Keeping tabs on pharma: DeepMind’s AI predicts the human proteome and Russia joins the trend of providing real-world evidence for clinical trials

The latest update from Pharma IQ breaks down recent breakthroughs in AI and protein identification and considers the implication of increasing access to real-world healthcare data

Add bookmark
Adam Jeffs
Adam Jeffs
07/26/2021

AI leaps in antibiotic research

This past week has seen a first in how artificial intelligence (AI) is driving ground-breaking leaps in the field of protein structure identification, and advances in regulations in Russia is providing healthcare research organizations with access to real-world data to accelerate clinical trial processes. Read on to dive into the latest trends happening in pharma.

DeepMind’s AI accelerates antibiotics development by identifying bacterial protein in 15 minutes

Deepmind’s AI and machine learning system, AlphaFold, uncovered a bacteria protein structure in just 15 minutes that Marcelo Sousa, a biochemist at the University of Colorado Boulder, has been working to identify for the past 10 years. Despite a decade of research resulting in a vast store of experimental data, traditional research has failed to accomplish what a machine learning system achieved in a heartbeat.

The protein that Sousa was attempting to identify could significantly advance the development of antibiotics by identifying inhibitors that prevents bacterial resistance from building.

Pharma IQ Special Report: Unlock the Power of Data to Advance Pharma Businesses

Read the report to learn the importance of using data to create scientific value and how to digitize data for more efficient lab work. Download the Report.

Learn More

"This will be one of the most important datasets since the mapping of the human genome," said EMBL Deputy Director General and EMBL-EBI Director, Ewan Birney.

"Making AlphaFold predictions accessible to the international scientific community opens up so many new research avenues, from neglected diseases to new enzymes for biotechnology and everything in between. This is a great new scientific tool, which complements existing technologies, and will allow us to push the boundaries of our understanding of the world," Birney added.

DeepMind released a paper in the research journal, Nature, which details over 350,000 protein structures including a prediction of the entire human proteome (proteins that make up the human body).

It has been almost 50 years since Nobel laureate, Christian Anfinsen suggested a theory for the way that proteins are formed. Over the years since, researchers have dedicated countless hours of time to predict and identify protein structures.

DeepMind has provided confidence measures, which are intended to guide researches in the use of protein structure predictions in their own research. This means that scientists can identify which structures can be relied upon and where further research is necessary to validate some of the structure predictions.

With DeepMind launching the full code and methodology for AlphaFold AI and announcing that it will be available for free through a partnership with the European Molecular Biology Laboratory, the way the pharma industry conducts future protein structure identification research is likely to change.

“It’s a game changer,” Andrei Lupas, Evolutionary Biologist at the Max Planck Institute for Developmental Biology in Tübingen, Germany told Nature. “This will change medicine. It will change research. It will change bioengineering. It will change everything.”

Achieve Digital Business Success in Pharma with Data-Driven Approaches

42% of the industry claim efficient lab data management will have the biggest impact on industry growth in the next five years. Find out how to get ahead of the curve. Download the Pharma IQ Report Now.

Learn More

Real-world evidence research methodologies gains further credibility as Russia joins the trend

Russia’s President Vladimir Putin singed in a law that will allow a regulatory sandbox for a number of innovative, digital projects. This will mean that pharma and biotech companies have the license to process personal data from the health records of citizens, meaning clinical trials and studies can now be conducted on a vast store of real-world data.

An excerpt from the published federal law noted that: “Real-world evidence studies are widely used abroad and are fundamental both in terms of accumulating scientific and medical data and in terms of forming a comprehensive evaluation of diagnostic methods, drug and non-drug treatments, prevention and rehabilitation.

“The use of research results allows [pharma and biotech companies] to evaluate and optimize clinical guidelines and standards of care to improve their clinical and economic efficiency, as well as in the framework of pharmacovigilance measures.”

Russia is not the first to implement a framework that recognizes the value or real-word data but the fact that more countries are supporting this trend suggests that the application of real-world evidence will only grow in prevalence globally within pharma.

Karem Ooms, Executive VP and Head of Statistics at Quanticate, told Outsourcing Pharma: “[The pharma industry] has seen an acceptance of real-world data in recent years when in 2019, Pfizer had the iBRANCE approval that was largely based on analysis from real-world data.

“The advantages of real-world data gives insight into investigational drug’s performance in a real-world setting,” Ooms added.

Following Russia’s new data act, data processing and analysis organizations like Data Matrix will be able to conduct retrospective clinical studies without the need for informed consent to obtain anonymized data from healthcare facilities and data organizations. This effectively removes sample size barriers in many areas of research and allows for research samples to be gathered in a fraction of the time.

Our mission to make pharma businesses better is fueled by readers like you. Add your comments to the comment section below and tell us what you think of today’s stories and what you would like us to cover in next week’s feature for Keeping tabs on pharma.