Metabolic Modelling for Media Design Patents: Who Leads, Gaps 2026
- Filing peaked in 2020 at 28 records, then fell sharply — 2021's 15 filings dropped to 2 by 2024, an 87% decline over that span.
- Five companies already hold 71.7% of the field — 76 of the 106 records in scope sit with the top 5 assignees, leaving a thin tail below them.
- Diagnosis and surgery classifications dominate the claim space — A61B appears on 56.6% of records, ahead of healthcare informatics and AI-based computing classes.
Filing growth compares 2021 (15 records) with 2024 (2) — a three-year span. 2024 is the most recent year we treat as complete: publication lags filing by roughly 18 months, so 2025 onwards are still filling in and any growth rate that ends there would understate the field. Top-5 share is the combined record count of the five largest assignees divided by all 106 records in scope (CR5), not by the ranked leaders only.
What this landscape covers
Metabolic modelling for media design applies computational models of cellular metabolism — most often flux balance analysis — to predict nutrient consumption, production rates and depletion patterns in a culture or infusion system. The 106 records in scope span from early insulin-infusion control patents through to genome-scale model-building methods and cell-culture metabolic prediction, filed between 2015 and mid-2026.
The dataset draws on a search string combining metabolic-model and in-silico media-optimization terminology with claim and description language around flux balance analysis, spent media analysis, consumption and production rates, predictive nutrient depletion, model validation and data requirements. That framing pulls in both clinical-device applications, such as insulin infusion control, and cell-culture or bioprocess applications, such as genome-scale metabolic model construction.
Filing trend and technology composition
Two views of the same 106 records: how filing activity has moved year over year, and which technology classes carry the claim density.
Filing trend, 2017-2026
Filings rose from zero in 2017 to a peak of 28 in 2020, then declined; 2021's 15 filings had fallen to 2 by 2024, an 87% drop over that three-year span. Records from 2025 onward are still incomplete because publication typically lags filing by roughly 18 months, so the most recent years understate actual filing activity.
IPC subclass composition
A61B (diagnosis and surgery) leads at 56.6% of the 106 records, followed by G16H (healthcare informatics) at 36.8% and G06N (AI-based computing) at 34.0%. Because a single record can carry several IPC classes, these shares sum to well over 100% and should be read against the 106-record total, not against each other.
Shares are the percentage of the 106 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Go deeper on Metabolic Modelling for Media Design with Eureka
This page is one run against one query. Ask Eureka your own question about metabolic modelling for media design and every answer comes back with the patent numbers behind it.
Try EurekaRepresentative filing and most-cited records
Method and electronic device for building comprehensive genome scale metabolic model
Systems and methods for building a comprehensive genome scale metabolic model. The method determines whether a hypothetical or uncharacterized profile annotation is available for a protein, then runs a machine learning procedure over that annotation following fuzzy string matching and ranking. It obtains candidate protein annotations through fuzzy string matching and ranks them to resolve the model's annotation gaps.Filed by Samsung Electronics, published 2021-07-08.
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US20080183060A1 | Model predictive method and system for controlling and supervising insulin infusion | 763 |
| 2 | WO2008094249A1 | Model predictive method and system for controlling and supervising insulin infusion | 100 |
| 3 | US20110282321A1 | Model predictive method and system for controlling and supervising insulin infusion | 57 |
| 4 | US20210050089A1 | Metabolic health using a precision treatment platform enabled by whole body digital twin technology | 45 |
| 5 | WO2019129891A1 | Predicting the metabolic condition of a cell culture | 29 |
| 6 | US20210045694A1 | Precision treatment with machine learning and digital twin technology for optimal metabolic outcomes | 23 |
| 7 | US20200377844A1 | Predicting the metabolic condition of a cell culture | 19 |
| 8 | WO2020230123A1 | A system and a method for health and diet management and nutritional monitoring | 18 |
| 9 | US20220061710A1 | Virtually monitoring glucose levels in a patient using machine learning and digital twin technology | 17 |
| 10 | US20110282320A1 | Model predictive method and system for controlling and supervising insulin infusion | 14 |
Citation counts favour older records simply because they have had longer to accumulate citations within the searched corpus; treat them as a signal of influence, not of current technical importance.
Each row carries its publication number; clicking a row searches Eureka by that number.
Put your own technology through the same analysis
Eureka on the web
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →MCP server & REST API
When it has to run inside your own pipeline.
Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.
Browse MCP servers →What the numbers mean for filing strategy
Three patterns stand out once the raw counts are set against each other: where filing has concentrated, how fast it has cooled, and which classes carry the actual claim density.
Filing sits with a small group
76 of the 106 records in scope belong to the five leading assignees, and the top 10 account for 87.7% (93 records). That leaves a short tail of single- or few-filing entrants below the leaders, rather than a broad field of active competitors.
Activity has cooled sharply from its peak
Filing peaked at 28 records in 2020, then fell: 2021's 15 filings dropped to 2 by 2024. 2025 and 2026 figures are still incomplete due to publication lag, so this decline should be read against 2024 as the last complete year, not against the partial recent years.
