Machine learning on alignment features for parent-of-origin classification of simulated hybrid RNA-seq.

BACKGROUND: Parent-of-origin allele-specific gene expression (ASE) can be detected in interspecies hybrids by virtue of RNA sequence variants between the parental haplotypes. ASE is detectable by differential expression analysis (DEA) applied to the counts of RNA-seq read pairs aligned to parental references, but aligners do not always choose the correct parental reference. RESULTS: We used public data for species that are known to hybridize. We measured our ability to assign RNA-seq read pairs to their proper transcriptome or genome references. We tested software packages that assign each read pair to a reference position and found that they often favored the incorrect species reference. To address this problem, we introduce a post process that extracts alignment features and trains a random forest classifier to choose the better alignment. On each simulated hybrid dataset tested, our machine-learning post-processor achieved higher accuracy than the aligner by itself at choosing the correct parent-of-origin per RNA-seq read pair. CONCLUSIONS: For the parent-of-origin classification of RNA-seq, machine learning can improve the accuracy of alignment-based methods. This approach could be useful for enhancing ASE detection in interspecies hybrids, though RNA-seq from real hybrids may present challenges not captured by our simulations. We believe this is the first application of machine learning to this problem domain.

Genetic tapestry of Capsicum fruit colors: a comparative analysis of four cultivated species.

KEY MESSAGE: Genome-wide association study of color spaces across the four cultivated Capsicum spp. revealed a shared set of genes influencing fruit color, suggesting mechanisms and pathways across Capsicum species are conserved during the speciation. Notably, Cytochrome P450 of the carotenoid pathway, MYB transcription factor, and pentatricopeptide repeat-containing protein are the major genes responsible for fruit color variation across the Capsicum species. Peppers (Capsicum spp.) rank among the most widely consumed spices globally. Fruit color, serving as a determinant for use in food colorants and cosmeceuticals and an indicator of nutritional contents, significantly influences market quality and price. Cultivated Capsicum species display extensive phenotypic diversity, especially in fruit coloration. Our study leveraged the genetic variance within four Capsicum species (Capsicum baccatum, Capsicum chinense, Capsicum frutescens, and Capsicum annuum) to elucidate the genetic mechanisms driving color variation in peppers and related Solanaceae species. We analyzed color metrics and chromatic attributes (Red, Green, Blue, L*, a*, b*, Luminosity, Hue, and Chroma) on samples cultivated over six years (2015-2021). We resolved genomic regions associated with fruit color diversity through the sets of SNPs obtained from Genotyping by Sequencing (GBS) and genome-wide association study (GWAS) with a Multi-Locus Mixed Linear Model (MLMM). Significant SNPs with FDR correction were identified, within the Cytochrome P450, MYB-related genes, Pentatricopeptide repeat proteins, and ABC transporter family were the most common among the four species, indicating comparative evolution of fruit colors. We further validated the role of a pentatricopeptide repeat-containing protein (Chr01:31,205,460) and a cytochrome P450 enzyme (Chr08:45,351,919) via competitive allele-specific PCR (KASP) genotyping. Our findings advance the understanding of the genetic underpinnings of Capsicum fruit coloration, with developed KASP assays holding potential for applications in crop breeding and aligning with consumer preferences. This study provides a cornerstone for future research into exploiting Capsicum's diverse fruit color variation.

Association of APOE gene with longitudinal changes of CSF amyloid beta and tau levels in Alzheimer's disease: racial differences.

