← BD Asset Due Diligence & Valuation (rNPV) comparison · model: Claude Opus 4.8
LLM-judge score: 3.4 / 5 · flawed
pos_selection: 5 rnpv_mechanics: 4 assumption_quality: 4 deal_recommendation: 2 faithfulness: 2
PoS selection is exact (10.75%) and rNPV mechanics are largely sound, recovering ~$311M risk-adjusted commercial value and a ~-$13.6M rNPV consistent with the key (minor R&D PV deviation $325M vs $298M due to slightly different costs/timing). However, the deal recommendation is severely off: the agent proposes $100-130M upfront / ~$1.2B biobucket against a near-zero rNPV, ~30x the reference's $2-4M upfront / $18-37M biobucket — internally contradictory since it admits the rNPV is break-even yet anchors to an apparently fabricated '$175M/$1,300M DLL3 comp' rather than the actual returned comparables. This fabricated comp and the resulting untethered deal numbers undermine faithfulness and produce a recommendation that would destroy value for the licensee.
Corporate Development / BD&L · Business-development / licensing analyst

BD Asset Due Diligence & Valuation (rNPV) — agent trajectory for expert review

claude-opus-4-8 · 2026-06-06T10:34:13.492842+00:00 · 4 tool calls · 32.1s · 9573 tokens
run id: bd_valuation_20260606_031816_bd-valuation__claude-opus-4-8

Query

Value asset ONC-201 for an in-licensing deal: compute its cumulative probability of success and rNPV, then recommend an upfront + milestone (biobucket) structure benchmarked to comparable oncology deals.

Trajectory

Agent · turn 1

I'll value ONC-201 step by step. Let me start by gathering all the necessary inputs.

⚙ calls get_asset(asset_id=ONC-201)
⚙ calls get_assumptions()
↳ get_asset result
show data
{
  "asset_id": "ONC-201",
  "name": "DLL3 T-cell engager (ES-SCLC)",
  "therapeutic_area": "oncology",
  "indication": "Extensive-stage small cell lung cancer (2L+)",
  "modality": "T-cell engager (bispecific)",
  "current_phase": "PHASE2",
  "peak_sales_usd_m": 1600,
  "years_to_launch": 4,
  "remaining_rd_cost_by_phase": {
    "PHASE2": 70,
    "PHASE3": 300,
    "FILED": 25
  },
  "launch_to_loe_years": 11,
  "discount_rate": 0.12,
  "net_margin": 0.55,
  "notes": "Crowded DLL3 space; incumbent already Phase 3. Strong single-arm Ph2 ORR signal supports a competitive peak. Thin rNPV given oncology PoS -> structure matters."
}
↳ get_assumptions result
show data
{
  "discount_rate_conventions": {
    "large_pharma": "8-10%",
    "established_biotech": "10-12%",
    "early_clinical_private_biotech": "12-15%",
    "preclinical_or_platform": "15-20%+",
    "note": "Higher risk / earlier stage / private -> higher discount rate. The PoS already captures technical/regulatory risk, so the discount rate should reflect time value + systematic risk, NOT be double-counted with PoS."
  },
  "rnpv_model": {
    "method": "Simplified peak-sales rNPV.",
    "steps": [
      "1. Cumulative PoS = product of remaining phase transitions (incl. NDA/BLA->approval) for the asset's current phase and therapeutic area.",
      "2. Peak commercial value = peak_sales * net_margin * REVENUE_YEARS_FACTOR, where REVENUE_YEARS_FACTOR approximates the sum of the on-market cash-flow stream as a multiple of one peak year (ramp up, plateau, decline to LoE).",
      "3. Discount the commercial value from the revenue mid-point (years_to_launch + REVENUE_MIDPOINT_OFFSET) to present at the discount rate.",
      "4. Risk-adjust the discounted commercial value by the cumulative PoS.",
      "5. Subtract risk-adjusted, discounted remaining R&D (each phase's spend discounted from its spend year and weighted by the PoS of having reached that phase \u2014 here we conservatively expense remaining R&D at full probability since the buyer pays it).",
      "6. rNPV = risk-adjusted discounted commercial value - discounted remaining R&D."
    ],
    "REVENUE_YEARS_FACTOR": 6.5,
    "REVENUE_MIDPOINT_OFFSET": 2.0,
    "note": "REVENUE_YEARS_FACTOR=6.5 means the lifetime on-market cash-flow stream (already net-of-margin) is modelled as ~6.5x a single peak year \u2014 a standard simplification for an ~10-13yr exclusivity window with ramp/plateau/decline, where the discounted stream is worth several peak years rather than the full undiscounted count. REVENUE_MIDPOINT_OFFSET=2 places the single discounting anchor ~2 years after launch (an early-plateau centre of mass for the discounted stream). These are deliberately transparent simplifications of a full year-by-year DCF; a real model would discount each revenue year separately."
  },
  "deal_structure_conventions": {
    "upfront_as_pct_of_rnpv": "Upfront typically 15-30% of asset rNPV at Ph2; lower (~5-15%) earlier, higher (~30-45%) at Ph3/filed.",
    "biobucket": "Total milestones+royalties (the 'biobucket') is benchmarked to comparable deals in the same area/phase and usually several multiples of the upfront.",
    "royalty": "Tiered royalty on net sales, typically high-single-digit to mid-teens for clinical-stage oncology/specialty assets."
  }
}
Agent · turn 2

Now let me get the PoS data for oncology at Phase 2 and comparable oncology deals.

