Early prediction of circulatory failure in the intensive care unit using machine learning | Nature Medicine
Intensive-care clinicians are presented with large quantities of measurements from multiple monitoring systems. Researchers used machine learning to develop an early-warning system that integrates measurements from multiple organ systems using a high-resolution database with 240 patient-years of data. It predicts 90% of circulatory-failure events in the test set, with 82% identified more than 2 h in advance, resulting in an area under the receiver operating characteristic curve of 0.94 and an area under the precision-recall curve of 0.63.
ProteoClade: A taxonomic toolkit for multi-species and metaproteomic analysis | PLOS Computational Biology
ProteoClade is a Python toolkit that performs taxa-specific peptide assignment, protein inference, and quantitation for multi-species proteomics experiments. ProteoClade scales to hundreds of millions of protein sequences, requires minimal computational resources, and is open source, multi-platform, and accessible to non-programmers.
A framework for transcriptome-wide association studies in breast cancer in diverse study populations | Genome Biology
The relationship between germline genetic variation and breast cancer survival is largely unknown, especially in understudied minority populations who often have poorer survival. Genome-wide association studies (GWAS) have interrogated breast cancer survival but often are underpowered due to subtype heterogeneity and clinical covariates and detect loci in non-coding regions that are difficult to interpret. Transcriptome-wide association studies (TWAS) show increased power in detecting functionally relevant loci by leveraging expression quantitative trait loci (eQTLs) from external reference panels in relevant tissues. Researchers provide a framework for TWAS for breast cancer in diverse populations, using data from the Carolina Breast Cancer Study (CBCS), a population-based cohort that oversampled black women.