SUMMARY: Structural variants (SVs) are key drivers of genetic variation and disease in the genome. Their discovery remains challenging, however, in large part due to the scarcity of validated SV callsets and comprehensive benchmarks, which are essential for method development and evaluation. The growing number of data-driven learning-based approaches for SV discovery, in particular, requires large, diverse, and well-balanced training datasets to achieve reliable performance. To address this need, SV simulation has served as a key tool for assessing method performance and training SV models. However, existing SV simulators only support a fixed and limited set of SV classes and do not provide fine-grained control over the placement of SVs within specific contexts of the genome. Here we present insilicoSV, a versatile framework for SV simulation, which models SVs using a simple and flexible grammar, allowing users to easily define standard and custom arbitrary genome rearrangements, as well as encode genome placement constraints. This design allows insilicoSV to naturally support new and bespoke SV types, such as the complex rearrangements of cancer genomes. In addition to grammar-based modeling, insilicoSV provides built-in support for 26 predefined SV types, placement of user-provided SVs, small variant simulation, streamlined workflows for the simulation of genome evolution and genome mixtures, read simulation, alignment, and visualization. These features enable the creation of comprehensive genomic datasets for a variety of downstream applications, such as in-depth benchmarking of alignment and variant calling methods, as well as training of data-driven learning-based approaches for SV detection. AVAILABILITY AND IMPLEMENTATION: insilicoSV is available under the MIT license at https://github.com/PopicLab/insilicoSV and https://doi.org/10.5281/zenodo.17402009.

MOTIVATION: A major hindrance towards using Machine Learning (ML) on medical datasets is the discrepancy between a large number of variables and small sample sizes. While multiple feature selection techniques have been proposed to avoid the resulting overfitting, overall ensemble techniques offer the best selection robustness. Yet, current methods designed to combine different algorithms generally fail to leverage the dependencies identified by their components. Here, we propose Graphical Ensembling (GE), a graph-theory-based ensemble feature selection technique designed to improve the stability and relevance of the selected features. RESULTS: Relying on four datasets, we show that GE increases classification performance with fewer selected features. For example, on rheumatoid arthritis patient stratification, GE outperforms the baseline methods by 9% Balanced Accuracy while relying on fewer features. We use data on sub-cellular networks to show that the selected features (proteins) are closer to the known disease genes, and the uncovered biological mechanisms are more diversified. By successfully tackling the complex correlations between biological variables, we anticipate that GE will improve the medical applications of ML. AVAILABILITY AND IMPLEMENTATION: https://github.com/ebattistella/auto_machine_learning.

Exploring and identifying a good feature representation to describe high-dimensional datasets is a challenge of prime importance. However, plenty of feature selection techniques and distance metrics exist, which entails an intricacy for identifying the one best suited to the task. This paper provides an algorithm to design high-order distance metrics over a sparse selection of features dedicated to classification. Our approach is based on Conditional Random Field (CRF) energy minimization and Dual Decomposition, which allow efficiency and great flexibility in the considered features. The optimization technique ensures the tractability of high-dimensionality problems using hundreds of features and samples. Our approach is evaluated on synthetic data as well as on Covid-19 patient stratification. Comparisons with state-of-the-art baselines and our proposed method on different classification results prove the learned metric’s relevance.

Precision medicine is a paradigm shift in healthcare relying heavily on genomics data. However, the complexity of biological interactions, the large number of genes as well as the lack of comparisons on the analysis of data, remain a tremendous bottleneck regarding clinical adoption. In this paper, we introduce a novel, automatic and unsupervised framework to discover low-dimensional gene biomarkers. Our method is based on the LP-Stability algorithm, a high dimensional center-based unsupervised clustering algorithm. It offers modularity as concerns metric functions and scalability, while being able to automatically determine the best number of clusters. Our evaluation includes both mathematical and biological criteria to define a quantitative metric. The recovered signature is applied to a variety of biological tasks, including screening of biological pathways and functions, and characterization relevance on tumor types and subtypes. Quantitative comparisons among different distance metrics, commonly used clustering methods and a referential gene signature used in the literature, confirm state of the art performance of our approach. In particular, our signature, based on 27 genes, reports at least 30 times better mathematical significance (average Dunn's Index) and 25% better biological significance (average Enrichment in Protein-Protein Interaction) than those produced by other referential clustering methods. Finally, our signature reports promising results on distinguishing immune inflammatory and immune desert tumors, while reporting a high balanced accuracy of 92% on tumor types classification and averaged balanced accuracy of 68% on tumor subtypes classification, which represents, respectively 7% and 9% higher performance compared to the referential signature.

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.

In this study, we propose a 3D deep neural network called U-ReSNet, a joint framework that can accurately register and segment medical volumes. The proposed network learns to automatically generate linear and elastic deformation models, trained by minimizing the mean square error and the local cross correlation similarity metrics. In parallel, a coupled architecture is integrated, seeking to provide segmentation maps for anatomies or tissue patterns using an additional decoder part trained with the dice coefficient metric. U-ReSNet is trained in an end to end fashion, while due to this joint optimization the generated network features are more informative leading to promising results compared to other deep learning-based methods existing in the literature. We evaluated the proposed architecture using the publicly available OASIS 3 dataset, measuring the dice coefficient metric for both registration and segmentation tasks. Our promising results indicate the potentials of our method which is composed from a convolutional architecture that is extremely simple and light in terms of parameters.