NGSEP 4: Efficient and accurate identification of orthogroups and whole-genome alignment.

Whole-genome alignment allows researchers to understand the genomic structure and variation among genomes. Approaches based on direct pairwise comparisons of DNA sequences require large computational capacities. As a consequence, pipelines combining tools for orthologous gene identification and synteny have been developed. In this manuscript, we present the latest functionalities implemented in NGSEP 4, to identify orthogroups and perform whole genome alignments. NGSEP implements functionalities for identification of clusters of homologus genes, synteny analysis and whole genome alignment. Our results showed that the NGSEP algorithm for orthogroups identification has competitive accuracy and efficiency in comparison to commonly used tools. The implementation also includes a visualization of the whole genome alignment based on synteny of the orthogroups that were identified, and a reconstruction of the pangenome based on frequencies of the orthogroups among the genomes. NGSEP 4 also includes a new graphical user interface based on the JavaFX technology. We expect that these new developments will be very useful for several studies in evolutionary biology and population genomics.

Machine learning models for accurate prioritization of variants of uncertain significance.

The growing use of next-generation sequencing technologies on genetic diagnosis has produced an exponential increase in the number of variants of uncertain significance (VUS). In this manuscript, we compare three machine learning methods to classify VUS as Pathogenic or No pathogenic, implementing a Random Forest (RF), a Support Vector Machine (SVM), and a Multilayer Perceptron. To train the models, we extracted high-quality variants from ClinVar that were previously classified as VUS. For each variant, we retrieved nine conservation scores, the loss-of-function tool, and allele frequencies. For the RF and SVM models, hyperparameters were tuned using cross-validation with a grid search. The three models were tested on a nonoverlapping set of variants that had been classified as VUS over the last 3 years, but had been reclassified in August 2020. The three models yielded superior accuracy on this set compared to the benchmarked tools. The RF-based model yielded the best performance across different variant types and was used to create VusPrize, an open-source software tool for prioritization of VUS. We believe that our model can improve the process of genetic diagnosis in research and clinical settings.