Platform uses artificial intelligence to diagnose Zika and other pathogens

June 13, 2018, FAPESP
Platform uses artificial intelligence to diagnose Zika and other pathogens
Method created in Brazil combines mass spectrometry analysis of blood serum with an algorithm that recognizes patterns associated with viral diseases as well as diseases of bacterial, fungal and even genetic origin. Credit: Wikimedia Commons/FAPESP

Scientists at the University of Campinas (UNICAMP) in Brazil have developed a platform that can diagnose several diseases with a high degree of precision using metabolic markers found in blood.

The method combines mass spectrometry, which can identify tens of thousands of molecules present in blood serum, with an capable of finding patterns associated with diseases of viral, bacterial, fungal and even genetic origin. The research was supported by the São Paulo Research Foundation—FAPESP and conducted as part of Carlos Fernando Odir Rodrigues Melo's Ph.D. The results have been published in Frontiers in Bioengineering and Biotechnology.

"We used infection by Zika virus as a model to develop the platform and showed that in this case, diagnostic accuracy exceeded 95 percent. One of the main advantages is that the method doesn't lose sensitivity, even if the virus mutates," said Melo's supervisor Rodrigo Ramos Catharino, principal investigator for the project. Catharino is a professor at UNICAMP's School of Pharmaceutical Sciences (FCF) and head of its Innovare Biomarker Laboratory.

Another strength of the platform, he added, is the capacity to identify positive cases of Zika even in analyzed 30 days after the start of infection, when the acute phase of the disease is over.

"None of the currently available diagnostic kits has the sensitivity to detect infection by Zika after the end of the acute phase. The method we developed could be useful to analyze transfusion blood bags, for example," Catharino said.

Machine learning

Development and validation of the platform involved analysis of blood samples from 203 patients treated at UNICAMP's general and teaching hospital. Of these, 82 were diagnosed with Zika by the method currently considered the gold standard in this field: real-time polymerase chain reaction (RT-PCR), which detects viral RNA in body fluids during the acute phase of the infection.

The other 121 patients were the . Approximately half had the same symptoms as the group that tested positive for Zika, such as fever, joint pain, conjunctivitis and rash, but had negative RT-PCR results for Zika. The rest had no symptoms and also tested negative or were diagnosed with dengue.

All collected samples were analyzed in a , a device that acts as a kind of molecular weighing scale, sorting molecules according to their mass.

"We identified some 10,000 different molecules in the patients' serum, including lipids, peptides, and fragments of DNA and RNA. Among these metabolites, there were particles produced both by Zika and by the patient's immune system in response to the infection," said the FAPESP scholarship supervisor.

All the data obtained in the spectrometry analysis of both the group that tested positive for Zika and the control group were then fed into a computer program running a random-forest machine learning algorithm. This type of artificial intelligence tool is capable of analyzing a large amount of data by specific statistical methods in search of patterns that can be used as a basis for classification, prediction, decision making, modeling and so on.

"The algorithm separates samples randomly, determines which one will be the training group and the blind group, and then carries out testing and validation. At the end, it tells us whether with that number of samples it was possible to obtain a set of metabolic markers capable of identifying patients infected by Zika," Catharino explained.

Each new set of patient data fed into the program enhances its learning capacity and makes it more sensitive, he went on. In the case of Zika, the FAPESP-funded study established a panel of 42 biomarkers as a specific key to identifying the virus. Twelve of these were found by the algorithm to be highly prevalent in the blood of patients who tested positive for the disease.

"In this platform, it isn't important to know a lot individually about each of the molecules that serve as markers of the infection. It's the set that matters and that will tell us with a high level of accuracy whether we're looking at Zika. Moreover, even if the virus mutates, the program adapts and changes too. It's not a static methodology," Catharino said.

The UNICAMP group is currently performing tests to evaluate the platform's capacity to diagnose systemic diseases caused by fungi. They also plan to test how well it detects bacterial and genetic diseases. Anderson de Rezende Rocha, a professor at the same university's Institute of Computing (IC-UNICAMP), is collaborating on the research.

