A new artificial intelligence framework could speed the development of vaccines to treat new COVID-19 mutations.

An artificial intelligence method can help combat emerging COVID-19 mutations by identifying the best potential vaccines to treat the virus, according to a study published in Scientific Reports. 

As COVID-19 begins to mutate in populations globally, scientists are concerned that the mutations will minimize the effectiveness of vaccines that are now being distributed. Recent variants of the virus in the UK, South Africa, and Brazil seem to spread more easily, which have the potential to lead to more hospitalizations and deaths. 

Researchers from the University of Southern California (USC) Viterbi School of Engineering set out to develop a new artificial intelligence method to combat emergent mutations of COVID-19 and accelerate vaccine development. 

The team used data from a bioinformatics database called the Immune Epitope Database (IEDB), in which scientists around the world have been collecting data about the coronavirus and other diseases. 

IEDB contains over 600,000 known epitopes from some 3,600 different species, along with the Virus Pathogen Resource, a complementary repository of information about pathogenic viruses. 

The newly-developed artificial intelligence method is designed to speed the analysis of vaccines and focus on the best potential preventive medical therapy. 

The method is easily adaptable to analyze potential mutations of the virus, ensuring the best possible vaccines are quickly identified. This can give humans a significant advantage over evolving mutations, with the model accomplishing vaccine design cycles that once took months or years in a matter of seconds or minutes. 

When applied to the virus that causes COVID-19, the AI tool quickly eliminated 95 percent of the compounds that could have possibly treated the pathogens and identified the best options.

The AI-assisted method predicted 26 potential vaccines that would work against coronavirus. Of these, scientists identified the best eleven from which to construct a multi-epitope vaccine, which can attack the spike proteins that the coronavirus uses to bind and penetrate a host cell.

Vaccines target the region, or epitope, of the contagion to disrupt the spike protein, neutralizing the ability of the virus to replicate.

“This AI framework, applied to the specifics of this virus, can provide vaccine candidates within seconds and move them to clinical trials quickly to achieve preventive medical therapies without compromising safety,” said Paul Bogdan, associate professor of electrical and computer engineering at USC Viterbi and corresponding author of the study. “Moreover, this can be adapted to help us stay ahead of the coronavirus as it mutates around the world.”

With the new AI framework, the team can also construct a new multi-epitope vaccine for a new virus in less than a minute and validate its quality within an hour. In comparison, current processes to control the virus require growing the pathogen in a lab, deactivating it, and injecting the virus that caused a disease. The process can take more than a year as the virus continues to spread.

Researchers expect that if the virus causing COVID-19 becomes uncontrollable by current vaccines, or if new vaccines are needed to deal with other emerging viruses, their AI method can help develop other preventive mechanisms quickly.

For example, researchers in the study used only one B-cell epitope and one T-cell epitope, whereas applying a bigger dataset and more possible combinations could help develop a more comprehensive and faster vaccine design tool. 

The study estimates that the model can perform accurate predictions with more than 700,000 different proteins in the dataset.

“The proposed vaccine design framework can tackle the three most frequently observed mutations and be extended to deal with other potentially unknown mutations,” Bogdan said.

The post Artificial Intelligence Tool Combats New COVID-19 Mutations appeared first on Artificial Intelligence.

During the past years, artificial intelligence (AI)—the capability of a machine to mimic human behavior—has become a key player in high-tech areas like drug development projects. AI tools help scientists to uncover the secret behind the big biological data using optimized computational algorithms. AI methods such as deep neural network improves decision making in biological and chemical applications i.e., prediction of disease-associated proteins, discovery of novel biomarkers and de novo design of small molecule drug leads. These state-of-the-art approaches help scientists to develop a potential drug more efficiently and economically.

A research team led by Professor Hongzhe Sun from the Department of Chemistry at the University of Hong Kong (HKU), in collaboration with Professor Junwen Wang from Mayo Clinic, Arizona in the United States (a former HKU colleague), implemented a robust deep learning approach to predict disease-associated mutations of the metal-binding sites in a protein. This is the first deep learning approach for the prediction of disease-associated metal-relevant site mutations in metalloproteins, providing a new platform to tackle human diseases. The research findings were recently published in a top scientific journal Nature Machine Intelligence.

Metal ions play pivotal roles either structurally or functionally in the (patho)physiology of human biological systems. Metals such as zinc, iron and copper are essential for all life, and their concentration in cells must be strictly regulated. A deficiency or an excess of these physiological metal ions can cause severe disease in humans. It was discovered that mutations in the human genome are strongly associated with different diseases. If these mutations happen in the coding region of DNA, they might disrupt metal-binding sites of the proteins and consequently initiate severe diseases in humans. Understanding of disease-associated mutations at the metal-binding sites of proteins will facilitate discovery of new drugs.

The team first integrated omics data from different databases to build a comprehensive training dataset. By looking at the statistics from the collected data, the team found that different metals have different disease associations. A mutation in zinc-binding sites has a major role in breast, liver, kidney, immune system and prostate diseases. By contrast, the mutations in calcium- and magnesium-binding sites are associated with muscular and immune system diseases, respectively. For iron-binding sites, mutations are more associated with metabolic diseases. Furthermore, mutations of manganese- and copper-binding sites are associated with cardiovascular diseases with the latter being associated with nervous system disease as well.

The researchers used a novel approach to extract spatial features from the metal binding sites using an energy-based affinity grid map. These spatial features have been merged with physicochemical sequential features to train the model. The final results show that using the spatial features enhanced the performance of the prediction with an area under the curve (AUC) of 0.90 and an accuracy of 0.82. Given the limited advanced techniques and platforms in the field of metallomics and metalloproteins, the proposed deep learning approach offers a method to integrate experimental data with bioinformatics analysis. The approach will help scientist to predict DNA mutations which are associated with diseases like cancer, cardiovascular diseases and genetic disorders.

Professor Sun said: “Machine learning and AI play important roles in the current biological and chemical sciences. In my group we worked on metals in biology and medicine using an integrative omics approach including metallomics and metalloproteomics, and we already produced a large amount of valuable data using in vivo/vitro experiments. We are now developing an artificial intelligence approach based on deep learning to turn these raw data into valuable knowledge, leading us to uncover secrets behind the diseases and to fight them. I believe this novel deep learning approach can be used in other projects, which is ongoing in our laboratory.”

The post Using deep learning to predict disease-associated mutations appeared first on Artificial Intelligence.