Tackling Malaria Drug Resistance with Open Innovation
In the fight against drug-resistant malaria, a crowdsourcing project achieves in months what it would've taken years through conventional research approaches.
Malaria is still one of the planet's biggest killers, a mosquito-borne parasitic disease that is endemic in many parts of the developing world. According to the latest figures from the World Health Organization, there were 219 million malaria cases worldwide in 2017, which resulted in 435,000 deaths.
Despite many advances in our understanding of the disease and progress with malaria control programs, health officials are still struggling to curb its spread. One of the biggest challenges they face is the rise of drug-resistant malaria strains.
The sense of urgency is enormous. As of 2019, resistance to artemisinin (the last line of defense against multi-drug-resistant malaria) has not spread to Africa, where most cases of malaria deaths occur. If it did, decades of progress in fighting the disease on the continent could be erased.
Global Open Innovation Call
To ramp up efforts to find more effective models for treatment and prevention, the University of Notre Dame put out a global call for researchers, data scientists and health professionals to help them better understand the mechanisms of resistance.
More than 350 participants from 31 countries took part in the first Malaria DREAM (Dialogue for Reverse Engineering Assessments and Methods) Challenge. This crowdsourcing challenge was open to anyone in the world to develop computational models for predicting emerging drug resistance to artemisinin.
Participants were tasked with determining how genomic data of artemisinin-resistant malaria parasites can be used to predict their drug resistance level, based on laboratory experiments and patient data. Emerging drug resistance is difficult to measure in the laboratory and in patients who have the disease. Hence, the emphasis on a new data-driven approach.
Two teams from Daegu University in South Korea and Case Western Reserve University tied for first place in modeling drug resistance levels with a measure of resistance obtained in laboratory experiments (known as inhibitory concentration 50 or IC50). Meanwhile, the top team in modeling resistance levels using another measure of drug response directly obtained from patients, commonly known as the parasite clearance rate, came from the University of Michigan.
Accelerated Knowledge Gathering
Among the many benefits of a crowdsourcing approach to the malaria drug resistance problem is that it can generate new modeling ideas into the field by attracting data scientists who don't ordinarily work on malaria. It can also accelerate understanding.
According to Geoffrey Siwo, research assistant professor in the Department of Biological Sciences and the Eck Institute for Global Health at Notre Dame, who led the challenge, the crowdsourcing initiative resulted in new knowledge that would've taken years to accumulate
"The challenge has demonstrated that with the right modeling approaches, predicting artemisinin drug response of malaria parasites using genomic data is a tractable problem," he said.
"More than 300 modelers were able to work on this single problem for four months, and through the source code and write-ups they have submitted in this challenge, they have contributed an enormous amount of knowledge that would take years to accrue.
"When biomedical problems are posed to the crowd, you have more eyes on a singular problem, in a way that even the largest company in the world cannot afford."
Next Story »