Diagnosis and surgery claims dominate
A61B (diagnosis and surgery) appears on 56.6% of the 106 records, well ahead of G16H healthcare informatics (36.8%) and G06N AI-based computing (34.0%). That skew reflects how much of this field's patent activity sits in clinical infusion and monitoring devices rather than pure bioprocess media design.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to metabolic modelling for media design, with the prior art for and against each one.
Who is filing, and where the gate sits
The ranked assignee list covers 18 companies across the 106 records in scope. Filing is led by a single company at 32 records, with the fifth-ranked assignee at 7 and the tenth at 3 — a steep drop from leader to mid-table that marks this as a leader-plus-tail field rather than a broad multi-player race.
A single company holds the largest single share
The leading assignee's 32 records are more than four times the fifth-place count of 7, indicating a durable filing programme rather than a one-off cluster of applications.
The drop-off after the leader is steep
From 32 records at the top to 7 at fifth place, the field thins quickly. Below tenth place (3 records), most assignees hold only one or two filings, consistent with occasional or defensive filing rather than sustained programmes.
Momentum has gone quiet across most leaders
Several of the top assignees show zero filings in the latest year tracked, and the one company still filing has slowed. This is consistent with the broader 2021-2024 decline rather than a leader-specific pullback.
| Assignee | Recent year | YoY |
|---|---|---|
| TWIN HEALTH INC | 1 | -50% |
| Medtronic MiniMed Inc | 0 | — |
| Dexcom Inc | 0 | — |
| F. Hoffmann-La Roche AG | 0 | — |
| Tata Consultancy Services Ltd | 0 | — |
| F. Hoffmann-La Roche & Co AG | 0 | — |
| Samsung Electronics Co., Ltd. | 0 | — |
| GlaxoSmithKline Biologicals SA | 0 | — |
Where to take this analysis
The counts and rankings here describe what has already been filed. The next step is deciding what that means for a specific product or claim strategy.
Check freedom-to-operate against the leader's portfolio
With one assignee holding 32 of 106 records, any new filing in insulin-infusion-adjacent metabolic modelling should be checked against that portfolio specifically, not just the field average.
Explore in EurekaTest the under-claimed branches for a first-filer position
Sub-areas like cross-batch model validation and non-insulin metabolite consumption show thinner claim density than the core A61B and G16H classes, which may leave room for a first, broadly drafted claim.
Run a white space search in EurekaCommon questions about this landscape
Filing in this field is concentrated: the top 5 assignees hold 76 of the 106 records in scope, or 71.7% of the total, and the top 10 hold 87.7%. The single leading assignee holds 32 records, more than four times the fifth-ranked company's 7. Below the top 10, most of the ranked 18 companies hold only one or two filings each, so the field is best described as a leader plus a short tail rather than a broad competitive set.
Filing peaked in 2020 at 28 records and has declined since: 2021's 15 filings had fallen to 2 by 2024, an 87% drop over that three-year span. Figures for 2025 and 2026 are still incomplete because publication typically lags filing by roughly 18 months, so those years should not be read as confirming the decline has stopped or continued — 2024 is the last year that can be treated as complete.
A61B (diagnosis and surgery) is the most common classification, appearing on 56.6% of the 106 records, followed by G16H (healthcare informatics) at 36.8% and G06N (AI-based computing) at 34.0%. Bioinformatics (G16B) and electric digital data processing (G06F) each appear on 20.8% of records. Because records often carry multiple classes, these percentages add up to more than 100% and should each be read against the full 106-record total.
US20210209100A1, filed by Samsung Electronics and published in July 2021, describes a method for building a comprehensive genome-scale metabolic model by resolving hypothetical or uncharacterized protein annotations. It uses machine learning combined with fuzzy string matching and ranking to assign candidate annotations to proteins where the existing profile data is incomplete. Its claims are narrow to that annotation-resolution step rather than to metabolic modelling broadly, so it constrains a specific technical approach rather than the whole field.
Sub-areas such as cross-batch model validation protocols, non-insulin metabolite consumption modelling, and bioprocess-specific data requirement standards show thinner claim density than the dominant clinical-device and AI-computing classes in this dataset. That does not guarantee freedom to operate — it means fewer records were found carrying those specific claim elements in the searched corpus, which is a starting point for deeper review, not a conclusion.
Research Metabolic Modelling for Media Design in depth with Eureka
Go past this page: query the whole metabolic modelling for media design corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.
Patent data carries inherent limitations: recent filings (typically the most recent 18–24 months) are under-counted due to standard publication lag; counts may be reported at either a patent-family or a patent-record basis and are not always directly comparable; classification, applicant-name, and citation data may contain errors, duplicates, or omissions; and the underlying search query defines and constrains the scope shown. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, or validity search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. Any patent, commercial, or strategic decision should be verified independently and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.
Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company’s registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.