A person walks next to the Google Cloud logo at the Mobile World Congress (MWC) in Barcelona, Spain, on February 27, 2023.
Sweet Nacho | Reuters
Google Cloud on Tuesday launched two new AI-powered tools designed to help biotech and pharmaceutical companies accelerate drug discovery and advance precision medicine.
A tool called the Target and Lead Identification Suite aims to help companies predict and understand the structure of proteins, a fundamental part of drug development. Another solution, the Multiomics Suite, will help researchers ingest, store, analyze and share large amounts of genomic data.
The new developments mark Google’s latest advance in the red-hot AI arms race, with tech companies competing for dominance in a market that analysts believe could one day be worth trillions. Since the release of OpenAI’s ChatGPT late last year, the company has been under pressure to showcase its generative artificial intelligence technology.
Google announced its generative chatbot Bard in February. Shares of parent company Alphabet rose 4.3% last week after Google unveiled several AI advances at its annual developer conference.
The two new Google Cloud suites help address a long-standing problem in the biopharmaceutical industry: the lengthy and costly process of bringing a new drug to the US market.
Pharmaceutical companies can invest anywhere from a few hundred million dollars and up more than $2 billion launch a single drug according to a recent Deloitte report. Their efforts are not always successful. Drugs that reach clinical trials have one 16% chance of approval in the US, according to another Deloitte report.
This high cost and dismal success rate comes with an extensive and lengthy research process that typically takes around 30 minutes 10 to 15 years.
The new suites will save companies a “statistically significant” amount of time and money throughout the drug development process, said Shweta Maniar, global director of life sciences strategy and solutions at Google Cloud. Google CNBC did not give specific figures.
“We help organizations get medicines to the right people faster,” Maniar said in an interview with CNBC. “I’m personally very excited, it’s something I and the team have been working on for a number of years.”
Both suites will be available to customers across the board from Tuesday. According to Google, costs vary by company. Several companies including Big Pharma Pfizer and the biotech companies Cerevel Therapeutics And Colossal Life Sciencesare already using the products.
Target and lead identification suite
According to Maniar, the Target and Lead Identification Suite aims to streamline the first critical step in drug development, identifying a biological target for researchers to focus on and develop a treatment.
Most commonly, it is a biological target a protein, an essential building block for disease and all other parts of life. Finding this target requires identifying a protein’s structure, which determines its function, or the role it plays in a disease.
“If you can understand the role, the protein structure, the role, you can start developing drugs on it now,” Maniar said.
However, this process is time-consuming and often unsuccessful.
Scientists can get around 12 months Just to identify a biological target, according to the National Center for Biotechnology Information. The two techniques According to Maniar, researchers traditionally employed to determine protein structures also have a high rate of error.
She also said that it is difficult for traditional technologies to increase or decrease the amount of work as needed.
Google Cloud’s suite takes a three-pronged approach to make this process more efficient.
The suite enables scientists to ingest, share and manage molecular data on a protein using Google Cloud Analytics Huba platform that allows users to securely share data between organizations.
Researchers can then use this data to predict a protein’s structure AlphaFold2a machine learning model developed by a subsidiary of Google.
AlphaFold2 runs on Google Vertex AI Pipeline, a platform that enables researchers to build and deploy machine learning models faster.
In minutes, AlphaFold2 can predict the 3D structure of a protein, more accurately than traditional technologies and at the scale researchers need. Predicting this structure is crucial because it can help researchers understand a protein’s function in a disease.
The final component of Google Cloud’s suite helps researchers figure out how the protein’s structure interacts with different molecules. A molecule can become the basis for a new drug if it changes the function of that protein and ultimately shows the ability to treat the disease.
Researchers can use Google Clouds High Performance Computing Resources to find “the most promising” molecules that could lead to the development of a new drug, according to a press release accompanying the new tools. These services provide the infrastructure Businesses need to accelerate, automate, and scale their work.
According to John Renger, Chief Scientific Officer, Cerevel, which focuses on developing treatments for neuroscientific diseases, typically has to sift through a large library of 3 million different molecules to find one that has a beneficial effect against a disease. He called this process “complicated, time-consuming and expensive”.
But Renger said that with Google Cloud’s suite, the company will be able to sort out molecules faster. Computers will take care of screening molecules and help Cerevel “get an answer really fast,” he said.
Renger estimates that Cerevel will save an average of at least three years by using the suite to discover a new drug. He said it’s difficult to estimate how much money the company will save, but stressed that the suite saves the resources and manual labor typically required to screen molecules.
“It means we can get to where we need to be quicker and cheaper, and we can get the medicines to patients much faster and without as many failures,” he told CNBC.
Cerevel has been working with Google for more than a month to better understand the suite and determine how the company will use it. But Renger hopes Cerevel will be “at a point where we’re getting some results” next month.
Google Cloud’s second solution, the Multiomics Suite, aims to help researchers solve another daunting challenge: analyzing genomic data.
Colossal Biosciences, a biotechnology company aiming to use DNA and genetic engineering to reverse extinctions, used the Multiomics Suite in their research.
As a startup, Colossal didn’t have the internal infrastructure needed to organize or decode massive amounts of genomic data. A human genome sequence alone requires more than 200 gigabytes of storage, and researchers predict they will need 40 exabytes by 2025 to store the world’s genomic data, the study found National Institute for Human Genome Research.
The institute estimates that every word ever spoken by humans could be stored in five exabytes, so building the technology to support genomic data analysis is no easy task.
Therefore, the Multiomics Suite aims to provide companies like Colossal with the infrastructure they need to make sense of big data so they can focus more on new scientific discoveries.
“If we had to do everything from scratch, that’s the power of Google Cloud, right?” Alexander Titus, vice president of strategy and computer science at Colossal, told CNBC in an interview. “We don’t have to build this from scratch, it definitely saves us time and money.”
Researchers’ ability to sequence DNA has historically exceeded their ability to decode and analyze it. However, as technology has improved in recent years, genomic data have provided new insights into areas such as the genetic variations associated with diseases.
Google Cloud’s Maniar said it could ultimately help develop more personalized medicines and treatments. In 2021 alone, two-thirds of the drugs approved by the Food and Drug Administration were supported by human genetics research, according to an article published in the journal “Nature.”
Maniar believes the Multiomics Suite will help drive further innovation.
Colossal CEO Ben Lamm said the Multiomics Suite is what gives the company the ability to conduct research “in any reasonable timeframe.” Colossal began piloting Google’s technology late last year. As a result, Lamm says the company is on track to produce a woolly mammoth by 2028.
According to Lamm, without the Multiomics Suite the company would have been set back by more than a decade.
“We wouldn’t be anywhere near where we are today,” he said.
Prior to using Google Cloud’s suite, much of Colossal’s data management was done manually using spreadsheets, Lamm said.
He said it would have been a “massive drain” on the company trying to create the more complex tools it needed for research.
“When it comes to biology, we’re not stuck in small amounts of data anymore,” said Titus of Colossal. “We think on the scale: How do we get insights into 10,000, 20,000, 10 million years of evolutionary history? And these questions simply cannot be answered without scalable computing infrastructure and tools like cloud computing and multiomics.”