AI Drug Discovery News (3): AstraZeneca and Novartis
AI/ML tools, startups, companies and investors
For the first and second part:
Quote of the Day 🦉
“Like musicians, like mathematicians—like elite athletes—scientists peak early and dwindle fast.
It isn’t creativity that fades, but stamina: science is an endurance sport.
To produce that single illuminating experiment, a thousand nonilluminating experiments have to be sent into the trash; it is battle between nature and nerve. Avery”.
By Siddhartha Mukherjee, The Gene: An Intimate History
AstraZeneca and AI Drug Discovery
AstraZeneca plc (AZ) is a British-Swedish multinational pharmaceutical and biotechnology company with its headquarters at the Cambridge Biomedical Campus in Cambridge, England. The company was founded in 1999 through the merger of the Swedish Astra AB and the British Zeneca Group. Since the merger it has been among the world's largest pharmaceutical companies and has made numerous corporate acquisitions, including Cambridge Antibody Technology (in 2006), MedImmune (in 2007), Spirogen (in 2013) and Definiens (by MedImmune in 2014). It has its research and development concentrated in three strategic centers: Cambridge, England; Gothenburg, Sweden and Gaithersburg in Maryland, US. It has a portfolio of products for major diseases in areas including oncology, cardiovascular, gastrointestinal, infection, neuroscience, respiratory and inflammation.
In particular, the Gothenburg R&D site is one of the major AZ research centers. The Molecular AI team in Discovery Sciences focuses on AI/ML applications in drug design. It has state-of-the-art computational tools and high performance computing resources. The team works in an interdisciplinary environment by closely interacting with experts from chemistry automation and medicinal chemistry, and have extensive experience working in EU and Swedish government funded projects, such as WASP, IMI2-MELLODDY, H2020-ExCAPE, H2020-BIGCHEM, etc.
AZ is also involved in the AI center Cambridge Centre for AI in Medicine, a collaboration between AstraZeneca, the University of Cambridge and GSK, that combines academia research with real-world industrial challenges and aims to develop cutting-edge AI for drug development. AZ announced in 2019 three large-scale initiatives (New Global R&D Centre, AI Innovation Centre and a joint investment fund with CICC/China International Capital Corporation Limited) in Shanghai China making a $1 billion capital infusion into the Chinese biotech landscape. And on February 16 2021, AZ announced a collaboration with Mila (a Quebec AI Institute) to drive forward AI innovation in healthcare for drug discovery and development.
On December 06, 2023, AbSci announced a potential $247M partnership with AZ to focus on the discovery of novel cancer treatments with the help of AI technology. The deal includes an upfront commitment, R&D money, milestone payments and royalties on product sales totaling up to $247M. The project will leverage Absci's Integrated Drug Creation platform, which combines scalable wet lab technologies with AI, and facilitates optimization of multiple drug features pivotal for therapeutic advantages, and AZ’s oncology research and development knowledge.
In January 2023, AbSci in Canada became the first company “to create and validate de novo antibodies in silico” using generative AI. In April 2023, AbSci and M2GEN (now Aster Insights), an oncology-focused health informatics solutions company with the most advanced lifetime consented clinico-genomics data, announced a partnership to create new cancer medicines. In particular, Absci’s generative AI drug creation platform will tap into M2GEN’s clinical and molecular data set, ORIEN AVATAR, to accelerate the creation of onco-therapeutics.
Let’s see now AZ’s AI drug discovery collaborations starting from 2019 ⛹️♂️
🏀 In 2019, AZ announced a collaboration with BenevolentAI in order to use ML and AI to discover potential new drugs for chronic kidney disease and idiopathic pulmonary fibrosis. BenevolentAI is using AI for scientific data mining, data contextualisation and deriving hypotheses. In particular, they have developed the Benevolent Platform® (the platform is disease agnostic), a drug discovery platform built on powerful data foundations.
On October 6, 2022, BenevolentAI announced that AZ has selected an additional two novel targets to enter its drug portfolio, for chronic kidney disease and idiopathic pulmonary fibrosis, resulting in two milestone payments to BenevolentAI.
🏀 In 2019, Gatehouse Bio (Massachusetts, United States, 2016) announced a collaboration with AZ to explore the identification of new targets for respiratory and cardiovascular diseases using Gatehouse Bio’s AI powered platform. Gatehouse Bio is using a technology that is based on a patented, revolutionary approach (RNAlytics platform) to uncover small RNA (sRNA) signatures of disease using ML.
On September 08, 2022, Gatehouse Bio Extended Its Partnership with AstraZeneca to Develop RNA Therapeutics for Heart Failure, since their ability to identify small RNA mutations opens a novel class of targetable biology and an opportunity for a portfolio of oligonucleotide therapeutics that target specific groups of patients.
🏀 In 2019, AZ announced a collaboration with DeepMatter (Glasgow, Scotland 2015) to improve the productivity and reproducibility of compound synthesis by combining the pharma's automated compound synthesis platform with Deepmattergroup’s DigitalGlassware™ data collection and structuring technology, through a collaboration whose value was not disclosed. DeepMatter is a big data and analysis company focused on enabling reproducibility in chemistry and SmartChemistry®, by building a cloud-based platform to share chemical reaction and sensor data direct from the laboratory to enable medicines to be made better and more quickly.
🏀 In 2020, AZ announced a collaboration with ProteinQure to apply structure-based design to the creation of therapeutic libraries with peptide therapeutics., by leveraging ProteinQure's expertise in computational methods and structure-based drug design. ProteinQure (Toronto, Canada 2017) uses AI and physics based methods for the computational design of de-novo protein therapeutics like antibodies, peptides, and other protein-based drugs that are capable of targeting a broad range of biological targets outside the scope of traditional small molecule therapeutics.
🏀 In January 2021, AZ teamed up with AliveCor, a maker of AI-enabled personal ECG devices (electrocardiogram) namely the KardiaMobile® devices, in an effort to study new ways of managing cardio, renal and metabolic issues. AliveCor (California US, 2010) offers an FDA-cleared mobile heart solution that helps save lives since their device (Kardia-K AI) will turn any smartphone into a clinical-quality electrocardiogram (ECG) recorder. The strategic collaboration with AZ will leverage AliveCor's diagnostics and AI capabilities to develop non-invasive (without needing to draw blood from the patient) potassium monitoring solutions to monitor kidney function.