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 →Filing growth compares 2021 (77 records) with 2024 (41) — 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 1,578 records in scope (CR5), not by the ranked leaders only.
This landscape tracks patent activity at the intersection of food protein characterization and safety screening — allergenicity assessment, protein digestibility, sequence homology screening, in vitro digestion, host residual protein detection, impurity identification by mass spectrometry, and amino acid composition analysis. The scope spans 1,578 published records filed between 2015 and mid-2026, drawn from assignees ranging from enzyme and ingredient majors to single-filing biotech entrants.
Because publication lags filing by roughly 18 months, the 2025 and 2026 figures in this dataset are still filling in and should not be read as a decline in activity. The more reliable read on recent momentum is the 2021-to-2024 window, where complete-year data is available.
Pick a task. Every answer cites the patents behind it.
The record set spans eight IPC subclasses and six receiving offices, with a filing curve that peaked in 2022 and has since eased off complete-year highs.
Filings rose from 70 in 2017 to a peak of 89 in 2022, then declined across the last complete three-year window on record: 77 in 2021 to 41 in 2024, a 47% fall. 2025 and 2026 figures are still incomplete due to publication lag and should not be read as a continuation of that decline.
Foods and non-alcoholic beverages (A23L) leads at 49.6% of the 1,578 records, closely followed by proteins and food peptides (A23J) at 41.4% and animal feed (A23K) at 33.9%. Microorganism and genetic engineering claims (C12N) sit at 33.7%, while fermentation and enzymatic synthesis (C12P) and baking/dough applications (A21D) are comparatively thin at 10.0% and 6.9% — records carry multiple classes, so these shares sum to well over 100%.
Shares are the percentage of the 1,578 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
This page is one run against one query. Ask Eureka your own question about food protein safety and characterization and every answer comes back with the patent numbers behind it.
Try EurekaA protein is set as an evaluation target, and a digestibility prediction result on protein digestibility of the evaluation target is obtained using a machine learning model in which an amino acid composition of protein is an explanatory variable and protein digestibility is an objective variable.This is a machine-learning approach to digestibility prediction, not a wet-lab assay — a distinct claim posture from the in vitro digestion methods that dominate older filings in this set.


| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US6858778B1 | Plants transformed with a DNA construct comprising a nucleic acid molecule encoding an 18 kD alpha-globulin | 411 |
| 2 | WO2003048353A1 | Polypeptides having protease activity and nucleic acids encoding same | 296 |
| 3 | US20100239712A1 | Food Compositions of Microalgal Biomass | 228 |
| 4 | US7009087B1 | Compositions and methods for altering the disulfide status of proteins | 221 |
| 5 | WO2010120923A1 | Novel microalgal food compositions | 218 |
| 6 | WO2010045368A2 | Food compositions of microalgal biomass | 213 |
| 7 | US7205453B2 | Crop plant cystatin proteinase inhibitors encoding nucleic acids and methods of use | 213 |
| 8 | US20050204418A1 | Grain quality through altered expression of seed proteins | 208 |
| 9 | US20050160488A1 | Grain quality through altered expression of seed proteins | 197 |
| 10 | US20100303990A1 | High Protein and High Fiber Algal Food Materials | 164 |
Citation counts favour older records that have had more time to accumulate citations within this searched corpus; treat them as a signal of influence, not of current relevance.
Each row carries its publication number; clicking a row searches Eureka by that number.
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 →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 →Three patterns matter more than any single ranking: where filing has concentrated, where it has cooled, and where citation weight sits on old rather than current art.
The top 5 assignees combined hold 28.7% of all 1,578 records, and the top 10 hold 41.9%. That leaves the majority of filings spread across a long tail of single- and few-filing entrants — enough concentration to warrant freedom-to-operate checks on leaders, but not enough to assume the field is closed.
Activity rose to a peak of 89 filings in 2022, then fell across the last complete three-year window to 41 in 2024. That's a real cooling in complete-year data, though 2025–2026 figures are still filling in due to publication lag and should not be read into the same trend line.
The most-cited records in this set, including the 411-citation plant-transformation patent and the 296-citation protease-activity filing, are older documents that have simply had more time to accumulate citations. High citation counts here are a marker of past influence in the citing corpus, not current commercial relevance.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to food protein safety and characterization, with the prior art for and against each one.
The ranked leader sits well ahead of the field at 186 records, with fifth place at 50 and tenth at 36 — a steep drop-off that flattens into a long tail beyond the top 10.
The top-ranked assignee holds 186 records, more than triple fifth place at 50. That gap is wide enough to matter for licensing conversations, but recent-year momentum data shows most of the leaders, including this one, logged zero filings in the latest year — a sign the leader's position is historical rather than actively expanding.
Beyond the top 10 (41.9% of records), the remaining 90 ranked assignees split the rest thinly. This is typical of a field still absorbing new entrants from adjacent sectors — enzyme producers, feed formulators, and alternative-protein biotech — rather than one dominated by a handful of blocking portfolios.
Only 10 co-assignee pairs appear in this dataset, and the strongest pairing recurs across several of them — pointing to a small number of longstanding research partnerships rather than a broad collaborative ecosystem across the field.
| Assignee | Recent year | YoY |
|---|---|---|
| Prairie Aqua Tech LLC | 1 | — |
| Novozymes A/S | 0 | — |
| Pronutria Biosciences Inc | 0 | — |
| DSM IP Assets B.V. | 0 | — |
| Axcella Health Inc | 0 | — |
| MycoTechnology Inc | 0 | — |
| Agrigenetics Inc | 0 | — |
| International N&H Denmark ApS | 0 | — |
The dataset points to specific next steps depending on whether the goal is freedom-to-operate, portfolio strategy, or identifying acquisition targets.
With 41.9% of records held by ten assignees, a targeted FTO review against that group is more efficient than screening the full long tail first.
Explore assignee claims in EurekaEP4775982A1 signals a shift toward ML-based prediction over wet-lab assay; watch for follow-on filings in this specific claim style.
Set up a monitoring alert in EurekaBaking-and-dough applications and fermentation process claims sit well below the core IPC classes in filing density, suggesting room for a first-mover claim.
Search white space in EurekaOne assignee leads the ranked field with 186 records, more than triple the fifth-place holder at 50. The top 5 assignees combined account for 28.7% of all 1,578 records in scope, and the top 10 account for 41.9%. That said, recent-year filing data shows most of these leaders posted zero filings in the latest year, so leadership in this dataset reflects historical filing volume more than current expansion.
Filing peaked at 89 records in 2022 and then declined across the most recent complete three-year window, from 77 in 2021 to 41 in 2024 — a 47% drop. The 2025 and 2026 figures look lower still, but that is expected: publication lags filing by roughly 18 months, so those years are still filling in and should not be read as evidence of a continued decline.
Foods and non-alcoholic beverages (IPC class A23L) appears in 49.6% of the 1,578 records, the single most common classification. Proteins and food peptides (A23J) and animal feed (A23K) follow at 41.4% and 33.9% respectively, with microorganism and genetic engineering claims (C12N) close behind at 33.7%. Because records often carry multiple IPC classes, these percentages overlap rather than sum to 100%.
The composition data shows comparatively thin filing in baking and dough applications (A21D, 6.9% of records) and fermentation/enzymatic synthesis process claims (C12P, 10.0%) relative to the dominant food and protein classes. Machine-learning-based digestibility prediction, exemplified by a recently published filing, also looks earlier-stage than the wet-lab in vitro digestion methods that dominate older records. These are reasonable starting points for scouting, though a full clearance search is still needed before committing claim language.
EP4775982A1, published July 2026 by Ajinomoto, claims a food product evaluation device and method that predicts protein digestibility using a machine learning model where amino acid composition is the explanatory variable and digestibility is the objective variable. It is a computational prediction approach rather than a physical in vitro digestion assay, which is the claim style that dominates most older records in this dataset. Anyone building digestibility-screening tools that rely on ML models trained on amino acid composition data should review this filing's claim scope directly.
Go past this page: query the whole food protein safety and characterization 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.
Help us improve
Something wrong, out of date, or missing on this page? Tell us and it goes straight to the team that maintains it.
This page