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

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

claude-opus-4-8 · 2026-06-06T09:09:42.246152+00:00 · 6 tool calls · 32.6s · 9905 tokens
run id: fto_patent_20260606_020818_02_we-want-to-develop-a-naked-anti-cldn18-2-monoclo

Query

We want to develop a naked anti-CLDN18.2 monoclonal antibody (zolbetuximab-class, binding the CLDN18.2 extracellular loop) for first-line gastric/GEJ adenocarcinoma. Give an FTO read: what blocks us, when does it expire, and is there a path to clear?

Trajectory

Agent · turn 1

I'll give you a freedom-to-operate read on a naked anti-CLDN18.2 mAb. Let me start by orienting myself in the corpus and pulling the relevant CLDN18.2 families.

⚙ 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

The naked-mAb families are the ones that matter for FTO (the ADC families claim conjugates, generally not infringed by a naked antibody, but I'll verify the key one's claim scope). Let me read the actual claims of the three naked-mAb families plus the Sotio ADC to confirm the conjugate limitation.

⚙ calls get_claims(publication_number=US9051370B2)
⚙ calls get_claims(publication_number=WO2016166122A1)
⚙ calls get_claims(publication_number=CN103509118A)
⚙ calls get_claims(publication_number=US11078291B2)
↳ 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": "WO2016166122A1",
  "title": "Combination therapy of a CLDN18.2 antibody with chemotherapy",
  "legal_status": "PENDING",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "method",
      "text": "A method of treating gastric or gastro-oesophageal junction adenocarcinoma comprising administering an anti-CLDN18.2 antibody in combination with a fluoropyrimidine- and platinum-containing chemotherapy regimen."
    }
  ]
}
↳ get_claims result
show data
{
  "publication_number": "CN103509118A",
  "title": "Antibodies for the diagnosis and treatment of claudin-18.2 expressing tumours",
  "legal_status": "EXPIRED",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "composition",
      "text": "An antibody binding CLDN18.2 conjugated to a detectable label for diagnostic imaging of claudin-18.2-expressing tumours."
    }
  ]
}
↳ 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

I have what I need. Here's the FTO read.

FTO Read: Naked anti-CLDN18.2 mAb, 1L gastric/GEJ

What blocks you

1. US9051370B2 (Ganymed/Astellas) — the genus composition-of-matter claim. This is your primary blocker.
- Claim 1 covers "a monoclonal antibody that binds the extracellular loop of human CLDN18.2 but does not bind CLDN18.1" — and antigen-binding fragments.
- This is a broad genus claim defined functionally by epitope/binding specificity, not limited to zolbetuximab's sequence. Your described product — a naked mAb binding the CLDN18.2 extracellular loop, CLDN18.1-sparing — reads squarely inside this claim. The fact that it's the zolbetuximab class makes the overlap essentially certain.
- Claim 14 separately covers the method of treating CLDN18.2-positive cancer with that antibody.
- GRANTED, expires 2029-01-03. This is a hard block on both the composition and the use.

2. WO2016166122A1 (Astellas) — combination/method-of-use blocker for your exact regimen.
- Claim 1: anti-CLDN18.2 antibody + fluoropyrimidine + platinum chemo in gastric/GEJ adenocarcinoma.
- This maps directly onto the registered 1L use (zolbetuximab + mFOLFOX6/CAPOX). So even after the genus composition claim expires, the first-line combination method is separately claimed.
- PENDING, expiry 2036-04-13 if granted. Watch prosecution — scope may narrow, and it's a method claim (only blocks the labeled combo use, not the molecule).

What does not block you

Path to clear

The ADCs are not a problem. The real questions are the two Astellas/Ganymed families:

  1. US9051370B2 (the genus claim) is the gating issue, and it's hard to design around because the claim is functional (epitope + CLDN18.1 sparing), not sequence-based. A differentiated CDR sequence does not get you out — to clear by design you'd have to bind a different epitope or lose CLDN18.1 selectivity, which defeats the "zolbetuximab-class" product rationale. Practical options:
    - Wait it out / time the launch. It expires Jan 3, 2029 (check for any PTE/term adjustment and ex-US equivalents, which aren't in this corpus). A US launch after expiry is clean on the composition claim.
    - License from Astellas if you want to enter before 2029.
    - Validity challenge — a functional genus claim from a 2008 priority date may be vulnerable on written-description/enablement grounds (does the spec enable the full functional genus or just the disclosed antibodies?). Worth a patentability/validity opinion before relying on it.