⚙ calls get_pos_table(phase=PHASE2, area=oncology)
⚙ calls get_comparable_deals(area=oncology)
↳ get_pos_table result
show data
{
  "area": "oncology",
  "label": "Oncology (solid + heme malignancy, ex-hematology benign)",
  "transitions": {
    "P1->P2": 0.629,
    "P2->P3": 0.241,
    "P3->REG": 0.477,
    "REG->APP": 0.935
  },
  "source": "BIO/Informa/QLS 2011-2020 oncology; Phase-1-to-approval LoA 5.3%. Wong-Siah-Lo (2019) report oncology LoA ~3.4% on an earlier window.",
  "phase": "PHASE2",
  "remaining_transitions": [
    "P2->P3",
    "P3->REG",
    "REG->APP"
  ],
  "cumulative_pos": 0.1075
}
↳ get_comparable_deals result
show data
{
  "count": 3,
  "deals": [
    {
      "deal": "DLL3 bispecific (oncology, Ph2)",
      "area": "oncology",
      "phase_at_deal": "PHASE2",
      "upfront_usd_m": 175,
      "biobucket_usd_m": 1300,
      "royalty_pct": "10-15%",
      "year": 2023
    },
    {
      "deal": "Solid-tumor ADC (oncology, Ph1/2)",
      "area": "oncology",
      "phase_at_deal": "PHASE1",
      "upfront_usd_m": 60,
      "biobucket_usd_m": 1000,
      "royalty_pct": "high single digit-12%",
      "year": 2023
    },
    {
      "deal": "Late-stage oncology asset (Ph3)",
      "area": "oncology",
      "phase_at_deal": "PHASE3",
      "upfront_usd_m": 400,
      "biobucket_usd_m": 1500,
      "royalty_pct": "12-18%",
      "year": 2022
    }
  ],
  "note": "Upfront/biobucket in $M; later-stage deals carry a larger upfront share."
}
Agent · turn 3

I now have everything needed. Let me work through the valuation.

1. Cumulative Probability of Success

ONC-201 is a Phase 2 oncology asset. Remaining transitions to approval:

Transition Probability
P2 → P3 0.241
P3 → REG 0.477
REG → APP 0.935

Cumulative PoS = 0.241 × 0.477 × 0.935 ≈ 10.75%

This is the key risk driver — a typical "Phase 2 oncology" survival rate, and it dominates the valuation.

2. rNPV Calculation

Step 1 — Peak commercial value (lifetime, net-of-margin):
- Peak sales = $1,600M
- Net margin = 0.55
- Revenue-years factor = 6.5
- Commercial value = 1,600 × 0.55 × 6.5 = $5,720M

Step 2 — Discount to present:
- Discounting anchor = years_to_launch (4) + midpoint offset (2) = 6 years
- Discount factor = 1 / (1.12)^6 = 1 / 1.9738 = 0.5066
- Discounted commercial value = 5,720 × 0.5066 = $2,897.8M

Step 3 — Risk-adjust by PoS:
- 2,897.8 × 0.1075 = $311.5M

Step 4 — Remaining R&D (discounted, expensed at full probability per convention):

Phase Spend Spend year Discount factor (1.12^–t) PV
Phase 2 $70M ~now (yr 0) 1.000 $70.0M
Phase 3 $300M ~yr 2 0.7972 $239.2M
Filed $25M ~yr 4 0.6355 $15.9M
Total $325.1M

(R&D timing aligned to the 4-year path to launch: Ph2 now, Ph3 mid-program, filing near launch.)

Step 5 — rNPV:
$$rNPV = 311.5 - 325.1 = \boxed{-\$13.6M}$$

The asset has a slightly negative / break-even rNPV on a fully-loaded basis.

This matches the note in the asset file ("thin rNPV given oncology PoS → structure matters"). The unrisked discounted commercial value is ~$2.9B, but the 10.75% PoS plus full R&D burden compresses it to roughly zero. Crucially, the buyer pays the R&D regardless — so the risk-adjusted commercial value of $311.5M is what a deal should be benchmarked against, not the net rNPV.

