I'll assess freedom-to-operate for your proposed DLL3 × CD3 T-cell engager. Let me start by orienting to the corpus and searching for relevant families.
{
"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"
]
}{
"count": 4,
"families": [
{
"publication_number": "US10000567B2",
"jurisdiction": "US",
"assignee": "Amgen",
"title": "Bispecific T-cell engaging molecules binding DLL3 and CD3",
"target": "DLL3",
"modality": "T-cell engager (bispecific)",
"priority_date": "2015-06-23",
"expiry": "2036-06-23",
"legal_status": "GRANTED",
"claim_types": [
"composition",
"method"
],
"keywords": [
"DLL3",
"CD3",
"bispecific",
"T-cell engager",
"BiTE",
"tarlatamab",
"SCLC",
"composition of matter",
"half-life extended"
]
},
{
"publication_number": "WO2021091960A1",
"jurisdiction": "WO",
"assignee": "Boehringer Ingelheim",
"title": "DLL3/CD3 bispecific antibodies with an IgG-like format",
"target": "DLL3",
"modality": "T-cell engager (bispecific)",
"priority_date": "2019-11-05",
"expiry": "2040-11-05",
"legal_status": "PENDING",
"claim_types": [
"composition"
],
"keywords": [
"DLL3",
"CD3",
"bispecific",
"2+1 format",
"knobs into holes",
"pending",
"IgG-like"
]
},
{
"publication_number": "US9382323B2",
"jurisdiction": "US",
"assignee": "AbbVie / Stemcentrx",
"title": "Anti-DLL3 antibody-drug conjugates (rovalpituzumab class)",
"target": "DLL3",
"modality": "Antibody-drug conjugate",
"priority_date": "2013-08-28",
"expiry": "2034-08-28",
"legal_status": "GRANTED",
"claim_types": [
"composition"
],
"keywords": [
"DLL3",
"ADC",
"PBD",
"rovalpituzumab",
"cleavable linker",
"composition of matter",
"SCLC"
]
},
{
"publication_number": "CN112457404A",
"jurisdiction": "CN",
"assignee": "Harbour BioMed",
"title": "Heavy-chain-only DLL3 x CD3 bispecific for small cell lung cancer",
"target": "DLL3",
"modality": "T-cell engager (bispecific)",
"priority_date": "2019-09-10",
"expiry": "2039-09-10",
"legal_status": "PENDING",
"claim_types": [
"method"
],
"keywords": [
"DLL3",
"CD3",
"bispecific",
"heavy chain only",
"step-up dosing",
"method of treatment",
"China",
"pending"
]
}
]
}The corpus has 4 DLL3 families, 3 of which are bispecific T-cell engagers directly on point. Let me pull the full claims for all four to analyze scope.
{
"publication_number": "US10000567B2",
"title": "Bispecific T-cell engaging molecules binding DLL3 and CD3",
"legal_status": "GRANTED",
"independent_claims": [
{
"claim_no": 1,
"claim_type": "composition",
"text": "A bispecific single-chain molecule comprising a first binding domain that specifically binds human DLL3 and a second binding domain that specifically binds human CD3 epsilon, optionally fused to an Fc domain extending half-life."
},
{
"claim_no": 11,
"claim_type": "method",
"text": "A method of treating small cell lung cancer comprising administering the bispecific molecule of claim 1."
}
]
}{
"publication_number": "WO2021091960A1",
"title": "DLL3/CD3 bispecific antibodies with an IgG-like format",
"legal_status": "PENDING",
"independent_claims": [
{
"claim_no": 1,
"claim_type": "composition",
"text": "A bispecific antibody in a 2+1 IgG format comprising two binding sites for human DLL3 and one binding site for human CD3, with a knobs-into-holes heterodimeric Fc."
}
]
}{
"publication_number": "CN112457404A",
"title": "Heavy-chain-only DLL3 x CD3 bispecific for small cell lung cancer",
"legal_status": "PENDING",
"independent_claims": [
{
"claim_no": 1,
"claim_type": "method",
"text": "A method of treating relapsed small cell lung cancer comprising administering a heavy-chain-only DLL3 x CD3 bispecific antibody at a step-up dosing schedule to mitigate cytokine release syndrome."
