← Patent / Freedom-to-Operate Analysis
BD / IP · IP / patent analyst

Patent / Freedom-to-Operate Analysis — agent trajectory for expert review

claude-opus-4-8 · 2026-06-06T09:09:09.551914+00:00 · 8 tool calls · 50.7s · 16080 tokens
run id: fto_patent_20260606_020818_01_assess-freedom-to-operate-for-a-proposed-anti-cl

Query

Assess freedom-to-operate for a proposed anti-CLDN18.2 antibody-drug conjugate (MMAE auristatin payload, protease-cleavable peptide linker) for gastric cancer in the US. Identify any blocking claims and credible design-arounds.

Trajectory

Agent · turn 1

I'll assess freedom-to-operate for your proposed anti-CLDN18.2 ADC. Let me start by orienting myself in the corpus and searching for relevant patents.

⚙ calls list_corpus()
⚙ calls search_patents(target=CLDN18.2)
↳ list_corpus result
show data
{
  "n_families": 14,
  "targets": {
    "CLDN18.2": {
      "modalities": [
        "Antibody-drug conjugate",
        "Naked monoclonal antibody"
      ],
      "n_families": 6
    },
    "HER2": {
      "modalities": [
        "Antibody-drug conjugate",
        "Naked monoclonal antibody"
      ],
      "n_families": 4
    },
    "DLL3": {
      "modalities": [
        "Antibody-drug conjugate",
        "T-cell engager (bispecific)"
      ],
      "n_families": 4
    }
  },
  "assignees": [
    "AbbVie / Stemcentrx",
    "Amgen",
    "Astellas Pharma",
    "Boehringer Ingelheim",
    "Byondis",
    "Daiichi Sankyo",
    "Ganymed Pharmaceuticals",
    "Ganymed Pharmaceuticals / Astellas",
    "Genentech",
    "Harbour BioMed",
    "ImmunoGen",
    "Keymed Biosciences",
    "LaNova Medicines",
    "Sotio Biotech"
  ],
  "jurisdictions": [
    "CN",
    "US",
    "WO"
  ]
}
↳ search_patents result
show data
{
  "count": 6,
  "families": [
    {
      "publication_number": "US9051370B2",
      "jurisdiction": "US",
      "assignee": "Ganymed Pharmaceuticals / Astellas",
      "title": "Antibodies binding to CLDN18.2 and uses thereof",
      "target": "CLDN18.2",
      "modality": "Naked monoclonal antibody",
      "priority_date": "2008-01-03",
      "expiry": "2029-01-03",
      "legal_status": "GRANTED",
      "claim_types": [
        "composition",
        "method"
      ],
      "keywords": [
        "CLDN18.2",
        "claudin",
        "zolbetuximab",
        "naked antibody",
        "gastric",
        "composition of matter",
        "extracellular loop"
      ]
    },
    {
      "publication_number": "WO2016166122A1",
      "jurisdiction": "WO",
      "assignee": "Astellas Pharma",
      "title": "Combination therapy of a CLDN18.2 antibody with chemotherapy",
      "target": "CLDN18.2",
      "modality": "Naked monoclonal antibody",
      "priority_date": "2015-04-13",
      "expiry": "2036-04-13",
      "legal_status": "PENDING",
      "claim_types": [
        "method"
      ],
      "keywords": [
        "CLDN18.2",
        "combination",
        "chemotherapy",
        "gastric",
        "GEJ",
        "method of treatment",
        "first line"
      ]
    },
    {
      "publication_number": "CN103509118A",
      "jurisdiction": "CN",
      "assignee": "Ganymed Pharmaceuticals",
      "title": "Antibodies for the diagnosis and treatment of claudin-18.2 expressing tumours",
      "target": "CLDN18.2",
      "modality": "Naked monoclonal antibody",
      "priority_date": "2009-11-24",
      "expiry": "2018-11-24",
      "legal_status": "EXPIRED",
      "claim_types": [
        "composition"
      ],
      "keywords": [
        "CLDN18.2",
        "diagnostic",
        "imaging",
        "expired",
        "early filing"
      ]
    },
    {
      "publication_number": "WO2019173420A1",
      "jurisdiction": "WO",
      "assignee": "LaNova Medicines",
      "title": "Anti-CLDN18.2 antibody-drug conjugates with a cleavable linker",
      "target": "CLDN18.2",
      "modality": "Antibody-drug conjugate",
      "priority_date": "2018-03-08",
      "expiry": "2039-03-08",
      "legal_status": "GRANTED",
      "claim_types": [
        "composition",
        "method"
      ],
      "keywords": [
        "CLDN18.2",
        "ADC",
        "MMAE",
        "auristatin",
        "cleavable linker",
        "DAR",
        "composition of matter",
        "payload genus"
      ]
    },
    {
      "publication_number": "CN114106192A",
      "jurisdiction": "CN",
      "assignee": "Keymed Biosciences",
      "title": "Anti-claudin18.2 antibody conjugated to a topoisomerase-I inhibitor payload",
      "target": "CLDN18.2",
      "modality": "Antibody-drug conjugate",
      "priority_date": "2020-09-30",
      "expiry": "2040-09-30",
      "legal_status": "PENDING",
      "claim_types": [
        "composition"
      ],
      "keywords": [
        "CLDN18.2",
        "ADC",
        "topoisomerase",
        "exatecan",
        "DXd",
        "cleavable linker",
        "pending",
        "China"
      ]
    },
    {
      "publication_number": "US11078291B2",
      "jurisdiction": "US",
      "assignee": "Sotio Biotech",
      "title": "Maytansinoid antibody-drug conjugates targeting CLDN18.2",
      "target": "CLDN18.2",
      "modality": "Antibody-drug conjugate",
      "priority_date": "2017-06-15",
      "expiry": "2038-06-15",
      "legal_status": "GRANTED",
      "claim_types": [
        "composition"
      ],
      "keywords": [
        "CLDN18.2",
        "ADC",
        "maytansinoid",
        "DM1",
        "DM4",
        "non-cleavable linker",
        "composition of matter"
      ]
    }
  ]
}
Agent · turn 2

