LBA501 Background: I-SPY2.2 is a multicenter phase 2 platform sequential multiple assignment randomized trial (SMART) in the neoadjuvant breast cancer setting that evaluates novel experimental regimens as first in a sequence (Block A) followed by standard chemo/targeted therapies (Blocks B/C) if indicated. The goal is to achieve a pCR after novel targeted agents alone or in sequence with standard therapies, with the optimal therapy assigned based on the tumor response predictive subtype (RPS). RPS incorporates expression-based immune, DNA repair deficiency (DRD), and luminal signatures with hormone receptor (HR) and HER2 status to subset patients into 6 subtypes: S1: HR+HER2-Immune-DRD-; S2: HR-HER2-Immune-DRD-; S3: HER2-Immune+; S4: HER2-Immune-DRD+; S5: HER2+/non-Luminal; S6: HER2+/Luminal. Methods: RPS S1, S2, S3, and S4 were eligible for assignment to Dato+Durva in Block A. Patients were followed by MRI during treatment (at 3, 6, and 12 weeks after start of Blocks A and B). Predicted responders by MRI and biopsy at the end of Block A or B have the option of going to surgery early; otherwise, they proceed to next treatment Block (B +/- C). Randomization to Block B includes a taxane-based regimen specific to the RPS, and options include S1: paclitaxel; S2 and S3: paclitaxel + carboplatin + pembrolizumab; S4: paclitaxel + carboplatin vs. paclitaxel + carboplatin + pembrolizumab. Patients who did not go to surgery after Block B proceeded to Block C (AC or AC + Pembrolizumab if HR-HER2-). The primary endpoint is pCR. Efficacy is evaluated within each RPS and HR+HER2- and HR-HER2- signatures. To estimate the arm's efficacy as a stand-alone therapy, we use a Bayesian covariate-adjusted model to estimate the pCR rate and compare the posterior distribution to a subtype-specific fixed threshold. This model uses pCR data when available and MRI data when pCR is not. To estimate pCR rate in the context of a multi-decision treatment regimen, we use a Bayesian model based on if and when a pCR occurred in the trial. The posterior is compared to a subtype-specific dynamic control generated from historical I-SPY data. Results: 106 patients were randomly assigned to the Dato+Durva arm between September 2022 and August 2023. The results for Dato+Durva as a stand-alone therapy are summarized in Table. After completion of Block A, 36 patients proceeded to surgery without completing Blocks B/C. Conclusions: Dato+Durva meets threshold for graduation within the RPS S3 subtype based on estimated pCR rate of 72% and warrants further investigation in a larger randomized controlled trial. Clinical trial information: NCT01042379 . Table: see text