significantly increased in their skeletal muscle, which was determined by a microarray analysis. In order to clarify the role of calsarcin-2 in muscle, lentiviral vectors containing the calsarcin-2 gene or short hairpin RNA targeted to calsarcin-2 were used to manipulate calsarcin-2 expressions in L6 myoblasts. We found that an overexpression of calsarcin-2 facilitated L6 myoblast differentiation, whereas a calsarcin-2 knockdown delayed myoblast differentiation, as determined by the expression of myogenin. However, the calsarcin-2 knockdown showed no significant effects on myoblast proliferation. In addition, to clarify the relationship between serum calsarcin-2 and sarcopenia, the bilateral gastrocnemius muscle mass per body weight in mice and appendicular skeletal muscle mass index in humans were measured. Although calsarcin-2 facilitated myoblast differentiation, the serum calsarcin-2 concentration was negatively related to skeletal muscle mass index in mice and human subjects. Taken together, calsarcin-2 might facilitate myoblast differentiation and appear to play a compensatory role in sarcopenia.

Tumor-intrinsic LKB1-LIF signaling axis establishes a myeloid niche to promote immune evasion and tumor growth.

Tumor mutations can influence the surrounding microenvironment leading to suppression of anti-tumor immune responses and thereby contributing to tumor progression and failure of cancer therapies. Here we use genetically engineered lung cancer mouse models and patient samples to dissect how LKB1 mutations accelerate tumor growth by reshaping the immune microenvironment. Comprehensive immune profiling of LKB1 -mutant vs wildtype tumors revealed dramatic changes in myeloid cells, specifically enrichment of Arg1 + interstitial macrophages and SiglecF Hi neutrophils. We discovered a novel mechanism whereby autocrine LIF signaling in Lkb1 -mutant tumors drives tumorigenesis by reprogramming myeloid cells in the immune microenvironment. Inhibiting LIF signaling in Lkb1 -mutant tumors, via gene targeting or with a neutralizing antibody, resulted in a striking reduction in Arg1 + interstitial macrophages and SiglecF Hi neutrophils, expansion of antigen specific T cells, and inhibition of tumor progression. Thus, targeting LIF signaling provides a new therapeutic approach to reverse the immunosuppressive microenvironment of LKB1 -mutant tumors.

Structural Analysis of Genomic and Proteomic Signatures Reveal Dynamic Expression of Intrinsically Disordered Regions in Breast Cancer and Tissue.

Structural features of proteins capture underlying information about protein evolution and function, which enhances the analysis of proteomic and transcriptomic data. Here we develop Structural Analysis of Gene and protein Expression Signatures (SAGES), a method that describes expression data using features calculated from sequence-based prediction methods and 3D structural models. We used SAGES, along with machine learning, to characterize tissues from healthy individuals and those with breast cancer. We analyzed gene expression data from 23 breast cancer patients and genetic mutation data from the COSMIC database as well as 17 breast tumor protein expression profiles. We identified prominent expression of intrinsically disordered regions in breast cancer proteins as well as relationships between drug perturbation signatures and breast cancer disease signatures. Our results suggest that SAGES is generally applicable to describe diverse biological phenomena including disease states and drug effects.

Predictive Models and Features of Patient Mortality across Dementia Types.

Dementia care is challenging due to the divergent trajectories in disease progression and outcomes. Predictive models are needed to identify patients at risk of near-term mortality. Here, we developed machine learning models predicting survival using a dataset of 45,275 unique participants and 163,782 visit records from the U.S. National Alzheimer's Coordinating Center (NACC). Our models achieved an AUC-ROC of over 0.82 utilizing nine parsimonious features for all one-, three-, five-, and ten-year thresholds. The trained models mainly consisted of dementia-related predictors such as specific neuropsychological tests and were minimally affected by other age-related causes of death, e.g., stroke and cardiovascular conditions. Notably, stratified analyses revealed shared and distinct predictors of mortality across eight dementia types. Unsupervised clustering of mortality predictors grouped vascular dementia with depression and Lewy body dementia with frontotemporal lobar dementia. This study demonstrates the feasibility of flagging dementia patients at risk of mortality for personalized clinical management.

Using EGFR amplification to stratify recurrent glioblastoma treated with immune checkpoint inhibitors.

PURPOSE: While immune checkpoint inhibitors (ICI) have had success with various malignancies, their efficacy in brain cancer is still unclear. Retrospective and prospective studies using PD-1 inhibitors for recurrent glioblastoma (GBM) have not established survival benefit. This study evaluated if ICI may be effective for select patients with recurrent GBM. METHODS: This was a single-center retrospective study of adult patients diagnosed with first recurrence GBM and received pembrolizumab or nivolumab with or without concurrent bevacizumab. Archival tissue was used for immunohistochemistry (IHC) and targeted DNA next-generation sequencing (NGS) analysis. RESULTS: Median overall survival (mOS) from initial diagnosis was 24.5 months (range 10-42). mOS from onset of ICI was 10 months (range 1-31) with 75% surviving > 6 months and 46% > 12 months. Additional IHC analysis on tumors from eight patients demonstrated a trend of longer survival after ICI for those with elevated PD-L1 expression. NGS of samples from 15 patients identified EGFR amplification at initial diagnosis and at any time point to be associated with worse survival after ICI (HR 12.2, 95% CI 1.37-108, p = 0.025 and HR 3.92, 95% CI 1.03-14.9, p = 0.045, respectively). This significance was corroborated with previously tested EGFR amplification via in situ hybridization. CONCLUSION: ICI did not extend overall survival for recurrent GBM. However, molecular sequencing identified EGFR amplification as associated with worse survival. Prospective studies can validate if EGFR amplification is a biomarker of ICI resistance and determine if its use can stratify responders from non-responders.

Multiethnic Investigation of Risk and Immune Determinants of COVID-19 Outcomes.

Background: Disparate COVID-19 outcomes have been observed between Hispanic, non-Hispanic Black, and White patients. The underlying causes for these disparities are not fully understood. Methods: This was a retrospective study utilizing electronic medical record data from five hospitals within a single academic health system based in New York City. Multivariable logistic regression models were used to identify demographic, clinical, and lab values associated with in-hospital mortality. Results: A total of 3,086 adult patients with self-reported race/ethnicity information presenting to the emergency department and hospitalized with COVID-19 up to April 13, 2020, were included in this study. While older age (multivariable odds ratio (OR) 1.06, 95% CI 1.05-1.07) and baseline hypoxia (multivariable OR 2.71, 95% CI 2.17-3.36) were associated with increased mortality overall and across all races/ethnicities, non-Hispanic Black (median age 67, interquartile range (IQR) 58-76) and Hispanic (median age 63, IQR 50-74) patients were younger and had different comorbidity profiles as compared to non-Hispanic White patients (median age 73, IQR 62-84; p < 0.05 for both comparisons). Among inflammatory markers associated with COVID-19 mortality, there was a significant interaction between the non-Hispanic Black population and interleukin-1-beta (interaction p-value 0.04). Conclusions: This analysis of a multiethnic cohort highlights the need for inclusion and consideration of diverse populations in ongoing COVID-19 trials targeting inflammatory cytokines.

Proteomic Analyses Identify Therapeutic Targets in Hepatocellular Carcinoma.

