AI driven MOA elucidation

Anima's Compass is built around Anima's MOAi technology - a breakthrough approach that for the time employs AI to address the huge problem of elucidating the mechanisms of action (MOA) of compounds discovered in phenotypic screening. With our MOAi technology, we are able to rapidly determine the MOA of discovered molecules and identify their molecular targets in the novel target space of mRNA biology modulators.

MOA recognition with AI mRNA image analysis


The first component of MOAi is AI-driven image analysis that suggests the most likely MOAs for the active compounds.

As the screening runs, hundreds of thousands of compounds are evaluated in millions of automated biology experiments. Each experiment is testing whether the compound is active in controlling mRNA biology for the protein of interest. The results are visible in high-resolution images where we can see the effect of the compound on the mRNA life cycle, such as mRNA translation, mRNA relocalization, mRNA stability, and mRNA splicing.

As an image is taken, it is uploaded to our cloud-based AI software and the AI image analysis takes over. By now, we have established a database of billions of images that came from dozens of projects on many different targets and were used to train the MOA recognition system. The system looks at the image and determines whether it has already seen a similar image before. The idea is like “facial recognition” technology applied to MOA elucidation. Compounds that work through a given MOA, generate images that are similar to other compounds' images with the same MOA.

Machine Learning (ML) guided MOA assays

The next step utilizes our machine learning guided system that takes the recommended MOAs, and based on our built in understanding of the biology around them, suggests experiments to further investigate the potential MOA.

By applying dozens of proprietary MOA assays, the system navigates like a Compass as it analyzes the results of experiments and uses its built-in knowledge graph of mRNA biology to point us to the next experiment that needs to be performed.

As experiments are executed, their results are integrated into the system and the algorithm iteratively determines the path of experiments, by calculating the probabilities of each proposed MOA based on all previously seen results, navigating until the mechanism of action is revealed, and final confirmatory experiments are then done on the proposed molecular target.

MOAi technology successfully utilized across Anima's lead programs

Area Indication mRNA modulation Target
Immunology Fibrosis Collagen-1 1
Oncology c-Myc tumors c-Myc 5

We have successfully employed our platform to discover the MOA of six different molecules in less than a year. It has allowed us to de-risk projects from the onset of their discovery stage.

Our lead compounds in Fibrosis and Oncology were identified to be acting through novel molecular targets that modulate the biology of COL1a1 and c-Myc mRNAs. The understanding of the novel mechanisms through which these compounds are working helped us to optimize all these compounds.