Plasma proteome dynamics of COVID-19 severity learnt by a graph convolutional network of multi-scale topology

Efforts to understand the molecular mechanisms of COVID-19 have led to the identification of ACE2 as the main receptor for the SARS-CoV-2 spike protein on cell surfaces. However, there are still important questions about the role of other proteins in disease progression. To address these questions, we modelled the plasma proteome of 384 COVID-19 patients using protein level measurements taken at three different times and incorporating comprehensive clinical evaluation data collected 28 d after hospitalisation. Our analysis can accurately assess the severity of the illness using a metric based on WHO scores. By using topological vectorisation, we identified proteins that vary most in expression based on disease severity, and then utilised these findings to construct a graph convolutional network. This dynamic model allows us to learn the molecular interactions between these proteins, providing a tool to determine the severity of a COVID-19 infection at an early stage and identify potential pharmacological treatments by studying the dynamic interactions between the most relevant proteins.

Learning models for colorectal cancer signature reconstruction and classification in patients with chronic inflammatory bowel disease

BACKGROUND

In their everyday life, clinicians face an overabundance of biological indicators potentially helpful during a disease therapy. In this context, to be able to reliably identify a reduced number of those markers showing the ability of optimising the classification of treatment outcomes becomes a factor of vital importance to medical prognosis. In this work, we focus our interest in inflammatory bowel disease (IBD), a long-life threaten with a continuous increasing prevalence worldwide. In particular, IBD can be described as a set of autoimmune conditions affecting the gastrointestinal tract whose two main types are Crohn’s disease and ulcerative colitis.

AIM

To identify the minimal signature of microRNA (miRNA) associated with colorectal cancer (CRC) in patients with one chronic IBD.

METHODS

We provide a framework of well-established statistical and computational learning methods wisely adapted to reconstructing a CRC network leveraged to stratify these patients.

RESULTS

Our strategy resulted in an adjusted signature of 5 miRNAs out of approximately 2600 in Crohn’s Disease (resp. 8 in Ulcerative Colitis) with a percentage of success in patient classification of 82% (resp. 81%).

CONCLUSION

Importantly, these two signatures optimally balance the proportion between the number of significant miRNAs and their percentage of success in patients’ stratification.

Repairing the human with artificial intelligence in oncology

Artificial intelligence is a groundbreaking tool to learn and analyse higher features extracted from any dataset at large scale. This ability makes it ideal to facing any complex problem that may generally arise in the biomedical domain or oncology in particular. In this work, we envisage to provide a global vision of this mathematical discipline outgrowth by linking some other related subdomains such as transfer, reinforcement or federated learning. Complementary, we also introduce the recently popular method of topological data analysis that improves the performance of learning models.

Singular manifolds of proteomic drivers to model the evolution of inflammatory bowel disease status

The conditions used to describe the presence of an immune disease are often represented by interaction graphs. These informative, but intricate structures are susceptible to perturbations at different levels. The mode in which that perturbation occurs is still of utmost importance in areas such as cell reprogramming and therapeutics models. In this sense, module identification can be useful to well characterise the global graph architecture. To help us with this identification, we perform topological overlap-related measures. Thanks to these measures, the location of highly disease-specific module regulators is possible. Such regulators can perturb other nodes, potentially causing the entire system to change behaviour or collapse. We provide a geometric framework explaining such situations in the context of inflammatory bowel diseases (IBD). IBD are severe chronic disorders of the gastrointestinal tract whose incidence is dramatically increasing worldwide. Our approach models different IBD status as Riemannian manifolds defined by the graph Laplacian of two high throughput proteome screenings. It also identifies module regulators as singularities within the manifolds (the so-called singular manifolds). Furthermore, it reinterprets the characteristic nonlinear dynamics of IBD as compensatory responses to perturbations on those singularities. Then, particular reconfigurations of the immune system could make the disease status move towards an innocuous target state.