BACKGROUND: The Apolipoprotein E (APOE) ε4 allele is a risk factor for late-onset Alzheimer's disease (AD). However, no investigation has focused on racial differences in the longitudinal effect of APOE genotypes on CSF amyloid beta (Aß42) and tau levels in AD. METHODS: This study used data from the Alzheimer's Disease Neuroimaging Initiative (ADNI): 222 participants with AD, 264 with cognitive normal (CN), and 692 with mild cognitive impairment (MCI) at baseline and two years follow-up. We used a linear mixed model to investigate the effect of APOE-ε4-genotypes on longitudinal changes in the amyloid beta and tau levels. RESULTS: Individuals with 1 or 2 APOE ε4 alleles revealed significantly higher t-Tau and p-Tau, but lower amyloid beta Aß42 compared with individuals without APOE ε4 alleles. Significantly higher levels of log-t-Tau, log-p-Tau, and low levels of log-Aß42 were observed in the subjects with older age, being female, and the two diagnostic groups (AD and MCI). The higher p-Tau and Aß42 values are associated with poor Mini-Mental State Examination (MMSE) performance. Non-Hispanic Africa American (AA) and Hispanic participants were associated with decreased log-t-Tau levels (ß = - 0.154, p = 0.0112; ß = - 0.207, and p = 0.0016, respectively) as compared to those observed in Whites. Furthermore, Hispanic participants were associated with a decreased log-p-Tau level (ß = - 0.224, p = 0.0023) compared to those observed in Whites. There were no differences in Aß42 level for non-Hispanic AA and Hispanic participants compared with White participants. CONCLUSION: Our study, for the first time, showed that the APOE ε4 allele was associated with these biomarkers, however with differing degrees among racial groups.

Dietary Curcumin Intake and Its Effects on the Transcriptome and Metabolome of Drosophila melanogaster.

Curcumin, a polyphenol derived from Curcuma longa, used as a dietary spice, has garnered attention for its therapeutic potential, including antioxidant, anti-inflammatory, and antimicrobial properties. Despite its known benefits, the precise mechanisms underlying curcumin's effects on consumers remain unclear. To address this gap, we employed the genetic model Drosophila melanogaster and leveraged two omics tools-transcriptomics and metabolomics. Our investigation revealed alterations in 1043 genes and 73 metabolites upon supplementing curcumin into the diet. Notably, we observed genetic modulation in pathways related to antioxidants, carbohydrates, and lipids, as well as genes associated with gustatory perception and reproductive processes. Metabolites implicated in carbohydrate metabolism, amino acid biosynthesis, and biomarkers linked to the prevention of neurodegenerative diseases such as schizophrenia, Alzheimer's, and aging were also identified. The study highlighted a strong correlation between the curcumin diet, antioxidant mechanisms, and amino acid metabolism. Conversely, a lower correlation was observed between carbohydrate metabolism and cholesterol biosynthesis. This research highlights the impact of curcumin on the diet, influencing perception, fertility, and molecular wellness. Furthermore, it directs future studies toward a more focused exploration of the specific effects of curcumin consumption.

Deep learning for biological age estimation.

Modern machine learning techniques (such as deep learning) offer immense opportunities in the field of human biological aging research. Aging is a complex process, experienced by all living organisms. While traditional machine learning and data mining approaches are still popular in aging research, they typically need feature engineering or feature extraction for robust performance. Explicit feature engineering represents a major challenge, as it requires significant domain knowledge. The latest advances in deep learning provide a paradigm shift in eliciting meaningful knowledge from complex data without performing explicit feature engineering. In this article, we review the recent literature on applying deep learning in biological age estimation. We consider the current data modalities that have been used to study aging and the deep learning architectures that have been applied. We identify four broad classes of measures to quantify the performance of algorithms for biological age estimation and based on these evaluate the current approaches. The paper concludes with a brief discussion on possible future directions in biological aging research using deep learning. This study has significant potentials for improving our understanding of the health status of individuals, for instance, based on their physical activities, blood samples and body shapes. Thus, the results of the study could have implications in different health care settings, from palliative care to public health.

Identification of all-against-all protein-protein interactions based on deep hash learning.

