AI & RoboticsNews

How Protai’s AI-powered platform is improving drug discovery

Did you miss a session from the Future of Work Summit? Head over to our Future of Work Summit on-demand library to stream.


As more healthcare providers and vendors continue working towards improving patient care using AI and data, Tel-Aviv-based, AI-powered drug discovery startup Protai claims it’s reshaping the drug discovery and development process using proteomics and an end-to-end AI-based platform. The company said its AI-powered platform maps the course of a disease on the protein level, thereby enhancing the capacity to observe cellular function and improving how new drugs are discovered cost-effectively.

Protai noted in a recent press release that regardless of the contribution of genome-level information to the efforts of drug research and development, it fails to represent the functional layer of the cell reflected and dominated by proteins.

“This lack of functional understanding of a disease’s molecular mechanisms is one of the main shortcomings of the current drug discovery and development process,” Protai said.

AI expert and Protai CTO Kirill Pezner told VentureBeat that Protai brings AI and a data-centered approach to everything it does. The company draws inspiration from “computational photography” techniques that are used in smartphone cameras for image enhancement features like HDR, 20x zoom, and night vision — applying similar ideas to the protein identification problem in the mass spectrometry process, according to Pevzner.

“We use the enhanced number of proteins and interactions we observe to gain explainable biology — predictions on how a given network of proteins (human or otherwise) will behave in different conditions. For example, how they behave after getting exposed to a drug,” Pevzner said.

Protai has emerged from stealth mode, along with $8 million in seed funding, to provide a proteomics-based platform for faster and more accurate drug discovery, the company said in a written statement. The funding was co-led by Grove Ventures and Pitango Venture Capital and will help to further develop Protai’s platform, accelerate its discovery programs, and enhance its partnerships with pharmaceutical companies.

Beyond the research phase

Protai said its technology has moved beyond the research phase. Pevzner said that the company already has a proof-of-concept in lung cancer, where it identified several valuable protein targets. The company added that it is currently pursuing these targets in preclinical development.

This approach aims to enable Protai to increase accuracy in drug discovery and improve the development process, saving time and lowering the costs of R&D, said the company.

Protai claims its approach is different from others in the industry because it focuses on the protein level of diseases, while most discovery platforms focus on genetics (DNA/ RNA) data, which is only a proxy to reality.

“Proteins and their interactions are where the real biological action happens,” Pevzner said.

Protai is like a unique compass for directing drug discovery, Protai CEO and cofounder Eran Seger said. He said the company is systematically mapping diseases on the protein level to create a new layer of functional information that enables it to identify therapeutic and diagnostic targets to better combat a wide range of complex diseases.

Market competition and collaboration opportunities

Although Protai has competition in tool companies and AI-for-pharma companies, the company says it’s staying ahead by building an internal drug development pipeline going from discovery to preclinical and clinical stages.

Pevzner said that Protai is collaborating with pharmaceutical companies on joint projects, with a focus on cancer, but will consider expanding to autoimmune and neurodegenerative diseases in the near future.

“The market can be segmented into several types of players. Big pharma companies pursue the same disease areas and indications as us. We are open to collaborating and bringing each company’s strength to the table,” Pevzner said.

While tool companies that develop solutions for better identifying proteins tend to optimize for the number of proteins identified, Protai says its platform has an edge as it optimizes for better biological explainability and predictability as well as drug development.

In addition, Protai says its technology is ahead of AI-for-pharma companies that use genomic and transcriptomic (RNA) data, as they provide only a proxy to reality, while the real action happens on the protein level.

Expanding R&D

On the heels of this additional capital, Protai will expand its platform to all drug R&D stages, which include the following:

  • Selecting the correct organism models when performing preclinical testing
  • Selecting the right patients during clinical trials
  • Expanding the indication of already approved drugs.

All of these are based on what the company calls “explainable biology,” and solve the challenge that biological predictions have on how a given protein network responds to a particular treatment.

Protai claims it has created the world’s largest and most diverse proteomics database with more than 50,000 clinical samples by harmonizing large clinical datasets, as well as healthy samples from various organs and indications.

The company says this allows it to establish a baseline that accurately simulates biological functional processes for a variety of diseases and accelerates drug R&D through clinical and preclinical stages.

VentureBeat

VentureBeat’s mission is to be a digital town square for technical decision-makers to gain knowledge about transformative technology and transact.

Our site delivers essential information on data technologies and strategies to guide you as you lead your organizations. We invite you to become a member of our community, to access:

  • up-to-date information on the subjects of interest to you
  • our newsletters
  • gated thought-leader content and discounted access to our prized events, such as Transform 2021: Learn More
  • networking features, and more

Become a member


Author: Kolawole Samuel Adebayo
Source: Venturebeat

Related posts
AI & RoboticsNews

DeepSeek’s first reasoning model R1-Lite-Preview turns heads, beating OpenAI o1 performance

AI & RoboticsNews

Snowflake beats Databricks to integrating Claude 3.5 directly

AI & RoboticsNews

OpenScholar: The open-source A.I. that’s outperforming GPT-4o in scientific research

DefenseNews

US Army fires Precision Strike Missile in salvo shot for first time

Sign up for our Newsletter and
stay informed!