Computer Model Designs Proteins by Matching Structure to Sequence
IBM's 2025 patent describes a computer system that designs new protein sequences by first understanding a target 3D protein shape and then generating a sequence that would fold into that shape.
Original patent title: “Embedding-based generative model for protein design”
IBM's 2025 patent describes a computer system that designs new protein sequences by first understanding a target 3D protein shape and then generating a sequence that would fold into that shape. Granted to International Business Machines in 2025 with 28 claims, and it is expected to expire in 2041.
Coverage
What does this patent actually cover?
This patent details a computer method for designing new protein sequences. It uses advanced AI models called transformers. First, it takes a known protein's 3D structure and converts it into a numerical representation (a 'latent fold representation') in a 'second latent space.' Simultaneously, it takes the protein's amino acid sequence and converts it into a numerical representation (a 'latent sequence representation') in a 'first latent space.' The system then trains a decoder to learn how these two representations relate, essentially creating a bridge between protein shape and protein sequence. When given a new target 3D protein structure, the system encodes it and uses the trained decoder to generate a new amino acid sequence that should fold into that specific target structure. For example, it could be used to design a protein that performs a specific function by first defining the necessary 3D shape for that function.
The gap
What does this patent NOT cover?
- Designing biological sequences without using a transformer model encoder
- Methods that do not involve generating latent sequence representations
- Methods that do not generate latent fold representations from 3D structures
- Systems that do not train a decoder to learn a joint latent space between sequence and fold representations
- Designing sequences for structures not represented in 3D voxels
- Methods that do not involve inverse folding of three-dimensional structures
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
The innovation lies in using two separate transformer encoders to create distinct numerical 'fingerprints' for both the protein's sequence and its 3D structure, then training a decoder to map between these fingerprints. This allows the system to 'design backwards' from a desired shape to a workable sequence.
The Patent Drawing
Schematic visualization of the patent's claim structure. Hand-drawn diagrams in progress for each landmark patent.
Where you've seen this
Real-world examples
Protein design software for drug discovery
AI-driven enzyme engineering platforms
Computational biology research tools
Why it matters
The bigger picture
Designing novel proteins with specific functions is crucial for developing new medicines, enzymes for industrial processes, and advanced materials. This patent represents a significant step in using AI to automate and accelerate the discovery of proteins with desired structural and functional properties.
Filed
May 11, 2021
Granted
September 9, 2025
Market context
Who's building on this
Companies in this space
Companies like DeepMind (Google), Generate Biomedicines, and Absci are actively developing AI platforms for protein design. IBM, as the assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →, is also a key player in this space with its AI research.
Market impact
This patent contributes to the growing field of AI-driven protein engineering, which aims to revolutionize drug discovery and biotechnology. By enabling the design of proteins with specific folds, it could accelerate the development of novel therapeutics and industrial enzymes, potentially creating new markets and disrupting existing ones.
Claim 1 — Plain English
What this patent covers
This patent details a computer method for designing new protein sequences. It uses advanced AI models called transformers. First, it takes a known protein's 3D structure and converts it into a numerical representation (a 'latent fold representation') in a 'second latent space.' Simultaneously, it takes the protein's amino acid sequence and converts it into a numerical representation (a 'latent sequence representation') in a 'first latent space.' The system then trains a decoder to learn how these two representations relate, essentially creating a bridge between protein shape and protein sequence. When given a new target 3D protein structure, the system encodes it and uses the trained decoder to generate a new amino acid sequence that should fold into that specific target structure. For example, it could be used to design a protein that performs a specific function by first defining the necessary 3D shape for that function.
The clever bit
The innovation lies in using two separate transformer encoders to create distinct numerical 'fingerprints' for both the protein's sequence and its 3D structure, then training a decoder to map between these fingerprints. This allows the system to 'design backwards' from a desired shape to a workable sequence.
What it does not cover
- Designing biological sequences without using a transformer model encoder
- Methods that do not involve generating latent sequence representations
- Methods that do not generate latent fold representations from 3D structures
- Systems that do not train a decoder to learn a joint latent space between sequence and fold representations
- Designing sequences for structures not represented in 3D voxels
- Methods that do not involve inverse folding of three-dimensional structures
Patent timeline
Application submitted to the patent office
Application published, typically 18 months after filing
Patent officially issued
Patent enters public domain
PatentBrief Score
Impact Score
Early stage
Citation count
0/40
No citations yet
Claim breadth
19/20
Very broad protection
Recency
20/20
Granted within 5 years
Assignee scale
0/20
Independent or smaller assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →
PatentBrief Impact Score — based on citation count, claim breadth, recency, and assignee scale. Not a legal assessment.
