Feature selection approaches are widely used in gene expression data analysis to identify the most relevant features and boost performance in regression and classification tasks. However, such algorithms solely consider each feature’s quantitative contribution to the task, possibly limiting the biological interpretability of the results. Feature-related prior knowledge, such as functional annotations and pathways information, can be incorporated into feature selection algorithms to potentially improve model performance and interpretability. We propose an embedded integrative approach to feature selection that combines weighted LASSO feature selection and prior biological knowledge in a single step, by means of a novel score of biological relevance that summarizes information extracted from popular biological knowledge bases. Findings from the performed experiments indicate that our proposed approach is able to identify the most predictive genes while simultaneously enhancing the biological interpretability of the results compared to the standard LASSO regularized model. Code is available at https://github.com/DEIB-GECO/GIS-weigthed_LASSO Supplementary data are available at Bioinformatics online.
In recent years, data-driven methodologies based on artificial intelligence (AI) technologies are taking the lead in many biomedical fields, including the interpretation of electroencephalogram (EEG) experiments collected by wereable Brain Computer Interfaces (BCI). Yet, the effectiveness of data in medical research hinges significantly on its volume and diversity. Traditional biomedical research faces constraints due to limited access to datasets often confined within individual medical centers, hindering potential breakthroughs. Reluctance to share patient data across institutions is driven by ethical, legal, and privacy concerns, with laws like GDPR rigorously protecting against privacy breaches. Overcoming these obstacles requires a paradigm shift towards decentralized AI training procedures, enabling secure and efficient usage of sensible data. In this work, we examine and evaluate the potential of federated learning for the task of emotion recognition from BCI data, focusing on performance with respect to centralized approaches. Our focus lies on comparing its performance against centralized approaches, delving into key metrics such as accuracy, efficiency, and privacy preservation.
The advancement of computational genomics has significantly enhanced the use of data-driven solutions in disease prediction and precision medicine. Yet, challenges such as data scarcity, privacy constraints, and biases persist. Synthetic data generation offers a promising solution to these issues. However, existing approaches based on generative artificial intelligence often fail to incorporate biological knowledge, limiting the realism and utility of generated samples. In this work, we present BioGAN, a novel generative framework that, for the first time, incorporates graph neural networks into a generative adversarial network architecture for transcriptomic data generation. By leveraging gene regulatory and co-expression networks, our model preserves biological properties in the generated transcriptomic profiles. We validate its effectiveness on E. coli and human gene expression datasets through extensive experiments using unsupervised and supervised evaluation metrics. The results demonstrate that incorporating a priori biological knowledge is an effective strategy for enhancing both the quality and utility of synthetic transcriptomic data. On human data, BioGAN achieves a 4.3% improvement in precision and an up to 2.6% higher correlation with real profiles compared to state-of-the-art models. In downstream disease and tissue classification tasks, our synthetic data improves prediction performance by an average of 5.7%. Results on E. coli further confirm BioGAN’s robustness, showing consistently strong recall and predictive utility.