Fastest
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 →https://www.patsnap.com/resources/blog/rd-blog/molecular-dynamics-for-target-assessment-patent-landscape/ · Patsnap · data cut-off 2026-07-31 · downloaded from the live page
Patent Landscape · Computational Drug DiscoveryMolecular Dynamics for Target Assessment: Patents Mapping Simulation-Driven Drug Discovery
- Filings jumped 240% from 2021 to 2024 (5 to 17 records) the sharpest sustained rise in the trend, concentrated around enhanced sampling and machine-learning-assisted structure prediction.
- The top 5 assignees hold just 29.2% of all 113 records and the top 10 only 46.9% — a long tail of single- and few-filing entrants dominates this space rather than a handful of incumbents.
- Bioinformatics (G16B) touches 47.8% of records while computational chemistry (G16C) and AI-based computing (G06N) each cover roughly a fifth, showing claims are being built at the software layer more than the physics layer.
113
Published Records
29%
Top-5 Share of All Records
+240%
Filing Growth 2021→2024
US
Leading Jurisdiction
Filing growth compares 2021 (5 records) with 2024 (17) — 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 113 records in scope (CR5), not by the ranked leaders only.
Published byPatsnap Research··6 min readSourced from Patsnap Eureka
Field Overview
What this landscape covers
This landscape tracks patent activity where molecular dynamics simulation, cryptic pocket detection and conformational ensemble methods intersect with the practical machinery of running them at scale: simulation timescale management, enhanced sampling, force field parameterization, membrane system setup, analysis reproducibility and experimental cross-checking. It is a narrow, methods-heavy corner of computational drug discovery rather than the whole of structural biology IP.
The scope spans 113 published records filed between 2015 and mid-2026, drawn from six receiving offices led by the United States and the WIPO PCT route. Because publication trails filing by roughly 18 months, the most recent one to two years in any trend understate real filing activity rather than reflect a slowdown.
Filing activity and technology composition, 2017-2026
Source: Patsnap Eureka. Assignee ranking and totals. Derived from a Patsnap search on Molecular Dynamics for Target Assessment covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Let an AI agent run this analysis on your own technology
Pick a task. Every answer cites the patents behind it.
10,000 free credits to start
The Data
Filing trends and technology composition
Two views of the same 113 records: how filing volume has moved year over year, and which IPC subclasses the claims actually sit in.
A decade of uneven growth, peaking in 2022
Filings rose from a single record in 2017 to a peak of 27 in 2022, before settling into the 2021-2024 window used for the +240% growth figure. 2025 and 2026 figures are still filling in as later publications catch up with their filing dates.
Bioinformatics dominates, but no single class controls the field
G16B (bioinformatics) appears in 47.8% of the 113 records, well ahead of G16C (computational chemistry) at 23.9% and G06N (AI-based computing) at 20.4%. Because records often carry multiple IPC codes, these shares overlap rather than sum to 100%, which itself signals that most filings blend simulation methodology with data-processing or machine-learning claims rather than staying purely mechanistic.
Shares are the percentage of the 113 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Source: Patsnap Eureka. Filing trend and technology composition. Derived from a Patsnap search on Molecular Dynamics for Target Assessment covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.
Go deeper on Molecular Dynamics for Target Assessment with Eureka
This page is one run against one query. Ask Eureka your own question about molecular dynamics for target assessment and every answer comes back with the patent numbers behind it.
Try EurekaKey Patents
Most-cited records and a recent representative filing
Representative Recent Filing
Prediction of protein structure ensembles
MICROSOFT TECHNOLOGY LICENSING, LLC
A computing system predicts protein structure ensembles through a staged training pipeline: a first phase clusters synthetic protein-sequence data and trains a diffusion model on the resulting pairs; a second phase compares diffusion-model output against a corresponding structure derived from a molecular dynamics simulation; a third phase refines the model further.Filed by Microsoft Technology Licensing, published 2026-05-07 — illustrates how ensemble prediction claims now route conformational data through diffusion models trained against MD-simulation ground truth rather than running MD as the sole method.