  2. WO2016166122A1 (1L combo method) — this is a method-of-use claim. Even if US9051370B2 expires in 2029, this could block the first-line fluoropyrimidine+platinum combination through ~2036 if granted. Mitigations:
    - Monitor its prosecution and final granted scope; method claims often narrow.
    - Consider a non-infringing regimen / label (different chemo backbone or monotherapy/other-line positioning) — though that compromises the 1L combo strategy that's the point of the program.
    - Re-assess validity once granted.

Bottom line

Two caveats: this corpus is US/WO/CN only, so confirm ex-US (EP/JP) equivalents and any patent term extension on US9051370B2, both of which could shift the 2029 date. If you tell me which markets you're prioritizing, I can dig further into jurisdiction-specific status.

Final output

I have what I need. Here's the FTO read.

FTO Read: Naked anti-CLDN18.2 mAb, 1L gastric/GEJ

What blocks you

1. US9051370B2 (Ganymed/Astellas) — the genus composition-of-matter claim. This is your primary blocker.
- Claim 1 covers "a monoclonal antibody that binds the extracellular loop of human CLDN18.2 but does not bind CLDN18.1" — and antigen-binding fragments.
- This is a broad genus claim defined functionally by epitope/binding specificity, not limited to zolbetuximab's sequence. Your described product — a naked mAb binding the CLDN18.2 extracellular loop, CLDN18.1-sparing — reads squarely inside this claim. The fact that it's the zolbetuximab class makes the overlap essentially certain.
- Claim 14 separately covers the method of treating CLDN18.2-positive cancer with that antibody.
- GRANTED, expires 2029-01-03. This is a hard block on both the composition and the use.

2. WO2016166122A1 (Astellas) — combination/method-of-use blocker for your exact regimen.
- Claim 1: anti-CLDN18.2 antibody + fluoropyrimidine + platinum chemo in gastric/GEJ adenocarcinoma.
- This maps directly onto the registered 1L use (zolbetuximab + mFOLFOX6/CAPOX). So even after the genus composition claim expires, the first-line combination method is separately claimed.
- PENDING, expiry 2036-04-13 if granted. Watch prosecution — scope may narrow, and it's a method claim (only blocks the labeled combo use, not the molecule).

What does not block you

Path to clear

The ADCs are not a problem. The real questions are the two Astellas/Ganymed families:

  1. US9051370B2 (the genus claim) is the gating issue, and it's hard to design around because the claim is functional (epitope + CLDN18.1 sparing), not sequence-based. A differentiated CDR sequence does not get you out — to clear by design you'd have to bind a different epitope or lose CLDN18.1 selectivity, which defeats the "zolbetuximab-class" product rationale. Practical options:
    - Wait it out / time the launch. It expires Jan 3, 2029 (check for any PTE/term adjustment and ex-US equivalents, which aren't in this corpus). A US launch after expiry is clean on the composition claim.
    - License from Astellas if you want to enter before 2029.
    - Validity challenge — a functional genus claim from a 2008 priority date may be vulnerable on written-description/enablement grounds (does the spec enable the full functional genus or just the disclosed antibodies?). Worth a patentability/validity opinion before relying on it.

  2. WO2016166122A1 (1L combo method) — this is a method-of-use claim. Even if US9051370B2 expires in 2029, this could block the first-line fluoropyrimidine+platinum combination through ~2036 if granted. Mitigations:
    - Monitor its prosecution and final granted scope; method claims often narrow.
    - Consider a non-infringing regimen / label (different chemo backbone or monotherapy/other-line positioning) — though that compromises the 1L combo strategy that's the point of the program.
    - Re-assess validity once granted.

Bottom line

Two caveats: this corpus is US/WO/CN only, so confirm ex-US (EP/JP) equivalents and any patent term extension on US9051370B2, both of which could shift the 2029 date. If you tell me which markets you're prioritizing, I can dig further into jurisdiction-specific status.

Reference answer key (deterministic) — open after grading

Heuristic reference over the curated corpus for target=CLDN18.2, modality=Naked monoclonal antibody. 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
US9051370B2Ganymed Pharmaceuticals / AstellasGRANTED2029-01-03composition, methodBLOCKING (granted composition-of-matter)
WO2016166122A1Astellas PharmaPENDING2036-04-13methodWATCH (pending — claims not yet fixed)
CN103509118AGanymed PharmaceuticalsEXPIRED2018-11-24compositionCLEARABLE (expired)
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)
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