Interspecific Sample Prioritization Can Improve QTL Detection With Tree-Based Predictive Models.
Ontology highlight
ABSTRACT:
SUBMITTER: Shin MG
PROVIDER: S-EPMC8450460 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Understanding the genetic basis of complex phenotypes is a central pursuit of genetics. Genome-wide Association Studies (GWAS) are a powerful way to find genetic loci associated with phenotypes. GWAS are widely and successfully used, but they face challenges related to the fact that variants are tested for association with a phenotype independently, whereas in reality variants at different sites are correlated because of their shared evolutionary history. One way to model this shared history is through the ancestral recombination graph (ARG), which encodes a series of local coalescent trees. Recent computational and methodological breakthroughs have made it feasible to estimate approximate ARGs from large-scale samples. Here, we explore the potential of an ARG-based approach to quantitative-trait locus (QTL) mapping, echoing existing variance-components approaches. We propose a framework that relies on the conditional expectation of a local genetic relatedness matrix given the ARG (local eGRM). Simulations show that our method is especially beneficial for finding QTLs in the presence of allelic heterogeneity. By framing QTL mapping in terms of the estimated ARG, we can also facilitate the detection of QTLs in understudied populations. We use local eGRM to identify a large-effect BMI locus, the CREBRF gene, in a sample of Native Hawaiians in which it was not previously detectable by GWAS because of a lack of population-specific imputation resources. Our investigations can provide intuition about the benefits of using estimated ARGs in population- and statistical-genetic methods in general.
| S-EPMC10104234 | biostudies-literature
Project description:This reproducibility study presents an algorithm to weigh in race distribution data of clinical research study samples when training biomedical embeddings. We extracted 12,864 PubMed abstracts published between January 1st, 2000 and January 1st, 2022 and weighed them based on the race distribution data extracted from their corresponding clinical trials registered on ClinicalTrials.gov. We trained Word2vec and BERT embeddings and evaluated their performance on predicting length of hospital stay (LHS) and intensive care unit (ICU) readmission using MIMIC-IV electronic health record data. We observed that models trained using race-sensitive embeddings do not consistently outperform the neutral embeddings ones when used for LHS prediction (with similar Mean Absolute Error 1.975 vs. 2.008) or ICU readmission prediction (with similar accuracy 74.61% vs. 75.17% and the same AUC 0.775), respectively. We conclude that demographic sensitive embeddings do not necessarily significantly improve the accuracy of health predictive models as previously reported in the literature.
| S-EPMC10283113 | biostudies-literature
Project description:Compared to bioclimatic variables, remote sensing predictors are rarely used for predictive species modelling. When used, the predictors represent typically habitat classifications or filters rather than gradual spectral, surface or biophysical properties. Consequently, the full potential of remotely sensed predictors for modelling the spatial distribution of species remains unexplored. Here we analysed the partial contributions of remotely sensed and climatic predictor sets to explain and predict the distribution of 19 tree species in Utah. We also tested how these partial contributions were related to characteristics such as successional types or species traits.We developed two spatial predictor sets of remotely sensed and topo-climatic variables to explain the distribution of tree species. We used variation partitioning techniques applied to generalized linear models to explore the combined and partial predictive powers of the two predictor sets. Non-parametric tests were used to explore the relationships between the partial model contributions of both predictor sets and species characteristics.More than 60% of the variation explained by the models represented contributions by one of the two partial predictor sets alone, with topo-climatic variables outperforming the remotely sensed predictors. However, the partial models derived from only remotely sensed predictors still provided high model accuracies, indicating a significant correlation between climate and remote sensing variables. The overall accuracy of the models was high, but small sample sizes had a strong effect on cross-validated accuracies for rare species.Models of early successional and broadleaf species benefited significantly more from adding remotely sensed predictors than did late seral and needleleaf species. The core-satellite species types differed significantly with respect to overall model accuracies. Models of satellite and urban species, both with low prevalence, benefited more from use of remotely sensed predictors than did the more frequent core species.Synthesis and applications. If carefully prepared, remotely sensed variables are useful additional predictors for the spatial distribution of trees. Major improvements resulted for deciduous, early successional, satellite and rare species. The ability to improve model accuracy for species having markedly different life history strategies is a crucial step for assessing effects of global change.