Let me read the full claims of the most relevant families — particularly the granted US patents and the LaNova ADC patent which appears most on-point.

⚙ calls get_claims(publication_number=WO2019173420A1)
⚙ calls get_claims(publication_number=US9051370B2)
⚙ calls get_claims(publication_number=US11078291B2)
↳ get_claims result
show data
{
  "publication_number": "WO2019173420A1",
  "title": "Anti-CLDN18.2 antibody-drug conjugates with a cleavable linker",
  "legal_status": "GRANTED",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "composition",
      "text": "An antibody-drug conjugate of formula Ab-(L-D)n wherein Ab is an antibody that specifically binds human CLDN18.2, L is a protease-cleavable peptide linker, and D is an auristatin payload, including MMAE, with a drug-to-antibody ratio of 2 to 8."
    },
    {
      "claim_no": 9,
      "claim_type": "method",
      "text": "A method of treating a CLDN18.2-positive solid tumour comprising administering the antibody-drug conjugate of claim 1."
    }
  ]
}
↳ get_claims result
show data
{
  "publication_number": "US9051370B2",
  "title": "Antibodies binding to CLDN18.2 and uses thereof",
  "legal_status": "GRANTED",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "composition",
      "text": "A monoclonal antibody that binds to the extracellular loop of human Claudin-18 splice variant 2 (CLDN18.2) but does not bind CLDN18.1, covering the antibody and antigen-binding fragments thereof."
    },
    {
      "claim_no": 14,
      "claim_type": "method",
      "text": "A method of treating a CLDN18.2-positive cancer comprising administering the antibody of claim 1."
    }
  ]
}
↳ get_claims result
show data
{
  "publication_number": "US11078291B2",
  "title": "Maytansinoid antibody-drug conjugates targeting CLDN18.2",
  "legal_status": "GRANTED",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "composition",
      "text": "An antibody-drug conjugate comprising an anti-CLDN18.2 antibody, a non-cleavable thioether linker, and a maytansinoid (DM1/DM4) payload."
    }
  ]
}
Agent · turn 3

The LaNova patent is the most on-point. Let me get its full record to check jurisdiction/family details (it's a WO — I need to know if there's a US counterpart), and check the Astellas combination therapy patent and full Ganymed record for method-of-treatment scope.

