Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing最新文献

Cells consist of large components, such as organelles, that recursively factor into smaller systems, such as condensates and protein complexes, forming a dynamic multi-scale structure of the cell. Recent technological innovations have paved the way for systematic interrogation of subcellular structures, yielding unprecedented insights into their roles and interactions. In this workshop, we discuss progress, challenges, and collaboration to marshal various computational approaches toward assembling an integrated structural map of the human cell.

Mild cognitive impairment (MCI) represents the early stage of dementia including Alzheimer's disease (AD) and is a crucial stage for therapeutic interventions and treatment. Early detection of MCI offers opportunities for early intervention and significantly benefits cohort enrichment for clinical trials. Imaging and in vivo markers in plasma and cerebrospinal fluid biomarkers have high detection performance, yet their prohibitive costs and intrusiveness demand more affordable and accessible alternatives. The recent advances in digital biomarkers, especially language markers, have shown great potential, where variables informative to MCI are derived from linguistic and/or speech and later used for predictive modeling. A major challenge in modeling language markers comes from the variability of how each person speaks. As the cohort size for language studies is usually small due to extensive data collection efforts, the variability among persons makes language markers hard to generalize to unseen subjects. In this paper, we propose a novel subject harmonization tool to address the issue of distributional differences in language markers across subjects, thus enhancing the generalization performance of machine learning models. Our empirical results show that machine learning models built on our harmonized features have improved prediction performance on unseen data. The source code and experiment scripts are available at https://github.com/illidanlab/subject_harmonization.

The advent of spatial transcriptomics technologies has heralded a renaissance in research to advance our understanding of the spatial cellular and transcriptional heterogeneity within tissues. Spatial transcriptomics allows investigation of the interplay between cells, molecular pathways, and the surrounding tissue architecture and can help elucidate developmental trajectories, disease pathogenesis, and various niches in the tumor microenvironment. Photoaging is the histological and molecular skin damage resulting from chronic/acute sun exposure and is a major risk factor for skin cancer. Spatial transcriptomics technologies hold promise for improving the reliability of evaluating photoaging and developing new therapeutics. Challenges to current methods include limited focus on dermal elastosis variations and reliance on self-reported measures, which can introduce subjectivity and inconsistency. Spatial transcriptomics offers an opportunity to assess photoaging objectively and reproducibly in studies of carcinogenesis and discern the effectiveness of therapies that intervene in photoaging and preventing cancer. Evaluation of distinct histological architectures using highly-multiplexed spatial technologies can identify specific cell lineages that have been understudied due to their location beyond the depth of UV penetration. However, the cost and interpatient variability using state-of-the-art assays such as the 10x Genomics Spatial Transcriptomics assays limits the scope and scale of large-scale molecular epidemiologic studies. Here, we investigate the inference of spatial transcriptomics information from routine hematoxylin and eosin-stained (H&E) tissue slides. We employed the Visium CytAssist spatial transcriptomics assay to analyze over 18,000 genes at a 50-micron resolution for four patients from a cohort of 261 skin specimens collected adjacent to surgical resection sites for basal cell and squamous cell keratinocyte tumors. The spatial transcriptomics data was co-registered with 40x resolution whole slide imaging (WSI) information. We developed machine learning models that achieved a macro-averaged median AUC and F1 score of 0.80 and 0.61 and Spearman coefficient of 0.60 in inferring transcriptomic profiles across the slides, and accurately captured biological pathways across various tissue architectures.

The following sections are included:OverviewDealing with the lack of diversity in current research datasetsDevelopment of fair machine learning algorithmsRace, genetic ancestry, and population structureConclusionAcknowledgments.

The availability of multiple publicly-available datasets studying the same phenomenon has the promise of accelerating scientific discovery. Meta-analysis can address issues of reproducibility and often increase power. The promise of meta-analysis is especially germane to rarer diseases like cystic fibrosis (CF), which affects roughly 100,000 people worldwide. A recent search of the National Institute of Health's Gene Expression Omnibus revealed 1.3 million data sets related to cancer compared to about 2,000 related to CF. These studies are highly diverse, involving different tissues, animal models, treatments, and clinical covariates. In our search for gene expression studies of primary human airway epithelial cells, we identified three studies with compatible methodologies and sufficient metadata: GSE139078, Sala Study, and PRJEB9292. Even so, experimental designs were not identical, and we identified significant batch effects that would have complicated functional analysis. Here we present quantile discretization and Bayesian network construction using the Hill climb method as a powerful tool to overcome experimental differences and reveal biologically relevant responses to the CF genotype itself, exposure to virus, bacteria, and drugs used to treat CF. Functional patterns revealed by cluster Profiler included interferon signaling, interferon gamma signaling, interleukins 4 and 13 signaling, interleukin 6 signaling, interleukin 21 signaling, and inactivation of CSF3/G-CSF signaling pathways showing significant alterations. These pathways were consistently associated with higher gene expression in CF epithelial cells compared to non-CF cells, suggesting that targeting these pathways could improve clinical outcomes. The success of quantile discretization and Bayesian network analysis in the context of CF suggests that these approaches might be applicable to other contexts where exactly comparable data sets are hard to find.

