← Patent / Freedom-to-Operate Analysis comparison · model: Claude Opus 4.8
LLM-judge score: 4.6 / 5 · strong
search_completeness: 5 claim_overlap: 5 status_expiry: 4 verdict_designaround: 5 faithfulness: 4
The agent surfaced all six relevant families, read claim text carefully, and correctly distinguished the Ganymed naked-antibody genus, LaNova ADC species, and Sotio's non-overlapping linker/payload chemistry, with credible design-arounds tied to specific blocking claims. Its main deviation from the key is treating LaNova as 'US status to be confirmed' rather than BLOCKING β€” defensible reasoning since a WO confers no US rights, but it under-calls one of the three reference blockers and never delivers a crisp overall BLOCKED verdict. Status/expiry handling is sound (expired CN cleared, pending flagged as watch), and factual claims trace to corpus data with only minor unverifiable elaborations on linker chemistry.
BD / IP · IP / patent analyst

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

claude-opus-4-8 · 2026-06-06T10:22:08.353972+00:00 · 11 tool calls · 54.3s · 22690 tokens
run id: fto_patent_20260606_031816_fto-patent__claude-opus-4-8

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 β€” the granted US patents and the ADC-specific filings.

⚙ calls get_claims(publication_number=US9051370B2)
⚙ calls get_claims(publication_number=WO2019173420A1)
⚙ 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": "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": "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 two most concerning patents are US9051370B2 (Ganymed/Astellas) and WO2019173420A1 (LaNova). Let me get full records to check jurisdiction reach, priority, expiry, and whether the LaNova WO has a US counterpart, plus check the broader corpus for any genus auristatin/linker claims that could read on this.

⚙ calls get_patent(publication_number=US9051370B2)
⚙ calls get_patent(publication_number=WO2019173420A1)
⚙ calls search_patents(keyword=MMAE)
⚙ calls search_patents(keyword=auristatin, jurisdiction=US)
↳ 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"
  ]
}
↳ 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"
  ]
}
↳ 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"
      ]
    }
  ]
}
↳ search_patents result
show data
{
  "count": 0,
  "families": []
}
Agent · turn 4

Let me verify the CLDN18.2 antibody landscape for design-around options (other naked antibody claims that might define usable binders) and confirm there's no separate US Astellas combination/method patent I'm missing.

⚙ calls search_patents(target=CLDN18.2, modality=Naked)
⚙ calls search_patents(keyword=gastric, jurisdiction=US)
↳ search_patents result
show data
{
  "count": 3,
  "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"
      ]
    }
  ]
}
↳ search_patents result
show data
{
  "count": 1,
  "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"
      ]
    }
  ]
}
Agent · turn 5

I now have a complete picture of the US-relevant landscape. Here is the FTO assessment.


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

Executive summary

Your proposed product faces two material blocking risks in the US: one genus composition-of-matter patent on the anti-CLDN18.2 antibody itself (Ganymed/Astellas), and one WO ADC patent whose claim language reads almost verbatim on your product (LaNova). The LaNova WO is not itself a US right, so its US enforceability depends on whether a US national-phase member issued β€” that must be confirmed outside this corpus. The Sotio ADC patent does not block you (different linker/payload chemistry).


Blocking analysis

πŸ”΄ 1. US9051370B2 β€” Ganymed/Astellas (HIGHEST RISK, confirmed US patent)

πŸ”΄ 2. WO2019173420A1 β€” LaNova Medicines (DIRECT-HIT claim scope; US status to be confirmed)

🟒 3. US11078291B2 β€” Sotio Biotech (NOT blocking)

Not US-relevant / not blocking


Design-around options

Risk Design-around Viability
US9051370B2 (antibody genus) Use an antibody that does not bind the extracellular loop / or that also binds CLDN18.1, etc. Poor. Sparing CLDN18.1 is required for safety; binding the extracellular loop is required for surface targeting. The claim is functionally drawn around exactly the antibody you need. Design-around is essentially infeasible without undermining the product.
US9051370B2 License from Astellas/Ganymed (likely the only clean path). Recommended primary strategy.
US9051370B2 Wait for expiry (Jan 2029) then launch. Viable if timeline tolerates it; also check for any later Astellas continuations/method patents (e.g., WO2016166122A1 family) extending coverage.
LaNova ADC claim Switch payload class: topoisomerase-I inhibitor (DXd/exatecan) or maytansinoid instead of auristatin. Strong technically — but note DXd implicates Keymed (China only here) and DM1/DM4 implicates Sotio (US, granted). Auristatin→maytansinoid would walk you into US11078291B2.
LaNova ADC claim Use a non-peptide / non-protease-cleavable linker (e.g., acid-labile, glucuronide-cleavable, or non-cleavable) while keeping MMAE. Moderate β€” moves outside "protease-cleavable peptide linker" element. Glucuronidase-cleavable linkers are enzyme-cleavable but not "peptide"; assess claim construction carefully.
LaNova ADC claim Operate at DAR outside 2–8 (e.g., site-specific DAR exactly 2 is within range; very high DAR is impractical). Weak β€” 2–8 covers essentially all practical DARs.
LaNova ADC claim Confirm no US family member exists; if abandoned/never filed, no design-around needed in US. First and cheapest step.