In theory, any laboratory equipped with a mass spectrometer could use the new diagnostic platform developed at UNICAMP. Mass spectrometers are routinely used in procedures such as measuring vitamin D and screening blood spots from newborns to detect metabolic diseases via the heel prick test.

"Our proposal is to make the platform available in the cloud, so that it can be downloaded to any mass spectrometer anywhere in the world, data analysis can be performed online. Whether it would be free or paid is yet to be defined," Catharino said.

Explore further: Metabolic pathway involved in immune response to Zika also participates in neurogenesis

More information: Carlos Fernando Odir Rodrigues Melo et al, A Machine Learning Application Based in Random Forest for Integrating Mass Spectrometry-Based Metabolomic Data: A Simple Screening Method for Patients With Zika Virus, Frontiers in Bioengineering and Biotechnology (2018). DOI: 10.3389/fbioe.2018.00031

Related Stories

Metabolic pathway involved in immune response to Zika also participates in neurogenesis

January 10, 2018
Researchers at the University of Campinas (UNICAMP) in São Paulo State, Brazil, have identified molecules that serve as markers of Zika in blood serum taken from patients with this viral infection.

Zika virus could help combat brain cancer

February 22, 2018
Zika virus, known for causing microcephaly in babies by attacking the cells that give rise to the fetus's cerebral cortex, could be an alternative for treatment of glioblastoma, the most common and aggressive malignant brain ...

Test detects prior infection by Zika virus

March 29, 2018
A test that detects antibodies against Zika virus in samples of blood serum with high specificity—and hence a low risk of cross-reaction with related microorganisms such as dengue virus—is set to enter the Brazilian market ...

Laboratory technique can detect Zika virus infection and make diagnostic tests more accessible

December 22, 2017
A new test for the Zika virus could help limit future outbreaks, especially in areas without access to sophisticated diagnostic methods.

How reliable is diagnostic testing for Zika?

March 2, 2018
Globally, Brazil has been the hardest hit by the current Zika outbreak, and the country reports almost all cases of Zika-associated malformations in newborns. DZIF scientists from the Charité - Universitätsmedizin Berlin ...

First test to detect Zika in blood donations approved

October 9, 2017
(HealthDay)—The cobas Zika test has been approved by the U.S. Food and Drug Administration—the first approved screening test to detect the Zika virus in blood donations.

Recommended for you

A versatile vaccine that can protect mice from emerging tick-borne viruses

December 18, 2018
A group of researchers led by Michael Diamond of Washington University School of Medicine in St. Louis have developed a vaccine that is effective in mice against Powassan virus, an emerging tick-borne virus that can cause ...

How cholera bacteria make people so sick

December 18, 2018
The enormous adaptability of the cholera bacterium explains why it is able to claim so many victims. Professor Ariane Briegel from the Leiden Institute of Biology has now discovered that this adaptability is due to rapid ...

Green leafy vegetables may prevent liver steatosis

December 17, 2018
A larger portion of green leafy vegetables in the diet may reduce the risk of developing liver steatosis, or fatty liver. In a study published in PNAS researchers from Karolinska Institutet in Sweden show how a larger intake ...

Discovery of novel mechanisms that cause migraines

December 17, 2018
Researchers at CNRS, Université Côte d'Azur and Inserm have demonstrated a new mechanism related to the onset of migraine. They found how a mutation that causes dysfunction in a protein which inhibits neuronal electrical ...

RNA processing and antiviral immunity

December 14, 2018
The RIG-I like receptors (RLRs) are intracellular enzyme sentries that detect viral infection and initiate a first line of antiviral defense. The cellular molecules that activate RLRs in vivo are not clear.

Faster test for Ebola shows promising results in field trials

December 13, 2018
A team of researchers with members from the U.S., Senegal and Guinea, in cooperation with Becton, Dickinson and Company (BD), has developed a faster test for the Ebola virus than those currently in use. In their paper published ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.