BACKGROUND: Protein-protein interaction (PPI) is vital for life processes, disease treatment, and drug discovery. The computational prediction of PPI is relatively inexpensive and efficient when compared to traditional wet-lab experiments. Given a new protein, one may wish to find whether the protein has any PPI relationship with other existing proteins. Current computational PPI prediction methods usually compare the new protein to existing proteins one by one in a pairwise manner. This is time consuming. RESULTS: In this work, we propose a more efficient model, called deep hash learning protein-and-protein interaction (DHL-PPI), to predict all-against-all PPI relationships in a database of proteins. First, DHL-PPI encodes a protein sequence into a binary hash code based on deep features extracted from the protein sequences using deep learning techniques. This encoding scheme enables us to turn the PPI discrimination problem into a much simpler searching problem. The binary hash code for a protein sequence can be regarded as a number. Thus, in the pre-screening stage of DHL-PPI, the string matching problem of comparing a protein sequence against a database with M proteins can be transformed into a much more simpler problem: to find a number inside a sorted array of length M. This pre-screening process narrows down the search to a much smaller set of candidate proteins for further confirmation. As a final step, DHL-PPI uses the Hamming distance to verify the final PPI relationship. CONCLUSIONS: The experimental results confirmed that DHL-PPI is feasible and effective. Using a dataset with strictly negative PPI examples of four species, DHL-PPI is shown to be superior or competitive when compared to the other state-of-the-art methods in terms of precision, recall or F1 score. Furthermore, in the prediction stage, the proposed DHL-PPI reduced the time complexity from [Formula: see text] to [Formula: see text] for performing an all-against-all PPI prediction for a database with M proteins. With the proposed approach, a protein database can be preprocessed and stored for later search using the proposed encoding scheme. This can provide a more efficient way to cope with the rapidly increasing volume of protein datasets.

Peppers in Diet: Genome-Wide Transcriptome and Metabolome Changes in Drosophila melanogaster.

The habanero pepper (Capsicum chinense) is an increasingly important spice and vegetable crop worldwide because of its high capsaicin content and pungent flavor. Diets supplemented with the phytochemicals found in habanero peppers might cause shifts in an organism's metabolism and gene expression. Thus, understanding how these interactions occur can reveal the potential health effects associated with such changes. We performed transcriptomic and metabolomic analyses of Drosophila melanogaster adult flies reared on a habanero pepper diet. We found 539 genes/59 metabolites that were differentially expressed/accumulated in flies fed a pepper versus control diet. Transcriptome results indicated that olfactory sensitivity and behavioral responses to the pepper diet were mediated by olfactory and nutrient-related genes including gustatory receptors (Gr63a, Gr66a, and Gr89a), odorant receptors (Or23a, Or59a, Or82a, and Orco), and odorant-binding proteins (Obp28a, Obp83a, Obp83b, Obp93a, and Obp99a). Metabolome analysis revealed that campesterol, sitosterol, and sucrose were highly upregulated and azelaic acid, ethyl phosphoric acid, and citric acid were the major metabolites downregulated in response to the habanero pepper diet. Further investigation by integration analysis between transcriptome and metabolome data at gene pathway levels revealed six unique enriched pathways, including phenylalanine metabolism; insect hormone biosynthesis; pyrimidine metabolism; glyoxylate, and dicarboxylate metabolism; glycine, serine, threonine metabolism; and glycerolipid metabolism. In view of the transcriptome and metabolome findings, our comprehensive analysis of the response to a pepper diet in Drosophila have implications for exploring the molecular mechanism of pepper consumption.

K2 and K2*: efficient alignment-free sequence similarity measurement based on Kendall statistics.

Motivation: Alignment-free sequence comparison methods can compute the pairwise similarity between a huge number of sequences much faster than sequence-alignment based methods. Results: We propose a new non-parametric alignment-free sequence comparison method, called K2, based on the Kendall statistics. Comparing to the other state-of-the-art alignment-free comparison methods, K2 demonstrates competitive performance in generating the phylogenetic tree, in evaluating functionally related regulatory sequences, and in computing the edit distance (similarity/dissimilarity) between sequences. Furthermore, the K2 approach is much faster than the other methods. An improved method, K2*, is also proposed, which is able to determine the appropriate algorithmic parameter (length) automatically, without first considering different values. Comparative analysis with the state-of-the-art alignment-free sequence similarity methods demonstrates the superiority of the proposed approaches, especially with increasing sequence length, or increasing dataset sizes. Availability and implementation: The K2 and K2* approaches are implemented in the R language as a package and is freely available for open access (http://community.wvu.edu/daadjeroh/projects/K2/K2_1.0.tar.gz). Contact: yueljiang@163.com. Supplementary information: Supplementary data are available at Bioinformatics online.