3. Recommended Deal Structure

Given the economics, this should be a back-end-loaded deal — modest upfront, large milestone biobucket that pays out only as risk retires.

Benchmark anchor: The closest comparable is the 2023 DLL3 bispecific at Ph2 (same modality, same target, same phase): $175M upfront / $1,300M biobucket / 10–15% royalty. That deal frames market expectations directly.

Calibration against our numbers:
- Convention: Ph2 upfront = 15–30% of rNPV. But net rNPV here is ~$0, so anchoring to rNPV alone breaks down. The market clearly prices off the risk-adjusted commercial value (~$311M) and strategic value, not net rNPV.
- A defensible upfront is ~15–20% of the risk-adjusted commercial value → ~$47–62M intrinsically, but the comparable DLL3 deal ($175M) is richer, reflecting competitive/strategic premium for the target class.

Recommendation

Component Recommendation Rationale
Upfront $100–130M Below the $175M comp — justified because we're a follower in a crowded DLL3 space (incumbent already Ph3) and net rNPV is break-even. Discounted from the comp to reflect competitive risk.
Biobucket (total milestones) $1,100–1,300M In line with the DLL3 comp. Heavily back-end loaded: skew toward Ph3 success, approval, and sales milestones so the seller captures upside only if the asset clears its 10.75% PoS gauntlet.
— Development/regulatory milestones ~$400–500M Tied to Ph3 start, Ph3 readout, approval.
— Sales milestones ~$700–800M Tied to $250M/$500M/$1B/$1.5B net-sales thresholds.
Royalty Tiered 10–14% on net sales Matches the DLL3 comp's 10–15% band; lower tier early, escalating with volume.

Deal rationale summary

Bottom line: License with ~$100–130M upfront, ~$1.2B biobucket weighted to Ph3/approval/sales, and a 10–14% tiered royalty — a structure that keeps capital-at-risk low against a break-even rNPV while paying generously only if the asset survives its oncology odds.

Final output

I now have everything needed. Let me work through the valuation.

1. Cumulative Probability of Success

ONC-201 is a Phase 2 oncology asset. Remaining transitions to approval:

Transition Probability
P2 → P3 0.241
P3 → REG 0.477
REG → APP 0.935

Cumulative PoS = 0.241 × 0.477 × 0.935 ≈ 10.75%

This is the key risk driver — a typical "Phase 2 oncology" survival rate, and it dominates the valuation.

2. rNPV Calculation

Step 1 — Peak commercial value (lifetime, net-of-margin):
- Peak sales = $1,600M
- Net margin = 0.55
- Revenue-years factor = 6.5
- Commercial value = 1,600 × 0.55 × 6.5 = $5,720M

Step 2 — Discount to present:
- Discounting anchor = years_to_launch (4) + midpoint offset (2) = 6 years
- Discount factor = 1 / (1.12)^6 = 1 / 1.9738 = 0.5066
- Discounted commercial value = 5,720 × 0.5066 = $2,897.8M

Step 3 — Risk-adjust by PoS:
- 2,897.8 × 0.1075 = $311.5M

Step 4 — Remaining R&D (discounted, expensed at full probability per convention):

Phase Spend Spend year Discount factor (1.12^–t) PV
Phase 2 $70M ~now (yr 0) 1.000 $70.0M
Phase 3 $300M ~yr 2 0.7972 $239.2M
Filed $25M ~yr 4 0.6355 $15.9M
Total $325.1M

(R&D timing aligned to the 4-year path to launch: Ph2 now, Ph3 mid-program, filing near launch.)

Step 5 — rNPV:
$$rNPV = 311.5 - 325.1 = \boxed{-\$13.6M}$$

The asset has a slightly negative / break-even rNPV on a fully-loaded basis.

This matches the note in the asset file ("thin rNPV given oncology PoS → structure matters"). The unrisked discounted commercial value is ~$2.9B, but the 10.75% PoS plus full R&D burden compresses it to roughly zero. Crucially, the buyer pays the R&D regardless — so the risk-adjusted commercial value of $311.5M is what a deal should be benchmarked against, not the net rNPV.

3. Recommended Deal Structure

Given the economics, this should be a back-end-loaded deal — modest upfront, large milestone biobucket that pays out only as risk retires.

Benchmark anchor: The closest comparable is the 2023 DLL3 bispecific at Ph2 (same modality, same target, same phase): $175M upfront / $1,300M biobucket / 10–15% royalty. That deal frames market expectations directly.

Calibration against our numbers:
- Convention: Ph2 upfront = 15–30% of rNPV. But net rNPV here is ~$0, so anchoring to rNPV alone breaks down. The market clearly prices off the risk-adjusted commercial value (~$311M) and strategic value, not net rNPV.
- A defensible upfront is ~15–20% of the risk-adjusted commercial value → ~$47–62M intrinsically, but the comparable DLL3 deal ($175M) is richer, reflecting competitive/strategic premium for the target class.

