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

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

claude-opus-4-8 · 2026-06-06T09:10:34.908531+00:00 · 12 tool calls · 52.6s · 20822 tokens
run id: fto_patent_20260606_020818_03_evaluate-freedom-to-operate-for-a-her2-directed

Query

Evaluate freedom-to-operate for a HER2-directed antibody-drug conjugate carrying an exatecan-derivative topoisomerase-I payload via a GGFG cleavable linker, for HER2-low breast cancer. Which families are blocking vs. expired, and what design-arounds exist?

Trajectory

Agent · turn 1

I'll analyze the freedom-to-operate landscape for your HER2-directed ADC. Let me start by orienting myself in the corpus.

⚙ calls list_corpus()
↳ 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"
  ]
}
Agent · turn 2

Let me search the HER2 families and the relevant payload/linker technology.

⚙ calls search_patents(target=HER2)
⚙ calls search_patents(keyword=exatecan)
⚙ calls search_patents(keyword=GGFG)
⚙ calls search_patents(keyword=topoisomerase)
↳ search_patents result
show data
{
  "count": 4,
  "families": [
    {
      "publication_number": "US10973920B2",
      "jurisdiction": "US",
      "assignee": "Daiichi Sankyo",
      "title": "Anti-HER2 antibody-drug conjugate with an exatecan-derivative payload",
      "target": "HER2",
      "modality": "Antibody-drug conjugate",
      "priority_date": "2014-09-30",
      "expiry": "2035-09-30",
      "legal_status": "GRANTED",
      "claim_types": [
        "composition"
      ],
      "keywords": [
        "HER2",
        "ADC",
        "deruxtecan",
        "DXd",
        "exatecan",
        "GGFG linker",
        "topoisomerase",
        "high DAR",
        "composition of matter"
      ]
    },
    {
      "publication_number": "US7575748B1",
      "jurisdiction": "US",
      "assignee": "Genentech",
      "title": "Humanized anti-HER2 antibodies",
      "target": "HER2",
      "modality": "Naked monoclonal antibody",
      "priority_date": "1998-08-27",
      "expiry": "2019-08-27",
      "legal_status": "EXPIRED",
      "claim_types": [
        "composition"
      ],
      "keywords": [
        "HER2",
        "trastuzumab",
        "naked antibody",
        "humanized",
        "expired",
        "extracellular domain",
        "composition of matter"
      ]
    },
    {
      "publication_number": "WO2020196474A1",
      "jurisdiction": "WO",
      "assignee": "Byondis",
      "title": "Anti-HER2 antibody-drug conjugate with a duocarmycin payload",
      "target": "HER2",
      "modality": "Antibody-drug conjugate",
      "priority_date": "2019-03-26",
      "expiry": "2040-03-26",
      "legal_status": "PENDING",
      "claim_types": [
        "composition"
      ],
      "keywords": [
        "HER2",
        "ADC",
        "duocarmycin",
        "vc linker",
        "cleavable linker",
        "pending",
        "alternative payload"
      ]
    },
    {
      "publication_number": "US9968687B2",
      "jurisdiction": "US",
      "assignee": "ImmunoGen",
      "title": "Anti-HER2 maytansinoid conjugate (T-DM1 class)",
      "target": "HER2",
      "modality": "Antibody-drug conjugate",
      "priority_date": "2010-02-24",
      "expiry": "2031-02-24",
      "legal_status": "GRANTED",
      "claim_types": [
        "composition",
        "method"
      ],
      "keywords": [
        "HER2",
        "ADC",
        "T-DM1",
        "maytansinoid",
        "DM1",
        "SMCC",
        "non-cleavable linker",
        "composition of matter"
      ]
    }
  ]
}
↳ search_patents result
show data
{
  "count": 2,
  "families": [
    {
      "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": "US10973920B2",
      "jurisdiction": "US",
      "assignee": "Daiichi Sankyo",
      "title": "Anti-HER2 antibody-drug conjugate with an exatecan-derivative payload",
      "target": "HER2",
      "modality": "Antibody-drug conjugate",
      "priority_date": "2014-09-30",
      "expiry": "2035-09-30",
      "legal_status": "GRANTED",
      "claim_types": [
        "composition"
      ],
      "keywords": [
        "HER2",
        "ADC",
        "deruxtecan",
        "DXd",
        "exatecan",
        "GGFG linker",
        "topoisomerase",
        "high DAR",
        "composition of matter"
      ]
    }
  ]
}
↳ search_patents result
show data
{
  "count": 1,
  "families": [
    {
      "publication_number": "US10973920B2",
      "jurisdiction": "US",
      "assignee": "Daiichi Sankyo",
      "title": "Anti-HER2 antibody-drug conjugate with an exatecan-derivative payload",
      "target": "HER2",
      "modality": "Antibody-drug conjugate",
      "priority_date": "2014-09-30",
      "expiry": "2035-09-30",
      "legal_status": "GRANTED",
      "claim_types": [
        "composition"
      ],
      "keywords": [
        "HER2",
        "ADC",
        "deruxtecan",
        "DXd",
        "exatecan",
        "GGFG linker",
        "topoisomerase",
        "high DAR",
        "composition of matter"
      ]
    }
  ]
}
↳ search_patents result
show data
{
  "count": 2,
  "families": [
    {
      "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": "US10973920B2",
      "jurisdiction": "US",
      "assignee": "Daiichi Sankyo",
      "title": "Anti-HER2 antibody-drug conjugate with an exatecan-derivative payload",
      "target": "HER2",
      "modality": "Antibody-drug conjugate",
      "priority_date": "2014-09-30",
      "expiry": "2035-09-30",
      "legal_status": "GRANTED",
      "claim_types": [
        "composition"
      ],
      "keywords": [
        "HER2",
        "ADC",
        "deruxtecan",
        "DXd",
        "exatecan",
        "GGFG linker",
        "topoisomerase",
        "high DAR",
        "composition of matter"
      ]
    }
  ]
}
Agent · turn 3

