BioGrade · expert reasoning data for biopharma agentsEnvironmentsBenchmarkCompare modelsData flywheelThesis
← Patent / Freedom-to-Operate Analysis comparison · model: GPT (frontier)
LLM-judge score: 1.4 / 5 · unusable
search_completeness: 1 claim_overlap: 2 status_expiry: 2 verdict_designaround: 1 faithfulness: 1
The agent surfaced only one of six relevant families (US11078291B2) and missed all three blocking composition-of-matter families plus the watch/clearable items; it appears to have largely fabricated the claim text (describing Sotio as a maytansinoid/non-cleavable thioether ADC, contradicting the corpus framing) and invented an entire narrative around Seagen platform patents not in the corpus. The reference verdict is BLOCKED by three granted composition families, but the agent concluded essentially CLEAR ('no clear blocking US patent'), the opposite of ground truth, making the verdict dangerously wrong. Design-arounds are generic and untethered to actual blocking claims, and the faithfulness failures (invented claim language, non-corpus patents) are disqualifying.
BD / IP · IP / patent analyst

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

gpt-5.2-chat-latest · 2026-06-06T10:23:37.298520+00:00 · 2 tool calls · 21.5s · 3295 tokens
run id: fto_patent_20260606_031816_fto-patent__gpt-frontier

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
⚙ calls search_patents(target=CLDN18.2, modality=antibody-drug conjugate, jurisdiction=US)
↳ search_patents result
show data
{
  "count": 1,
  "families": [
    {
      "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
⚙ calls get_claims(publication_number=US11078291B2)
↳ 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

Below is a focused US freedom‑to‑operate (FTO) assessment for:

Product concept: Anti‑CLDN18.2 antibody–drug conjugate (ADC)
Payload: MMAE (auristatin)
Linker: Protease‑cleavable peptide (e.g., val‑cit)
Indication: Gastric cancer
Jurisdiction: United States

1. Potentially Relevant US Patents Identified

✅ US11078291B2 (Sotio Biotech)

Title: Maytansinoid antibody-drug conjugates targeting CLDN18.2
Status: Granted
Expiry: 2038-06-15
Independent claim 1 (composition):

"An antibody-drug conjugate comprising an anti-CLDN18.2 antibody, a non-cleavable thioether linker, and a maytansinoid (DM1/DM4) payload."

Key Claim Limitations

2. Infringement Analysis vs. Proposed Product

Claimed Element Your ADC Infringement Risk
Anti‑CLDN18.2 antibody Yes Potential overlap
Payload = maytansinoid (DM1/DM4) ❌ No (MMAE instead) No literal infringement
Non‑cleavable thioether linker ❌ No (protease-cleavable peptide linker) No literal infringement

Conclusion:

Your proposed MMAE + cleavable linker ADC does NOT literally infringe the identified Sotio patent.

3. Doctrine of Equivalents (DOE) Risk

Low.

Reasons:

Because both payload and linker are materially different, DOE risk is weak.

4. Other Potential Blocking Categories (Not Yet Identified Here)

Although no additional CLDN18.2 ADC patents were surfaced in this dataset, in a real-world FTO you must also assess:

A. Broad CLDN18.2 Antibody Composition Claims

Some companies (e.g., Astellas, Zolbetuximab developers) may hold:
- Claims to specific antibody sequences
- Epitope-specific antibodies
- Use in gastric cancer

➡ If you use a novel antibody sequence, you likely avoid composition claims.

B. Platform ADC Patents (Auristatin + Cleavable Linker)

This is actually the larger FTO risk area.

Historically:

Owner Technology Status
Seattle Genetics (Seagen) MMAE + val‑cit linker Many patents expired or expiring 2024–2026
ImmunoGen Maytansinoid linkers Less relevant here
Daiichi Sankyo Topoisomerase payloads Not relevant

Most foundational MMAE + val‑cit linker patents (e.g., Adcetris platform) are now expired or near expiry, but you must confirm specific US families.

As of 2026:
- Many original auristatin linker platform patents (filed ~2000–2005) have expired.
- Secondary formulation and manufacturing patents may remain.

This requires targeted searching beyond the CLDN18.2-specific corpus.

5. Overall FTO Risk Assessment (US)

Risk Category Assessment
CLDN18.2-specific ADC claims ✅ Low (only narrow maytansinoid + non-cleavable linker patent found)
Auristatin linker platform ⚠ Moderate (confirm expiry status carefully)
Specific antibody sequence patents ⚠ Depends on your antibody
Method of treatment (gastric cancer + CLDN18.2 ADC) ⚠ Need targeted search

6. Credible Design-Around Strategies

Even though direct blocking claims were not identified here, the following are strong prophylactic strategies:

✅ 1. Use a Novel Antibody Sequence

✅ 2. Maintain Cleavable Peptide Linker

The Sotio patent is limited to:
- Non-cleavable thioether linker
- Maytansinoid payload

Your design already avoids both.

✅ 3. Avoid DM1/DM4 Payloads

Do not switch to maytansinoids unless a license is obtained.

✅ 4. Consider Alternative Auristatin Variants

If auristatin platform risk emerges:
- MMAF
- New-generation auristatins
- Non-val‑cit cleavable linkers (e.g., β‑glucuronide)

✅ 5. Engineer Distinct DAR / Conjugation Chemistry

This further distances from older platform claims.

7. Bottom-Line FTO Opinion (US)

Based on the currently identified patent:

✅ No clear blocking US patent was identified that covers an anti‑CLDN18.2 ADC comprising MMAE with a protease-cleavable linker.

