Conditions such as Alzheimer’s, Parkinson’s, Huntington’s, and cystic fibrosis are suspected to be caused by misfolded proteins. Being able to predict a protein’s shape enables a greater understanding of its role within the body.

Previous techniques used for determining the shapes of proteins – such as cryo-electron microscopy, nuclear magnetic resonance, and X-ray crystallography – takes years and costs tens of thousands of dollars per structure.

AI, the researchers hope, will enable target shapes to be modelled from scratch without requiring previously solved proteins to be used as templates.

DeepMind calls their AI-powered folding efforts AlphaFold.

AlphaFold uses two different methods to construct predictions of protein structures:

1. 1. The first method repeatedly replaces pieces of a protein structure with new protein fragments, building on a technique commonly used in structural biology. A neural network invents new fragments.

1. The second method is called ‘gradient descent’ which is a mathematical technique applied to entire protein chains rather than pieces and makes small, incremental improvements.

Image Credit: DeepMind

DeepMind says its work is a successful demonstration of how AI can reduce the complexity of tasks such as protein folding; speeding up the diagnosis and treatment of some of the world’s most debilitating conditions.

In a contest organised by the Protein Structure Prediction Centre, AlphaMind was judged the winner among a total 98 algorithms by predicting the shapes of 25 out of 43 proteins. The runner-up, in comparison, could only predict three of the 43 proteins.

“For us, this is a really key moment,” said Demis Hassabis, co-founder and CEO of DeepMind. “This is a lighthouse project, our first major investment in terms of people and resources into a fundamental, very important, real-world scientific problem.”

 AI & >.

The post DeepMind is using AI for protein folding breakthroughs appeared first on AI News.

Earlier diagnosis of any medical problem is always good. Often it increases the chance of successful treatment, minimises suffering, and can increase life expectancy in terminal cases.

Parkinson’s is a degenerative affliction without any known cure. Caught early, however, and measures can be taken which helps to slow its progression.

Speaking to Forbes, Medopad CEO Dan Vahdat said:

“Our partnership with Tencent comes from a shared vision to change the future of healthcare as we know it.

In combining Medopad’s medical expertise and Tencent’s technical capabilities, we hope to provide the technology needed to support clinicians to predict preventable complications for people with Parkinson’s disease.”

The disease affects the central nervous system, predominately the motor system. As such, the most obvious symptoms early on are shaking, rigidity, slowness of movement, and difficulty walking.

Tencent and Medopad use AI trained on existing video footage of patients to spot for concerning symptoms. The video analysis was conducted in collaboration with Kings College Hospital in London.

Both companies hope their system will reduce how long it takes for a motor function assessment to be performed from over 30 minutes to less than three. Speeding up diagnosis helps more people to begin treatment faster.

Medopad is known for using wearables for its healthcare solutions, but the AI system will not require any physical sensors or devices to be worn. Reducing the amount of hardware required helps to reduce cost and complexity so more healthcare providers can get started.

The firms are not the only companies looking to use AI to improve healthcare (in fact, we’ve got a whole category dedicated to it – if you’re so inclined.)

Most AI healthcare developments we’ve covered focus on the scourge of cancer, which now affects one in two people. Almost everyone has either had it or knows someone close to them.

Back in August, we covered how AI is reducing how long it takes to produce cancer treatment plans from days to potentially minutes. For those undergoing treatment, AI is even stepping in to help make treatment more bearable.

Tencent and Medopad are delivering another example of how AI can have a huge impact on healthcare, and not just for cancer.

  Attend the co-located AI & , and >

The post Tencent uses AI to speed up Parkinson’s diagnosis appeared first on AI News.