}
]
}{
"publication_number": "US9382323B2",
"title": "Anti-DLL3 antibody-drug conjugates (rovalpituzumab class)",
"legal_status": "GRANTED",
"independent_claims": [
{
"claim_no": 1,
"claim_type": "composition",
"text": "An antibody-drug conjugate comprising an anti-DLL3 antibody conjugated via a cleavable linker to a pyrrolobenzodiazepine (PBD) dimer payload."
}
]
}I have full claim scope for all four families. Let me pull the full record on the Amgen patent — the dominant threat — to confirm priority/expiry and any dependent specificity.
{
"publication_number": "US10000567B2",
"jurisdiction": "US",
"assignee": "Amgen",
"priority_date": "2015-06-23",
"expiry": "2036-06-23",
"legal_status": "GRANTED",
"title": "Bispecific T-cell engaging molecules binding DLL3 and CD3",
"target": "DLL3",
"modality": "T-cell engager (bispecific)",
"independent_claims": [
{
"claim_no": 1,
"claim_type": "composition",
"text": "A bispecific single-chain molecule comprising a first binding domain that specifically binds human DLL3 and a second binding domain that specifically binds human CD3 epsilon, optionally fused to an Fc domain extending half-life."
},
{
"claim_no": 11,
"claim_type": "method",
"text": "A method of treating small cell lung cancer comprising administering the bispecific molecule of claim 1."
}
],
"keywords": [
"DLL3",
"CD3",
"bispecific",
"T-cell engager",
"BiTE",
"tarlatamab",
"SCLC",
"composition of matter",
"half-life extended"
]
}Four DLL3 families; three are directly relevant bispecific TCEs, one is an off-modality ADC.
| Family | Assignee | Juris. | Modality | Claim types | Status | Expiry |
|---|---|---|---|---|---|---|
| US10000567B2 | Amgen (tarlatamab) | US | DLL3×CD3 TCE | Composition + Method | GRANTED | 2036-06-23 |
| WO2021091960A1 | Boehringer Ingelheim | WO | DLL3×CD3 2+1 IgG | Composition | PENDING | 2040-11-05 |
| CN112457404A | Harbour BioMed | CN | DLL3×CD3 HCAb | Method | PENDING | 2039-09-10 |
| US9382323B2 | AbbVie/Stemcentrx | US | DLL3 ADC | Composition | GRANTED | 2034-08-28 |
The Amgen genus composition claim is granted, in-force, US, and written at a level of generality that an ordinary DLL3×CD3 single-chain bispecific cannot escape on format or sequence alone. Until June 23, 2036, US activity is exposed on both composition and method.
To escape Amgen claim 1 (the priority task):
1. Avoid the single-chain construct. Claim 1 recites a "bispecific single-chain molecule." A two-chain, full-length heterodimeric IgG-like or Fab-arm-exchange format may fall outside the literal claim language — requires careful claim-construction/file-history review of "single-chain" to confirm it isn't construed to read on the binding-domain arrangement generally.
2. Target CD3 via a non-epsilon epitope (e.g., CD3γ/δ) — claim 1 specifies "CD3 epsilon." A genuinely non-ε-binder would be outside, though most functional CD3 engagers hit ε; verify epitope experimentally.
3. Confirm validity exposure. Test whether the 2015 genus claim is vulnerable to written-description/enablement challenge (it claims any DLL3 + any CD3ε binder without sequence support) — potential invalidity/IPR lever rather than design-around.
To avoid Boehringer WO: use a 1+1 monovalent-DLL3 architecture or non-KiH heterodimerization (e.g., charge-pair, CrossMab without KiH). Monitor national-phase claims.
To avoid Harbour CN (if China commercialization intended): use conventional VH/VL (not heavy-chain-only) and/or a non–step-up dosing regimen; or limit China launch.
Jurisdiction/timing strategy:
- The Amgen barrier is US. Confirm whether Amgen has corresponding WO/EP/CN family members (not in this corpus — recommend external family-member search) before assuming ex-US freedom.
