Dokter Algoritme

Algoritmen kunnen inzichten bereiken waar een mens moeilijk toe komt. Computeralgoritmen kunnen almaar beter moeilijke diagnosen stellen, soms zelfs beter dan artsen. Immunologe Erika Van Nieuwenhove van de Leuvense tak aan het Vlaams Instituut voor Biotechnologie (VIB) en haar collega’s melden in Annals of the Rheumatic Diseases dat ze een zelflerend algoritme hebben ontwikkeld dat met bijna 90 procent zekerheid artritis bij kinderen kan vaststellen, louter op basis van een bloedtest.

Het gaat om de vaakst voorkomende vorm van reuma bij kinderen, maar omdat de ernst en de evolutie van de symptomen sterk kunnen variëren, is een diagnose stellen niet altijd gemakkelijk. Het algoritme evalueert alleen de samenstelling van het immuunsysteem van de patiënten. Het zal nuttig zijn om te bepalen welke behandeling aangewezen is.

Knack - 24 Apr. 2019 - Page 86

Using machine learning to diagnose disease

Profiling the immune system in paediatric arthritis patients offers hope for improved diagnosis and treatment

A team of scientists from VIB and KU Leuven has developed a machine learning algorithm that identifies children with juvenile arthritis with almost 90% accuracy from a simple blood test. The new findings, published this week in Annals of the Rheumatic Diseases, pave the way for the use of machine learning to improve diagnosis and to predict which juvenile arthritis patients may respond best to different treatment options. The work was led by Professor Adrian Liston, a group leader at the Babraham Institute in Cambridge, UK and at VIB and KU Leuven in Leuven, Belgium.

Juvenile idiopathic arthritis is the most common rheumatic disease in children, but it presents in many different severities and forms. This diversity makes clinical assessment and patient classification difficult.

A team of researchers at Belgian research organisations VIB, KU Leuven and UZ Leuven undertook a detailed biological characterisation of the immune system of hundreds of children with and without juvenile arthritis to help the diagnosis or treatment decisions for this disease.

“Essentially, we took blood samples from more than 100 children, two thirds of whom had childhood arthritis,” explains Erika Van Nieuwenhove (VIB-KU Leuven), and first author of the study. “We analysed their immune system at a greater level of detail than was ever done before for this disease, and simply using this data we then used machine learning to see if we could tell which children had arthritis.”

The results were quite remarkable: the algorithm was about 90% accurate at identifying the children with the disease. “Using only information on the immune system, and no clinical data at all, we could design a machine learning algorithm that was about 90% accurate at spotting which kids had arthritis,” says Professor Adrian Liston (Babraham Institute, Cambridge, UK and VIB-KU Leuven). “This result is a proof-of-principle demonstration that immune phenotyping combined with machine learning holds huge potential to diagnose disease. Similar approaches could be applied to improve patient selection for treatments and clinical trials.”

The researchers are hopeful about the impact of this research in improving patient outcomes. “The tool needs further validation but otherwise there are no scientific barriers to this approach being quickly translated to the clinic,” comments Professor Carine Wouters (UZ Leuven), who was the clinical lead for this study. “Down the line, we could use this kind of detailed classification information—and machine learning analysis—to identify which patients will respond best to specific treatment options.”

EMBO Young Investigator meeting

Great meeting with great people

Punting on the Cam

Visiting the original lab books of Rosalind Franklin

Identical twins light the way for new genetic cause of arthritis

Identical twin girls who presented with severe arthritis helped scientists to identify the first gene mutation that can single-handedly cause a juvenile form of this inflammatory joint disease. By investigating the DNA of individual blood cells of both children and then modelling the genetic defect in a mouse model, the research team led by Adrian Liston (VIB-KU Leuven) was able to unravel the disease mechanism. The findings will help to develop an appropriate treatment as well.

Juvenile idiopathic arthritis is the most common form of all childhood rheumatic diseases. It is defined as arthritis that starts at a young age and persists throughout adulthood, but which does not have a defined cause. Patients present with a highly variable clinical picture, and scientists have long suspected that different combinations of specific genetic susceptibilities and environmental triggers drive the disease.