Highest-cited records in scope
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | WO2020016579A2 | Machine learning based methods of analysing drug-like molecules | 60 |
| 2 | US20080147360A1 | System and method for simulating the time-dependent behaviour of atomic and/or molecular systems subject to s… | 56 |
| 3 | US20220383992A1 | Machine learning based methods of analysing drug-like molecules | 54 |
| 4 | US8374828B1 | Computer implemented system for protein and drug target design utilizing quantified stability and flexibility… | 38 |
| 5 | US20230317202A1 | Computer implemented method and system for small molecule drug discovery | 16 |
| 6 | WO2019051419A1 | Engineered CAS9 variants | 15 |
| 7 | WO2024187031A2 | Systems and methods for dynamic-backbone protein-ligand structure prediction with multiscale generative diffu… | 14 |
| 8 | US20230129485A1 | System and method for determining material properties of molecular systems from an ab-initio parameterized fo… | 13 |
| 9 | US20180068053A1 | Systems and methods of selecting compounds with reduced risk of cardiotoxicity using cardiac sodium ion chann… | 13 |
| 10 | WO2022043690A1 | Computer implemented method and system for small molecule drug discovery | 10 |
Citation counts favour older filings that have had more time to accumulate citations within the searched corpus; treat them as a measure of influence, not of current commercial relevance.
Each row carries its publication number; clicking a row searches Eureka by that number.
Source: Patsnap Eureka. Citation counts and representative records. Derived from a Patsnap search on Molecular Dynamics for Target Assessment covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Run it yourself
Put your own technology through the same analysis
Where to run it
For builders
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 →Insights
What the numbers mean for filing strategy
Three patterns stand out once the ranking, the trend and the IPC composition are read together.
Concentration
29.2% / 46.9%
top 5 / top 10 share of 113 records
No single assignee controls the field
With the leader holding 8 records out of 113 and the top 10 combined reaching just under half the corpus, this is a fragmented landscape rather than one gated by a handful of blocking portfolios. New entrants are still filing first-in-class claims rather than working around an established leader.
Read as: room to file, not room to copy.
Growth
+240%
records, 2021 to 2024
Filing accelerated sharply through the early 2020s
The rise from 5 records in 2021 to 17 in 2024, against a 2022 peak of 27, tracks the broader uptake of machine-learning-assisted structure prediction layered onto classical MD workflows. Treat 2025-2026 counts as incomplete rather than as a plateau.
Peak year so far: 2022.
Claim layering
47.8% G16B
of records tagged bioinformatics
Claims cluster at the data layer, not the physics layer
Bioinformatics and AI-based computing classes each touch a large share of records alongside computational chemistry, meaning most recent filings claim the analysis and prediction pipeline around a simulation rather than the simulation method itself.
Pure force-field or sampling-algorithm claims are comparatively rare.
Eureka AI Agent
Looking for what nobody has claimed yet?
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to molecular dynamics for target assessment, with the prior art for and against each one.
Source: Patsnap Eureka. Co-assignee relationships and derived observations. Derived from a Patsnap search on Molecular Dynamics for Target Assessment covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Players
Who is filing, and where the field is still open
The ranked leaders span pharmaceutical-adjacent computing firms, universities and hardware vendors, with several co-filing pairs suggesting joint research programs rather than pure licensing arrangements.
Leader
8 records
top-ranked assignee
A modest lead, not a moat
The top-ranked assignee holds 8 of 113 records, a lead that reflects sustained filing rather than a dominant blocking position given how thin the top-10 share is overall.
Fifth place holds 5; tenth place holds 4.
Co-filing
8 pairs
co-assignee combinations found
A small cluster of joint filers
Eight co-assignee pairs appear across the corpus, with the strongest ties recurring at a count of 4 between the same three organisations — a signal of shared research infrastructure or sponsored academic-industry programs rather than broad industry consolidation.
