Machine Learning Approach to Identify Nipah Virus

According to a survey, it was reported that a total of 19 Nipah virus (NiV) cases, including 17 deaths had occured in Kerala. 18 of these cases were confirmed in the laboratory. Today machine learning has come up with a way to help identify bats that are prone to carry the Nipah virus. A team of scientists, whose research was funded by the National Science Foundation’s Ecology and Evolution of Infectious Diseases (EEID) program, the Defense Advanced Research Projects Agency’s PREventing EMerging Pathogenic Threats (PREEMPT) program, and the National Institutes of Health’s National Institute of General Medical Sciences, used machine learning algorithms to flag bat species that have traits to possess the virus of Nipah.

Data Used

The data that was used for this machine learning approach to identify the bats prone to carrying the virus, consists of a data with bat species, that in the past have known to carry the Nipah virus. It also had data of the bat species with other bat-borne viruses globally.

Get quality help now

Prof. Finch

Verified writer

Proficient in: Classification of virus

4.7 (346)

“ This writer never make an mistake for me always deliver long before due date. Am telling you man this writer is absolutely the best. ”

+84 relevant experts are online

Hire writer

This data taken belonged to 523 different bat species.

Following was the data:

1. Traits of the 523 bat species. These traits were 48 in number.
2.  Data on foraging methods, diet composition, geographic ranges and reproduction.
3. Torpur and migration behavior.
4. Biological and ecological attributes.
5. Environmental conditions were also taken into this study.

These are the environmental conditions of the places in which the Nipunah virus had spread. Following processses is what the data went through:

1. The model was trained only on 80 percent of the total dataset. It had 50,000 trees specifying a Bernoulli error distribution.
   Get to Know The Price Estimate For Your Paper

   Topic

   Deadline: 10 days left

   Number of pages

   Email Invalid email

   By clicking “Check Writers’ Offers”, you agree to our terms of service and privacy policy. We’ll occasionally send you promo and account related email

   "You must agree to out terms of services and privacy policy"

   Write my paper

   You won’t be charged yet!

2. In order to prevent overfitting, the distribution was built with 10-fold cross validation.
3. Each specie of the bat was weighted by its sample size to account for the fact that some species are more frequently sampled for henipaviruses compared to others.
4.  To calculate the corrected area under the curve, target shuffling methods were applied.

The ML AlgorithmThere were the following three basic objectives of the approach:

1. To predict the bat species that may carry the Nipah virus: After the appropriatte data is collected, it was clubbed together. A trait-based machine learning approach to a subset of species belonging to Asia, Austrilia and Oceania were applied. The team used a model called the regression model. This model was applied to the data that characterized 48 traits of the 523 species.
2. Virus prone with respect to region: It had to be found out, with respect to a particular region, about how some bats are found to be Nipah virus positive compared to some others in the same region. This was done by examining various traits of species that are most likely to have the Nipah virus.
3.  To find out whether a greater data for an enhanced study leads to trait profiles that describe the virus: It had to be found out if the traits that describe species of bats provide better studies of the species or the species where evidence of the virus injection has been reported does it better.

For this reason, the team conducted a second generalised boosted regression analysis. This was to know if a greater data availabliltiy for better studied species leads to which of the either of the two. In order to do this, they used the number of citations in Web of Science for the scientific name of each specie. The models were again trained on 80 percent of the data and built with 10-fold cross-validation to prevent overfitting.

Result Of The Algorithm

The ML algorithm used could do the following things:1. Successfully identified the kmown Nipah-positive bats with an accuracy of 83 percent. 2. Identified 6 bat species that occur in Asia, Australia and Oceana. These bats species that are identified are the ones that showed traits supporting them to be possible suspects of the host of the virus. Four of these six species occur in India, among which, two are found in Kerala.For every data recorded, classification was dfone on the basis of species, country of sampling, diagnostic method, sample size, sampling and reporting method.