A single gene mutation

In a new study by researchers at VIB, KU Leuven and UZ Leuven, the cause of juvenile arthritis in a young pair of identical twins was traced back to a single genetic mutation.

"Single-cell sequencing let us track what was going wrong in every cell type in the twin’s blood, creating a link from genetic mutation to disease onset,” explains Dr. Stephanie Humblet-Baron, one of the researchers involved in the study. “It was the combination of next generation genetics and immunology approaches that allowed us to find out why these patients were developing arthritis at such a young age.”

Of mice and men

Parallel studies in mice confirmed that the gene defect found in the patients’ blood cells indeed led to an enhanced susceptibility to arthritis. Prof. Susan Schlenner, first author of the study, stresses the relevance of this approach: "New genetic editing approaches bring mouse research much closer to the patient. We can now rapidly produce new mouse models that reproduce human mutations in mice, allowing us to model the disease of individual patients."

According to immunology prof. Adrian Liston such insights prove invaluable in biomedical research: “Understanding the cause of the disease unlocks the key to treating the patient.”

From cause to cure

Liston’s team collaborated closely with prof. Carine Wouters, who coordinated the clinical aspect of the research: "The identification of a single gene that can cause juvenile idiopathic arthritis is an important milestone. A parallel mouse model with the same genetic mutation is a great tool to dissect the disease mechanism in more detail and to develop more effective targeted therapies for this condition.”

And the little patients? They are relieved to know that scientists found the cause of their symptoms: "We are delighted to know that an explanation has been found for our illness and more so because we are sure it will help other children."

Thankfully, the children’s arthritis is under good control at the moment. Thanks to the new scientific findings, their doctors will be in a much better position to treat any future flare-ups.

NFIL3 mutations alter immune homeostasis and sensitise for arthritis pathology 

Schlenner et al. 2018 Annals of the Reumatic Diseases

The genetics behind immune system variation

Unlocking The Secrets Of A Rare Immune Disease

by Adrian Liston and Josselyn Garcia-Perez 

Primary immunodeficiencies (PID) are a heterogeneous group of disorders that disturb the host’s immunity, creating susceptibility to infections. PIDs are genetically diverse, with mutations in many different genes capable of causing immunodeficiency. The clinical symptoms of PIDs include, but are not limited to, susceptibility to infections, inflammation, and autoimmunity, although each gene mutated, and indeed each individual mutation, can lead to different manifestations.

Central to understanding PIDs is to understand which immune cell type is rendered defective by the mutation the patient carries. The type of infections the patient develops is often a key indicator of the underlying immunodeficiency; for example, pulmonary infections and bacterial septicemia are associated with B cell defect, whereas fungal susceptibility is associated with defects in certain types of T cells. Candidate pathways can be investigated using genetics and immune screening, and successful identification of the underlying causes allows a treatment program to be tailored to the patient.

Read the full story on Science Trends

Golden Pipette won by Dr Carly Whyte

Congratulations to Dr Carly Whyte, for winning the Golden Pipette!

Carly won the Golden Pipette for her mind-boggling data on how the cellular source of IL-2 profoundly alters the impact of this key cytokine on the cells around it. Data to be published, as soon as we understand it!

Carly will be moving over to the Babraham in January. Will the Golden Pipette be won back by team Leuven in time? Or will Cambridge take ownership of this proud trophy?  

Our immune systems are incredibly diverse. How much of that diversity is due to our genes?

Each of our immune systems acts a little bit differently. Environmental factors have an impact, but so do our genes. A team of researchers in Leuven went looking for links between more than 10 million genetic variations and more than 50 immunological traits. Their findings help to explain why some people have a higher risk for immune diseases than others.

Our immune systems are molded by our unique genetic make-up. Add to that a complex mix of environmental drivers, and you get an enormous functional diversity. From an evolutionary point of view, this diversity is essential to minimize the chance that a pathogen could wipe out an entire population.

But the flip-side is that we’re also greatly diverse when it comes to susceptibility or resistance to a broad range of diseases – not only those with an obvious immunological component, such as autoimmunity, allergy, inflammation and cancer, but also those with a more indirect link to immune-deregulation, such as cardiovascular, metabolic and neurological diseases.

