Methods and apparatuses for generating peptides by synthesizing a portion of a design space to identify peptides having non-canonical amino acids
Inventors
Lee, Francis • STECKBECK, Jonathan D. • Holste, Hannes
Assignees
Publication Number
US-11512345-B1
Publication Date
2022-11-29
Expiration Date
2041-08-13
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
In one aspect, a computer-implemented automated flow synthesis platform configured to use an artificial intelligence (AI) engine is disclosed and includes a reaction chamber configured to synthesize a sequence, detectors configured to monitor the synthesis of the sequence in the reaction chamber, wherein the synthesis uses an automated flow process, and a computing device communicatively coupled to the detectors. The computing device receives measurements from the one or more detectors, wherein the measurements comprise a spectral profile at each coupling of each amino acid in the sequence, trains, using training data comprising the measurements, machine learning models to determine a synthesizing recipe that enables the sequence to be synthesized, wherein the synthesizing recipe comprises parameters used during the automated flow process to synthesize the sequence, and controls, using the synthesizing recipe, the synthesis of the sequence in the reaction chamber.
Core Innovation
The invention provides a computer-implemented automated flow synthesis platform that utilizes an artificial intelligence (AI) engine, particularly machine learning models, to optimize and control the synthesis of peptide and peptidomimetic sequences. The system includes a reaction chamber for synthesis, detectors to monitor each amino acid coupling event via spectral profiles, and a computing device to receive and process measurements. Specifically, the approach enables the real-time collection and use of data representing the chemical reactions during synthesis cycles.
By analyzing spectral profiles from each coupling of amino acids, the AI system is trained to determine optimized synthesizing recipes. These recipes specify parameter attributes such as temperature, solvent, protecting group, resin anchor, catalysts, and other synthesis conditions. This enables the platform to dynamically control the automated flow process, ensuring desired chemical reactions and minimizing undesirable side reactions, even when incorporating non-canonical amino acids.
The problem addressed by the invention is the inefficiency and limited discovery capability of conventional drug and peptide synthesis approaches. Traditional synthesis methods rely heavily on human design and trial-and-error, are restricted to narrow design spaces, and often require labor-intensive experimentation that wastes resources and provides limited or suboptimal results, particularly for sequences containing non-canonical amino acids. The patent's system seeks to overcome these obstacles by leveraging AI and real-time process analytics for efficient, scalable, and robust peptide and peptidomimetic discovery and synthesis.
Claims Coverage
There is one independent claim in the patent, which defines the primary inventive features of the computer-implemented automated flow synthesis platform utilizing an AI engine.
Automated flow synthesis platform integrated with AI-driven real-time process analytics
The platform comprises: - A reaction chamber configured to synthesize a sequence via an automated flow process. - One or more detectors monitoring the synthesis in the reaction chamber and generating measurements including spectral profiles at each coupling of each amino acid in the sequence. - A computing device communicatively coupled to the detectors, configured to receive the measurements. - Training of one or more machine learning models using the training data (measurements) to determine a synthesizing recipe enabling synthesis of the sequence. The synthesizing recipe includes one or more parameters used to control at least the reaction chamber during the automated flow process. - The computing device controls, using the synthesizing recipe, the synthesis of the sequence in the reaction chamber.
The claim’s coverage centers on an automated flow synthesis system with integrated AI that receives real-time reaction measurements, trains machine learning models to determine and apply optimized synthesis recipes, and precisely controls sequence synthesis processes.
Stated Advantages
Enables efficient, automated, and scalable discovery and synthesis of peptides and peptidomimetics, including those with non-canonical amino acids, by expanding the design space beyond conventional techniques.
Reduces waste and resource consumption by allowing real-time optimization of synthesis parameters, minimizing undesired side reactions and improving yield.
Provides higher accuracy, efficiency, and speed in generating and synthesizing candidate drug compounds compared to traditional trial-and-error or batch methods.
Improves economic performance by synthesizing minimum required amounts for data collection, thus saving costly reagents and enhancing process throughput.
Enables dynamic adjustment and continuous refinement of synthesis recipes using machine learning models trained on real-time spectral and analytical data.
Documented Applications
Synthesis and discovery of therapeutic peptide and peptidomimetic drug candidates, including sequences containing canonical and non-canonical amino acids.
Application in the anti-infective market for discovery and synthesis of therapeutics for infections such as prosthetic joint, urinary tract, respiratory, and wound infections.
Use in the anti-cancer, anti-microbial, anti-biofilm, anti-inflammatory, animal health/veterinary, and industrial anti-biofouling domains for generating optimized therapeutic or functional biomaterial peptides.
Manufacture and testing of candidate peptides for specific biomedical activities such as anti-infective, anti-cancer, immunomodulatory, cytotoxic, or neuromodulatory effects.
Interested in licensing this patent?