Heuristic Value Estimate
What this patent might be worth
$31K – $100K
Midpoint $62K · 14.7 yr remaining · industry ×1.6
Heuristic only — blends forward/backward citation counts, claim scope, time remaining, litigation history, and CPC-derived industry baseline. Real valuations need a professional appraisal.
Claim text not yet imported for this patent
The original legal language
Original claims
28 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Chen, P., Cao, Y., Melnyk, I., Vijil, E. C., & Das, P. (2025). Computer Model Designs Proteins by Matching Structure to Sequence (U.S. Patent No. 12,412,637). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/12412637/embedding-based-generative-model-for-protein-design
Auto-generated from the patent record. Double-check author order and the issue date against the official USPTO document before submitting.
Embed
Add this patent to your site
Drop this plain-English patent card into any blog post or article — free, no signup. It always links back to the full breakdown here.
<div data-patentlens-widget data-patent-number="US12412637"></div> <script src="https://patentbrief.org/embed.js" async></script>
Stay in the loop
Get a weekly digest of new patents.
One email per week. No spam. Unsubscribe anytime.
Keep exploring
Related patents you should know
US 4683195 · 1987
How to Make Billions of Copies of a DNA Segment
This patent describes the Polymerase Chain Reaction (PCR), a method to rapidly create many copies of a specific piece of DNA or RNA, enabling its detection and analysis.
Cetus Corp
US 8697359 · 2014
How to Edit Genes in Human Cells Using an Engineered CRISPR System
This patent describes an engineered CRISPR-Cas9 system for precisely cutting DNA in eukaryotic cells to change how genes work, opening the door for gene editing in complex organisms.
Massachusetts Institute of Technology
US 7657849 · 2010
How the iPhone's Slide-to-Unlock Gesture Works
Apple's 2010 patent describes unlocking a device by dragging a specific graphical image across the touchscreen along a predefined path, a gesture that became iconic with the original iPhone.
Apple Inc
US 4733665 · 1988
How Doctors Implant a Permanent Stent Using a Balloon
This patent describes the method for placing a permanent, expandable wire mesh tube inside a blood vessel or other body tube using a balloon-tipped catheter to widen it and keep it open.
Expandable Grafts Partnership
US 4965188 · 1990
How to Make Many Copies of a DNA Piece with Heat
This patent describes the Polymerase Chain Reaction (PCR) method, a technique to make millions of copies of a specific DNA segment using a heat-resistant enzyme and repeated temperature changes.
Cetus Corp
US 4235871 · 1980
How to Encapsulate Active Materials in Lipid Bubbles Efficiently
This patent describes a method for trapping biologically active substances inside tiny, multi-layered fat bubbles called liposomes, using a specific water-in-oil emulsion and gel-forming process to improve how much material gets captured.
Individual
Semantically similar
You might also find these interesting
US 20240412809 · DeepMind Technologies
AI Predicts 3D Protein Shapes from Genetic Code
US 12437843 · 2025 · GDM Holding
Using AI to Predict Protein Shapes for Drug Discovery
US 20210280268 · Dnastar
How Computers Predict Protein Shapes Faster Using Smart Templates
US 11176462 · 2021 · RO5
Predicting How Molecules Interact with Proteins Using Two AI Streams
More to explore
More in Biotech & Medicine
US 4683195 · 1987 · Cetus Corp
How to Make Billions of Copies of a DNA Segment
US 8697359 · 2014 · Massachusetts Institute of Technology
How to Edit Genes in Human Cells Using an Engineered CRISPR System
US 4733665 · 1988 · Expandable Grafts Partnership
How Doctors Implant a Permanent Stent Using a Balloon
US 4965188 · 1990 · Cetus Corp
How to Make Many Copies of a DNA Piece with Heat
New to patents?
Common Questions
Frequently Asked Questions
What does Computer Model Designs Proteins by Matching Structure to Sequence cover?
IBM's 2025 patent describes a computer system that designs new protein sequences by first understanding a target 3D protein shape and then generating a sequence that would fold into that shape.
Who owns patent US 12412637?
International Business Machines owns this patent, granted in 2025.
When does this patent expire?
This patent is expected to expire on May 11, 2041, when the invention enters the public domain.
What problem does this patent solve?
Designing novel proteins with specific functions is crucial for developing new medicines, enzymes for industrial processes, and advanced materials. This patent represents a significant step in using AI to automate and accelerate the discovery of proteins with desired structural and functional properties.
What does this patent NOT cover?
Designing biological sequences without using a transformer model encoder
Same assignee
More from International Business Machines
Patent monitoring