The Daiichi Sankyo family (US10973920B2) is the centerpiece — it directly reads on your described product (this is trastuzumab deruxtecan / Enhertu chemistry). Let me read the actual claims of the most relevant families to assess scope.

⚙ calls get_claims(publication_number=US10973920B2)
⚙ calls get_claims(publication_number=CN114106192A)
⚙ calls get_claims(publication_number=US7575748B1)
⚙ calls get_claims(publication_number=WO2020196474A1)
⚙ calls get_claims(publication_number=US9968687B2)
↳ get_claims result
show data
{
  "publication_number": "US10973920B2",
  "title": "Anti-HER2 antibody-drug conjugate with an exatecan-derivative payload",
  "legal_status": "GRANTED",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "composition",
      "text": "An antibody-drug conjugate wherein an anti-HER2 antibody is conjugated through a maleimide-GGFG peptide linker to a DX-8951 (exatecan) derivative topoisomerase-I inhibitor, at a drug-to-antibody ratio of about 7 to 8."
    },
    {
      "claim_no": 12,
      "claim_type": "composition",
      "text": "The drug-linker intermediate of the conjugate of claim 1, comprising the GGFG tetrapeptide spacer and self-immolative aminomethyl group."
    }
  ]
}
↳ get_claims result
show data
{
  "publication_number": "CN114106192A",
  "title": "Anti-claudin18.2 antibody conjugated to a topoisomerase-I inhibitor payload",
  "legal_status": "PENDING",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "composition",
      "text": "An antibody-drug conjugate comprising an anti-CLDN18.2 antibody covalently linked via a tetrapeptide-based cleavable linker to an exatecan-derivative topoisomerase-I inhibitor payload."
    }
  ]
}
↳ get_claims result
show data
{
  "publication_number": "US7575748B1",
  "title": "Humanized anti-HER2 antibodies",
  "legal_status": "EXPIRED",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "composition",
      "text": "A humanized antibody that binds the extracellular domain of human HER2/neu, comprising the trastuzumab heavy- and light-chain variable regions."
    }
  ]
}
↳ get_claims result
show data
{
  "publication_number": "WO2020196474A1",
  "title": "Anti-HER2 antibody-drug conjugate with a duocarmycin payload",
  "legal_status": "PENDING",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "composition",
      "text": "An antibody-drug conjugate comprising an anti-HER2 antibody, a cleavable valine-citrulline linker, and a seco-duocarmycin-hydroxybenzamide-azaindole (duocarmycin) payload."
    }
  ]
}
↳ get_claims result
show data
{
  "publication_number": "US9968687B2",
  "title": "Anti-HER2 maytansinoid conjugate (T-DM1 class)",
  "legal_status": "GRANTED",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "composition",
      "text": "An immunoconjugate comprising trastuzumab linked via a non-cleavable SMCC linker to the maytansinoid DM1."
    },
    {
      "claim_no": 8,
      "claim_type": "method",
      "text": "A method of treating HER2-positive metastatic breast cancer that has progressed on trastuzumab and a taxane, comprising administering the immunoconjugate of claim 1."
    }
  ]
}
Agent · turn 4

