-
Categories
-
Pharmaceutical Intermediates
-
Active Pharmaceutical Ingredients
-
Food Additives
- Industrial Coatings
- Agrochemicals
- Dyes and Pigments
- Surfactant
- Flavors and Fragrances
- Chemical Reagents
- Catalyst and Auxiliary
- Natural Products
- Inorganic Chemistry
-
Organic Chemistry
-
Biochemical Engineering
- Analytical Chemistry
-
Cosmetic Ingredient
- Water Treatment Chemical
-
Pharmaceutical Intermediates
Promotion
ECHEMI Mall
Wholesale
Weekly Price
Exhibition
News
-
Trade Service
Scientists at the Broad Institute of MIT, Harvard University and the University of Massachusetts Medical School have developed a machine learning model that can analyze millions of SARS-CoV-2 genomes and predict which viral variants are likely to dominate and cause COVID-19 cases sur.
The findings were published in the journal Scien.
The researchers trained a machine learning model using 6 million SARS-CoV-2 genomes in the January 2022 GISAID databa.
The research team included first author Fritz Obermeyer, and senior author Jacob Lemieux, a member of the Broad Institute, Pardis Sabe.
PyR0 is based on a machine learning framework called Pyro, originally developed by a team at Uber AI La.
"This work is the result of a joint effort of biologists, geneticists, software engineers and computer scientists," Lemieux sa.
"This machine-learning-based approach can look at all the data and combine it into a single prediction, which is very valuable," Sabeti sa.
The future of coronavirus
Since the early days of the pandemic, researchers around the world have struggled to predict the fitness of different SARS-CoV-2 viral varian.
In contrast, PyR0 can analyze millions of genomes—all publicly available SARS-CoV-2 data—in about an ho.
Next, the model determined which mutations became more common and estimated how quickly each mutation caused the virus to spre.
The model also provides biological insights into the spread and progression of COVID-19 by identifying which mutations are important for the fitness of specific varian.
"The SARS-CoV-2 genome has now accumulated many mutations, so it becomes extremely challenging to detect all combinations of mutatio.
Early warning
The researchers say their study shows that the current increase in viral fitness stems from the virus' ability to evade immune respons.
New versions of this or similar models could further improve predictions by accounting for interactions between mutatio.
"The vast amount of data we have, combined with the methods we've developed, allows us to see in real time the evolution of the virus in different locations around the world, something that wasn't possible in previous outbrea.
Original title:
Analysis of 4 million SARS-CoV-2 genomes identifies mutations associated with fitness