Most assignees, however, file alone.
Long tail
78 assignees
in the ranked list
Fragmentation favours new entrants
Across the 78 ranked assignees, momentum in the latest tracked year is flat to negative for several previously active filers, consistent with a field where individual research groups file in bursts rather than maintaining continuous pipelines.
No assignee shows sustained latest-year growth in the evidence reviewed.
Recent-year filing momentum by assignee
| Assignee | Recent year | YoY |
|---|---|---|
| Nanjing University | 0 | — |
| Invitae Corp | 0 | — |
| Iambic Therapeutics Inc | 0 | -100% |
| KUANO LTD | 0 | -100% |
| City of Hope | 0 | — |
| Peptone Ltd | 0 | -100% |
| NVIDIA Corp | 0 | -100% |
| Trustees of Tufts College | 0 | — |
Source: Patsnap Eureka. Assignee-level momentum. Derived from a Patsnap search on Molecular Dynamics for Target Assessment covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
What's Next
Where to take this analysis
The dataset points to a field still being staked out at the claim level rather than one settled by a few dominant portfolios.
Check freedom to operate against the most-cited records
The highest-cited filings concentrate on machine-learning analysis of drug-like molecules and on core MD simulation infrastructure; any new filing touching those areas should be checked against them specifically rather than the corpus as a whole.
Run a citation check in EurekaModel the under-claimed branches before filing
Membrane system setup, force field parameterization and analysis reproducibility all show thinner filing density than the bioinformatics and AI-based computing classes, which suggests room for narrowly drafted first claims.
Explore white space in EurekaSource: Patsnap Eureka. Forward-looking reading of the same dataset. Derived from a Patsnap search on Molecular Dynamics for Target Assessment covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
FAQ
Common questions on this landscape
No single organisation dominates this field: the top-ranked assignee holds 8 of the 113 records in scope, and the top 5 combined account for only 29.2% of all records. The top 10 assignees together reach 46.9%, meaning more than half of the corpus is held by the remaining long tail of the 78 ranked assignees. This fragmentation reflects a field where academic groups, hardware vendors and drug-discovery software firms all file in relatively small numbers rather than one incumbent building a dominant portfolio.
Filings rose sharply from 5 records in 2021 to 17 in 2024, a 240% increase over that three-year span, with a peak of 27 records in 2022. Filing activity in 2025 and 2026 appears lower in the raw counts, but publication typically lags filing by around 18 months, so those recent years are still incomplete rather than showing an actual decline. The safest complete read on growth ends at 2024.
The largest share of records, 47.8%, carries a bioinformatics classification (IPC G16B), followed by computational chemistry at 23.9% and AI-based computing methods at 20.4%. Medicinal preparations, peptide and protein chemistry, and material analysis and testing classes each appear in a smaller but meaningful share of records. Because many filings carry multiple classifications, most patents in this space combine a simulation or chemistry claim with a data-processing or machine-learning claim rather than isolating one discipline.
Relative to the dense bioinformatics and computational-chemistry claim areas, sub-areas such as membrane system setup automation, force field parameterization for novel chemotypes, and analysis reproducibility tooling show thinner filing density in this dataset. Enhanced sampling techniques applied specifically to cryptic pocket detection also appear less crowded than general conformational ensemble claims. These are reasonable starting points for narrowly scoped claims, though any filing strategy should still be checked against the most-cited records in the corpus.
Not necessarily. Citation counts accumulate over time within a searched corpus, so older records such as the ones dated well before 2020 tend to show higher counts simply because they have had longer to be cited. A recent, technically significant filing may show a low citation count purely because it has not had time to accumulate them. Citation counts are best read as a signal of historical influence on the field, not as a ranking of present-day commercial relevance.
Answers are grounded in the same dataset. Derived from a Patsnap search on Molecular Dynamics for Target Assessment covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Research Molecular Dynamics for Target Assessment in depth with Eureka
Go past this page: query the whole molecular dynamics for target assessment 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.