- Earliest clean US entry is mid-2036 absent a successful design-around or invalidity outcome.
Caveat: This analysis is limited to the supplied 14-family corpus. Family members in untested jurisdictions and unpublished applications are not captured; a full FTO requires a broader patent database search and qualified patent-counsel opinion.
Four DLL3 families; three are directly relevant bispecific TCEs, one is an off-modality ADC.
| Family | Assignee | Juris. | Modality | Claim types | Status | Expiry |
|---|---|---|---|---|---|---|
| US10000567B2 | Amgen (tarlatamab) | US | DLL3×CD3 TCE | Composition + Method | GRANTED | 2036-06-23 |
| WO2021091960A1 | Boehringer Ingelheim | WO | DLL3×CD3 2+1 IgG | Composition | PENDING | 2040-11-05 |
| CN112457404A | Harbour BioMed | CN | DLL3×CD3 HCAb | Method | PENDING | 2039-09-10 |
| US9382323B2 | AbbVie/Stemcentrx | US | DLL3 ADC | Composition | GRANTED | 2034-08-28 |
The Amgen genus composition claim is granted, in-force, US, and written at a level of generality that an ordinary DLL3×CD3 single-chain bispecific cannot escape on format or sequence alone. Until June 23, 2036, US activity is exposed on both composition and method.
To escape Amgen claim 1 (the priority task):
1. Avoid the single-chain construct. Claim 1 recites a "bispecific single-chain molecule." A two-chain, full-length heterodimeric IgG-like or Fab-arm-exchange format may fall outside the literal claim language — requires careful claim-construction/file-history review of "single-chain" to confirm it isn't construed to read on the binding-domain arrangement generally.
2. Target CD3 via a non-epsilon epitope (e.g., CD3γ/δ) — claim 1 specifies "CD3 epsilon." A genuinely non-ε-binder would be outside, though most functional CD3 engagers hit ε; verify epitope experimentally.
3. Confirm validity exposure. Test whether the 2015 genus claim is vulnerable to written-description/enablement challenge (it claims any DLL3 + any CD3ε binder without sequence support) — potential invalidity/IPR lever rather than design-around.
To avoid Boehringer WO: use a 1+1 monovalent-DLL3 architecture or non-KiH heterodimerization (e.g., charge-pair, CrossMab without KiH). Monitor national-phase claims.
To avoid Harbour CN (if China commercialization intended): use conventional VH/VL (not heavy-chain-only) and/or a non–step-up dosing regimen; or limit China launch.
Jurisdiction/timing strategy:
- The Amgen barrier is US. Confirm whether Amgen has corresponding WO/EP/CN family members (not in this corpus — recommend external family-member search) before assuming ex-US freedom.
- Earliest clean US entry is mid-2036 absent a successful design-around or invalidity outcome.
Caveat: This analysis is limited to the supplied 14-family corpus. Family members in untested jurisdictions and unpublished applications are not captured; a full FTO requires a broader patent database search and qualified patent-counsel opinion.
Heuristic reference over the curated corpus for target=DLL3, modality=T-cell engager (bispecific). Families in scope: 4 ({'GRANTED': 2, 'PENDING': 2}). 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 # | Assignee | Legal status | Expiry | Claim type(s) | FTO relevance |
|---|---|---|---|---|---|
| US10000567B2 | Amgen | GRANTED | 2036-06-23 | composition, method | BLOCKING (granted composition-of-matter) |
| WO2021091960A1 | Boehringer Ingelheim | PENDING | 2040-11-05 | composition | WATCH (pending — claims not yet fixed) |
| CN112457404A | Harbour BioMed | PENDING | 2039-09-10 | method | WATCH (pending — claims not yet fixed) |
| US9382323B2 | AbbVie / Stemcentrx | GRANTED | 2034-08-28 | composition | BLOCKING (granted composition-of-matter) |
| OVERALL FTO VERDICT (heuristic) | BLOCKED — 2 granted composition-of-matter family(ies) read on the proposed product; need a licence or a design-around. |