Functional brain networks represent dynamic and complex interactions among anatomical regions of interest (ROIs), providing crucial clinical insights for neural pattern discovery and disorder diagnosis. In recent years, graph neural networks (GNNs) have proven immense success and effectiveness in analyzing structured network data. However, due to the high complexity of data acquisition, resulting in limited training resources of neuroimaging data, GNNs, like all deep learning models, suffer from overfitting. Moreover, their capability to capture useful neural patterns for downstream prediction is also adversely affected. To address such challenge, this study proposes BrainSTEAM, an integrated framework featuring a spatio-temporal module that consists of an EdgeConv GNN model, an autoencoder network, and a Mixup strategy. In particular, the spatio-temporal module aims to dynamically segment the time series signals of the ROI features for each subject into chunked sequences. We leverage each sequence to construct correlation networks, thereby increasing the training data. Additionally, we employ the EdgeConv GNN to capture ROI connectivity structures, an autoencoder for data denoising, and mixup for enhancing model training through linear data augmentation. We evaluate our framework on two real-world neuroimaging datasets, ABIDE for Autism prediction and HCP for gender prediction. Extensive experiments demonstrate the superiority and robustness of BrainSTEAM when compared to a variety of existing models, showcasing the strong potential of our proposed mechanisms in generalizing to other studies for connectome-based fMRI analysis.

There is a desire in research to move away from the concept of race as a clinical factor because it is a societal construct used as an imprecise proxy for geographic ancestry. In this study, we leverage the biobank from Vanderbilt University Medical Center, BioVU, to investigate relationships between genetic ancestry proportion and the clinical phenome. For all samples in BioVU, we calculated six ancestry proportions based on 1000 Genomes references: eastern African (EAFR), western African (WAFR), northern European (NEUR), southern European (SEUR), eastern Asian (EAS), and southern Asian (SAS). From PheWAS, we found phecode categories significantly enriched neoplasms for EAFR, WAFR, and SEUR, and pregnancy complication in SEUR, NEUR, SAS, and EAS (p < 0.003). We then selected phenotypes hypertension (HTN) and atrial fibrillation (AFib) to further investigate the relationships between these phenotypes and EAFR, WAFR, SEUR, and NEUR using logistic regression modeling and non-linear restricted cubic spline modeling (RCS). For EAS and SAS, we chose renal failure (RF) for further modeling. The relationships between HTN and AFib and the ancestries EAFR, WAFR, and SEUR were best fit by the linear model (beta p < 1x10-4 for all) while the relationships with NEUR were best fit with RCS (HTN ANOVA p = 0.001, AFib ANOVA p < 1x10-4). For RF, the relationship with SAS was best fit with a linear model (beta p < 1x10-4) while RCS model was a better fit for EAS (ANOVA p < 1x10-4). In this study, we identify relationships between genetic ancestry and phenotypes that are best fit with non-linear modeling techniques. The assumption of linearity for regression modeling is integral for proper fitting of a model and there is no knowing a priori to modeling if the relationship is truly linear.

Classical machine learning and deep learning models for Computer-Aided Diagnosis (CAD) commonly focus on overall classification performance, treating misclassification errors (false negatives and false positives) equally during training. This uniform treatment overlooks the distinct costs associated with each type of error, leading to suboptimal decision-making, particularly in the medical domain where it is important to improve the prediction sensitivity without significantly compromising overall accuracy. This study introduces a novel deep learning-based CAD system that incorporates a cost-sensitive parameter into the activation function. By applying our methodologies to two medical imaging datasets, our proposed study shows statistically significant increases of 3.84% and 5.4% in sensitivity while maintaining overall accuracy for Lung Image Database Consortium (LIDC) and Breast Cancer Histological Database (BreakHis), respectively. Our findings underscore the significance of integrating cost-sensitive parameters into future CAD systems to optimize performance and ultimately reduce costs and improve patient outcomes.

This study quantifies health outcome disparities in invasive Methicillin-Resistant Staphylococcus aureus (MRSA) infections by leveraging a novel artificial intelligence (AI) fairness algorithm, the Fairness-Aware Causal paThs (FACTS) decomposition, and applying it to real-world electronic health record (EHR) data. We spatiotemporally linked 9 years of EHRs from a large healthcare provider in Florida, USA, with contextual social determinants of health (SDoH). We first created a causal structure graph connecting SDoH with individual clinical measurements before/upon diagnosis of invasive MRSA infection, treatments, side effects, and outcomes; then, we applied FACTS to quantify outcome potential disparities of different causal pathways including SDoH, clinical and demographic variables. We found moderate disparity with respect to demographics and SDoH, and all the top ranked pathways that led to outcome disparities in age, gender, race, and income, included comorbidity. Prior kidney impairment, vancomycin use, and timing were associated with racial disparity, while income, rurality, and available healthcare facilities contributed to gender disparity. From an intervention standpoint, our results highlight the necessity of devising policies that consider both clinical factors and SDoH. In conclusion, this work demonstrates a practical utility of fairness AI methods in public health settings.

The problem of microdissection of heterogeneous tissue samples is of great interest for both fundamental biology and biomedical research. Until now, microdissection in the form of supervised deconvolution of mixed sequencing samples has been limited to assays measuring gene expression (RNA-seq) or chromatin accessibility (ATAC-seq). We present here the first attempt at solving the supervised deconvolution problem for run-on nascent sequencing data (GRO-seq and PRO-seq), a readout of active transcription. Then, we develop a novel filtering method suited to the mixed set of promoter and enhancer regions provided by nascent sequencing, and apply best-practice standards from the RNA-seq literature, using in-silico mixtures of cells. Using these methods, we find that enhancer RNAs are highly informative features for supervised deconvolution. In most cases, simple deconvolution methods perform better than more complex ones for solving the nascent deconvolution problem. Furthermore, undifferentiated cell types confound deconvolution of nascent sequencing data, likely as a consequence of transcriptional activity over the highly open chromatin regions of undifferentiated cell types. Our results suggest that while the problem of nascent deconvolution is generally tractable, stronger approaches integrating other sequencing protocols may be required to solve mixtures containing undifferentiated celltypes.