Biology subjects

Sheffield, N.

Publications and source records attributed to Sheffield, N..

4 recordsLinked to original sources

bioRxiv2024

AI-readiness for Biomedical Data: Bridge2AI Recommendations

Biomedical research is rapidly adopting artificial intelligence (AI). Yet the inherent complexity of biomedical data preparation requires implementing actionable, robust criteria for ethical and explainable AI (XAI) at the "pre-model" stage, encompassing data acquisition, detailed transformations, and ethical governance. Simple conformance to FAIR (Findable, Accessible, Interoperable, Reusable) Principles is insufficient. Here, we define criteria and practices for reliable AI-readiness of biomedical data, developed by the NIH Bridge to Artificial Intelligence (Bridge2AI) Standards Working Group across seven core dimensions of dataset AI-readiness: FAIRness, Provenance, Characterization, Ethics, Pre-model Explainability, Sustainability, and Computability. Conformance to these criteria provides a basis for pre-model scientific rigor and ethical integrity, mitigating downstream risks of bias and error prior to AI modeling. We apply and evaluate these standards across all four Bridge2AI flagship datasets, spanning functional genomics to clinical medicine, and encode them in machine-actionable metadata bound to the datasets. This framework sets a benchmark for preparing ethical, reusable datasets in biomedical AI and provides standardized methods for reliable pre-model data evaluation.

bioinformatics↗

bioRxiv2022

Integrative single-cell meta-analysis reveals disease-relevant vascular cell states and markers in human atherosclerosis

Coronary artery disease (CAD) and atherosclerosis are characterized by plaque formation in the arteries wall. CAD progression involves complex interactions and phenotypic plasticity within and between distinct vascular and immune cell lineages. Single-cell RNA-seq (scRNA-seq) studies have highlighted lineage-specific transcriptomic signatures, but the reported cell phenotypes in humans remain controversial. Here, we meta-analyzed four scRNA-seq datasets, creating the first map of human cell diversity in atherosclerosis. We generated an atlas of 118,578 high-quality cells, characterized cell-type diversity and provided insights into smooth muscle cell (SMC) phenotypic modulation, transcription factor activity and cell-cell communication. We integrated genome-wide association study (GWAS) data and uncovered a critical role for modulated SMC phenotypes in CAD and coronary calcification. Finally, we identified candidate markers of fibromyocyte and fibrochondrogenic human SMCs (LTBP1 and CRTAC1) that may serve as proxies of atherosclerosis progression. Altogether, we created a unified cellular map of atherosclerosis informing cell state-specific mechanistic and translational studies of cardiovascular diseases.

genomics↗

bioRxiv2019

Augmented Interval List: a novel data structure for efficient genomic interval search

MotivationGenomic data is frequently stored as segments or intervals. Because this data type is so common, interval-based comparisons are fundamental to genomic analysis. As the volume of available genomic data grows, developing efficient and scalable methods for searching interval data is necessary.\n\nResultsWe present a new data structure, the augmented interval list (AIList), to enumerate intersections between a query interval q and an interval set R. An AIList is constructed by first sorting R as a list by the interval start coordinate, then decomposing it into a few approximately flattened components (sublists), and then augmenting each sublist with the running maximum interval end. The query time for AIList is O(log2N + n + m), where n is the number of overlaps between R and q, N is the number of intervals in the set R, and m is the average number of extra comparisons required to find the n overlaps. Tested on real genomic interval datasets, AIList code runs 5 - 18 times faster than standard high-performance code based on augmented interval-trees (AITree), nested containment lists (NCList), or R-trees (BEDTools). For large datasets, the memory-usage for AIList is 4% - 60% of other methods. The AIList data structure, therefore, provides a significantly improved fundamental operation for highly scalable genomic data analysis.\n\nAvailabilityAn implementation of the AIList data structure with both construction and search algorithms is available at code.databio.org/AIList.

bioinformatics↗

bioRxiv2018

BART: a transcription factor prediction tool with query gene sets or epigenomic profiles

SummaryIdentification of functional transcription factors that regulate a given gene set is an important problem in gene regulation studies. Conventional approaches for identifying transcription factors, such as DNA sequence motif analysis, are unable to predict functional binding of specific factors and not sensitive to detect factors binding at distal enhancers. Here we present Binding Analysis for Regulation of Transcription (BART), a novel computational method and software package for predicting functional transcription factors that regulate a query gene set or associate with a query genomic profile, based on more than 6,000 existing ChIP-seq datasets for over 400 factors in human or mouse. This method demonstrates the advantage of utilizing publicly available data for functional genomics research.\n\nAvailabilityBART is implemented in Python and available at http://faculty.virginia.edu/zanglab/bart\n\nContact: zang@virginia.edu

bioinformatics↗