Let me get the full record on the Daiichi family to check for any HER2-low method claims or additional details that bear on the indication.

⚙ calls get_patent(publication_number=US10973920B2)
⚙ calls search_patents(keyword=HER2-low)
↳ get_patent result
show data
{
  "publication_number": "US10973920B2",
  "jurisdiction": "US",
  "assignee": "Daiichi Sankyo",
  "priority_date": "2014-09-30",
  "expiry": "2035-09-30",
  "legal_status": "GRANTED",
  "title": "Anti-HER2 antibody-drug conjugate with an exatecan-derivative payload",
  "target": "HER2",
  "modality": "Antibody-drug conjugate",
  "independent_claims": [
    {
      "claim_no": 1,
      "claim_type": "composition",
      "text": "An antibody-drug conjugate wherein an anti-HER2 antibody is conjugated through a maleimide-GGFG peptide linker to a DX-8951 (exatecan) derivative topoisomerase-I inhibitor, at a drug-to-antibody ratio of about 7 to 8."
    },
    {
      "claim_no": 12,
      "claim_type": "composition",
      "text": "The drug-linker intermediate of the conjugate of claim 1, comprising the GGFG tetrapeptide spacer and self-immolative aminomethyl group."
    }
  ],
  "keywords": [
    "HER2",
    "ADC",
    "deruxtecan",
    "DXd",
    "exatecan",
    "GGFG linker",
    "topoisomerase",
    "high DAR",
    "composition of matter"
  ]
}
↳ search_patents result
show data
{
  "count": 0,
  "families": []
}
Agent · turn 5

I now have a complete picture of the FTO landscape. Here is my assessment.


Freedom-to-Operate Assessment: HER2-ADC with Exatecan/DXd Payload + GGFG Linker (HER2-low Breast Cancer)

Bottom line

Your proposed product is essentially trastuzumab deruxtecan (Enhertu) chemistry. As designed, it falls squarely within a granted, in-force composition-of-matter claim owned by Daiichi Sankyo. FTO is not clear — you have a hard blocking position on the core composition, and meaningful design-arounds require moving off the exatecan/GGFG/high-DAR combination.


1. The blocking family — US10973920B2 (Daiichi Sankyo)

Attribute Detail
Status GRANTED / in force
Priority 2014-09-30
Expiry 2035-09-30 (no PTE/SPC modeled here)
Claim 1 Anti-HER2 antibody + maleimide-GGFG peptide linker + DX-8951 (exatecan) derivative topo-I inhibitor at DAR ~7–8
Claim 12 The drug-linker intermediate (GGFG tetrapeptide + self-immolative aminomethyl)

Element-by-element read against your product:

Conclusion: Literal infringement of claim 1 if your DAR is in the 7–8 range. This is a genuine blocking patent through September 2035. The indication (HER2-low) is irrelevant — claim 1 is a pure composition claim; it does not matter what cancer you treat. Note: no HER2-low method claim exists in this corpus, but you cannot reach the method-of-use design-around because making/selling the composition itself infringes.