Recommendation

Component Recommendation Rationale
Upfront $100–130M Below the $175M comp — justified because we're a follower in a crowded DLL3 space (incumbent already Ph3) and net rNPV is break-even. Discounted from the comp to reflect competitive risk.
Biobucket (total milestones) $1,100–1,300M In line with the DLL3 comp. Heavily back-end loaded: skew toward Ph3 success, approval, and sales milestones so the seller captures upside only if the asset clears its 10.75% PoS gauntlet.
— Development/regulatory milestones ~$400–500M Tied to Ph3 start, Ph3 readout, approval.
— Sales milestones ~$700–800M Tied to $250M/$500M/$1B/$1.5B net-sales thresholds.
Royalty Tiered 10–14% on net sales Matches the DLL3 comp's 10–15% band; lower tier early, escalating with volume.

Deal rationale summary

Bottom line: License with ~$100–130M upfront, ~$1.2B biobucket weighted to Ph3/approval/sales, and a 10–14% tiered royalty — a structure that keeps capital-at-risk low against a break-even rNPV while paying generously only if the asset survives its oncology odds.

Reference answer key (deterministic) — open after grading

Deterministic simplified peak-sales rNPV (model in data.ASSUMPTIONS['rnpv_model']). PoS from BIO/Informa/QLS 2011-2020 & Wong-Siah-Lo (2019). A strong agent should recover the cumulative PoS, a discounted risk-adjusted value in this ballpark, net out remaining R&D, and propose a deal range benchmarked to the comparables — using only the returned inputs (no fabricated peak-sales or PoS numbers).

StepValueDetail / formula
AssetONC-201DLL3 T-cell engager (ES-SCLC) — PHASE2, Oncology (solid + heme malignancy, ex-hematology benign)
Cumulative PoS to approval10.7%P2->P3=0.241 x P3->REG=0.477 x REG->APP=0.935 = 0.1075
Unrisked commercial value$5720Mpeak $1600M x margin 0.55 x revenue-years 6.5
Discounting/(1+0.12)^6 = 0.507launch in 4y + midpoint offset 2.0
Risk-adj. discounted commercial value$311Mcommercial $5720M x disc 0.507 x PoS 0.1075
Remaining R&D (PV)$298Mby phase: {'PHASE2': 62.5, 'PHASE3': 213.5, 'FILED': 22.3}
rNPV$13Mrisk-adj discounted commercial value − R&D PV
Suggested upfront$2M – $4M15–30% of rNPV (PHASE2 band)
Suggested total biobucket$18M – $37M~9.3x upfront, from 3 oncology comps
Structure noterNPV thin/negative at base assumptions: keep upfront minimal and shift value to back-loaded development/approval & sales milestones (risk-sharing).

Expert grading

PoS selection (phase × area) 1 (poor) 5 (excellent)
5: Pulls the correct therapeutic-area row and current phase, multiplies the right remaining transition probabilities (incl. the NDA/BLA->approval step) to get the cumulative PoS, and cites the BIO/Wong-Siah-Lo source.
1: Uses the wrong area or phase, forgets the regulatory step, mixes up transition vs. cumulative PoS, or invents a success rate not in the table.
rNPV mechanics 1 (poor) 5 (excellent)
5: Risk-adjusts the commercial value by the cumulative PoS AND discounts it to present value at the asset's discount rate, nets out (discounted) remaining R&D, and avoids double-counting risk between PoS and discount rate. Arithmetic is right.
1: Forgets to risk-adjust or to discount, double-counts risk, ignores remaining R&D, or makes arithmetic errors that move the rNPV materially.
Assumption quality 1 (poor) 5 (excellent)
5: Uses sensible, stated assumptions for peak sales, the revenue ramp/years factor, discount rate (appropriate to stage), margin, and LoE timing — consistent with the returned inputs and the assumption conventions.
1: Picks an unjustified discount rate or revenue horizon, ignores LoE/margin, or makes assumptions inconsistent with the asset's returned parameters.
Deal recommendation & comparables benchmarking 1 (poor) 5 (excellent)
5: Translates the rNPV into a concrete upfront + biobucket (+ royalty) range, anchors the upfront as a sensible fraction of rNPV for the phase, and benchmarks against the comparable deals returned for the area/phase.
1: Gives no concrete numbers, an upfront untethered from the rNPV, or ignores the comparable deals entirely.
Evidence faithfulness 1 (poor) 5 (excellent)
5: Every PoS, peak-sales, cost, and comp figure traces to a tool output; no fabricated numbers; the model is stated transparently and is reproducible.
1: Hallucinates PoS/peak-sales/comp numbers, contradicts the returned inputs, or hides an opaque/irreproducible valuation.
Overall verdict
Your name / ID