| S-EPMC2368764 | biostudies-literature
Project description:Bulk transcriptomic analyses of autism spectrum disorder (ASD) have revealed dysregulated pathways, while the brain cell type-specific molecular pathology of ASD still needs to be studied. Machine learning-based studies can be conducted for ASD, prioritizing high-confidence gene candidates and promoting the design of effective interventions. Using human brain nucleus gene expression of ASD and controls, we construct cell type-specific predictive models for ASD based on individual genes and gene sets, respectively, to screen cell type-specific ASD-associated genes and gene sets. These two kinds of predictive models can predict the diagnosis of a nucleus with known cell type. Then, we construct a multi-label predictive model for predicting the cell type and diagnosis of a nucleus at the same time. Our findings suggest that layer 2/3 and layer 4 excitatory neurons, layer 5/6 cortico-cortical projection neurons, parvalbumin interneurons, and protoplasmic astrocytes are preferentially affected in ASD. The functions of genes with predictive power for ASD are different and the top important genes are distinct across different cells, highlighting the cell-type heterogeneity of ASD. The constructed predictive models can promote the diagnosis of ASD, and the prioritized cell type-specific ASD-associated genes and gene sets may be used as potential biomarkers of ASD.
| S-EPMC7844401 | biostudies-literature
Project description:Multinomial Logistic Regression (MLR) has been advocated for developing clinical prediction models that distinguish between three or more unordered outcomes. We present a full-factorial simulation study to examine the predictive performance of MLR models in relation to the relative size of outcome categories, number of predictors and the number of events per variable. It is shown that MLR estimated by Maximum Likelihood yields overfitted prediction models in small to medium sized data. In most cases, the calibration and overall predictive performance of the multinomial prediction model is improved by using penalized MLR. Our simulation study also highlights the importance of events per variable in the multinomial context as well as the total sample size. As expected, our study demonstrates the need for optimism correction of the predictive performance measures when developing the multinomial logistic prediction model. We recommend the use of penalized MLR when prediction models are developed in small data sets or in medium sized data sets with a small total sample size (ie, when the sizes of the outcome categories are balanced). Finally, we present a case study in which we illustrate the development and validation of penalized and unpenalized multinomial prediction models for predicting malignancy of ovarian cancer.
| S-EPMC6590172 | biostudies-literature
Project description:MotivationPositive-unlabeled data consists of points with either positive or unknown labels. It is widespread in medical, genetic, and biological settings, creating a high demand for predictive positive-unlabeled models. The performance of such models is usually estimated using validation sets, assumed to be selected completely at random (SCAR) from known positive examples. For certain metrics, this assumption enables unbiased performance estimation when treating positive-unlabeled data as positive/negative. However, the SCAR assumption is often adopted without proper justifications, simply for the sake of convenience.ResultsWe provide an algorithm that under the weak assumptions of a lower bound on the number of positive examples can test for the violation of the SCAR assumption. Applying it to the problem of gene prioritization for complex genetic traits, we illustrate that the SCAR assumption is often violated there, causing the inflation of performance estimates, which we refer to as validation bias. We estimate the potential impact of validation bias on performance estimation. Our analysis reveals that validation bias is widespread in gene prioritization data and can significantly overestimate the performance of models. This finding elucidates the discrepancy between the reported good performance of models and their limited practical applications.Availability and implementationPython code with examples of application of the validation bias detection algorithm is available at github.com/ArtomovLab/ValidationBias.