Recommended actions (priority order)

  1. Confirm LaNova US status β€” pull USPTO Patent Center for any application claiming PCT priority 2018-03-08. This single fact determines whether your product is blocked on composition in the US through ~2039.
  2. Plan to license US9051370B2 from Astellas/Ganymed β€” the antibody genus claim is the unavoidable gate through Jan 2029 and is not designable-around. Confirm in-force status, term adjustments/extensions (PTA/PTE), and look for later continuation/method families.
  3. If LaNova has a live US member: prefer a payload or linker design-around β€” but route carefully to avoid Sotio (US, maytansinoid/non-cleavable). A retained-MMAE-with-non-peptide-cleavable-linker may be the narrowest deviation; a wholly different payload is the cleanest.
  4. Obtain outside opinion-of-counsel before clinical/commercial commitment, including a full prior-art / validity review of US9051370B2 and any LaNova US claims (a function-defined antibody genus from 2008 may have written-description/enablement vulnerabilities worth assessing as a backstop).

Caveats: This analysis is limited to the 14-family corpus provided and to US scope; it is not legal advice. The LaNova WO→US determination and any Astellas continuations/PTE require off-corpus public-register confirmation. Doctrine-of-equivalents and validity opinions require full prosecution-history and prior-art review.

Final output

I now have a complete picture of the US-relevant landscape. Here is the FTO assessment.


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

Executive summary

Your proposed product faces two material blocking risks in the US: one genus composition-of-matter patent on the anti-CLDN18.2 antibody itself (Ganymed/Astellas), and one WO ADC patent whose claim language reads almost verbatim on your product (LaNova). The LaNova WO is not itself a US right, so its US enforceability depends on whether a US national-phase member issued β€” that must be confirmed outside this corpus. The Sotio ADC patent does not block you (different linker/payload chemistry).


Blocking analysis

πŸ”΄ 1. US9051370B2 β€” Ganymed/Astellas (HIGHEST RISK, confirmed US patent)

πŸ”΄ 2. WO2019173420A1 β€” LaNova Medicines (DIRECT-HIT claim scope; US status to be confirmed)

🟒 3. US11078291B2 β€” Sotio Biotech (NOT blocking)

Not US-relevant / not blocking


Design-around options

Risk Design-around Viability
US9051370B2 (antibody genus) Use an antibody that does not bind the extracellular loop / or that also binds CLDN18.1, etc. Poor. Sparing CLDN18.1 is required for safety; binding the extracellular loop is required for surface targeting. The claim is functionally drawn around exactly the antibody you need. Design-around is essentially infeasible without undermining the product.
US9051370B2 License from Astellas/Ganymed (likely the only clean path). Recommended primary strategy.
US9051370B2 Wait for expiry (Jan 2029) then launch. Viable if timeline tolerates it; also check for any later Astellas continuations/method patents (e.g., WO2016166122A1 family) extending coverage.
LaNova ADC claim Switch payload class: topoisomerase-I inhibitor (DXd/exatecan) or maytansinoid instead of auristatin. Strong technically — but note DXd implicates Keymed (China only here) and DM1/DM4 implicates Sotio (US, granted). Auristatin→maytansinoid would walk you into US11078291B2.
LaNova ADC claim Use a non-peptide / non-protease-cleavable linker (e.g., acid-labile, glucuronide-cleavable, or non-cleavable) while keeping MMAE. Moderate β€” moves outside "protease-cleavable peptide linker" element. Glucuronidase-cleavable linkers are enzyme-cleavable but not "peptide"; assess claim construction carefully.
LaNova ADC claim Operate at DAR outside 2–8 (e.g., site-specific DAR exactly 2 is within range; very high DAR is impractical). Weak β€” 2–8 covers essentially all practical DARs.
LaNova ADC claim Confirm no US family member exists; if abandoned/never filed, no design-around needed in US. First and cheapest step.

Recommended actions (priority order)

  1. Confirm LaNova US status β€” pull USPTO Patent Center for any application claiming PCT priority 2018-03-08. This single fact determines whether your product is blocked on composition in the US through ~2039.
  2. Plan to license US9051370B2 from Astellas/Ganymed β€” the antibody genus claim is the unavoidable gate through Jan 2029 and is not designable-around. Confirm in-force status, term adjustments/extensions (PTA/PTE), and look for later continuation/method families.
  3. If LaNova has a live US member: prefer a payload or linker design-around β€” but route carefully to avoid Sotio (US, maytansinoid/non-cleavable). A retained-MMAE-with-non-peptide-cleavable-linker may be the narrowest deviation; a wholly different payload is the cleanest.
  4. Obtain outside opinion-of-counsel before clinical/commercial commitment, including a full prior-art / validity review of US9051370B2 and any LaNova US claims (a function-defined antibody genus from 2008 may have written-description/enablement vulnerabilities worth assessing as a backstop).

Caveats: This analysis is limited to the 14-family corpus provided and to US scope; it is not legal advice. The LaNova WO→US determination and any Astellas continuations/PTE require off-corpus public-register confirmation. Doctrine-of-equivalents and validity opinions require full prosecution-history and prior-art review.

Reference answer key (deterministic) β€” 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 β€” 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 β€” claims not yet fixed)
CN103509118AGanymed PharmaceuticalsEXPIRED2018-11-24compositionCLEARABLE (expired)
OVERALL FTO VERDICT (heuristic)BLOCKED β€” 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 β€” 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 β€” 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