EXSCIENTIA
20.9.2022 15:01:35 CEST | Business Wire | Press release
Exscientia (Nasdaq: EXAI), ETH Zurich, the Medical University of Vienna, and the Center for Molecular Medicine (CeMM) today announced a new publication in Blood Cancer Discovery, a journal of the American Association for Cancer Research, titled “Deep Morphology Learning Enhances Precision Medicine by Image-Based Ex Vivo Drug Testing” from the laboratory of Prof. Berend Snijder. This post-hoc analysis builds on the transformative work of the EXALT-1 trial, published in Cancer Discovery, by using deep learning algorithms to classify complex cell morphologies in patient cancer tissue samples into disease “morphotypes.”
EXALT-1 was the first prospective trial to demonstrate significantly improved outcomes for late-stage haematological cancer patients using an AI-supported precision medicine platform to guide personalised treatment recommendations as compared to physician’s choice of treatment. In EXALT-1, 40% of patients experienced exceptional responses lasting at least three times longer than expected for their respective disease. The post-hoc analysis published today in Blood Cancer Discovery shows that combining the technology as used in EXALT-1 with new deep learning advancements that take advantage of cell-specific features in high-content images revealed a potential to further increase these patient outcomes.
“Following results of the EXALT-1 study, these findings continue to validate that our AI-guided precision medicine platform has the ability to identify highly actionable clinical treatment recommendations for blood cancers, deepening our insights and enhancing the clinical predictive power of the platform to help patients,” said Gregory Vladimer, Ph.D., VP Translational Research at Exscientia and co-inventor of the platform technology. “Cell morphology, or assessing the characteristics of cells, is fundamental to the diagnosis of cancer. Within this research, we were able to utilise deep learning within the platform to improve our ability to identify personalised cancer treatments, leading to improved clinical outcomes for patients. At Exscientia, we are excited to expand the platform’s applications in order to bring personalised medicine to broader populations.”
“We believe performing drug screens directly in tumour tissues of cancer patients is a great step forward in understanding tumour complexity compared to traditional cell model systems. The fact that we can now harness the power of deep learning to turn these terabytes of images into actionable insights is very exciting indeed,” added Prof. Berend Snijder, Principal Investigator at the Institute of Molecular Systems Biology of the ETH Zurich in Switzerland.
The impact of deep learning on the clinical predictive power of ex vivo drug screening was assessed in a post-hoc analysis of 66 patients over a period of three years in a combined data set of 1.3 billion patient cells across 136 ex vivo tested drugs across haematological diagnoses including acute myeloid leukaemia, T-cell lymphomas, diffuse large B-cell lymphomas, chronic lymphocytic leukaemia and multiple myeloma. Patients receiving treatments that were recommended by the platform’s immunofluorescence analysis or deep learning on cell morphologies showed an increased rate of achievement of exceptional clinical response, defined as a progression free survival period that lasted three times longer than expected for each patient’s respective disease. Post-hoc analyses confirmed that the clinical predictions became more accurate when also considering the drug toxicity on the healthy cells within the tested patient sample.
Exscientia’s precision medicine platform uses custom deep learning and computer vision techniques to extract meaningful single-cell data from high content images of individual patient tissue samples. This analysis generates clinically-relevant insights into which treatments will deliver the most benefit to an individual patient. Further evaluation of individual patient results through Exscientia’s genomics and transcriptomics capabilities may help Exscientia further understand which other patients may benefit from similar treatments. The underlying technology was developed by Dr. Gregory Vladimer and Prof. Berend Snijder while working in the laboratory of Giulio Superti-Furga at the CeMM Research Center for Molecular Medicine in Austria.
About Exscientia
Exscientia is an AI-driven pharmatech company committed to discovering, designing and developing the best possible drugs in the fastest and most effective manner. Exscientia developed the first-ever functional precision oncology platform to successfully guide treatment selection and improve patient outcomes in a prospective interventional clinical study, as well as to progress AI-designed small molecules into the clinical setting. Our internal pipeline is focused on leveraging our precision medicine platform in oncology, while our partnered pipeline broadens our approach to other therapeutic areas. By pioneering a new approach to medicine creation, we believe the best ideas of science can rapidly become the best medicines for patients.
Exscientia is headquartered in Oxford (England, U.K.), with offices in Vienna (Austria), Dundee (Scotland, U.K.), Boston (Mass., U.S.), Miami (Fla., U.S.), Cambridge (England, U.K.), and Osaka (Japan).
Visit us at https://www.exscientia.ai or follow us on Twitter @exscientiaAI.
Forward-Looking Statements
This press release contains certain forward-looking statements within the meaning of the “safe harbor” provisions of the Private Securities Litigation Reform Act of 1995, including statements with regard to Exscientia’s expectations with respect to the progress of development of candidate molecules, timing and progress of, and data reported from, preclinical studies and clinical trials of Exscientia’s product candidates, and Exscientia’s expectations regarding its precision medicine platform and AI-driven drug discovery platform. Words such as “anticipates,” "believes," “expects,” "intends," "projects," "anticipates," and "future" or similar expressions are intended to identify forward-looking statements. These forward-looking statements are subject to the uncertainties inherent in predicting future results and conditions, including the scope, progress and expansion of Exscientia’s product development efforts; the initiation, scope and progress of Exscientia’s and its partners’ clinical trials and ramifications for the cost thereof; clinical, scientific, regulatory and technical developments; and those inherent in the process of discovering, developing and commercialising product candidates that are safe and effective for use as human therapeutics, and in the endeavor of building a business around such product candidates. Exscientia undertakes no obligation to publicly update or revise any forward-looking statements, whether as a result of new information, future events or otherwise, except as may be required by law.
