Search

Abstract Background Understanding the impact of gene interactions on disease phenotypes is increasingly recognised as a crucial aspect of genetic disease research. This trend is reflected by the growing amount of clinical research on oligogenic diseases, where disease manifestations are influenced by combinations of variants on a few specific genes. Although statistical machine-learning methods have been developed to identify relevant genetic variant or gene combinations associated with oligogenic diseases, they rely on abstract features and black-box models, posing challenges to interpretability for medical experts and impeding their ability to comprehend and validate predictions. In this work, we present a novel, interpretable predictive approach based on a knowledge graph that not only provides accurate predictions of disease-causing gene interactions but also offers explanations for these results. Results We introduce BOCK, a knowledge graph constructed to explore disease-causing genetic interactions, integrating curated information on oligogenic diseases from clinical cases with relevant biomedical networks and ontologies. Using this graph, we developed a novel predictive framework based on heterogenous paths connecting gene pairs. This method trains an interpretable decision set model that not only accurately predicts pathogenic gene interactions, but also unveils the patterns associated with these diseases. A unique aspect of our approach is its ability to offer, along with each positive prediction, explanations in the form of subgraphs, revealing the specific entities and relationships that led to each pathogenic prediction. Conclusion Our method, built with interpretability in mind, leverages heterogenous path information in knowledge graphs to predict pathogenic gene interactions and generate meaningful explanations. This not only broadens our understanding of the molecular mechanisms underlying oligogenic diseases, but also presents a novel application of knowledge graphs in creating more transparent and insightful predictors for genetic research.

Abstract Background The prediction of potentially pathogenic variant combinations in patients remains a key task in the field of medical genetics for the understanding and detection of oligogenic/multilocus diseases. Models tailored towards such cases can help shorten the gap of missing diagnoses and can aid researchers in dealing with the high complexity of the derived data. The predictor VarCoPP (Variant Combinations Pathogenicity Predictor) that was published in 2019 and identified potentially pathogenic variant combinations in gene pairs (bilocus variant combinations), was the first important step in this direction. Despite its usefulness and applicability, several issues still remained that hindered a better performance, such as its False Positive (FP) rate, the quality of its training set and its complex architecture. Results We present VarCoPP2.0: the successor of VarCoPP that is a simplified, faster and more accurate predictive model identifying potentially pathogenic bilocus variant combinations. Results from cross-validation and on independent data sets reveal that VarCoPP2.0 has improved in terms of both sensitivity (95% in cross-validation and 98% during testing) and specificity (5% FP rate). At the same time, its running time shows a significant 150-fold decrease due to the selection of a simpler Balanced Random Forest model. Its positive training set now consists of variant combinations that are more confidently linked with evidence of pathogenicity, based on the confidence scores present in OLIDA, the Oligogenic Diseases Database ( https://olida.ibsquare.be ). The improvement of its performance is also attributed to a more careful selection of up-to-date features identified via an original wrapper method. We show that the combination of different variant and gene pair features together is important for predictions, highlighting the usefulness of integrating biological information at different levels. Conclusions Through its improved performance and faster execution time, VarCoPP2.0 enables a more accurate analysis of larger data sets linked to oligogenic diseases. Users can access the ORVAL platform ( https://orval.ibsquare.be ) to apply VarCoPP2.0 on their data.

In recent years, immersive virtual reality technology has emerged in the field of health. Its use could allow the assessment of the motor behavior of individuals in adaptable and reproducible immersive environments, simulating real situations. This study aimed to assess the effect of an immersive scenario on functional mobility during a simple locomotor task according to age. Sixty young adults and 60 older volunteers, who were autonomous and without cognitive and neurological impairment participated. A locomotor task based on the “Timed Up and Go” task was performed in real and virtual conditions. A functional mobility score was calculated by combining the time and the number of steps used and compared between young and older people. Results showed that correlations between time and the number of steps were the same in VR and real conditions, but the locomotor performance decreased significantly in VR for both populations. Additionally, older people exhibited a more reduced locomotor performance in a virtual environment than young adults, thereby their functional mobility score decreased more to complete the task, reflecting the adoption of a more secure locomotion strategy often related to the fear of falling, with an increase in time and number of steps to support balance. The major difference between reality and VR is the visual immersion with an HMD, and visual information is more important in the sensory integration of older people. Therefore, the reduction in visual field and lack of visual exproprioceptive information about the body segments in the virtual environment could explain these results. Finally, the effect of immersion in a virtual scenario on mobility exists for both populations but is accentuated by the aging process and is therefore age dependent.

Immersive virtual reality makes possible to perceive and interact in a standardized, reproductible and digital environment, with a wide range of simulated situations possibilities. This study aimed to measure the potential effect of virtual reality on time and number of steps when performing a locomotor task, in a young adult’s population. Sixty young adults (32W, 28M, mean age 21.55 ± 1.32), who had their first immersive virtual reality experience, performed a locomotor task based on "Timed Up and Go" (TUG) task in real, in virtual reality in a stopped train and in virtual reality in a moving train. Time and number of steps variables representing primary locomotion indicators were measured and compared between each condition. Results showed significant increases in time and number of steps in the two virtual reality conditions compared to real but not between the two virtual reality conditions. There was an effect of virtual reality in young adults when performing the locomotor task. It means that technological and digital characteristics of the immersive virtual reality experience led to modify motor strategies employed. Adding a plausible visual optic flow did not appear to affect motor control further when the information is negligible and not essential for performing the task.

Abstract Background The Critical Assessment of Functional Annotation (CAFA) is an ongoing, global, community-driven effort to evaluate and improve the computational annotation of protein function. Results Here, we report on the results of the third CAFA challenge, CAFA3, that featured an expanded analysis over the previous CAFA rounds, both in terms of volume of data analyzed and the types of analysis performed. In a novel and major new development, computational predictions and assessment goals drove some of the experimental assays, resulting in new functional annotations for more than 1000 genes. Specifically, we performed experimental whole-genome mutation screening in Candida albicans and Pseudomonas aureginosa genomes, which provided us with genome-wide experimental data for genes associated with biofilm formation and motility. We further performed targeted assays on selected genes in Drosophila melanogaster, which we suspected of being involved in long-term memory. Conclusion We conclude that while predictions of the molecular function and biological process annotations have slightly improved over time, those of the cellular component have not. Term-centric prediction of experimental annotations remains equally challenging; although the performance of the top methods is significantly better than the expectations set by baseline methods in C. albicans and D. melanogaster, it leaves considerable room and need for improvement. Finally, we report that the CAFA community now involves a broad range of participants with expertise in bioinformatics, biological experimentation, biocuration, and bio-ontologies, working together to improve functional annotation, computational function prediction, and our ability to manage big data in the era of large experimental screens.