⚙ calls get_patent(publication_number=WO2019173420A1)
⚙ calls get_patent(publication_number=US9051370B2)
⚙ calls search_patents(keyword=MMAE)
↳ get_patent result
show data
{
  "publication_number": "WO2019173420A1",
  "jurisdiction": "WO",
  "assignee": "LaNova Medicines",
  "priority_date": "2018-03-08",
  "expiry": "2039-03-08",
  "legal_status": "GRANTED",
  "title": "Anti-CLDN18.2 antibody-drug conjugates with a cleavable linker",
  "target": "CLDN18.2",
  "modality": "Antibody-drug conjugate",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "composition",
      "text": "An antibody-drug conjugate of formula Ab-(L-D)n wherein Ab is an antibody that specifically binds human CLDN18.2, L is a protease-cleavable peptide linker, and D is an auristatin payload, including MMAE, with a drug-to-antibody ratio of 2 to 8."
    },
    {
      "claim_no": 9,
      "claim_type": "method",
      "text": "A method of treating a CLDN18.2-positive solid tumour comprising administering the antibody-drug conjugate of claim 1."
    }
  ],
  "keywords": [
    "CLDN18.2",
    "ADC",
    "MMAE",
    "auristatin",
    "cleavable linker",
    "DAR",
    "composition of matter",
    "payload genus"
  ]
}
↳ get_patent result
show data
{
  "publication_number": "US9051370B2",
  "jurisdiction": "US",
  "assignee": "Ganymed Pharmaceuticals / Astellas",
  "priority_date": "2008-01-03",
  "expiry": "2029-01-03",
  "legal_status": "GRANTED",
  "title": "Antibodies binding to CLDN18.2 and uses thereof",
  "target": "CLDN18.2",
  "modality": "Naked monoclonal antibody",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "composition",
      "text": "A monoclonal antibody that binds to the extracellular loop of human Claudin-18 splice variant 2 (CLDN18.2) but does not bind CLDN18.1, covering the antibody and antigen-binding fragments thereof."
    },
    {
      "claim_no": 14,
      "claim_type": "method",
      "text": "A method of treating a CLDN18.2-positive cancer comprising administering the antibody of claim 1."
    }
  ],
  "keywords": [
    "CLDN18.2",
    "claudin",
    "zolbetuximab",
    "naked antibody",
    "gastric",
    "composition of matter",
    "extracellular loop"
  ]
}
↳ search_patents result
show data
{
  "count": 1,
  "families": [
    {
      "publication_number": "WO2019173420A1",
      "jurisdiction": "WO",
      "assignee": "LaNova Medicines",
      "title": "Anti-CLDN18.2 antibody-drug conjugates with a cleavable linker",
      "target": "CLDN18.2",
      "modality": "Antibody-drug conjugate",
      "priority_date": "2018-03-08",
      "expiry": "2039-03-08",
      "legal_status": "GRANTED",
      "claim_types": [
        "composition",
        "method"
      ],
      "keywords": [
        "CLDN18.2",
        "ADC",
        "MMAE",
        "auristatin",
        "cleavable linker",
        "DAR",
        "composition of matter",
        "payload genus"
      ]
    }
  ]
}
Agent · turn 4

I have enough to deliver the FTO assessment. Here is the analysis.


Freedom-to-Operate Assessment: Anti-CLDN18.2 ADC (MMAE / protease-cleavable peptide linker), Gastric Cancer, US

Proposed product profile


Two distinct claim layers create exposure

An ADC infringes if it falls within either (a) a claim to the antibody/binding component, or (b) a claim to the conjugate construct. Both must be cleared.

1. LaNova WO2019173420A1 — the primary blocking risk (conjugate layer)

Claim 1 reads almost verbatim on your product: "Ab-(L-D)n wherein Ab specifically binds human CLDN18.2, L is a protease-cleavable peptide linker, and D is an auristatin payload, including MMAE, with a DAR of 2 to 8."