Hepatocellular carcinoma (HCC) is the fourth cause of cancer-related mortality worldwide. While many targeted therapies have been developed, the majority of HCC tumors do not harbor clinically actionable mutations. Protein-level aberrations, especially those not evident at the genomic level, present therapeutic opportunities but have rarely been systematically characterized in HCC. In this study, we performed proteogenomic analyses of 260 primary tumors from two HBV-related HCC patient cohorts with global mass-spectrometry (MS) proteomics data. Combining tumor-normal and inter-tumor analyses, we identified overexpressed targets including PDGFRB, FGFR4, ERBB2/3, CDK6 kinases and MFAP5, HMCN1, and Hsp proteins in HCC, many of which showed low frequencies of genomic and/or transcriptomic aberrations. Protein expression of FGFR4 kinase and Hsp proteins were significantly associated with response to their corresponding inhibitors. Our results provide a catalog of protein targets in HCC and demonstrate the potential of proteomics approaches in advancing precision medicine in cancer types lacking druggable mutations.

Multi-ethnic Investigation of Risk and Immune Determinants of COVID-19 Outcomes.

Background: Disparate COVID-19 outcomes have been observed between Hispanic, Non-Hispanic Black, and White patients. The underlying causes for these disparities are not fully understood. Methods: This was a retrospective study utilizing electronic medical record data from five hospitals within a single academic health system based in New York City. Multivariable logistic regression models were used to identify demographic, clinical, and lab values associated with in-hospital mortality. Results: 3,086 adult patients with self-reported race/ethnicity information presenting to the emergency department and hospitalized with COVID-19 up to April 13, 2020 were included in this study. While older age (multivariable OR 1.06, 95% CI 1.05-1.07) and baseline hypoxia (multivariable OR 2.71, 95% CI 2.17-3.36) were associated with increased mortality overall and across all races/ethnicities, Non-Hispanic Black (median age 67, IQR 58-76) and Hispanic (median age 63, IQR 50-74) patients were younger and had different comorbidity profiles compared to Non-Hispanic White patients (median age 73, IQR 62-84; p<0.05 for both comparisons). Among inflammatory markers associated with COVID-19 mortality, there was a significant interaction between the Non-Hispanic Black population and interleukin-1-beta (interaction p-value 0.04). Conclusions: This analysis of a multi-ethnic cohort highlights the need for inclusion and consideration of diverse popualtions in ongoing COVID-19 trials targeting inflammatory cytokines.

Modeling COVID-19 dynamic using a two-strain model with vaccination.

Multiple strains of the SARS-CoV-2 have arisen and jointly influence the trajectory of the coronavirus disease (COVID-19) pandemic. However, current models rarely account for this multi-strain dynamics and their different transmission rate and response to vaccines. We propose a new mathematical model that accounts for two virus variants and the deployment of a vaccination program. To demonstrate utility, we applied the model to determine the control reproduction number ( R c ) and the per day infection, death and recovery rates of each strain in the US pandemic. The model dynamics predicted the rise of the alpha variant and shed light on potential impact of the delta variant in 2021. We obtained the minimum percentage of fully vaccinated individuals to reduce the spread of the variants in combination with other intervention strategies to deaccelerate the rise of a multi-strain pandemic.

Genomic and molecular features distinguish young adult cancer from later-onset cancer.

Young adult cancer has increased in incidence worldwide, but its molecular etiologies remain unclear. We systematically characterize genomic profiles of young adult tumors with ages of onset ≤50 years and compare them to later-onset tumors using over 6,000 cases across 14 cancer types. While young adult tumors generally show lower mutation burdens and comparable copy-number variation rates compared to later-onset cases, they are enriched for multiple driver mutations and copy-number alterations in subtype-specific contexts. Characterization of tumor immune microenvironments reveals pan-cancer patterns of elevated TGF-ß response/dendritic cells and lower IFN-γ response/macrophages relative to later-onset tumors, corresponding to age-related responses to immunotherapy in several cancer types. Finally, we identify prevalent clinically actionable events that disproportionally affect young adult or later-onset cases. The resulting catalog of age-related molecular drivers can guide precision diagnostics and treatments for young adult cancer.

UQCRC1 engages cytochrome c for neuronal apoptotic cell death.