A genome-wide survey

While scientists have studied the links between genetic variations and a whole range of different diseases, the characterization of this “genotype-phenotype relationship” for the immune system itself has received far less attention.

That is why a team of scientists led by An Goris (KU Leuven) and Adrian Liston (VIB-KU Leuven) undertook a large genetic study with almost 500 participants. In a so-called genome-wide association study, or GWAS, they probed more than 10 million genetic variations, spread out across the genome, for links to 54 different traits relevant to adaptive immunity. This allowed the researchers to determine which genetic variants were, for example, typical for people with high or low levels of different pro- or anti-inflammatory cytokines.

“We found eight previously unknown associations,” says An Goris, lead geneticist of the study. “The strongest connection was for a genetic variant present in only 2% of the study participants.” All of the identified genetic associations provide important biological insights into what drives variation in our immune systems.

This is only the tip of the iceberg, according to Goris: “What we know now, explains about 10% of the variation, but we are still in the initial discovery phase. There might be many more genetic variants—including relatively rare ones—that affect our immune response and thus our susceptibility to certain diseases.”

Helping to map disease risk and refine treatment

Mapping how genetic variants affect immune function will not only help us understand disease mechanism better, it should also help to refine treatment options.

“The clearest example is the clinical implication offered by genetic variation in the RICTOR gene,” explains Adrian Liston, lead immunologist on the study. “We now know that RICTOR changes the production of a cytokine called IL-4, providing a new therapeutic target for treatment of autoimmune diseases and asthma.”

In many cases, the effects are more subtle and indirect, adds Liston: “Most people will carry dozens of genetic variants that may skew the immune system in a particular direction. This accounts for part of the reason why different people have different risks for immune diseases, but we are much more than the sum of our genes.”

—

Lagou et al. 2018 Cell Reports. 'Genetic architecture of adaptive immune system identifies key immune regulators'.

Scientists uncover new genetic cause of lupus on World Lupus Day

A team of scientists and clinicians has identified a novel mutation causing an unusual form of the autoimmune disease lupus. The genetic analysis of a Belgian family sheds new light on the disease mechanisms underlying lupus, which could possibly yield new therapeutic approaches for patients. The findings are published in the Journal of Allergy and Clinical Immunology in the week leading up to World Lupus Day.

Lupus is an autoimmune disorder, meaning that the body’s immune system mistakenly attacks its own tissues. Lupus can affect multiple organs but its cause is often not clear. Usually a combination of genetic and environmental factors is at play.

Researchers in Leuven have now discovered a novel genetic mutation in a patient that presented at the age of 12 with both lupus and problems in the ability of the immune system to fight common infections. This unusual combination of symptoms was quite puzzling.

By analyzing the patient’s DNA and that of the parents, the scientists could trace the problem down to a specific mutation in the so-called Ikaros gene. This gene encodes the Ikaros protein that in turn binds DNA to affect the expression of other proteins.

Erika Van Nieuwenhove, clinician and scientist at VIB-KU Leuven, explains how the mutation caused the patient’s immune system to be hyperactive: “Because of the mutation, Ikaros can no longer bind its target DNA properly. We also observed that certain immune cells of the patients were hyperactive, even in the absence of stimulation. The link between both observations turned out to be CD22, a protein that normally dampens the immune response. In normal conditions, Ikaros stimulates the expression of this inhibitor, but this was not the case in this patient.”

About 5 million people worldwide have lupus, but a causative mutation in Ikaros is very rare. “Small changes in Ikaros are associated with susceptibility to adult-onset lupus, but because the effects are weak it is hard to work out what Ikaros is doing to the immune system,” explains prof. Adrian Liston (VIB-KU Leuven), who heads the lab for translational immunology and is lead author of the study. “In this particular family, however, a mutation created a large change in Ikaros, causing early-onset lupus. The mutation was strong enough to allow us to work out how changes in Ikaros cause lupus and immune deficiency.”