Critical caveat — this is a WO (PCT) publication, not a granted US patent. "GRANTED" here reflects the family's status, but the corpus shows no US member. Action item before relying on this analysis: confirm whether a US national-phase application (likely a US10/11-series patent) issued, and pull the as-granted US claims, which may be narrower than the PCT claim 1. The PCT priority date of 2018-03-08 yields an expiry ~2039-03-08. If a US counterpart exists with claims of this breadth, it is a hard block through 2039.

2. Ganymed/Astellas US9051370B2 — antibody-layer block (the zolbetuximab patent)

3. Sotio US11078291B2 — likely NOT blocking

4. Others (lower priority)


Bottom line on blocking claims

Patent Layer Blocks your product? Expiry
LaNova WO2019173420A1 Conjugate (linker+payload genus) YES — direct read (pending US-member confirmation) ~2039
Ganymed/Astellas US9051370B2 Antibody (selective CLDN18.2 binder genus) YES 2029
Sotio US11078291B2 Conjugate (maytansinoid/non-cleavable) No 2038

The LaNova family is the controlling long-term obstacle; Ganymed is a serious but time-limited obstacle.


Credible design-arounds

Against Sotio: already cleared — no action needed.

Against Ganymed US9051370B2 (antibody genus, expires 2029):
1. Wait/launch timing — the patent expires 2029; FTO clears naturally if launch can follow.
2. Epitope design-around — claim 1 is limited to antibodies binding the extracellular loop of CLDN18.2 that do not bind CLDN18.1. Hard to avoid functionally, since CLDN18.2 selectivity is essential. A weak design-around; treat as time-limited rather than engineerable.
3. License — consider a license, as Astellas controls the foundational antibody IP.

Against LaNova WO2019173420A1 (the real challenge — three limitations to attack):
The claim couples three elements: (a) CLDN18.2 antibody, (b) protease-cleavable peptide linker, (c) auristatin payload, (d) DAR 2–8. Breaking any one removes literal infringement:

  1. Change the payload class — switch from auristatin/MMAE to a topoisomerase-I inhibitor (DXd/exatecan) or another non-auristatin payload. This exits the "D is an auristatin" limitation entirely. (Note: a DXd approach implicates Keymed CN114106192A — but that's China-only and PENDING, so it does not affect US FTO. Daiichi/other DXd IP would need separate clearance.) Strongest design-around if you can tolerate changing the warhead.
  2. Change the linker chemistry — move to a non-cleavable linker or a non-peptide cleavable linker (e.g., acid-labile hydrazone, disulfide, or glucuronide/β-glucuronidase-cleavable rather than protease-cleavable peptide). A glucuronide linker arguably falls outside "protease-cleavable peptide linker." But note non-cleavable + auristatin may raise other-art questions, and non-cleavable auristatin ADCs are pharmacologically less attractive.
  3. DAR outside 2–8 — only relevant if the granted US claim retains the 2–8 range; a homogeneous DAR-2 or high-DAR (>8) construct could fall outside, but this is a fragile, easily-amended design-around and not recommended as a primary strategy.

Most robust combined strategy: non-auristatin payload (e.g., a topoisomerase-I inhibitor) and/or a non-peptide/non-protease-cleavable linker design-arounds LaNova on the conjugate layer, while the Ganymed antibody patent runs out by 2029.


Required next steps (diligence gaps)

  1. Confirm the US member of the LaNova family and pull its as-granted US claims — this is the single most important open item; WO claim breadth ≠ US claim scope.
  2. Check for additional CLDN18.2 ADC and Daiichi-type auristatin/linker patents outside this corpus (this corpus has only 14 families; real-world FTO requires a broader landscape search, including Mablink/Phanes/other CLDN18.2 ADC players and auristatin-linker platform IP from Seagen).
  3. Obtain antibody sequence freedom analysis — verify your specific antibody clone vs. Ganymed's claimed binders and any sequence-specific claims.
  4. Evaluate licensing of the Ganymed/Astellas antibody estate as a parallel track.

This is a patent-landscape analysis based on the provided corpus, not a legal opinion; a formal FTO opinion from qualified patent counsel with full claim files and your product's exact sequences/chemistry is required before clinical/commercial decisions.

Final output

I have enough to deliver the FTO assessment. Here is the analysis.