Human ubiquinol-cytochrome c reductase core protein 1 (UQCRC1) is an evolutionarily conserved core subunit of mitochondrial respiratory chain complex III. We recently identified the disease-associated variants of UQCRC1 from patients with familial parkinsonism, but its function remains unclear. Here we investigate the endogenous function of UQCRC1 in the human neuronal cell line and the Drosophila nervous system. Flies with neuronal knockdown of uqcrc1 exhibit age-dependent parkinsonism-resembling defects, including dopaminergic neuron reduction and locomotor decline, and are ameliorated by UQCRC1 expression. Lethality of uqcrc1-KO is also rescued by neuronally expressing UQCRC1, but not the disease-causing variant, providing a platform to discern the pathogenicity of this mutation. Furthermore, UQCRC1 associates with the apoptosis trigger cytochrome c (cyt-c), and uqcrc1 deficiency increases cyt-c in the cytoplasmic fraction and activates the caspase cascade. Depleting cyt-c or expression of the anti-apoptotic p35 ameliorates uqcrc1-mediated neurodegeneration. Our findings identify a role for UQCRC1 in regulating cyt-c-induced apoptosis.

Non-cancer-related pathogenic germline variants and expression consequences in ten-thousand cancer genomes.

BACKGROUND: DNA sequencing is increasingly incorporated into the routine care of cancer patients, many of whom also carry inherited, moderate/high-penetrance variants associated with other diseases. Yet, the prevalence and consequence of such variants remain unclear. METHODS: We analyzed the germline genomes of 10,389 adult cancer cases in the TCGA cohort, identifying pathogenic/likely pathogenic variants in autosomal-dominant genes, autosomal-recessive genes, and 59 medically actionable genes curated by the American College of Molecular Genetics (i.e., the ACMG 59 genes). We also analyzed variant- and gene-level expression consequences in carriers. RESULTS: The affected genes exhibited varying pan-ancestry and population-specific patterns, and overall, the European population showed the highest frequency of pathogenic/likely pathogenic variants. We further identified genes showing expression consequence supporting variant functionality, including altered gene expression, allelic specific expression, and mis-splicing determined by a massively parallel splicing assay. CONCLUSIONS: Our results demonstrate that expression-altering variants are found in a substantial fraction of cases and illustrate the yield of genomic risk assessments for a wide range of diseases across diverse populations.

Genomic Determinants of Homologous Recombination Deficiency across Human Cancers.

Germline BRCA1/2 mutations associated with HRD are clinical biomarkers for sensitivity to poly-ADP ribose polymerase inhibitors (PARPi) treatment in breast, ovarian, pancreatic, and prostate cancers. However, it remains unclear whether other mutations may also lead to HRD and PARPi sensitivity across a broader range of cancer types. Our goal was to determine the germline or somatic alterations associated with the HRD phenotype that might therefore confer PARPi sensitivity. Using germline and somatic genomic data from over 9000 tumors representing 32 cancer types, we examined associations between HRD scores and pathogenic germline variants, somatic driver mutations, and copy number deletions in 30 candidate genes involved in homologous recombination. We identified several germline and somatic mutations (e.g., BRCA1/2, PALB2, ATM, and ATR mutations) associated with HRD phenotype in ovarian, breast, pancreatic, stomach, bladder, and lung cancer. The co-occurrence of germline BRCA1 variants and somatic TP53 mutations was significantly associated with increasing HRD in breast cancer. Notably, we also identified multiple somatic copy number deletions associated with HRD. Our study suggests that multiple cancer types include tumor subsets that show HRD phenotype and should be considered in the future clinical studies of PARPi and synthetic lethality strategies exploiting HRD, which can be caused by a large number of genomic alterations.

Pan-cancer proteogenomic investigations identify post-transcriptional kinase targets.