Online continual decoding of streaming EEG signal with a balanced and informative memory buffer.

Electroencephalography (EEG) based Brain Computer Interface (BCI) systems play a significant role in facilitating how individuals with neurological impairments effectively interact with their environment. In real world applications of BCI system for clinical assistance and rehabilitation training, the EEG classifier often needs to learn on sequentially arriving subjects in an online manner. As patterns of EEG signals can be significantly different for different subjects, the EEG classifier can easily erase knowledge of learnt subjects after learning on later ones as it performs decoding in online streaming scenario, namely catastrophic forgetting. In this work, we tackle this problem with a memory-based approach, which considers the following conditions: (1) subjects arrive sequentially in an online manner, with no large scale dataset available for joint training beforehand, (2) data volume from the different subjects could be imbalanced, (3) decoding difficulty of the sequential streaming signal vary, (4) continual classification for a long time is required. This online sequential EEG decoding problem is more challenging than classic cross subject EEG decoding as there is no large-scale training data from the different subjects available beforehand. The proposed model keeps a small balanced memory buffer during sequential learning, with memory data dynamically selected based on joint consideration of data volume and informativeness. Furthermore, for the more general scenarios where subject identity is unknown to the EEG decoder, aka. subject agnostic scenario, we propose a kernel based subject shift detection method that identifies underlying subject changes on the fly in a computationally efficient manner. We develop challenging benchmarks of streaming EEG data from sequentially arriving subjects with both balanced and imbalanced data volumes, and performed extensive experiments with a detailed ablation study on the proposed model. The results show the effectiveness of our proposed approach, enabling the decoder to maintain performance on all previously seen subjects over a long period of sequential decoding. The model demonstrates the potential for real-world applications.

sCL-ST: Supervised Contrastive Learning With Semantic Transformations for Multiple Lead ECG Arrhythmia Classification.

The automatic classification of electrocardiogram (ECG) signals has played an important role in cardiovascular diseases diagnosis and prediction. With recent advancements in deep neural networks (DNNs), particularly Convolutional Neural Networks (CNNs), learning deep features automatically from the original data is becoming an effective and widespread approach in a variety of intelligent tasks including biomedical and health informatics. However, most of the existing approaches are trained on either 1D CNNs or 2D CNNs, and they suffer from the limitations of random phenomena (i.e. random initial weights). Furthermore, the ability to train such DNNs in a supervised manner in healthcare is often limited due to the scarcity of labeled training data. To address the problems of weight initialization and limited annotated data, in this work, we leverage recent self-supervised learning technique, namely, contrastive learning, and present supervised contrastive learning (sCL). Different from existing self-supervised contrastive learning approaches, which often generate false negatives because of random selection of negative anchors, our contrastive learning makes use of labeled data to pull the same class closer together and push different classes far apart to avoid potential false negatives. Furthermore, unlike other kinds of signals (e.g. speech, image, video), ECG signal is sensitive to changes, and inappropriate transformation could directly affect diagnosis results. To deal with this issue, we present two semantic transformations, i.e. semantic split-join and semantic weighted peaks noise smoothing. The proposed deep neural network sCL-ST with supervised contrastive learning and semantic transformations is trained as an end-to-end framework for the multi-label classification of 12-lead ECGs. Our sCL-ST network contains two sub-networks i.e. pre-text task and down-stream task. Our experimental results have been evaluated on 12-lead PhysioNet 2020 dataset and shown that our proposed network outperforms the state-of-the-art existing approaches.

A Critical Review of Data Science Applications in Resource Recovery and Carbon Capture from Organic Waste.

