This week Immunai raised $215 M to map our immune system with the help of AI. This round of funding comes after two acquisitions in the current year. The first one was single-cell genomics software firm Dropprint Genomics in March and second being Swiss bioinformatics company Nebion in July. These acquisitions and the financing are going to help to create the largest single-cell immune database in the world as per the co-founder and CEO Noam Solomon. The company spent its first two years largely focused on immuno-oncology and cancer research. For the past nine months, though, Immunai has expanded into autoimmune, cardiovascular and neuroinflammation indications, Solomon said. Immunai has around 30 partners ranging from Fortune 500 Pharma companies to academic institutes. The company hopes to help partners with pre-clinical and then also clinical trials using the proprietary database.
Immunai’s approach to developing new insights around the human immune system uses a “multiomic” approach — essentially layering analysis of different types of biological data, including a cell’s genome, microbiome, epigenome (a genome’s chemical instruction set) and more. The startup’s unique edge is in combining the largest and richest data set of its type available, formed in partnership with world-leading immunological research organizations, with its own machine learning technology to deliver analytics at unprecedented scale. They are moving from just observing cells, but actually to going and perturbing them, and seeing what the outcome is,” explained Voloch. This, from the computational side, later allows us to move from correlative assessments to actually causal assessments, which makes our models a lot more powerful. The next step is to say, ‘Okay, now that we understand the human immune profile, can we develop new drugs?’ Basically, they are using machine learning to identify what targets might be useful for drugmakers, what drugs might cause toxic reactions, and ultimately predict how a patient might respond to a potential treatment. Immunai claims this data set, called the Annotated Multi-omic Immune Cell Atlas, AMICA, is the largest in the world. By the end of 2020 the company had 12M cells in AMICA.
The company founders strongly believe in this approach and said they don’t have a reliance on stronger upfront payments but care much more about success-based payments.
This week
Insilico medicine, an AI-first end-to-end drug discovery company founded in 2014 had very exciting news to share. Insilico Medicine started its first in humans clinical trial using the cellular target as well as the molecule discovered by its artificial intelligence platforms in just less than 18 month. For a total cost of about $2.6 million the company was able to discover and whittle down more than 20 disease targets and dozens of deep-learning-generated molecules to predict the most successful candidate through its Pharma.AI platform. For reference a typical preclinical program which is estimated to be around
$430 million out-of-pocket expenses and above $1 billion capitalized, and takes anywhere from
three to six years to finalize. This week first healthy volunteer in an Australian study has received a limited, intravenous dose of the company’s ISM001-055, a small-molecule inhibitor aimed at the chronic lung disease. The CEO claimed “There are very few examples of a pharmaceutical company discovering a new target for a broad range of diseases, designing a novel molecule and initiating human clinical trials. To my knowledge, nobody has achieved this with AI to-date.”. He further added "The failure rates in preclinical target discovery are very high and even after the targets are validated in animal models, over half of phase 2 clinical trials fail primarily due to the choice of target, Target discovery is the fundamental grand challenge of the pharmaceutical industry."
The company’s AI suite includes PandaOmics for narrowing down disease targets, Chemistry42 for generating potentially druglike compounds and InClinico for aiding in the design of clinical trials and predicting their success through actuarial modeling. In addition to the chronic lung disease trial, the company hopes to finish pre-clinical testing for kidney focussed molecules by the end of 2022.
No comments:
Post a Comment