DeepMind Breakthrough Helps to Solve How Diseases Invade Cells

(Bloomberg) — Google’s artificial intelligence unit took a giant step to predict the structure of proteins, potentially decoding a problem that has been described as akin to mapping the genome.



a hand holding a cellphone: A Deepmind Health logo sits displayed on the screen of an Apple Inc. iPhone in this arranged photograph in London, U.K. on Monday, Nov. 26, 2018. Three years ago, artificial intelligence company DeepMind Technologies Ltd. embarked on a landmark effort to transform health care in the U.K. Now plans by owner Alphabet Inc. to wrap the partnership into its Google search engine business are tripping alarm bells about privacy.


© Bloomberg
A Deepmind Health logo sits displayed on the screen of an Apple Inc. iPhone in this arranged photograph in London, U.K. on Monday, Nov. 26, 2018. Three years ago, artificial intelligence company DeepMind Technologies Ltd. embarked on a landmark effort to transform health care in the U.K. Now plans by owner Alphabet Inc. to wrap the partnership into its Google search engine business are tripping alarm bells about privacy.

DeepMind Technologies Ltd.’s AlphaFold reached the threshold for “solving” the problem at the latest Critical Assessment of Structure Prediction competition. The event started in 1994 and is held every two years to accelerate research on the topic.

Loading...

Load Error

Different folds in a protein determine how it will interact

Read More

DeepMind open-sources the FermiNet, a neural network that simulates electron behaviors

In September, Alphabet’s DeepMind published a paper in the journal Physical Review Research detailing Fermionic Neural Network (FermiNet), a new neural network architecture that’s well-suited to modeling the quantum state of large collections of electrons. The FermiNet, which DeepMind claims is one of the first demonstrations of AI for computing atomic energy, is now available in open source on GitHub — and ostensibly remains one of the most accurate methods to date.

In quantum systems, particles like electrons don’t have exact locations. Their positions are instead described by a probability cloud. Representing the state of a quantum system is challenging, because probabilities have to be assigned to possible configurations of electron positions. These are encoded in the wavefunction, which assigns a positive or negative number to every configuration of electrons; the wavefunction squared gives the probability of finding the system in that configuration.

The space of possible configurations is enormous

Read More