The integration of deep learning (DL) with multi-omics data has significantly advanced our understanding of biological systems, particularly in cancer research. DL enables the analysis of high-dimensional datasets and the discovery of novel disease mechanisms and biomarkers, contributing to improved patient treatment and management. This review provides a detailed overview of recent developments in deep learning models applied to genomics data, with a focus on cancer type classification, driver gene identification, survival analysis, and drug response prediction. We introduce the foundational concepts of machine and deep learning and explain the characteristics of multi-omics data, addressing a broad and interdisciplinary audience. Methods published since 2020 are systematically reviewed, including their model architectures, datasets, and key innovations.

Several computational pipelines for biomedical data have been proposed to stratify patients and to predict their prognosis through survival analysis. However, these analyses are usually performed independently, without integrating the information derived from each of them. Clustering of survival data is an underexplored problem, and current approaches are limited for biomedical applications, whose data are usually heterogeneous and multimodal, with poor scalability for high-dimensionality. We introduce VAE-Surv, a multimodal computational framework for patients' stratification and prognosis prediction. VAE-Surv integrates a Variational Autoencoder (VAE), which reduces the high-dimensional space characterizing the molecular data, with a deep survival model, which combines the embedded information with the clinical features. The VAE embedding step prioritizes local coherence within the feature space to detect potential nonlinear relationships among the molecular markers. The latent representation is then exploited to perform K-means clustering. To test the clinical robustness of the algorithm, VAE-Surv was applied to the Genomed4all cohort of Myelodysplastic Syndromes (MDS), comparing the identified subtypes with the World Health Organization (WHO) classification. The survival outcome was compared with the state-of-the-art Cox model and its penalized versions. Finally, to assess the generalizability of the results, the method was also validated on an external MDS cohort. Tested on 2,043 patients in the GenomMed4All cohort, VAE-Surv achieved a median C-index of 0.78, outperforming classical approaches. In addition, the latent space enhanced the clustering performance compared to a traditional approach that applies the clustering directly to the input data. Compared to the WHO 2016 MDS subtypes, the analysis of the identified clusters showed that the proposed framework can capture existing clinical categorizations while also suggesting novel, data-driven patient groups. Even tested in an external MDS cohort of 2,384 patients, VAE-Surv achieved a good prediction performance (median C-index=0.74), preserving the interpretability of the main clinical and genetic features. VAE-Surv enables automatic identification of patients' clusters, while outperforming the traditional CoxPH model in survival prediction tasks at the same time. Applied to MDS use case, the obtained genetic-based clusters exhibit a clear survival stratification, and the application of the clinical information allowed high performance in prognosis prediction.

Introduction: An evidence-based selection between fractional flow reserve (FFR) and optical coherence tomography (OCT) to drive percutaneous coronary intervention is still lacking. Methods: Patients enrolled in the Fractional Flow Reserve vs. Optical Coherence Tomography to Guide Revascularization of Intermediate Coronary Stenoses (FORZA) trial and in the OCT-Features Of moRphology, coMposItion anD instABility of culprit and not culprit coronary pLaquE in ACS patient (OCT-FORMIDABLE) registry were included. Target vessel revascularisation (TVR) and major adverse cardiac events (MACE), a composite endpoint of cardiac death, myocardial infarction (MI) and TVR were considered as coprimary endpoints. Phenomapping with clustering was performed: incidence of outcomes according to FFR and OCT was explored. Results: 405 patients were treated according to OCT and 405 to FFR. Three different clusters were identified. 48% of the patients were included in the first cluster, presenting mainly with stable angina and a relevant burden of risk factors (cardiovascular risk factors, CVRFs). 21% of the patients were included in the second cluster, presenting with ST segment elevation MI (STEMI) and with low rates of CVRFs. 31% of the patients, being admitted mostly for non-STEMI (NSTEMI) and with high rates of CVRFs, were included in the third cluster. FFR and OCT performed similarly in terms of MACE and TVR in the first cluster. In the second cluster, rates of MACE were lower in the OCT arm (3% vs 12%, p 0.04), mainly driven by TVR (2% vs 6%, p 0.18). In the third cluster, rates of TVR were significantly reduced in the OCT arm (6% vs 14%, p 0.037) with a neutral impact on MACE (12% vs 15%, p 0.71). Conclusions: Compared with a functional assessment, an OCT-based approach reduces revascularisation in patients with STEMI/NSTEMI, while FFR proved non-inferior for patients with stable angina.