Thanks to the large amount of -omics data becoming increasingly available, sophisticated computational models are developed for new fields such as immunology and the predictions they generate will help identify key molecules in inflammatory processes. The application of such computational systems biology approaches to immunology could lead to novel and more efficacious therapeutic strategies. 

“The recent work of our two teams on the modulation of hyper inflammation in COVID-19 illustrates really well how the synergy between experimental and computational researchers can accelerate the discovery of molecules of interest,” explains Prof. Antonio Del Sol, head of the Computational Biology groups at the LCSB and CIC bioGUNE. “By using computational modeling to inform traditional experimental approaches, we confirmed in a few months a potential target for medical intervention in COVID-19 patients. This is indeed very promising.”

Understanding the “cytokine storm” in COVID-19

In recent studies, researchers from the LCSB and CIC bioGUNE - on the computational side - and from the Kanneganti Lab at St. Jude Children’s Research Hospital - on the experimental side - focused on the mechanisms underlying the hyperinflammatory response in COVID-19. Hyperinflammation is caused when the immune response is amplified and maintained by positive feedback loops above the level needed to control the disease. Kanneganti’s lab recently found that in COVID-19, as well as other diseases, this hyperinflammatory “cytokine storm” could be mechanistically defined as a life-threatening condition caused by excessive production of proinflammatory proteins, cytokines, mediated by a form of inflammatory cell death called PANoptosis. In COVID-19, PANoptosis and the concomitant cytokine storm cause organ damage and increase the severity of the symptoms. This makes treatment challenging, as therapeutics need to alleviate inflammation while maintaining the patient’s ability to clear the virus through cell death and other pathways. It is, therefore, crucial to identify the molecules that amplify and maintain the inflammatory response. It is the first step towards new and putative life-saving therapeutic strategies.

Two studies identify protein TLR2 as a target

In a first study published in Science Advances, researchers from the Computational Biology groups of the LCSB and CIC bioGUNE used a novel computational method to analyze over 1700 cell-cell interactions and create a comprehensive map of the immune response in the lungs of COVID-19 patients. Their model identified Toll-like Receptor 2 (TLR2) as a molecule that might be able to modulate the inflammatory response, predicting that the inhibition of this protein could disrupt up to 75% of the feedback loops without interfering with the general immune response. The study put TLR2 on the map as a potential target for medical intervention in severe COVID-19 cases.

Separately, the team of Dr. Thirumala-Devi Kanneganti from the Department of Immunology of St Jude Children’s Research Hospital published a study in Nature Immunology that independently suggested that TLR2 might act as a key modulator of COVID-19-induced hyperinflammation. Using in vitro and in vivo experiments, the researchers found that increased expression of TLR2 in the blood of patients with COVID-19 correlated with disease severity and that, upon infection by the virus, TLR2 mediated the production of cytokines. The study also showed that treatment of transgenic mice with a TLR2 inhibitor protected the animals against SARS-CoV-2-mediated inflammatory cytokine production and mortality. “Experimental validation of computationally derived biomarkers is critical to provide multiple lines of evidence to support the proof-of-concept for the utility of targeting TLR2 to modulate inflammation. It is imperative to combine computational and experimental approaches to understand mechanisms involved in inflammatory processes,” underlines Dr. Kanneganti.

A coordinated effort to achieve full potential

This example is far from the only one: In a growing number of studies, systems immunology approaches are being successfully employed to help predict novel therapeutic targets for modulating uncontrolled immune responses. “Computational modeling and experimental validation will become key partnerships in biomedical research and should be systematically developed to achieve their full potential,” details Dr. Ilya Potapov, member of the Computational Biology group at the LCSB.

In their recent paper published in November in Trends in Immunology, the three co-authors mention the challenges researchers will have to tackle when building computational models in the context of hyper inflammation – such as technological limitations, shortage of good experimental models, and mutual unawareness – and postulate that experimental and computational efforts should be synergized from the onset. “The technological advances have set the stage for us. Now, we need to work together to build accurate computational models, define the necessary data, and design experiments to validate the computational predictions. This is the key to designing novel and more efficacious therapeutic strategies,” concludes Prof. Del Sol.

A new study by the Oregon State University College of Engineering shows that machine learning techniques can offer powerful new tools for advancing personalized medicine, care that optimizes outcomes for individual patients based on unique aspects of their biology and disease features. 

The research with machine learning, a branch of artificial intelligence in which computer systems use algorithms and statistical models to look for trends in data, tackles long-unsolvable problems in biological systems at the cellular level, said Oregon State’s Brian D. Wood, who conducted the study with then OSU Ph.D. student Ehsan Taghizadeh and Helen M. Byrne of the University of Oxford.

“Those systems tend to have high complexity – first because of the vast number of individual cells and second, because of the highly nonlinear way in which cells can behave,” said Wood, a professor of environmental engineering. “Nonlinear systems present a challenge for upscaling methods, which is the primary means by which researchers can accurately model biological systems at the larger scales that are often the most relevant.”

A linear system in science or mathematics means any change to the system’s input results in a proportional change to the output; a linear equation, for example, might describe a slope that gains 2 feet vertically for every foot of horizontal distance.

Nonlinear systems don’t work that way, and many of the world’s systems, including biological ones, are nonlinear.

The new research, funded in part by the U.S. Department of Energy and published in the Journal of Computational Physics, is one of the first examples of using machine learning to address issues with modeling nonlinear systems and understanding complex processes that might occur in human tissues, Wood said.

“The advent of machine learning has given us a new tool in our arsenal to solve problems we could not solve before,” he explained. “While the tools themselves are not necessarily new, the particular applications we have are very different. We are beginning to apply machine learning in a more constrained way, and this is allowing us to solve physical problems we had no way of solving before.”

In modeling cellular activity within an organ, it is not possible to individually model each cell in that organ – a cubic centimeter of tissue may contain a billion cells – so researchers rely on what’s known as upscaling.

Upscaling seeks to decrease the data required to analyze or model a particular biological process while maintaining the fidelity – the degree to which a model accurately reproduces something – of the core biology, chemistry, and physics occurring at the cellular level.  

Biological systems, Wood notes, resist traditional upscaling techniques, and that’s where machine learning methods come in.

By reducing the information load for a very complicated system at the cellular level, researchers can better analyze and model the impact or response of those cells with high fidelity without having to model each one. Wood describes it as “simplifying a computational problem that has tens of millions of data points by reducing it to thousands of data points.”

The new approach could pave the way to potential patient treatments based on numerical model outcomes. In this study, researchers were able to employ machine learning and develop a novel method to resolve classic nonlinear problems in biological and chemical systems.

“Our work capitalizes on what is called deep neural networks to upscale the nonlinear processes found in transport and reactions within tissues,” Wood said.

Wood is collaborating on another research project employing machine learning techniques to model blood flow through the body.

“The promises of individualized medicine are rapidly becoming a reality,” he said. “The combination of multiple disciplines – such as molecular biology, applied mathematics, and continuum mechanics – are being combined in new ways to make this possible.  One of the key components of this will certainly be the continuing advances in machine learning methods.”