Musculoskeletal Computed Tomography: How to Add Value When Reporting Adult Lower Limb Trauma.

Computed tomography plays an ever-increasing role in the management of fractures and dislocations due to its capability in efficiently providing multiplanar reformats and 3-dimensional volume rendered images. It can reveal findings that are occult on plain radiography and therefore allow for more accurate decision making with regard to fracture classification and management. Clinical radiologists play a critical role in facilitating the processing of imaging to provide adequate image reformats in the desired planes, producing 3 dimensional images but most crucially identifying pertinent findings, which will contribute between the selection of nonoperative and operative management and potentially influence surgical technique.

Deriving Mendelian Randomization-based Causal Networks of Brain Imaging Phenotypes and Bipolar Disorder.

Neuroanatomical variation in individuals with bipolar disorder (BD) has been previously described in observational studies. However, the causal dynamics of these relationships remain unexplored. We performed Mendelian Randomization of 297 structural and functional neuroimaging phenotypes from the UK BioBank and BD using genome-wide association study summary statistics.

Leveraging functional annotations to map rare variants associated with Alzheimer's disease with gruyere.

The increasing availability of whole-genome sequencing (WGS) has begun to elucidate the contribution of rare variants (RVs), both coding and non-coding, to complex disease. Multiple RV association tests are available to study the relationship between genotype and phenotype, but most are restricted to per-gene models and do not fully leverage the availability of variant-level functional annotations. We propose Genome-wide Rare Variant EnRichment Evaluation (gruyere), a Bayesian probabilistic model that complements existing methods by learning global, trait-specific weights for functional annotations to improve variant prioritization.

Vector embeddings by sequence similarity and context for improved compression, similarity search, clustering, organization, and manipulation of cDNA libraries.

This paper demonstrates the utility of organized numerical representations of genes in research involving flat string gene formats (i.e., FASTA/FASTQ).

Disentangling Interpretable Factors with Supervised Independent Subspace Principal Component Analysis.

The success of machine learning models relies heavily on effectively representing high-dimensional data. However, ensuring data representations capture human-understandable concepts remains difficult, often requiring the incorporation of prior knowledge and decomposition of data into multiple subspaces. Traditional linear methods fall short in modeling more than one space, while more expressive deep learning approaches lack interpretability.