Municipal and agricultural organic waste can be treated to recover energy, nutrients, and carbon through resource recovery and carbon capture (RRCC) technologies such as anaerobic digestion, struvite precipitation, and pyrolysis. Data science could benefit such technologies by improving their efficiency through data-driven process modeling along with reducing environmental and economic burdens via life cycle assessment (LCA) and techno-economic analysis (TEA), respectively. We critically reviewed 616 peer-reviewed articles on the use of data science in RRCC published during 2002-2022. Although applications of machine learning (ML) methods have drastically increased over time for modeling RRCC technologies, the reviewed studies exhibited significant knowledge gaps at various model development stages. In terms of sustainability, an increasing number of studies included LCA with TEA to quantify both environmental and economic impacts of RRCC. Integration of ML methods with LCA and TEA has the potential to cost-effectively investigate the trade-off between efficiency and sustainability of RRCC, although the literature lacked such integration of techniques. Therefore, we propose an integrated data science framework to inform efficient and sustainable RRCC from organic waste based on the review. Overall, the findings from this review can inform practitioners about the effective utilization of various data science methods for real-world implementation of RRCC technologies.

Inflammatory Bone Marrow Mesenchymal Stem Cells in Multiple Myeloma: Transcriptional Signature and In Vitro Modeling.

Bone marrow mesenchymal stem cells (BM MSCs) play a tumor-supportive role in promoting drug resistance and disease relapse in multiple myeloma (MM). Recent studies have discovered a sub-population of MSCs, known as inflammatory MSCs (iMSCs), exclusive to the MM BM microenvironment and implicated in drug resistance. Through a sophisticated analysis of public expression data from unexpanded BM MSCs, we uncovered a positive association between iMSC signature expression and minimal residual disease. While in vitro expansion generally results in the loss of the iMSC signature, our meta-analysis of additional public expression data demonstrated that cytokine stimulation, including IL1-ß and TNF-α, as well as immune cells such as neutrophils, macrophages, and MM cells, can reactivate the signature expression of iMSCs to varying extents. These findings underscore the importance and potential utility of cytokine stimulation in mimicking the gene expression signature of early passage of iMSCs for functional characterizations of their tumor-supportive roles in MM.

Interdisciplinary Inquiry via PanelGPT: Application to Explore Chatbot Application in Sports Rehabilitation.

Background: ChatGPT showcases exceptional conversational capabilities and extensive cross-disciplinary knowledge. In addition, it possesses the ability to perform multiple roles within a single chat session. This unique multi-role-playing feature positions ChatGPT as a promising tool to explore interdisciplinary subjects. Objective: The study intended to guide ChatGPT for interdisciplinary exploration through simulated panel discussions. As a proof-of-concept, we employed this method to evaluate the advantages and challenges of using chatbots in sports rehabilitation. Methods: We proposed a model termed PanelGPT to explore ChatGPTs' knowledge graph on interdisciplinary topics through simulated panel discussions. Applied to "chatbots in sports rehabilitation", ChatGPT role-played both the moderator and panelists, which included a physiotherapist, psychologist, nutritionist, AI expert, and an athlete. We act as the audience posed questions to the panel, with ChatGPT acting as both the panelists for responses and the moderator for hosting the discussion. We performed the simulation using the ChatGPT-4 model and evaluated the responses with existing literature and human expertise. Results: Each simulation mimicked a real-life panel discussion: The moderator introduced the panel and posed opening/closing questions, to which all panelists responded. The experts engaged with each other to address inquiries from the audience, primarily from their respective fields of expertise. By tackling questions related to education, physiotherapy, physiology, nutrition, and ethical consideration, the discussion highlighted benefits such as 24/7 support, personalized advice, automated tracking, and reminders. It also emphasized the importance of user education and identified challenges such as limited interaction modes, inaccuracies in emotion-related advice, assurance on data privacy and security, transparency in data handling, and fairness in model training. The panelists reached a consensus that chatbots are designed to assist, not replace, human healthcare professionals in the rehabilitation process. Conclusions: Compared to a typical conversation with ChatGPT, the multi-perspective approach of PanelGPT facilitates a comprehensive understanding of an interdisciplinary topic by integrating insights from experts with complementary knowledge. Beyond addressing the exemplified topic of chatbots in sports rehabilitation, the model can be adapted to tackle a wide array of interdisciplinary topics within educational, research, and healthcare settings.

Emergency medical services shock index is the most accurate predictor of patient outcomes after blunt torso trauma.