2. Expired / non-blocking families

Family Assignee Status Why it doesn't block you
US7575748B1 Genentech EXPIRED (2019) The trastuzumab humanized-antibody composition claim is expired. You are free to use the trastuzumab antibody scaffold itself — the antibody is no longer a barrier. The barrier is the conjugate.
US9968687B2 (T-DM1) ImmunoGen Granted, but non-overlapping Claims a non-cleavable SMCC linker + maytansinoid DM1. Different linker chemistry and different payload class — does not read on a GGFG/exatecan ADC. Its method claim is limited to HER2-positive post-trastuzumab/taxane, also not implicated. Expires 2031.

The expiry of the Genentech antibody patent is the key positive: the binder is free; only the payload+linker+DAR combination is encumbered.


3. Other in-corpus families to monitor (not directly blocking)

Family Assignee Status Relevance
WO2020196474A1 Byondis PENDING HER2 ADC but duocarmycin payload + vc linker — a competing design-around archetype, not a blocker against you. Confirms the duocarmycin route is being staked out by others.
CN114106192A Keymed PENDING (CN) Anti-CLDN18.2 + tetrapeptide linker + exatecan/DXd. Different target, so no overlap on a HER2 product. BUT note its claim 1 is drafted to a tetrapeptide-based cleavable linker + exatecan payload generically — watch its prosecution; relevant only if you ever extend the platform to CLDN18.2. CN-only jurisdiction.

4. Design-around options (ranked by separation from the blocking claim)

Claim 1's three pillars are (a) exatecan-derivative payload, (b) GGFG linker, (c) DAR ~7–8. Defeating any one element avoids literal infringement, but watch doctrine of equivalents.

Strongest design-arounds (change the payload class — cleanest escape):
1. Switch payload chemistry entirely — e.g., the duocarmycin route (cf. Byondis WO2020196474A1) or a maytansinoid/auristatin. This exits "exatecan-derivative topo-I" and is the most defensible. Caveat: you then need FTO against those families (Byondis pending; ImmunoGen for maytansinoids).

Moderate (keep topo-I MoA but engineer off the literal claim — higher DoE risk):
2. Non-exatecan topo-I payload — a camptothecin/SN-38-type or a structurally distinct topo-I warhead that is not a "DX-8951/exatecan derivative." Preserves the topo-I mechanism and bystander effect attractive for HER2-low, but DoE risk is highest here because the patentee will argue equivalence of topo-I exatecan-likes.
3. Replace the GGFG tetrapeptide linker — e.g., a different cleavable peptide (val-cit, val-ala) or a glycosidase/disulfide-cleavable chemistry, dropping the self-immolative aminomethyl of claim 12. Reduces overlap on both claim 1 (linker) and claim 12 (intermediate). Strongest if combined with a non-maleimide conjugation handle.

Weakest (do not rely on alone):
4. DAR engineering — moving to a homogeneous DAR ~2–4 technically exits "about 7–8." This is brittle: "about" invites a DoE argument, and a high-DAR topo-I bystander payload is much of what makes the product work for HER2-low. Use only as a secondary differentiator, never the sole basis.

Procedural levers:
5. Geographic strategy — confirm whether the Daiichi family is granted/in-force in each target jurisdiction; FTO is country-by-country. The exatecan-topo-I CLDN18.2 art is CN-pending, indicating active CN filing activity in this space.
6. License — given a literal in-force composition claim through 2035, an in-license from Daiichi Sankyo is the realistic path if you want to keep the exact exatecan/GGFG/high-DAR design (which is what makes Enhertu effective in HER2-low).
7. Validity challenge — assess prior art against the 2014 priority date if a design-around isn't commercially viable; not modeled in this corpus.


