By identifying somatic mutations, whole-exome sequencing (WES) has become a technology of choice for the diagnosis and guiding treatment decisions in many cancers. Despite advances in the field of somatic variant detection and the emergence of sophisticated tools incorporating machine learning, accurately identifying somatic variants remains challenging. Each new somatic variant caller is often accompanied by claims of superior performance compared to predecessors. Furthermore, most comparative studies focus on a limited set of tools and reference datasets, leading to inconsistent results and making it difficult for laboratories to select the optimal solution. Our study comprehensively evaluated 20 somatic variant callers across four reference WES datasets. We subsequently assessed the performance of ensemble approaches by exploring all possible combinations of these callers, generating 8178 and 1013 combinations for single-nucleotide variants (SNVs) and indels, respectively, with varying voting thresholds. Our analysis identified five high-performing individual somatic variant callers: Muse, Mutect2, Dragen, TNScope, and NeuSomatic. For somatic SNVs, an ensemble combining LoFreq, Muse, Mutect2, SomaticSniper, Strelka, and Lancet outperformed the top-performing caller (Dragen) by >3.6% (mean F1 score = 0.927). Similarly, for somatic indels, an ensemble of Mutect2, Strelka, Varscan2, and Pindel outperformed the best individual caller (Neusomatic) by >3.5% (mean F1 score = 0.867). By considering the computational costs of each combination, we were able to identify an optimal solution involving four somatic variant callers, Muse, Mutect2, and Strelka for the SNVs and Mutect2, Strelka, and Varscan2 for the indels, enabling accurate and cost-effective somatic variant detection in whole exome.

Cytometry enables precise single-cell phenotyping within heterogeneous populations. These cell types are traditionally annotated via manual gating, but this method lacks reproducibility and sensitivity to batch effect. Also, the most recent cytometers-spectral flow or mass cytometers-create rich and high-dimensional data whose analysis via manual gating becomes challenging and time-consuming. To tackle these limitations, we introduce Scyan https://github.com/MICS-Lab/scyan, a Single-cell Cytometry Annotation Network that automatically annotates cell types using only prior expert knowledge about the cytometry panel. For this, it uses a normalizing flow-a type of deep generative model-that maps protein expressions into a biologically relevant latent space. We demonstrate that Scyan significantly outperforms the related state-of-the-art models on multiple public datasets while being faster and interpretable. In addition, Scyan overcomes several complementary tasks, such as batch-effect correction, debarcoding and population discovery. Overall, this model accelerates and eases cell population characterization, quantification and discovery in cytometry.

Coronavirus disease 2019 (COVID-19) emerged in 2019 and disseminated around the world rapidly. Computed tomography (CT) imaging has been proven to be an important tool for screening, disease quantification and staging. The latter is of extreme importance for organizational anticipation (availability of intensive care unit beds, patient management planning) as well as to accelerate drug development through rapid, reproducible and quantified assessment of treatment response. Even if currently there are no specific guidelines for the staging of the patients, CT together with some clinical and biological biomarkers are used. In this study, we collected a multi-center cohort and we investigated the use of medical imaging and artificial intelligence for disease quantification, staging and outcome prediction. Our approach relies on automatic deep learning-based disease quantification using an ensemble of architectures, and a data-driven consensus for the staging and outcome prediction of the patients fusing imaging biomarkers with clinical and biological attributes. Highly promising results on multiple external/independent evaluation cohorts as well as comparisons with expert human readers demonstrate the potentials of our approach.

UNLABELLED: We present rCGH, a comprehensive array-based comparative genomic hybridization analysis workflow, integrating computational improvements and functionalities specifically designed for precision medicine. rCGH supports the major microarray platforms, ensures a full traceability and facilitates profiles interpretation and decision-making through sharable interactive visualizations. AVAILABILITY AND IMPLEMENTATION: The rCGH R package is available on bioconductor (under Artistic-2.0). The aCGH-viewer is available at https://fredcommo.shinyapps.io/aCGH_viewer, and the application implementation is freely available for installation at https://github.com/fredcommo/aCGH_viewer CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: DNA microarray technology has emerged as a major tool for exploring cancer biology and solving clinical issues. Predicting a patient's response to chemotherapy is one such issue; successful prediction would make it possible to give patients the most appropriate chemotherapy regimen. Patient response can be classified as either a pathologic complete response (PCR) or residual disease (NoPCR), and these strongly correlate with patient outcome. Microarrays can be used as multigenic predictors of patient response, but probe selection remains problematic. In this study, each probe set was considered as an elementary predictor of the response and was ranked on its ability to predict a high number of PCR and NoPCR cases in a ratio similar to that seen in the learning set. We defined a valuation function that assigned high values to probe sets according to how different the expression of the genes was and to how closely the relative proportions of PCR and NoPCR predictions to the proportions observed in the learning set was. Multigenic predictors were designed by selecting probe sets highly ranked in their predictions and tested using several validation sets. RESULTS: Our method defined three types of probe sets: 71% were mono-informative probe sets (59% predicted only NoPCR, and 12% predicted only PCR), 25% were bi-informative, and 4% were non-informative. Using a valuation function to rank the probe sets allowed us to select those that correctly predicted the response of a high number of patient cases in the training set and that predicted a PCR/NoPCR ratio for validation sets that was similar to that of the whole learning set. Based on DLDA and the nearest centroid method, bi-informative probes proved more successful predictors than probes selected using a t test. CONCLUSION: Prediction of the response to breast cancer preoperative chemotherapy was significantly improved by selecting DNA probe sets that were successful in predicting outcomes for the entire learning set, both in terms of accurately predicting a high number of cases and in correctly predicting the ratio of PCR to NoPCR cases.