INTRODUCTION: Shock index (SI) and delta shock index (∆SI) predict mortality and blood transfusion in trauma patients. This study aimed to evaluate the predictive ability of SI and ∆SI in a rural environment with prolonged transport times and transfers from critical access hospitals or level IV trauma centers. METHODS: We completed a retrospective database review at an American College of Surgeons verified level 1 trauma center for 2 years. Adult subjects analyzed sustained torso trauma. Subjects with missing data or severe head trauma were excluded. For analysis, poisson regression and binomial logistic regression were used to study the effect of time in transport and SI/∆SI on resource utilization and outcomes. p < 0.05 was considered significant. RESULTS: Complete data were available on 549 scene patients and 127 transfers. Mean Injury Severity Score was 11 (interquartile range, 9.0) for scene and 13 (interquartile range, 6.5) for transfers. Initial emergency medical services SI was the most significant predictor for blood transfusion and intensive care unit care in both scene and transferred patients (p < 0.0001) compared with trauma center arrival SI or transferring center SI. A negative ∆SI was significantly associated with the need for transfusion and the number of units transfused. Longer transport time also had a significant relationship with increasing intensive care unit length of stay. Cohorts were analyzed separately. CONCLUSION: Providers must maintain a high level of clinical suspicion for patients who had an initially elevated SI. Emergency medical services SI was the greatest predictor of injury and need for resources. Enroute SI and ∆SI were less predictive as time from injury increased. This highlights the improvements in en route care but does not eliminate the need for high-level trauma intervention. LEVEL OF EVIDENCE: Therapeutic/care management, level IV.

Bone Marrow Stroma-Induced Transcriptome and Regulome Signatures of Multiple Myeloma.

Multiple myeloma (MM) is a hematological cancer with inevitable drug resistance. MM cells interacting with bone marrow stromal cells (BMSCs) undergo substantial changes in the transcriptome and develop de novo multi-drug resistance. As a critical component in transcriptional regulation, how the chromatin landscape is transformed in MM cells exposed to BMSCs and contributes to the transcriptional response to BMSCs remains elusive. We profiled the transcriptome and regulome for MM cells using a transwell coculture system with BMSCs. The transcriptome and regulome of MM cells from the upper transwell resembled MM cells that coexisted with BMSCs from the lower chamber but were distinctive to monoculture. BMSC-induced genes were enriched in the JAK2/STAT3 signaling pathway, unfolded protein stress, signatures of early plasma cells, and response to proteasome inhibitors. Genes with increasing accessibility at multiple regulatory sites were preferentially induced by BMSCs; these genes were enriched in functions linked to responses to drugs and unfavorable clinic outcomes. We proposed JUNB and ATF4::CEBPß as candidate transcription factors (TFs) that modulate the BMSC-induced transformation of the regulome linked to the transcriptional response. Together, we characterized the BMSC-induced transcriptome and regulome signatures of MM cells to facilitate research on epigenetic mechanisms of BMSC-induced multi-drug resistance in MM.

Ultrasonic Texture Features for Assessing Cardiac Remodeling and Dysfunction.

BACKGROUND: Changes in cardiac size, myocardial mass, cardiomyocyte appearance, and, ultimately, the function of the entire organ are interrelated features of cardiac remodeling that profoundly affect patient outcomes. OBJECTIVES: This study proposes that the application of radiomics for extracting cardiac ultrasonic textural features (ultrasomics) can aid rapid, automated assessment of left ventricular (LV) structure and function without requiring manual measurements. METHODS: This study developed machine-learning models using cardiac ultrasound images from 1,915 subjects in 3 clinical cohorts: 1) an expert-annotated cardiac point-of-care-ultrasound (POCUS) registry (n = 943, 80% training/testing and 20% internal validation); 2) a prospective POCUS cohort for external validation (n = 275); and 3) a prospective external validation on high-end ultrasound systems (n = 484). In a type 2 diabetes murine model, echocardiography of wild-type (n = 10) and Leptr-/- (n = 8) mice were assessed longitudinally at 3 and 25 weeks, and ultrasomics features were correlated with histopathological features of hypertrophy. RESULTS: The ultrasomics model predicted LV remodeling in the POCUS and high-end ultrasound external validation studies (area under the curve: 0.78 [95% CI: 0.68-0.88] and 0.79 [95% CI: 0.73-0.86], respectively). Similarly, the ultrasomics model predicted LV remodeling was significantly associated with major adverse cardiovascular events in both cohorts (P < 0.0001 and P = 0.0008, respectively). Moreover, on multivariate analysis, the ultrasomics probability score was an independent echocardiographic predictor of major adverse cardiovascular events in the high-end ultrasound cohort (HR: 8.53; 95% CI: 4.75-32.1; P = 0.0003). In the murine model, cardiomyocyte hypertrophy positively correlated with 2 ultrasomics biomarkers (R2 = 0.57 and 0.52, Q < 0.05). CONCLUSIONS: Cardiac ultrasomics-based biomarkers may aid development of machine-learning models that provide an expert-level assessment of LV structure and function.