Summary table

Family Assignee Status Verdict for your product
US10973920B2 Daiichi Sankyo Granted, expires 2035 BLOCKING — literal read on Ab+GGFG+exatecan+DAR7-8
US7575748B1 Genentech Expired 2019 Clear — trastuzumab scaffold free to use
US9968687B2 ImmunoGen Granted, 2031 Not blocking — different (SMCC/maytansinoid) chemistry
WO2020196474A1 Byondis Pending Not blocking — duocarmycin; a design-around template
CN114106192A Keymed Pending (CN) Not blocking (CLDN18.2 target); monitor if platform extends

Recommendation: As specified, your candidate is blocked by US10973920B2 until 2035. To obtain FTO you should either (1) license from Daiichi Sankyo, or (2) re-engineer the payload class (most robust — e.g., off topo-I entirely, or to a clearly non-exatecan warhead) ideally combined with a non-GGFG cleavable linker, rather than relying on DAR adjustment alone. The HER2-low indication itself raises no method-claim barrier in this corpus — the obstacle is entirely the composition.

Caveats: this analysis covers only the 14-family corpus provided; no PTE/SPC term extensions, foreign counterparts outside US/WO/CN, or pending continuations are reflected. Confirm jurisdiction-by-jurisdiction status and obtain formal patent-counsel opinion before clearance.

Final output

I now have a complete picture of the FTO landscape. Here is my assessment.


Freedom-to-Operate Assessment: HER2-ADC with Exatecan/DXd Payload + GGFG Linker (HER2-low Breast Cancer)

Bottom line

Your proposed product is essentially trastuzumab deruxtecan (Enhertu) chemistry. As designed, it falls squarely within a granted, in-force composition-of-matter claim owned by Daiichi Sankyo. FTO is not clear — you have a hard blocking position on the core composition, and meaningful design-arounds require moving off the exatecan/GGFG/high-DAR combination.


1. The blocking family — US10973920B2 (Daiichi Sankyo)

Attribute Detail
Status GRANTED / in force
Priority 2014-09-30
Expiry 2035-09-30 (no PTE/SPC modeled here)
Claim 1 Anti-HER2 antibody + maleimide-GGFG peptide linker + DX-8951 (exatecan) derivative topo-I inhibitor at DAR ~7–8
Claim 12 The drug-linker intermediate (GGFG tetrapeptide + self-immolative aminomethyl)

Element-by-element read against your product:

Conclusion: Literal infringement of claim 1 if your DAR is in the 7–8 range. This is a genuine blocking patent through September 2035. The indication (HER2-low) is irrelevant — claim 1 is a pure composition claim; it does not matter what cancer you treat. Note: no HER2-low method claim exists in this corpus, but you cannot reach the method-of-use design-around because making/selling the composition itself infringes.


2. Expired / non-blocking families

Family Assignee Status Why it doesn't block you
US7575748B1 Genentech EXPIRED (2019) The trastuzumab humanized-antibody composition claim is expired. You are free to use the trastuzumab antibody scaffold itself — the antibody is no longer a barrier. The barrier is the conjugate.
US9968687B2 (T-DM1) ImmunoGen Granted, but non-overlapping Claims a non-cleavable SMCC linker + maytansinoid DM1. Different linker chemistry and different payload class — does not read on a GGFG/exatecan ADC. Its method claim is limited to HER2-positive post-trastuzumab/taxane, also not implicated. Expires 2031.

The expiry of the Genentech antibody patent is the key positive: the binder is free; only the payload+linker+DAR combination is encumbered.


3. Other in-corpus families to monitor (not directly blocking)

Family Assignee Status Relevance
WO2020196474A1 Byondis PENDING HER2 ADC but duocarmycin payload + vc linker — a competing design-around archetype, not a blocker against you. Confirms the duocarmycin route is being staked out by others.
CN114106192A Keymed PENDING (CN) Anti-CLDN18.2 + tetrapeptide linker + exatecan/DXd. Different target, so no overlap on a HER2 product. BUT note its claim 1 is drafted to a tetrapeptide-based cleavable linker + exatecan payload generically — watch its prosecution; relevant only if you ever extend the platform to CLDN18.2. CN-only jurisdiction.

4. Design-around options (ranked by separation from the blocking claim)

Claim 1's three pillars are (a) exatecan-derivative payload, (b) GGFG linker, (c) DAR ~7–8. Defeating any one element avoids literal infringement, but watch doctrine of equivalents.