Freedom-to-Operate Assessment: Anti-CLDN18.2 ADC (MMAE / protease-cleavable peptide linker), Gastric Cancer, US

Proposed product profile


Two distinct claim layers create exposure

An ADC infringes if it falls within either (a) a claim to the antibody/binding component, or (b) a claim to the conjugate construct. Both must be cleared.

1. LaNova WO2019173420A1 — the primary blocking risk (conjugate layer)

Claim 1 reads almost verbatim on your product: "Ab-(L-D)n wherein Ab specifically binds human CLDN18.2, L is a protease-cleavable peptide linker, and D is an auristatin payload, including MMAE, with a DAR of 2 to 8."

Critical caveat — this is a WO (PCT) publication, not a granted US patent. "GRANTED" here reflects the family's status, but the corpus shows no US member. Action item before relying on this analysis: confirm whether a US national-phase application (likely a US10/11-series patent) issued, and pull the as-granted US claims, which may be narrower than the PCT claim 1. The PCT priority date of 2018-03-08 yields an expiry ~2039-03-08. If a US counterpart exists with claims of this breadth, it is a hard block through 2039.

2. Ganymed/Astellas US9051370B2 — antibody-layer block (the zolbetuximab patent)

3. Sotio US11078291B2 — likely NOT blocking

4. Others (lower priority)


Bottom line on blocking claims

Patent Layer Blocks your product? Expiry
LaNova WO2019173420A1 Conjugate (linker+payload genus) YES — direct read (pending US-member confirmation) ~2039
Ganymed/Astellas US9051370B2 Antibody (selective CLDN18.2 binder genus) YES 2029
Sotio US11078291B2 Conjugate (maytansinoid/non-cleavable) No 2038

The LaNova family is the controlling long-term obstacle; Ganymed is a serious but time-limited obstacle.


Credible design-arounds

Against Sotio: already cleared — no action needed.

Against Ganymed US9051370B2 (antibody genus, expires 2029):
1. Wait/launch timing — the patent expires 2029; FTO clears naturally if launch can follow.
2. Epitope design-around — claim 1 is limited to antibodies binding the extracellular loop of CLDN18.2 that do not bind CLDN18.1. Hard to avoid functionally, since CLDN18.2 selectivity is essential. A weak design-around; treat as time-limited rather than engineerable.
3. License — consider a license, as Astellas controls the foundational antibody IP.

Against LaNova WO2019173420A1 (the real challenge — three limitations to attack):
The claim couples three elements: (a) CLDN18.2 antibody, (b) protease-cleavable peptide linker, (c) auristatin payload, (d) DAR 2–8. Breaking any one removes literal infringement:

  1. Change the payload class — switch from auristatin/MMAE to a topoisomerase-I inhibitor (DXd/exatecan) or another non-auristatin payload. This exits the "D is an auristatin" limitation entirely. (Note: a DXd approach implicates Keymed CN114106192A — but that's China-only and PENDING, so it does not affect US FTO. Daiichi/other DXd IP would need separate clearance.) Strongest design-around if you can tolerate changing the warhead.
  2. Change the linker chemistry — move to a non-cleavable linker or a non-peptide cleavable linker (e.g., acid-labile hydrazone, disulfide, or glucuronide/β-glucuronidase-cleavable rather than protease-cleavable peptide). A glucuronide linker arguably falls outside "protease-cleavable peptide linker." But note non-cleavable + auristatin may raise other-art questions, and non-cleavable auristatin ADCs are pharmacologically less attractive.
  3. DAR outside 2–8 — only relevant if the granted US claim retains the 2–8 range; a homogeneous DAR-2 or high-DAR (>8) construct could fall outside, but this is a fragile, easily-amended design-around and not recommended as a primary strategy.

Most robust combined strategy: non-auristatin payload (e.g., a topoisomerase-I inhibitor) and/or a non-peptide/non-protease-cleavable linker design-arounds LaNova on the conjugate layer, while the Ganymed antibody patent runs out by 2029.