The only located granted patent is narrowly limited to:
- Maytansinoid payloads
- Non-cleavable linkers

Your product falls outside its literal scope.

8. Recommended Next Steps for a Real Transaction-Grade FTO

To elevate this to investment-grade:

  1. Full US search for:
    - CLDN18.2 antibody composition claims
    - CLDN18.2 method-of-treatment claims
    - Auristatin + val‑cit linker patents still in force
  2. Sequence clearance vs known anti‑CLDN18.2 antibodies
  3. Evaluate terminal disclaimers / continuation families
  4. Confirm expiry of Seattle Genetics auristatin platform patents

If you’d like, I can next:
- Conduct a target-agnostic search for active US auristatin linker patents, or
- Perform a method-of-treatment focused search (CLDN18.2 + gastric cancer).

Final output

Below is a focused US freedom‑to‑operate (FTO) assessment for:

Product concept: Anti‑CLDN18.2 antibody–drug conjugate (ADC)
Payload: MMAE (auristatin)
Linker: Protease‑cleavable peptide (e.g., val‑cit)
Indication: Gastric cancer
Jurisdiction: United States

1. Potentially Relevant US Patents Identified

✅ US11078291B2 (Sotio Biotech)

Title: Maytansinoid antibody-drug conjugates targeting CLDN18.2
Status: Granted
Expiry: 2038-06-15
Independent claim 1 (composition):

"An antibody-drug conjugate comprising an anti-CLDN18.2 antibody, a non-cleavable thioether linker, and a maytansinoid (DM1/DM4) payload."

Key Claim Limitations

2. Infringement Analysis vs. Proposed Product

Claimed Element Your ADC Infringement Risk
Anti‑CLDN18.2 antibody Yes Potential overlap
Payload = maytansinoid (DM1/DM4) ❌ No (MMAE instead) No literal infringement
Non‑cleavable thioether linker ❌ No (protease-cleavable peptide linker) No literal infringement

Conclusion:

Your proposed MMAE + cleavable linker ADC does NOT literally infringe the identified Sotio patent.

3. Doctrine of Equivalents (DOE) Risk

Low.

Reasons:

Because both payload and linker are materially different, DOE risk is weak.

4. Other Potential Blocking Categories (Not Yet Identified Here)

Although no additional CLDN18.2 ADC patents were surfaced in this dataset, in a real-world FTO you must also assess:

A. Broad CLDN18.2 Antibody Composition Claims

Some companies (e.g., Astellas, Zolbetuximab developers) may hold:
- Claims to specific antibody sequences
- Epitope-specific antibodies
- Use in gastric cancer

➡ If you use a novel antibody sequence, you likely avoid composition claims.

B. Platform ADC Patents (Auristatin + Cleavable Linker)

This is actually the larger FTO risk area.

Historically:

Owner Technology Status
Seattle Genetics (Seagen) MMAE + val‑cit linker Many patents expired or expiring 2024–2026
ImmunoGen Maytansinoid linkers Less relevant here
Daiichi Sankyo Topoisomerase payloads Not relevant

Most foundational MMAE + val‑cit linker patents (e.g., Adcetris platform) are now expired or near expiry, but you must confirm specific US families.

As of 2026:
- Many original auristatin linker platform patents (filed ~2000–2005) have expired.
- Secondary formulation and manufacturing patents may remain.

This requires targeted searching beyond the CLDN18.2-specific corpus.

5. Overall FTO Risk Assessment (US)

Risk Category Assessment
CLDN18.2-specific ADC claims ✅ Low (only narrow maytansinoid + non-cleavable linker patent found)
Auristatin linker platform ⚠ Moderate (confirm expiry status carefully)
Specific antibody sequence patents ⚠ Depends on your antibody
Method of treatment (gastric cancer + CLDN18.2 ADC) ⚠ Need targeted search

6. Credible Design-Around Strategies

Even though direct blocking claims were not identified here, the following are strong prophylactic strategies:

✅ 1. Use a Novel Antibody Sequence

✅ 2. Maintain Cleavable Peptide Linker

The Sotio patent is limited to:
- Non-cleavable thioether linker
- Maytansinoid payload

Your design already avoids both.

✅ 3. Avoid DM1/DM4 Payloads

Do not switch to maytansinoids unless a license is obtained.

✅ 4. Consider Alternative Auristatin Variants

If auristatin platform risk emerges:
- MMAF
- New-generation auristatins
- Non-val‑cit cleavable linkers (e.g., β‑glucuronide)

✅ 5. Engineer Distinct DAR / Conjugation Chemistry

This further distances from older platform claims.

7. Bottom-Line FTO Opinion (US)

Based on the currently identified patent:

✅ No clear blocking US patent was identified that covers an anti‑CLDN18.2 ADC comprising MMAE with a protease-cleavable linker.

The only located granted patent is narrowly limited to:
- Maytansinoid payloads
- Non-cleavable linkers

Your product falls outside its literal scope.

8. Recommended Next Steps for a Real Transaction-Grade FTO

To elevate this to investment-grade:

  1. Full US search for:
    - CLDN18.2 antibody composition claims
    - CLDN18.2 method-of-treatment claims
    - Auristatin + val‑cit linker patents still in force
  2. Sequence clearance vs known anti‑CLDN18.2 antibodies
  3. Evaluate terminal disclaimers / continuation families
  4. Confirm expiry of Seattle Genetics auristatin platform patents

If you’d like, I can next:
- Conduct a target-agnostic search for active US auristatin linker patents, or
- Perform a method-of-treatment focused search (CLDN18.2 + gastric cancer).

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