Cross-attention enables deep learning on limited omics-imaging-clinical data of 130 lung cancer patients.

Deep-learning tools that extract prognostic factors derived from multi-omics data have recently contributed to individualized predictions of survival outcomes. However, the limited size of integrated omics-imaging-clinical datasets poses challenges. Here, we propose two biologically interpretable and robust deep-learning architectures for survival prediction of non-small cell lung cancer (NSCLC) patients, learning simultaneously from computed tomography (CT) scan images, gene expression data, and clinical information.

Polarization Control in Integrated Graphene-Silicon Quantum Photonics Waveguides.

We numerically investigated the use of graphene nanoribbons placed on top of silicon-on-insulator (SOI) strip waveguides for light polarization control in silicon photonic-integrated waveguides. We found that two factors mainly affected the polarization control: the graphene chemical potential and the geometrical parameters of the waveguide, such as the waveguide and nanoribbon widths and distance. We show that the graphene chemical potential influences both TE and TM polarizations almost in the same way, while the waveguide width tapering enables both TE-pass and TM-pass polarizing functionalities.

Clinical stratification improves the diagnostic accuracy of small omics datasets within machine learning and genome-scale metabolic modelling methods.

Background: Recently, multi-omic machine learning architectures have been proposed for the early detection of cancer. However, for rare cancers and their associated small datasets, it is still unclear how to use the available multi-omics data to achieve a mechanistic prediction of cancer onset and progression, due to the limited data available. Hepatoblastoma is the most frequent liver cancer in infancy and childhood, and whose incidence has been lately increasing in several developed countries.

Recognizing the Emergent and Submerged Iceberg of the Celiac Disease: ITAMA Project-Global Strategy Protocol.

Coeliac disease (CD) is frequently underdiagnosed with a consequent heavy burden in terms of morbidity and health care costs. Diagnosis of CD is based on the evaluation of symptoms and anti-transglutaminase antibodies IgA (TGA-IgA) levels, with values above a tenfold increase being the basis of the biopsy-free diagnostic approach suggested by present guidelines. This study showcased the largest screening project for CD carried out to date in school children (n=20,000) aimed at assessing the diagnostic accuracy of minimally invasive finger prick point-of-care tests (POCT) which, combined with conventional celiac serology and the aid of an artificial intelligence-based system, may eliminate the need for intestinal biopsy.

A Practical Guide to Integrating Multimodal Machine Learning and Metabolic Modeling.

Complex, distributed, and dynamic sets of clinical biomedical data are collectively referred to as multimodal clinical data. In order to accommodate the volume and heterogeneity of such diverse data types and aid in their interpretation when they are combined with a multi-scale predictive model, machine learning is a useful tool that can be wielded to deconstruct biological complexity and extract relevant outputs. Additionally, genome-scale metabolic models (GSMMs) are one of the main frameworks striving to bridge the gap between genotype and phenotype by incorporating prior biological knowledge into mechanistic models.