protein folding Archives - Medical Design Sourcing

From AI transformers to computer-based reasoning to rethinking drug design: AI pioneers discuss the future

Jensen Huang at GTC

In a packed panel discussion at GTC, moderated by NVIDIA Founder and CEO Jensen Huang, the architects of the groundbreaking transformer model gathered to explore their creation’s potential. The panel featured seven of the eight authors of the seminal “Attention Is All You Need Paper” paper, which introduced transformers – a type of neural network designed to handle sequential data, like text or time series, in a way that allows for much more parallel processing than previous architectures like recurrent neural networks (RNNs). Transformers accomplish this through a mechanism called “attention,” which enables the model to differentially weigh the importance of different parts of the input data.

The transformer architecture powers large language models like GPT-4 and has ignited widespread interest in AI applications across industries including in biology, wher…

Why AI alone won’t resolve drug discovery challenges

A digital representation of a protein structure. [Image courtesy of NIH]

Big Pharma and researchers are sharpening their focus on AI to speed drug discovery. But the path to fully AI-driven drug discovery faces substantial hurdles, according to Adityo Prakash, CEO of Verseon. “When it comes to drug discovery, AI has a data problem with which the pharmaceutical industry has not yet come to terms,” he said.

Prakash explained there is simply “not enough data” to rely on AI as the primary means of small molecule drug discovery. He discussed these challenges further in an article in American Pharmaceutical Review titled “Exploring New Chemical Space for the Treatments of Tomorrow.”

The limitations and challenges of AI-first methods

Even with high-throughput screening to automate the process of testing pre-synthesized drug candidates against disease-associated target proteins, the pharma…

What Google DeepMind’s introduction of AlphaDev sorting algorithm could mean for drug discovery

Researchers at Google’s DeepMind AI team have used AI to create advanced sorting algorithms, which although not specifically designed for drug discovery, could potentially benefit the field.

Published in Nature, DeepMind’s latest work demonstrates the use of deep reinforcement learning to create more efficient routines for sorting and hashing. These algorithms find use in various computational tasks, especially in computationally heavy processes such as drug discovery and simulations.

The researchers from DeepMind created an AI focused on code generation. To this end, they adapted the AlphaGo AI, a system known for defeating a human champion in the game of Go in 2016. The researchers created the AI system, known as AlphaDev, after staging a “game” approach, in which the AI treated a set of computer instructions like game moves. The AI then learned to “win” by sorting lists of three and five items as efficiently as possible. The resulting algor…

AlphaFold: Redefining drug discovery with digital biology and AI

[Christoph Burgstedt/Adobe Stock]

At the Nvidia GTC 2023, DeepMind’s Founder and CEO, Demis Hassabis, provided an in-depth look into the seismic potential of their protein folding AI system, AlphaFold. Hassabis said AlphaFold was a contender for the organization’s “biggest project to date.”

Hassabis noted that DeepMind’s AlphaFold has made strides in addressing the protein folding problem, a challenge that has stumped scientists for more than five decades. The protein folding problem involves predicting the 3D structure of proteins solely from the amino acid sequence. Until AlphaFold, determining a protein’s structure was a complex and time-consuming process, often taking years of experimental work.

At the end of 2022, the company announced that it updated AlphaFold with the structure predictions of more than 200 million proteins.

Hassabis explained the enormity of the challenge, …

7 case studies highlighting the potential of DeepMind’s AlphaFold

[Image courtesy of DeepMind]

Alphabet subsidiary DeepMind has announced that its AI system AlphaFold has predicted the structure of more than 200 million proteins, representing almost every known cataloged protein. In addition, AlphaFold and its partner, the EMBL’s European Bioinformatics Institute, announced that the recent release expanded the database by more than 200 fold, from almost 1 million to more than 200 million structures.

“When we launched the database last July, it was sort of recognized as a pretty big leap forward for biology,” said Demis Hassabis, founder and CEO of DeepMind, in a press conference. The release last year included roughly 350,000 high-quality predictions, including all proteins in the human body.

The continued advances of AlphaFold make it possible to search for the 3-D structure of proteins “almost as easily as doing a keyword Google search,” …