Identifying genomic alterations of cancer proteins has guided the development of targeted therapies, but proteomic analyses are required to validate and reveal new treatment opportunities. Herein, we develop a new algorithm, OPPTI, to discover overexpressed kinase proteins across 10 cancer types using global mass spectrometry proteomics data of 1,071 cases. OPPTI outperforms existing methods by leveraging multiple co-expressed markers to identify targets overexpressed in a subset of tumors. OPPTI-identified overexpression of ERBB2 and EGFR proteins correlates with genomic amplifications, while CDK4/6, PDK1, and MET protein overexpression frequently occur without corresponding DNA- and RNA-level alterations. Analyzing CRISPR screen data, we confirm expression-driven dependencies of multiple currently-druggable and new target kinases whose expressions are validated by immunochemistry. Identified kinases are further associated with up-regulated phosphorylation levels of corresponding signaling pathways. Collectively, our results reveal protein-level aberrations-sometimes not observed by genomics-represent cancer vulnerabilities that may be targeted in precision oncology.

Prediction of individual COVID-19 diagnosis using baseline demographics and lab data.

The global surge in COVID-19 cases underscores the need for fast, scalable, and reliable testing. Current COVID-19 diagnostic tests are limited by turnaround time, limited availability, or occasional false findings. Here, we developed a machine learning-based framework for predicting individual COVID-19 positive diagnosis relying only on readily-available baseline data, including patient demographics, comorbidities, and common lab values. Leveraging a cohort of 31,739 adults within an academic health system, we trained and tested multiple types of machine learning models, achieving an area under the curve of 0.75. Feature importance analyses highlighted serum calcium levels, temperature, age, lymphocyte count, smoking, hemoglobin levels, aspartate aminotransferase levels, and oxygen saturation as key predictors. Additionally, we developed a single decision tree model that provided an operable method for stratifying sub-populations. Overall, this study provides a proof-of-concept that COVID-19 diagnosis prediction models can be developed using only baseline data. The resulting prediction can complement existing tests to enhance screening and pandemic containment workflows.

Diverse immune response of DNA damage repair-deficient tumors.

Tumors with DNA damage repair (DDR) deficiency accumulate genomic alterations that may serve as neoantigens and increase sensitivity to immune checkpoint inhibitor. However, over half of DDR-deficient tumors are refractory to immunotherapy, and it remains unclear which mutations may promote immunogenicity in which cancer types. We integrate deleterious somatic and germline mutations and methylation data of DDR genes in 10,080 cancers representing 32 cancer types and evaluate the associations of these alterations with tumor neoantigens and immune infiltrates. Our analyses identify DDR pathway mutations that are associated with higher neoantigen loads, adaptive immune markers, and survival outcomes of immune checkpoint inhibitor-treated animal models and patients. Different immune phenotypes are associated with distinct types of DDR deficiency, depending on the cancer type context. The comprehensive catalog of immune response-associated DDR deficiency may explain variations in immunotherapy outcomes across DDR-deficient cancers and facilitate the development of genomic biomarkers for immunotherapy.

Genetic dependency of Alzheimer's disease-associated genes across cells and tissue types.

Effective treatments targeting disease etiology are urgently needed for Alzheimer's disease (AD). Although candidate AD genes have been identified and altering their levels may serve as therapeutic strategies, the consequence of such alterations remain largely unknown. Herein, we analyzed CRISPR knockout/RNAi knockdown screen data for over 700 cell lines and evaluated cellular dependencies of 104 AD-associated genes previously identified by genome-wide association studies (GWAS) and gene expression network studies. Multiple genes showed widespread cell dependencies across tissue lineages, suggesting their inhibition may yield off-target effects. Meanwhile, several genes including SPI1, MEF2C, GAB2, ABCC11, ATCG1 were identified as genes of interest since their genetic knockouts specifically affected high-expressing cells whose tissue lineages are relevant to cell types found in AD. Overall, analyses of genetic screen data identified AD-associated genes whose knockout or knockdown selectively affected cell lines of relevant tissue lineages, prioritizing targets for potential AD treatments.