Although the patient in this study has a very rare form of lupus, the discovery nevertheless helps to map the overall disease mechanisms, underscores prof. Carine Wouters, pediatric rheumatologist at University Hospitals Leuven and co-lead of the study: “The mechanism we uncovered in this patient could also be meaningful in a different context with other patients. Now that we understand what goes wrong in this particular case, it could help us think of better targeted treatments for others as well.”

Original research: Van Nieuwenhove et al. 2018 Journal of Allergy and Clinical Immunology. "A kindred with mutant IKAROS and autoimmunity"

If you would like to support our clinical research, and allow us to take on more cases like these, you can make a tax-deductable donation the Ped IMID fund, by transferring to IBAN-number BE45 7340 1941 7789, BIC-code: KREDBEBB with the label "voor EBD-FOPIIA-O2010".

Nieuwe genetische oorzaak van lupus ontdekt

Leuvense artsen en onderzoekers ontdekken een DNA-fout die een ongewone vorm van de auto-immuunziekte lupus kan veroorzaken. Door het DNA van een jonge patiënt en diens ouders na te gaan slaagden ze erin het ziektemechanisme beter te belichten, wat op termijn tot betere behandelingsmogelijkheden zou kunnen leiden, ook voor andere patiënten. De resultaten werden vlak voor Wereld Lupusdag gepubliceerd in het vakblad ‘Journal of Allergy and Clinical Immunology’.

Lupus is een auto-immuunziekte die verschillende organen kan aantasten. Het afweersysteem maakt hierbij antistoffen aan tegen het eigen lichaam. De oorzaak is in veel gevallen onduidelijk, vaak speelt er een combinatie van zowel erfelijke als omgevingsfactoren.

Leuvense onderzoekers ontdekten nu een nieuwe genetische mutatie bij een patiënt die al op 12-jarige leeftijd lupus kreeg, maar tegelijkertijd ook heel weinig antistoffen aanmaakte om zich te beschermen tegen infecties. Deze ongewone combinatie van symptomen vormde een raadsel voor de artsen.

Dankzij een speurtocht in het DNA van de patiënt en van beide ouders, kon het team van wetenschappers de oorzaak herleiden naar een specifieke fout in het gen voor Ikaros. Dit gen is de blauwdruk voor een eiwit dat op zijn beurt aan DNA kan binden om de productie van andere eiwitten te stimuleren.

Erika Van Nieuwenhove, arts-onderzoeker aan VIB-KU Leuven, verduidelijkt waarom de drempel voor activatie van het afweersysteem daardoor zo laag is bij deze patiënt: “Door de fout in het gen kan Ikaros niet meer goed aan het DNA binden. We zagen ook dat bepaalde immuuncellen van de patiënt hyperactief waren, zelfs zonder stimulatie. De link tussen beide was het CD22 eiwit, dat normaalgezien de immuunreactie tempert. Ikaros stimuleert normaal de productie van deze demper, maar dus niet bij deze patiënt.”

Lupus bij kinderen komt relatief vaak voor, maar dat de oorzaak bij het Ikaros eiwit ligt is heel zeldzaam. “Kleine wijzigingen in Ikaros verhogen de kans op lupus bij volwassenen, maar omdat de effecten zo klein zijn was het aanvankelijk moeilijk om uit te vissen hoe Ikaros het immuunsysteem beïnvloedt,” vertelt professor Adrian Liston (VIB-KU Leuven), die aan het hoofd van het labo voor translationele immunologie staat. “Bij deze familie gaat het om een genetische wijziging met grotere gevolgen, die dan ook al op jonge leeftijd lupus veroorzaakt. Maar net door het grotere effect konden we nu uitklaren op welke manier het defecte Ikaros de immuunreactie verstoort.”

Hoewel het gaat om een zeldzame vorm van lupus helpt deze doorbraak om het hele plaatje beter in kaart te brengen, bevestigt Prof. Carine Wouters, kinderreumatoloog aan UZ Leuven, die samen met prof. Liston de studie leidde: “Het mechanisme dat we bij deze patiënt ontdekten kan ook een rol van betekenis spelen bij andere patiënten. Nu we bij deze persoon begrijpen wat er fout loopt kan dat ook helpen om voor anderen meer gerichtere therapieën te ontwikkelen.”