Strongest design-arounds (change the payload class — cleanest escape):
1. Switch payload chemistry entirely — e.g., the duocarmycin route (cf. Byondis WO2020196474A1) or a maytansinoid/auristatin. This exits "exatecan-derivative topo-I" and is the most defensible. Caveat: you then need FTO against those families (Byondis pending; ImmunoGen for maytansinoids).

Moderate (keep topo-I MoA but engineer off the literal claim — higher DoE risk):
2. Non-exatecan topo-I payload — a camptothecin/SN-38-type or a structurally distinct topo-I warhead that is not a "DX-8951/exatecan derivative." Preserves the topo-I mechanism and bystander effect attractive for HER2-low, but DoE risk is highest here because the patentee will argue equivalence of topo-I exatecan-likes.
3. Replace the GGFG tetrapeptide linker — e.g., a different cleavable peptide (val-cit, val-ala) or a glycosidase/disulfide-cleavable chemistry, dropping the self-immolative aminomethyl of claim 12. Reduces overlap on both claim 1 (linker) and claim 12 (intermediate). Strongest if combined with a non-maleimide conjugation handle.

Weakest (do not rely on alone):
4. DAR engineering — moving to a homogeneous DAR ~2–4 technically exits "about 7–8." This is brittle: "about" invites a DoE argument, and a high-DAR topo-I bystander payload is much of what makes the product work for HER2-low. Use only as a secondary differentiator, never the sole basis.

Procedural levers:
5. Geographic strategy — confirm whether the Daiichi family is granted/in-force in each target jurisdiction; FTO is country-by-country. The exatecan-topo-I CLDN18.2 art is CN-pending, indicating active CN filing activity in this space.
6. License — given a literal in-force composition claim through 2035, an in-license from Daiichi Sankyo is the realistic path if you want to keep the exact exatecan/GGFG/high-DAR design (which is what makes Enhertu effective in HER2-low).
7. Validity challenge — assess prior art against the 2014 priority date if a design-around isn't commercially viable; not modeled in this corpus.


Summary table

Family Assignee Status Verdict for your product
US10973920B2 Daiichi Sankyo Granted, expires 2035 BLOCKING — literal read on Ab+GGFG+exatecan+DAR7-8
US7575748B1 Genentech Expired 2019 Clear — trastuzumab scaffold free to use
US9968687B2 ImmunoGen Granted, 2031 Not blocking — different (SMCC/maytansinoid) chemistry
WO2020196474A1 Byondis Pending Not blocking — duocarmycin; a design-around template
CN114106192A Keymed Pending (CN) Not blocking (CLDN18.2 target); monitor if platform extends

Recommendation: As specified, your candidate is blocked by US10973920B2 until 2035. To obtain FTO you should either (1) license from Daiichi Sankyo, or (2) re-engineer the payload class (most robust — e.g., off topo-I entirely, or to a clearly non-exatecan warhead) ideally combined with a non-GGFG cleavable linker, rather than relying on DAR adjustment alone. The HER2-low indication itself raises no method-claim barrier in this corpus — the obstacle is entirely the composition.

Caveats: this analysis covers only the 14-family corpus provided; no PTE/SPC term extensions, foreign counterparts outside US/WO/CN, or pending continuations are reflected. Confirm jurisdiction-by-jurisdiction status and obtain formal patent-counsel opinion before clearance.

Reference answer key (deterministic) — open after grading

Heuristic reference over the curated corpus for target=HER2, modality=Antibody-drug conjugate. Families in scope: 4 ({'GRANTED': 2, 'PENDING': 1, '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
US10973920B2Daiichi SankyoGRANTED2035-09-30compositionBLOCKING (granted composition-of-matter)
WO2020196474A1ByondisPENDING2040-03-26compositionWATCH (pending — claims not yet fixed)
US9968687B2ImmunoGenGRANTED2031-02-24composition, methodBLOCKING (granted composition-of-matter)
US7575748B1GenentechEXPIRED2019-08-27compositionCLEARABLE (expired)
OVERALL FTO VERDICT (heuristic)BLOCKED — 2 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