Using AI to Design Drugs by Understanding Molecular Shapes
This patent describes a computer system that uses advanced math to describe molecule shapes and then feeds that information into artificial intelligence to predict how well potential drugs will work or if they'll be toxic.
Original patent title: “System and methods for machine learning for drug design and discovery”
This patent describes a computer system that uses advanced math to describe molecule shapes and then feeds that information into artificial intelligence to predict how well potential drugs will work or if they'll be toxic. Owned by Michigan State University with 23 claims and 101 forward citations, and it is expected to expire in 2039.
Coverage
What does this patent actually cover?
The system identifies potential drug compounds based on desired characteristics or clinical applications (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1). It then uses special mathematical techniques like "persistent homology" and "graph theory" to create "feature data" that describes their complex 3D structures (AbstractabstractA short summary at the front of the patent describing the invention. Not legally binding.Read more →, Claim 1). This feature data, which can include "element specific topological fingerprint records" (Claim 3) or "interactive element specific persistent homology barcodes" (Claim 4), is then fed into "trained machine learning models" (Claim 1). These models predict important characteristics, such as "protein binding affinity" (Claim 3) or "protein folding energy change upon mutation" (Claim 4). Finally, the system displays an "ordered list" of the most promising compounds based on these predictions (Claim 1, Claim 2). For example, it could predict which new molecule will bind most effectively to a specific protein target.
The gap
What does this patent NOT cover?
- Does not cover drug design methods that do not use machine learning to predict molecular characteristics.
- Does not cover predicting molecular characteristics without using feature data derived from persistent homology or graph theory.
- Does not cover systems that predict drug properties without displaying an ordered list of candidate compounds.
- Does not cover traditional drug screening methods that rely solely on laboratory experiments without computational prediction.
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
The noveltynoveltyThe requirement that an invention be different from anything publicly known before its priority date.Read more → lies in combining sophisticated mathematical tools like persistent homology and graph theory to capture the complex, multi-scale geometric and topological features of molecules, and then feeding these unique "fingerprints" into powerful machine learning algorithms to accurately predict molecular characteristics. This allows the AI to "see" and understand molecular shapes in a way that was previously difficult for computers.
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
Computational drug discovery platforms
AI-driven pharmaceutical research
Virtual screening for new drug candidates
Predicting protein-ligand interactions
Optimizing drug toxicity profiles
Why it matters
The bigger picture
Drug discovery is a long, expensive process. This patent aims to speed it up significantly by using computers to predict how potential drugs will behave before they are even synthesized or tested in a lab. By identifying promising compounds earlier, it could reduce costs and accelerate the development of new medicines, making the process more efficient.
Filed
April 1, 2019
Market context
Who's building on this
Companies in this space
Major pharmaceutical companies like Pfizer, Novartis, and AstraZeneca are investing heavily in AI for drug discovery. Startups such as Recursion Pharmaceuticals, BenevolentAI, and Insilico Medicine are also developing similar computational platforms. Academic institutions like Michigan State University continue to advance research in this area, often collaborating with industry partners.
Market impact
This technology contributes to the growing field of in silico (computer-based) drug discovery, which aims to reduce the time and cost of bringing new drugs to market. It enables faster identification of promising drug candidates and better prediction of their properties, potentially leading to more efficient R&D pipelines and a shift away from purely experimental screening methods. This could significantly reshape how pharmaceutical research and development are conducted.
Claim 1 — Plain English
What this patent covers
The system identifies potential drug compounds based on desired characteristics or clinical applications (Claim 1). It then uses special mathematical techniques like "persistent homology" and "graph theory" to create "feature data" that describes their complex 3D structures (Abstract, Claim 1). This feature data, which can include "element specific topological fingerprint records" (Claim 3) or "interactive element specific persistent homology barcodes" (Claim 4), is then fed into "trained machine learning models" (Claim 1). These models predict important characteristics, such as "protein binding affinity" (Claim 3) or "protein folding energy change upon mutation" (Claim 4). Finally, the system displays an "ordered list" of the most promising compounds based on these predictions (Claim 1, Claim 2). For example, it could predict which new molecule will bind most effectively to a specific protein target.
The clever bit
The novelty lies in combining sophisticated mathematical tools like persistent homology and graph theory to capture the complex, multi-scale geometric and topological features of molecules, and then feeding these unique "fingerprints" into powerful machine learning algorithms to accurately predict molecular characteristics. This allows the AI to "see" and understand molecular shapes in a way that was previously difficult for computers.
What it does not cover
- Does not cover drug design methods that do not use machine learning to predict molecular characteristics.
- Does not cover predicting molecular characteristics without using feature data derived from persistent homology or graph theory.
- Does not cover systems that predict drug properties without displaying an ordered list of candidate compounds.
- Does not cover traditional drug screening methods that rely solely on laboratory experiments without computational prediction.
Patent timeline
Application submitted to the patent office
Patent enters public domain
PatentBrief Score
Impact Score
Moderate
Citation count
40/40
Highly cited
Claim breadth
15/20
Broad claimsclaimsThe numbered statements at the end of a patent that legally define what the inventor owns.Read more →
Recency
0/20
Older than 20 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
$624K – $2.0M
Midpoint $1.2M · 12.4 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
23 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Wei, G., Cang, Z., & Nguyen, D. Using AI to Design Drugs by Understanding Molecular Shapes (U.S. Patent No. 20,190,304,568). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/20190304568/system-and-methods-for-machine-learning-for-drug-design-and-discovery
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="US20190304568"></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 12437843 · 2025 · GDM Holding
Using AI to Predict Protein Shapes for Drug Discovery
US 11176462 · 2021 · RO5
Predicting How Molecules Interact with Proteins Using Two AI Streams
US 12603151 · 2026 · Florida State University Research Foundation
Using AI to Design and Predict Protein Structures
US 12655176 · 2026 · University of Toronto
How AI Designs New Protein Sequences for Specific Shapes
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 Using AI to Design Drugs by Understanding Molecular Shapes cover?
This patent describes a computer system that uses advanced math to describe molecule shapes and then feeds that information into artificial intelligence to predict how well potential drugs will work or if they'll be toxic.
Who owns patent US 20190304568?
This patent is owned by Michigan State University.
When does this patent expire?
This patent is expected to expire on April 1, 2039, when the invention enters the public domain.
What is patent US 20190304568 cited by?
This patent has been cited by 101 later patents that build on its ideas.
What problem does this patent solve?
Drug discovery is a long, expensive process. This patent aims to speed it up significantly by using computers to predict how potential drugs will behave before they are even synthesized or tested in a lab. By identifying promising compounds earlier, it could reduce costs and accelerate the development of new medicines, making the process more efficient.
What does this patent NOT cover?
Does not cover drug design methods that do not use machine learning to predict molecular characteristics.
Patent monitoring



