AI system
- System
-
Schrodinger physics-based computational drug-design platform with machine learning, used by Nimbus Therapeutics to discover NDI-034858 (TAK-279, zasocitinib)
- Model
-
Not assessed
- Release
-
Exact release not established.
- Application developer
-
Schrodinger (platform); Nimbus Therapeutics (compound)
- Role
-
Not assessed
- Configuration
-
Not assessed
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Computational structure-based design and laboratory testing of a selective allosteric TYK2 inhibitor. Sponsor-led randomized clinical trials against placebo and deucravacitinib.
- Human oversight
-
Not assessed
- Relation to AI
-
The original developer accounts describe computational structure-based design, free-energy calculations, and virtual screening. Takeda’s Warren Winkelman calls the approach AI-assisted. Physics-based computation alone does not establish an AI contribution. The discovery paper and developer accounts do not provide a controlled estimate of AI’s contribution to clinical efficacy, discovery speed, or the acquisition price.
- AI contribution
-
The original developer accounts describe computational structure-based design, free-energy calculations, and virtual screening. Takeda’s Warren Winkelman calls the approach AI-assisted. Physics-based computation alone does not establish an AI contribution. The discovery paper and developer accounts do not provide a controlled estimate of AI’s contribution to clinical efficacy, discovery speed, or the acquisition price.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
PASI 100 36.5% vs 13.9% for deucravacitinib at week 16
- Category
-
Improved Physical Health
- Status
-
Not assessed
- Beneficiary groups
-
People. Organizations. Society.
- Beneficiaries
-
Not assessed
- Reach
-
Not assessed
- Distribution and access
-
Not assessed
- Duration
-
Not assessed
- Expected?
-
Yes
- Costs and harms
-
Not assessed
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
PASI 100 36.5% vs 13.9% for deucravacitinib at week 16
- Comparison
-
deucravacitinib (Sotyktu), the active comparator in the LATITUDE Atlas phase 3 trial
- Results
-
Reference: 13.9% of those receiving deucravacitinib (n = 303). Result: 36.5% of patients (n = 301) achieving PASI 100 at week 16.
- Additional value from AI
-
Not assessed
- Limitations
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Approximately $4 billion upfront for acquisition of the TYK2 program subsidiary, subject to closing adjustments; a transfer rather than an estimate of AI-created value.
- Amount
-
$4 billion
- Currency and prices
-
USD, stated in the source. Nominal source amount; price year not separately stated.
- Period and unit
-
Acquisition closed February 8, 2023; payment is reported in the fiscal-2023 annual securities report filed June 26, 2024. One acquisition’s upfront consideration.
- Realization
-
Paid.
- Recipients and payers
-
Nimbus (seller), paid by Takeda
- Gross or net
-
Gross acquisition consideration, not drug revenue, seller profit, clinical benefit, or newly created societal wealth.
- Included costs
-
Not assessed
- Comparison
-
No estimate of the transaction value without AI-assisted design is supplied.
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer: Schrodinger (platform); Nimbus Therapeutics (compound). Operator: Takeda (clinical development, LATITUDE phase 3 program).
- Jurisdictions
-
Benefit:
United States (Nimbus, Boston; Takeda Development Center Americas, Cambridge, MA); phase 2b at 55 sites in the US and 
Canada; phase 3 sites unverified. Developer: United States. Operator: 
Japan. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
Phase 3 efficacy and safety confirmed in regulatory review. Independent documentation of the computational platform's contribution to the molecule.
- Replication attempts
-
2 follow-up entries. Benefit recurred: 1. Outcome unresolved: 1.
- Later findings
-
14 September 2026. Takeda reported FDA priority review with a decision expected in the first quarter of 2027 and EMA acceptance of the application. These sponsor announcements do not establish approval.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0262-source-0001–0007
- Language
-
Not assessed
- Original evidence
-
The phase 3 presentation, full discovery paper, and phase 2b supplements were inaccessible. [1] [2] [3] [4] [5] [6] [7]
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
People. Organizations. Society.
- Depth
-
People: 3. Organizations: 2. Society: Not assessed.
- Reasons
-
People: Trial participants achieved complete skin clearance at higher rates. PASI 100 was 36.5% vs 13.9% at week 16 in LATITUDE Atlas, and 33% at 30 mg in phase 2b. Organizations: Takeda reported acceptance of its application for FDA priority review in September 2026 after acquiring the program for approximately $4 billion upfront. Application acceptance is not regulatory confirmation of efficacy or an estimate of AI-created value. Society: No approval or population-level outcome as of 20 October 2026.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
The makers' claim
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Health; drug discovery. Adults with moderate-to-severe plaque psoriasis.
- Purpose
-
Design a selective oral allosteric TYK2 inhibitor for plaque psoriasis and other immune-mediated diseases
- Dates
-
Date basis unassessed: 2026 (precision unassessed). Updated: 24 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 8369c6c4cda4…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
7 revisions. Latest: 24 October 2026.
Sources
-
Press release Developer
Takeda. Zasocitinib demonstrates superior efficacy to deucravacitinib in LATITUDE Atlas. 2026-09-30. Original sponsor announcement of EADV 2026 late-breaking results, citing Stein Gold et al., LB-312, session D3T01.3.
makers
-
Peer-reviewed study Developer
Armstrong AW, Gooderham M, Lynde C, et al.. Tyrosine Kinase 2 Inhibition With Zasocitinib (TAK-279) in Psoriasis: A Randomized Clinical Trial. 2024-08-21. JAMA Dermatology 160(10). doi:10.1001/jamadermatol.2024.2701. Nimbus funded the trial and participated in design, analysis, and interpretation.
makers
-
Dataset Developer
Takeda; ClinicalTrials.gov. NCT06973291: LATITUDE Atlas. 2025-05-15. Sponsor-submitted registration; first posted May 15, 2025, updated May 1, 2026. No posted results.
makers
-
Report Developer
Schrödinger. Design of a highly selective, allosteric, picomolar TYK2 inhibitor using novel FEP+ strategies. n.d. Original developer account; JH2 program section concerns TAK-279.
makers
-
News report Developer
Drug Target Review, interview with Takeda’s Warren Winkelman. Inside Zasocitinib: A New Model for TYK2 Inhibition in Immune-Mediated Diseases. 2025-09-26. A firsthand sponsor account of the AI-assisted design claim, rather than independent verification.
makers
-
Press release Developer
Takeda. FDA Grants Priority Review to Zasocitinib for Moderate-to-Severe Plaque Psoriasis. 2026-09-14. Sponsor reports FDA priority review and EMA application acceptance; no approval reported.
makers
-
Press release Developer
Takeda. Takeda Completes Acquisition of Nimbus Therapeutics’ TYK2 Program Subsidiary. 2023-02-08. Closing announcement. Approximately $4 billion upfront, subject to closing adjustments, with contingent milestones.
makers