Molecularly-informed prediction of treatment efficacy in the GENIE BPC NSCLC cohort using computational reasoning
Presenter: ISTVAN PETAK Session: AACR Project GENIE: Predictive Models and AI Time: 4/19/2026 2:00:00 PM → 4/19/2026 5:00:00 PM
Authors
Barbara Vodicska 1 , Eniko Kispeter 1 , Dora Lakatos 1 , Gabor Gy Kalmar 1 , Robert Doczi 1 , Dora Gorog-Tihanyi 1 , Anna Dirner 1 , Reka Szalkai-Denes 1 , William T. Beck 2 , Arkadiusz Z. Dudek 3 , Christophe Le Tourneau 4 , Istvan Petak 1 1 Genomate Health, Cambridge, MA, 2 University of Illinois at Chicago, Chicago, IL, 3 Division of Oncology, Mayo Clinic, Rochester, MN, 4 Gustave Roussy, Villejuif, France
Abstract
Background: Digital Drug Assignment (DDA) is a computational reasoning model that scores cancer therapies based on the complete molecular profile of a tumor, and stratifies them by predicted efficacy (Petak et al., 2021). In a prior study of 111 lung cancer patients, DDA-derived high-score molecularly targeted agents (MTAs) were associated with improved clinical outcomes (Dirner et al., 2025). Here, we extend this analysis to the GENIE BPC NSCLC cohort to assess the broader clinical validity of DDA. Methods: From the GENIE BPC NSCLC cohort data available on Synapse, we included 1,078 patients with a single-sample genomic profile, available primary treatment data and survival outcomes (total 2,103 treatment lines, therapies included: afatinib, erlotinib, osimertinib, crizotinib, nivolumab, pembrolizumab, atezolizumab, bevacizumab+chemo, ramucirumab+chemo; and chemotherapy alone). DDA scores were generated for all cases, and the individual score of the administered MTAs (incl. immune checkpoint inhibitors) was used to stratify outcomes into low ( Results: Median PFS and OS differed significantly across DDA score tiers, increasing with higher scores (see table). Intermediate-tier drugs had similar mPFS values as chemotherapies (3.9 vs 4.2 months). Six-month PFS and twelve-month OS rates increased with DDA-tiers and were all significantly different by χ² test. DDA-high therapies provided greater benefit across treatment types than lower-score counterparts. Conclusions: Across a large, real-world NSCLC cohort, DDA effectively distinguished therapies with higher clinical efficacy based on the full molecular profile of each patient. These results reinforce the potential of DDA to enhance personalized treatment selection based on NGS diagnostics in precision oncology. DDA-low DDA-intermediate DDA-high Statistical test Chemo mPFS (months) 1.7 (n = 72) 3.9 (n = 303) 5.1 (n = 554) log-rank p 4.2 (n = 709) mOS (months) 9.0 (n = 74) 16.2 (n = 327) 23.3 (n = 601) log-rank p 23.5 (n = 1094) 6-month PFS rate 14% 28% 40% Χ² p 25% 12-month OS rate 36% 53% 63% Χ² p 65%
Disclosure
B. Vodicska, Genomate Health Employment. E. Kispeter, Genomate Health Employment. D. Lakatos, Genomate Health Employment. G. G. Kalmar, Genomate Health Employment. R. Doczi, Genomate Health Employment. D. Gorog-Tihanyi, Genomate Health Employment. A. Dirner, Genomate Health Employment. R. Szalkai-Denes, Genomate Health Employment. W. T. Beck, Genomate Health Stock, Stock Option. A. Z. Dudek, Iovance Other, Honorarium for participation in Advisory Board. C. Le Tourneau, Transgene, MSD, LEO Pharma, BMS, J&J, DOB Pharmaceuticals, Bicara, Merus, Immutep, Owkin, Roche, GSK, Clinigen, Merck Serono, Aveon, ALX Oncology, Seagen Other, Advisory Board. I. Petak, Genomate Health Employment.
Cited in
Control: 1078 · Presentation Id: 3393 · Meeting 21436