Recursion Pharmaceuticals. has been granted a patent for a method that employs machine learning to analyze perturbation data from various biological experiments. The process involves generating, aligning, and aggregating embeddings to facilitate comparisons of perturbation effects, enhancing the evaluation of biological maps and user interfaces. GlobalData’s report on Recursion Pharmaceuticals gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Recursion Pharmaceuticals, Vehicle driver physiological monitoring was a key innovation area identified from patents. Recursion Pharmaceuticals's grant share as of July 2024 was 39%. Grant share is based on the ratio of number of grants to total number of patents.
Machine learning methods for biological perturbation data analysis
The patent US12073638B1 outlines a computer-implemented method and system for processing perturbation data from various experimental units. The method involves several key steps: receiving perturbation data, generating embeddings using a machine learning model, aligning these embeddings through a statistical alignment model, and aggregating the aligned embeddings to create comprehensive representations. The aggregated embeddings can be utilized to generate comparisons between different perturbations, enhancing the understanding of their effects. The method also allows for the generation of various types of embeddings, including well-level, gene-level, and pathway-level embeddings, which can be derived from transcriptomic profiles, phenomic images, or invivomic data.
Additionally, the patent describes the use of convolutional neural networks for generating embeddings and includes provisions for filtering embeddings based on quality criteria. The alignment process can involve multiple perturbation classes, ensuring that embeddings from different experiments are accurately compared. The system is designed to provide similarity measures between perturbation-level embeddings, which can be displayed on client devices. Furthermore, the method incorporates a proximity bias model to correct for biases in the data, ensuring more accurate alignment and aggregation of embeddings. Overall, this patent presents a comprehensive approach to analyzing perturbation data, leveraging advanced machine learning techniques to facilitate meaningful comparisons and insights in experimental research.
To know more about GlobalData’s detailed insights on Recursion Pharmaceuticals, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies
