Crystal Structure Prediction Patents: Leaders & White Space 2026
- 52.3% concentration. The top five assignees hold 34 of 65 records in scope — over half the field sits with a handful of filers, with a long tail beyond them.
- +100% filing growth. Filings rose from 6 in 2021 to 12 in 2024, the last year that can be treated as complete under an 18-month publication lag.
- G16C dominates, but not alone. Computational chemistry classes cover 41.5% of records, while G01N, G06F and G06N each carry a meaningful secondary share.
Filing growth compares 2021 (6 records) with 2024 (12) — 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 65 records in scope (CR5), not by the ranked leaders only.
What this field covers
Crystal structure prediction and computational polymorph modelling sit at the intersection of computational chemistry and pharmaceutical formulation. The claims in scope span force field parameterisation, lattice energy calculation, search algorithms over conformational and packing space, and the experimental confirmation steps that tie a predicted structure back to a measured crystal form. 65 records fall within the search string across the 2015–2026 window, with 18.5% also touching material analysis and testing (G01N) and 16.9% touching general digital data processing (G06F).
The dataset draws on receiving-office filings concentrated in the United States and under the PCT, with smaller volumes in Europe, Canada, Japan and Australia. Because publication lags filing by roughly 18 months, the 2025 and 2026 counts in any trend chart understate true filing activity for those years.
Let an AI agent run this analysis on your own technology
Pick a task. Every answer cites the patents behind it.
Filing trends and technology composition
The figures below are drawn directly from the 65 records in scope and the IPC classification each record carries; a record can carry more than one class, so class shares add up to more than the record total.
Filing trend, 2015–2026
Filings moved from 0 in 2017 to a peak of 12 in 2024, with growth of +100% between 2021 (6) and 2024 (12). 2025 and 2026 figures are still filling in under the publication lag and should not be read as a slowdown.
Technology composition by IPC subclass
G16C (computational chemistry) covers 41.5% of the 65 records, ahead of G01N (18.5%) and G06F (16.9%). B01D, C30B, G06N and G16B each sit at 10.8%, and C40B (combinatorial libraries) at 7.7% marks the smallest documented branch.
Shares are the percentage of the 65 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Go deeper on Crystal Structure Prediction and Modelling with Eureka
This page is one run against one query. Ask Eureka your own question about crystal structure prediction and modelling and every answer comes back with the patent numbers behind it.
Try EurekaMost-cited records in this field
Tailor-made force fields for crystal structure prediction
A general procedure is presented to derive force field parameters for molecules in the crystalline state on a case by case basis. The force field parameters are fitted to accurate energies and forces generated by means of a hybrid method that combines DFT calculations with an empirical van der Waals correction. The mathematical structure of the force field, the generation of reference data, the choice of the figure of merit, the optimization algorithm and the parameter refinement strategy are discussed in detail.Filed by Avant-garde Materials Simulation SARL, published 2010-01-28. One of the most-cited records in this dataset, and a useful reference point for how force field derivation claims are drafted.
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | WO2009009790A1 | Air-stable, high hole mobility thieno-thiophene derivatives | 58 |
| 2 | US20100023473A1 | Tailor-made force fields for crystal structure prediction | 23 |
| 3 | WO2007071095A1 | Method for crystal structure determination | 16 |
| 4 | WO2008071540A1 | Tailor-made force fields for crystal structure prediction | 15 |
| 5 | US20150127307A1 | Method and apparatus for crystal structure optimization | 12 |
| 6 | US20200134246A1 | Gromacs cloud computing process control method | 6 |
| 7 | US20220180978A1 | Configurational energy calculation and crystal structure prediction | 5 |
| 8 | JP2021032617A | Crystal structure calculation method, crystal structure calculation program and crystal structure calculation… | 5 |
| 9 | US20250014688A1 | Methods and systems for machine-learning based molecule generation and scoring | 4 |
| 10 | US10133852B2 | Method and apparatus for crystal structure optimization | 4 |
Citation counts reward older filings that have had more time to accumulate citations within the searched corpus; treat them as a signal of influence rather than of current 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 in the data matter more for a filing decision than the raw counts on their own.
Half the field sits with a handful of filers
The top five assignees combine for 34 of 65 records — 52.3% of the field. The top ten extend that to 80.0%, meaning the remaining 35 ranked companies each hold small, often single-digit positions. A new entrant is not filing into empty space at the aggregate level, but the concentration is held by relatively few organisations rather than spread evenly.
Filing activity roughly doubled in three years
Filings grew from 6 in 2021 to 12 in 2024, the last year with a complete publication record. That growth sits ahead of the field's overall size, suggesting the underlying computational methods are attracting renewed patenting interest rather than settling into a mature, low-activity pattern.
Computational chemistry is the dominant class, not the only one
G16C covers 41.5% of the 65 records, but material analysis (G01N, 18.5%), digital data processing (G06F, 16.9%) and AI-based computing (G06N, 10.8%) each carry a real share. Claims that combine a computational method with an experimental confirmation step often cross two or more of these classes.
Cross-institution filing is limited but concentrated
Only six co-assignee pairs appear in the dataset, and the strongest recurring pairings involve the same small cluster of French research institutions filing jointly. Most records in scope carry a single assignee.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to crystal structure prediction and modelling, with the prior art for and against each one.
The assignee landscape
The ranking covers 45 companies counted in records — the whole ranking the data endpoint returns, not a top-50 or top-100 cut. Filing activity is concentrated at the top, with a long tail of entrants holding one or two records each.
A single filer leads the ranked field
The leading assignee holds 9 records, ahead of a fifth-place position at 5 and a tenth-place position at 3. The gap between first and fifth place is proportionally larger than the gap from fifth to tenth, which is typical of a field with one clear leader and a competitive second tier.
A competitive cluster sits just behind the leader
Positions two through five each hold meaningfully fewer records than the leader but still contribute to the 52.3% top-five share. This is the tier most likely to be actively defending or extending claim positions rather than sitting on legacy filings.
Most ranked companies hold only a handful of records
Beyond the top ten assignees, who together account for 80.0% of the 65 records, the remaining ranked companies each hold small positions. This long tail includes academic and research institutions alongside specialist computational chemistry firms.
| Assignee | Recent year | YoY |
|---|---|---|
| Allergan Inc. | 0 | — |
| University College Dublin | 0 | — |
| University of Montreal | 0 | — |
| Good Chemistry Inc. | 0 | — |
| PsiQuantum Corp. | 0 | — |
| University of Lorraine | 0 | — |
| Centre National de la Recherche Scientifique (CNRS) | 0 | — |
| Institut National de la Santé et de la Recherche Médicale (INSERM) | 0 | — |
Where to take this
The dataset points to specific next steps depending on whether the goal is freedom-to-operate, portfolio strategy or identifying open claim space.
Map claims against the leader's portfolio
With one assignee holding 9 of 65 records, a freedom-to-operate review should start with that portfolio before assessing the second tier.
Explore assignee portfolios in EurekaTrack the under-claimed branches
Combinatorial libraries (C40B, 7.7%) and AI-based search (G06N, 10.8%) carry the lowest documented shares among the classes in scope, worth monitoring for new entrants.
Monitor white space in EurekaWatch the 2024 filing peak play out
2024's peak of 12 filings, against a backdrop of a publication lag, means 2025-2026 data will keep revising upward for some time yet.
Set up filing alerts in EurekaCommon questions about this field
Crystal structure prediction (CSP) is a computational method for determining how a molecule will pack into a crystal lattice before that form has been observed experimentally. In patent filings, CSP claims typically cover the force field or energy calculation method, the search algorithm used to explore possible packing arrangements, and often a step confirming the predicted structure against experimental data. This dataset shows CSP-related claims most commonly classified under G16C (computational chemistry), at 41.5% of the 65 records in scope.
The ranking of 45 companies shows a clear leader holding 9 records, with the top five assignees together accounting for 34 of 65 records (52.3%). Beyond the top ten, who collectively hold 80.0% of records, filing activity drops off into a long tail of single- or low-digit filers, including academic institutions and specialist computational chemistry firms. No single filer approaches dominance of the entire field.
Filing activity grew from 6 records in 2021 to 12 in 2024, a +100% increase, and 2024 is the most recent year that can be treated as a complete data point. Because patent publication typically lags filing by around 18 months, the lower counts shown for 2025 and 2026 do not indicate a real slowdown; they reflect filings that have not yet published. Based on the 2021-2024 trajectory, the field's genuine trend is upward.
Material analysis and testing (G01N) appears in 18.5% of the 65 records, and general digital data processing (G06F) in 16.9%, reflecting how prediction methods are frequently claimed alongside characterisation techniques or software implementation details. AI-based computing methods (G06N) and bioinformatics (G16B) each cover 10.8% of records, showing a smaller but real overlap with machine-learning-driven approaches. Crystal growth (C30B) and separation processes (B01D) each also sit at 10.8%, tying the computational claims back to physical manufacturing steps.
Combinatorial polymorph library claims (C40B) cover only 7.7% of the 65 records, the lowest share among the classes documented here, and AI-assisted energy landscape search sits at 10.8% alongside bioinformatics-linked screening. These lower-density branches suggest room for claims that combine machine-learning search methods with explicit experimental confirmation steps, an area not yet dominated by any single assignee based on the co-assignee data showing only six pairings in total.
Research Crystal Structure Prediction and Modelling in depth with Eureka
Go past this page: query the whole crystal structure prediction and modelling 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.