To view this piece of content from cts.businesswire.com, please give your consent at the top of this page.
View source version on businesswire.com: https://www.businesswire.com/news/home/20220919005867/en/
About Business Wire
Subscribe to releases from Business Wire
Subscribe to all the latest releases from Business Wire by registering your e-mail address below. You can unsubscribe at any time.
Latest releases from Business Wire
Would You Let AI Manage Your Next Trip?17.11.2026 13:06:00 CET | Press release
New research suggests AI agents could change how travelers choose airlines and hotels by 2032The Intelligent Journey 2032 explores four directions travel could take by early in the next decade, and how technology, particularly AI, will connect travelers with airlines, airports, hotels and other travel companies.The study suggests the future will be defined by travelers deciding what they are willing to delegate, with clear consent, spending limits, and the ability to retain control as key considerations.It also identifies travel orchestration as the strategic prize for the industry, as AI could reshape travel commerce, and shift value toward those able to coordinate the entire journey across suppliers, payments, identity, disruption and service. AI is already transforming the traveler journey, helping people discover, plan and navigate their trips. The question is how far travelers will let AI make decisions for them in the future: booking, paying, changing plans and recovering from di
Iconic Raises $10M to Build Software That Understands the World’s Biggest Projects17.11.2026 13:01:00 CET | Press release
Iconic has raised $10 million in seed funding led by Peak Capital, with participation from Bridford Group, Common Magic, Graduate Ventures, NP-Hard, and Tiny VC. Since its founding in mid-2025, Iconic has signed five clients in energy, infrastructure, and AI infrastructure: a global energy major, a leading European utility, a major European airport, a European rail infrastructure owner, and a global contractor building semiconductor fabs and data centers. Each spends over $1 billion annually on capital projects. An estimated $15 trillion is invested in capital projects annually, yet fewer than 3% are delivered on time, on budget, and to plan. Capital projects rarely fail because of engineering complexity, but because decisions are made without a complete understanding of the project. Information is fragmented across documents and systems shared by owners, contractors, and engineering firms. Decisions are hard to reverse, with consequences lasting years through delays, claims, and cost
Quaise Energy Signs 50 MW Geothermal Power Purchase Agreement with Google17.11.2026 12:50:00 CET | Press release
Agreement advances development of commercial-scale superhot geothermal, will supply carbon-free energy to Oregon communities as early as 2030 Quaise Energy, a leading developer of utility-scale superhot geothermal energy, today announced that Google has signed a power purchase agreement (PPA) for 50 megawatts (MW) of superhot geothermal power from Project Obsidian, Quaise’s flagship project in Central Oregon. Once online, this always-on, carbon-free energy is slated to support Google’s existing data center operations in The Dalles, Ore. and the region’s communities. The agreement will help catalyze the commercial development of superhot geothermal energy, providing benefits for ratepayers and helping protect the environment. This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20261117923219/en/ Beginning as early as 2030, Google will purchase 50 MW of power from Project Obsidian. The initial phase of development will use convention
Nowhere to Sit, Nothing to Do: Europe’s Biggest Airports Fall Short for Passengers17.11.2026 12:24:00 CET | Press release
AirHelp data shows that nearly half of Europe’s biggest airports score below the global average for both seating and entertainment. One in four of Europe’s 50 biggest airports scores below the global average on all four parts of the experience passengers rated, according to AirHelp data covering 279 airports worldwide. Passengers rated each airport on wait times, restaurants, seating and entertainment. Twelve airports, including Dublin, Manchester, Lisbon, London Luton and Milan Bergamo, came in below the global average on all four. Only four beat all four averages: Zurich, Warsaw, Naples and Ankara. Entertainment is the weak spot almost everywhere Entertainment was the lowest-rated part of the experience at 45 of the 50 airports, averaging 6.5 out of 10, with more than half of the airports falling below the global average of 6.7. Seven airports scored less than 6, including Manchester, Stansted, Dublin and Oslo. The data also suggests that passengers who can’t find a seat usually have
Infobip Expands Relationship With Anthropic With Verified Claude Connector for Global Messaging17.11.2026 10:00:00 CET | Press release
New integration enables Claude users to send and track messages across SMS, RCS, MMS and Viber through Infobip. Global AI-first cloud communications platform Infobip has expanded its collaboration with Anthropic with the launch of the Infobip Message connector in the Claude Marketplace. The Anthropic-verified connector enables developers, enterprises and builders using Claude to add global messaging capabilities to AI agents without building separate integrations for individual communication channels. The integration connects Claude with Infobip’s global communications infrastructure, enabling AI agents to send messages across SMS, RCS, MMS and Viber through a single connector. Using Infobip’s send and check status tools, agents can trigger outbound messages and track their delivery status, allowing them to incorporate real-world communication into automated workflows. For businesses building agentic AI applications, the connector can support use cases such as order confirmations, deli
In our pressroom you can read all our latest releases, find our press contacts, images, documents and other relevant information about us.
Visit our pressroom
