GSK neladalkib

ALK-positive lung cancer · NDA

Of 100 applications in this same position, about 92 get approved.

Until the FDA deadline53d

Base rate76%

Gap+16pts

PDUFA target date 2026-11-27the FDA may act earlier or later

Summary

We put approval in this review cycle at 92%, well above the ~76% base rate for small/mid-cap original NDAs. The FDA has a long record of approving targeted lung-cancer drugs on durable single-arm response data. ALKOVE-1 showed a 31% response rate in 253 heavily pretreated ALK-positive patients (26% after lorlatinib, where no approved option exists), with long responses and brain activity. The drug has Breakthrough designation and Priority Review. The same sponsor's zidesamtinib was approved two months early in July 2026. GSK, which completed its Nuvalent acquisition in July, now owns the application. The main risks are a liver-enzyme signal and undisclosed details of the manufacturing sites.

Recorded 2026-10-04 19:58 UTC · v1Proof ↓

Evidence · 8 items

Why 92%, not 76%

Indication

ALK-positive locally advanced or metastatic NSCLC previously treated with an ALK tyrosine kinase inhibitor (TKI pre-treated)

76% of comparable applications were approved in the past: the opponent every forecast has to beat. Below are the reasons this forecast differs.

▲ supports approval, ▼ counts against it. More squares, more weight.

01▲ SupportsMedium Durable responses in a large, heavily pretreated single-arm cohort with no approved option after lorlatinib

ALKOVE-1 pivotal cohort (n=253 TKI-pretreated; 78% had at least 2 prior ALK TKIs; median 3 prior lines). ORR by blinded central review was 31% (95% CI 26-37), and 64% of responses lasted at least 12 months. Lorlatinib-pretreated patients (n=190): ORR 26%, median DOR 17.6 months. Lorlatinib-naive patients (n=63): ORR 46%. G1202R mutation: ORR 68%. Intracranial ORR was 32% overall and 63% in lorlatinib-naive patients. FDA Breakthrough Therapy designation is for patients after at least 2 ALK TKIs.

Source: Nuvalent press release 2025-11-17; ASCO 2026 abstract 8503 (JCO 44:16_suppl); Nuvalent 10-Q filed 2026-05-07
02▲ SupportsMedium Same sponsor, same FDA division, same kind of evidence: zidesamtinib was approved early in July 2026

Nuvalent's ROS1 inhibitor zidesamtinib (Jideytro) was approved on 2026-07-22 on single-arm ARROS-1 data in TKI-pretreated ROS1+ NSCLC, almost two months before its 2026-09-18 PDUFA date. That shows the agency accepts this development model from this sponsor, and that Nuvalent's regulatory and CMC organization has already taken a product through FDA review. Single-arm approvals of targeted TKIs in resistant NSCLC are well established (for example, lorlatinib in 2018).

Source: GSK 6-K Q2 2026 results (2026-07-28); ASCO Post 2026-07 approval report
03▲ SupportsSmall Breakthrough Therapy, Priority Review and no advisory committee announced

The NDA was submitted in April 2026 and accepted 2026-05-27 with Priority Review and a PDUFA date of 2026-11-27. No ODAC meeting has been announced as of 2026-10-04. The product also has Orphan Drug designation.

Source: Nuvalent 8-K 2026-04-07; Nuvalent press release 2026-05-27; Royalty Pharma 10-Q filed 2026-08-05
04▲ SupportsSmall GSK now owns the application

GSK completed its $10.6B acquisition of Nuvalent on 2026-07-15. GSK lists the US regulatory decision for neladalkib as an H2 2026 event and expects a 2026 launch if approved. Big-pharma applications have a ~95%+ base rate, but this NDA was compiled by Nuvalent before the deal, so I count ownership as a step rather than switching the anchor.

Source: Nuvalent 8-K 2026-07-15 (merger completion); GSK press release on completion; GSK 6-K Q2 2026
05▲ SupportsSmall Oral small molecule whose supply chain has already supported an FDA approval

Nuvalent built its commercial-scale process through CMOs, and that network supported the zidesamtinib approval. The neladalkib-specific sites are not disclosed, so I cannot confirm overlap.

Source: Nuvalent 10-Q filed 2026-05-07
06▼ AgainstSmall Liver-enzyme signal needs label management

In the RP2D safety population (n=656), ALT increase occurred in 47% and AST increase in 44%. The company describes these as mostly low-grade, transient and reversible. Discontinuation for TEAEs was 5% and dose reduction 17%. This is likely to mean label monitoring rather than a barrier to approval.

Source: Nuvalent press release 2025-11-17
07▼ AgainstSmall Some suppliers are in China

Nuvalent's risk factors say some manufacturers and suppliers are located in China and cite the BIOSECURE law enacted in December 2025. That law limits federal procurement rather than FDA approval, and it did not stop zidesamtinib's approval.

Source: Nuvalent 10-Q filed 2026-05-07 (risk factors)
08▼ AgainstSmall Single-arm evidence; pathway and confirmatory plan not stated

The NDA rests on ORR and DOR from a Phase 1/2 trial. Whether accelerated or regular approval is sought has not been disclosed. If accelerated, the randomized Phase 3 ALKAZAR trial (neladalkib vs alectinib, TKI-naive) is enrolling and could serve as the confirmatory trial. The label could be narrower than 'TKI pre-treated', but that would still count as approval.

Source: Nuvalent Q1 2026 results (8-K Ex.99.1, 2026-05-07); ClinicalTrials.gov NCT06765109

What would change this forecast

01
An ODAC being scheduled, or a PDUFA extension (major amendment)
02
GSK disclosing label negotiations or an early approval (the zidesamtinib precedent suggests early action is possible)
03
New hepatotoxicity findings, such as Hy's-law cases, in updated ALKOVE-1 safety data
04
Any manufacturing or import issue affecting China-based suppliers

Any change is published as a new version; earlier versions stay exactly as they were.

Confidence

Medium

Manufacturing and inspection risk

Low

This is an oral small-molecule kinase inhibitor. Nuvalent's CMO network just supported FDA approval of its sister TKI zidesamtinib (July 2026), and GSK now owns the program. The residual risks are undisclosed site-level inspection outcomes and China-based suppliers named in the risk factors.

Record · version 1

Written on 2026-10-04, 54 days before the PDUFA target date.

Timeline

Versions

v1 2026-10-04 19:58 UTC 92% Current version JSON ↓.ots ↓ ○ Timestamp submitted, awaiting block confirmation

Fingerprint

SHA-256b1810dbaa82d767457c5d28317832aec8e37ef4121a575ed2140b59d3c3f451c

The fingerprint of the v1 file. It is what the timestamp commits to: change one character of the file and the fingerprint no longer matches.

Verify it yourself

Download the JSON file above and the .ots file of the same name into one folder.
Compute the SHA-256 of the file. It should match the fingerprint above.
Verify with OpenTimestamps. Once the timestamp is in a Bitcoin block, ots verify reports the block time if you run a Bitcoin node; without one, drop both files on the verifier at opentimestamps.org, or run ots info to see the block height and look it up in any block explorer. If the block time is before the FDA’s decision, the file cannot have been written afterwards.

pip install opentimestamps-client
shasum -a 256 v1_20261004T195813Z.json
ots verify v1_20261004T195813Z.json.ots
ots info v1_20261004T195813Z.json.ots

Scoring rule

What is scored is the last version recorded at least 2 days before the PDUFA target date; if the FDA decides early, only versions recorded before the day of its decision count. For this forecast the cutoff is 2026-11-25. Its error (also called the Brier score) is the squared distance between the forecast and the outcome, set against the error of quoting the base rate only.