Required next steps (diligence gaps)

  1. Confirm the US member of the LaNova family and pull its as-granted US claims — this is the single most important open item; WO claim breadth ≠ US claim scope.
  2. Check for additional CLDN18.2 ADC and Daiichi-type auristatin/linker patents outside this corpus (this corpus has only 14 families; real-world FTO requires a broader landscape search, including Mablink/Phanes/other CLDN18.2 ADC players and auristatin-linker platform IP from Seagen).
  3. Obtain antibody sequence freedom analysis — verify your specific antibody clone vs. Ganymed's claimed binders and any sequence-specific claims.
  4. Evaluate licensing of the Ganymed/Astellas antibody estate as a parallel track.

This is a patent-landscape analysis based on the provided corpus, not a legal opinion; a formal FTO opinion from qualified patent counsel with full claim files and your product's exact sequences/chemistry is required before clinical/commercial decisions.

Reference answer key (deterministic) — open after grading

Heuristic reference over the curated corpus for target=CLDN18.2, modality=Antibody-drug conjugate. Families in scope: 6 ({'GRANTED': 3, 'PENDING': 2, 'EXPIRED': 1}). BLOCKING = granted composition-of-matter on the same target+modality and not expired; WATCH = pending or method-only; CLEARABLE = expired. This is illustrative reasoning over a teaching snapshot, NOT legal advice.

Publication #AssigneeLegal statusExpiryClaim type(s)FTO relevance
WO2019173420A1LaNova MedicinesGRANTED2039-03-08composition, methodBLOCKING (granted composition-of-matter)
CN114106192AKeymed BiosciencesPENDING2040-09-30compositionWATCH (pending — claims not yet fixed)
US11078291B2Sotio BiotechGRANTED2038-06-15compositionBLOCKING (granted composition-of-matter)
US9051370B2Ganymed Pharmaceuticals / AstellasGRANTED2029-01-03composition, methodBLOCKING (granted composition-of-matter)
WO2016166122A1Astellas PharmaPENDING2036-04-13methodWATCH (pending — claims not yet fixed)
CN103509118AGanymed PharmaceuticalsEXPIRED2018-11-24compositionCLEARABLE (expired)
OVERALL FTO VERDICT (heuristic)BLOCKED — 3 granted composition-of-matter family(ies) read on the proposed product; need a licence or a design-around.

Expert grading

Corpus search completeness 1 (poor) 5 (excellent)
5: Systematically searches the corpus (orients via list_corpus, then queries by target, modality, keyword, and across CN/US/WO) and surfaces the full set of relevant families for the proposed product — including the same-target naked-antibody composition family that can read on an ADC built from it.
1: Runs one narrow query or reasons from memory; misses blocking families or whole jurisdictions; treats the corpus as smaller than it is.
Claim-overlap analysis 1 (poor) 5 (excellent)
5: Reads actual claim text and distinguishes composition-of-matter (molecule/ADC/sequence) from method-of-treatment, and genus from species — e.g. recognises an auristatin/MMAE genus ADC claim reads on a specific MMAE construct, or that a naked-antibody composition claim covers the antibody used in an ADC.
1: Conflates a narrow method claim with a composition claim, ignores genus/species scope, or asserts overlap/non-overlap without reading the claim text.
Legal-status & expiry handling 1 (poor) 5 (excellent)
5: Correctly treats expired families as non-blocking, separates granted from pending (pending claims are not yet enforceable but are a WATCH), and uses priority/expiry dates to reason about when a blocker falls away.
1: Calls an expired patent blocking, treats a pending application as a hard block (or ignores it entirely), or never checks legal status / expiry dates.
FTO verdict & design-around quality 1 (poor) 5 (excellent)
5: Renders a CLEAR/WATCH/BLOCKED verdict that follows from the claims found, and proposes credible, specific design-arounds (e.g. switch from a claimed MMAE/auristatin payload to an unclaimed payload class, change linker chemistry, or wait out an expiring family) tied to the actual blocking claim scope.
1: Verdict contradicts the evidence, is hedged into uselessness, or design-arounds are generic ('use a different antibody') and not tied to specific blocking claims.
Evidence faithfulness 1 (poor) 5 (excellent)
5: Every cited family, claim number, assignee, status, and date traces to tool output; claim-scope statements quote or paraphrase the real claim text; no invented patents.
1: Fabricates publication numbers, claims, assignees, or dates, or contradicts the returned corpus data.
Overall verdict
Your name / ID