Machine learning-enhanced noninvasive prenatal testing of monogenic disorders.

OBJECTIVE: Single-nucleotide variants (SNVs) are of great significance in prenatal diagnosis as they are the leading cause of inherited single-gene disorders (SGDs). Identifying SNVs in a non-invasive prenatal screening (NIPS) scenario is particularly challenging for maternally inherited SNVs. We present an improved method to predict inherited SNVs from maternal or paternal origin in a genome-wide manner. METHODS: We performed SNV-NIPS based on the combination of fragments of cell free DNA (cfDNA) features, Bayesian inference and a machine-learning (ML) prediction refinement step using random forest (RF) classifiers trained on millions of non-pathogenic variants. We next evaluate the real-world performance of our refined method in a clinical setting by testing our models on 16 families with singleton pregnancies and varying fetal fraction (FF) levels, and validate the results over millions of inherited variants in each fetus. RESULTS: The average area under the ROC curve (AUC) values are 0.996 over all families for paternally inherited variants, 0.81 for the challenging maternally inherited variants, 0.86 for homozygous biallelic variants and 0.95 for compound heterozygous variants. Discriminative AUCs were achieved even in families with a low FF. We further investigate the performance of our method in correctly predicting SNVs in coding regions of clinically relevant genes and demonstrate significantly improved AUCs in these regions. Finally, we focus on the pathogenic variants in our cohort and show that our method correctly predicts if the fetus is unaffected or affected in all (10/10, 100%) of the families containing a pathogenic SNV. CONCLUSIONS: Overall, we demonstrate our ability to perform genome-wide NIPS for maternal and homozygous biallelic variants and showcase the utility of our method in a clinical setting.

First Community-Wide, Comparative Cross-Linking Mass Spectrometry Study.

The number of publications in the field of chemical cross-linking combined with mass spectrometry (XL-MS) to derive constraints for protein three-dimensional structure modeling and to probe protein-protein interactions has increased during the last years. As the technique is now becoming routine for in vitro and in vivo applications in proteomics and structural biology there is a pressing need to define protocols as well as data analysis and reporting formats. Such consensus formats should become accepted in the field and be shown to lead to reproducible results. This first, community-based harmonization study on XL-MS is based on the results of 32 groups participating worldwide. The aim of this paper is to summarize the status quo of XL-MS and to compare and evaluate existing cross-linking strategies. Our study therefore builds the framework for establishing best practice guidelines to conduct cross-linking experiments, perform data analysis, and define reporting formats with the ultimate goal of assisting scientists to generate accurate and reproducible XL-MS results.

When safeguarding goes wrong: Impact of oxidative stress on protein homeostasis in health and neurodegenerative disorders.

Cellular redox status is an established player in many different cellular functions. The buildup of oxidants within the cell is tightly regulated to maintain a balance between the positive and negative outcomes of cellular oxidants. Proteins are highly sensitive to oxidation, since modification can cause widespread unfolding and the formation of toxic aggregates. In response, cells have developed highly regulated systems that contribute to the maintenance of both the global redox status and protein homeostasis at large. Changes to these systems have been found to correlate with aging and age-related disorders, such as neurodegenerative pathologies. This raises intriguing questions as to the source of the imbalance in the redox and protein homeostasis systems, their interconnectivity, and their role in disease progression. Here we focus on the crosstalk between the redox and protein homeostasis systems in neurodegenerative diseases, specifically in Alzheimer's, Parkinson's, and ALS. We elaborate on some of the main players of the stress response systems, including the master regulators of oxidative stress and the heat shock response, Nrf2 and Hsf1, which are essential features of protein folding, and mediators of protein turnover. We illustrate the elegant mechanisms used by these components to provide an immediate response, including protein plasticity controlled by redox-sensing cysteines and the recruitment of naive proteins to the redox homeostasis array that act as chaperons in an ATP-independent manner.