Random KNN feature selection - a fast and stable alternative to Random Forests.

BACKGROUND: Successfully modeling high-dimensional data involving thousands of variables is challenging. This is especially true for gene expression profiling experiments, given the large number of genes involved and the small number of samples available. Random Forests (RF) is a popular and widely used approach to feature selection for such "small n, large p problems." However, Random Forests suffers from instability, especially in the presence of noisy and/or unbalanced inputs. RESULTS: We present RKNN-FS, an innovative feature selection procedure for "small n, large p problems." RKNN-FS is based on Random KNN (RKNN), a novel generalization of traditional nearest-neighbor modeling. RKNN consists of an ensemble of base k-nearest neighbor models, each constructed from a random subset of the input variables. To rank the importance of the variables, we define a criterion on the RKNN framework, using the notion of support. A two-stage backward model selection method is then developed based on this criterion. Empirical results on microarray data sets with thousands of variables and relatively few samples show that RKNN-FS is an effective feature selection approach for high-dimensional data. RKNN is similar to Random Forests in terms of classification accuracy without feature selection. However, RKNN provides much better classification accuracy than RF when each method incorporates a feature-selection step. Our results show that RKNN is significantly more stable and more robust than Random Forests for feature selection when the input data are noisy and/or unbalanced. Further, RKNN-FS is much faster than the Random Forests feature selection method (RF-FS), especially for large scale problems, involving thousands of variables and multiple classes. CONCLUSIONS: Given the superiority of Random KNN in classification performance when compared with Random Forests, RKNN-FS's simplicity and ease of implementation, and its superiority in speed and stability, we propose RKNN-FS as a faster and more stable alternative to Random Forests in classification problems involving feature selection for high-dimensional datasets.

Levels of Angiotensin-Converting Enzyme and Apolipoproteins Are Associated with Alzheimer's Disease and Cardiovascular Diseases.

Angiotensin-converting enzyme-1 (ACE1) and apolipoproteins (APOs) may play important roles in the development of Alzheimer's disease (AD) and cardiovascular diseases (CVDs). This study aimed to examine the associations of AD, CVD, and endocrine-metabolic diseases (EMDs) with the levels of ACE1 and 9 APO proteins (ApoAI, ApoAII, ApoAIV, ApoB, ApoCI, ApoCIII, ApoD, ApoE, and ApoH). Non-Hispanic white individuals including 109 patients with AD, 356 mild cognitive impairment (MCI), 373 CVD, 198 EMD and controls were selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Multivariable general linear model (GLM) was used to examine the associations. ApoE ε4 allele was associated with AD, as well as ApoAIV, ApoB and ApoE proteins, but not associated with CVD and EMD. Both AD and CVD were associated with levels of ACE1, ApoB, and ApoH proteins. AD, MCI and EMD were associated with levels of ACE1, ApoAII, and ApoE proteins. This is the first study to report associations of ACE1 and several APO proteins with AD, MCI, CVD and EMD, respectively, including upregulated and downregulated protein levels. In conclusion, as specific or shared biomarkers, the levels of ACE1 and APO proteins are implicated for AD, CVD, EMD and ApoE ε4 allele. Further studies are required for validation to establish reliable biomarkers for these health conditions.