| S-EPMC10517638 | biostudies-literature
Project description:We developed MicroKPNN, a prior-knowledge guided interpretable neural network for microbiome-based human host phenotype prediction. The prior knowledge used in MicroKPNN includes the metabolic activities of different bacterial species, phylogenetic relationships, and bacterial community structure, all in a shallow neural network. Application of MicroKPNN to seven gut microbiome datasets (involving five different human diseases including inflammatory bowel disease, type 2 diabetes, liver cirrhosis, colorectal cancer, and obesity) shows that incorporation of the prior knowledge helped improve the microbiome-based host phenotype prediction. MicroKPNN outperformed fully connected neural network-based approaches in all seven cases, with the most improvement of accuracy in the prediction of type 2 diabetes. MicroKPNN outperformed a recently developed deep-learning based approach DeepMicro, which selects the best combination of autoencoder and machine learning approach to make predictions, in all of the seven cases. Importantly, we showed that MicroKPNN provides a way for interpretation of the predictive models. Using importance scores estimated for the hidden nodes, MicroKPNN could provide explanations for prior research findings by highlighting the roles of specific microbiome components in phenotype predictions. In addition, it may suggest potential future research directions for studying the impacts of microbiome on host health and diseases. MicroKPNN is publicly available at https://github.com/mgtools/MicroKPNN.
| S-EPMC10793686 | biostudies-literature
Project description:This SuperSeries is composed of the SubSeries listed below.
2024-10-15 | GSE245484 | GEO
Project description:MotivationIn spite of great success of genome-wide association studies (GWAS), multiple challenges still remain. First, complex traits are often associated with many single nucleotide polymorphisms (SNPs), each with small or moderate effect sizes. Second, our understanding of the functional mechanisms through which genetic variants are associated with complex traits is still limited. To address these challenges, we propose GPA-Tree and it simultaneously implements association mapping and identifies key combinations of functional annotations related to risk-associated SNPs by combining a decision tree algorithm with a hierarchical modeling framework.ResultsFirst, we implemented simulation studies to evaluate the proposed GPA-Tree method and compared its performance with existing statistical approaches. The results indicate that GPA-Tree outperforms existing statistical approaches in detecting risk-associated SNPs and identifying the true combinations of functional annotations with high accuracy. Second, we applied GPA-Tree to a systemic lupus erythematosus (SLE) GWAS and functional annotation data including GenoSkyline and GenoSkylinePlus. The results from GPA-Tree highlight the dysregulation of blood immune cells, including but not limited to primary B, memory helper T, regulatory T, neutrophils and CD8+ memory T cells in SLE. These results demonstrate that GPA-Tree can be a powerful tool that improves association mapping while facilitating understanding of the underlying genetic architecture of complex traits and potential mechanisms linking risk-associated SNPs with complex traits.Availability and implementationThe GPATree software is available at https://dongjunchung.github.io/GPATree/.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC10060690 | biostudies-literature
Project description:Key messageSoftware for high imputation accuracy in soybean was identified. Imputed dataset could significantly reduce the interval of genomic regions controlling traits, thus greatly improve the efficiency of candidate gene identification. Genotype imputation is a strategy to increase marker density of existing datasets without additional genotyping. We compared imputation performance of software BEAGLE 5.0, IMPUTE 5 and AlphaPlantImpute and tested software parameters that may help to improve imputation accuracy in soybean populations. Several factors including marker density, extent of linkage disequilibrium (LD), minor allele frequency (MAF), etc., were examined for their effects on imputation accuracy across different software. Our results showed that AlphaPlantImpute had a higher imputation accuracy than BEAGLE 5.0 or IMPUTE 5 tested in each soybean family, especially if the study progeny were genotyped with an extremely low number of markers. LD extent, MAF and reference panel size were positively correlated with imputation accuracy, a minimum number of 50 markers per chromosome and MAF of SNPs > 0.2 in soybean line were required to avoid a significant loss of imputation accuracy. Using the software, we imputed 5176 soybean lines in the soybean nested mapping population (NAM) with high-density markers of the 40 parents. The dataset containing 423,419 markers for 5176 lines and 40 parents was deposited at the Soybase. The imputed NAM dataset was further examined for the improvement of mapping quantitative trait loci (QTL) controlling soybean seed protein content. Most of the QTL identified were at identical or at similar position based on initial and imputed datasets; however, QTL intervals were greatly narrowed. The resulting genotypic dataset of NAM population will facilitate QTL mapping of traits and downstream applications. The information will also help to improve genotyping imputation accuracy in self-pollinated crops.
| S-EPMC9110473 | biostudies-literature