Interpretable Recurrent Neural Networks for Modeling Temporal Dynamics of Acquired Drug Resistance in Targeted Therapy
International Journal of Drug Delivery Technology · 25.05.2026 · 16 (32s)
DOI: 10.25258/ijddt.16.32s.11 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 25.05.2026. Verfasst von V. Pushpalatha und 9 weiteren Autor:innen.
Abstract (Originalsprache)
Acquired drug resistance remains a fundamental obstacle in targeted cancer therapy, often arising from complex temporal evolutionary dynamics within tumor cell populations. Traditional pharmacokinetic-pharmacodynamic (PKPD) models struggle to capture nonlinear, long-term sequential dependencies, while standard recurrent neural networks (RNNs) suffer from black-box opacity. In this paper, we propose IRNN-DR (Interpretable RNN for Drug Resistance), a novel architecture combining Long Short-Term Memory (LSTM) units with an attention-based temporal relevance mask and a learnable dynamical system backbone. Using longitudinal singlecell resistance data from EGFR-mutant non-small cell lung cancer (NSCLC) cell lines treated with osimertinib, we demonstrate that IRNN-DR achieves high predictive accuracy (AUC-ROC = 0.94) while providing explicit interpretations of resistance-driving time points and genetic pathways. Our contribution includes a temporal Shapley value module and a resistance trajectory clustering method. Results indicate that IRNN-DR can identify early "critical windows" of resistance emergence, with potential clinical utility for adaptive therapy scheduling.
Zitieren
APA
Pushpalatha, V., I, T. K., Kamaleshwar, D. T., Jini, A. J., Nagalakshmidevi, J., Susmitha, V., Sathyaraju, S., Jayasudha, D. R., Deepa, D. A., & Vengatesh, D. T. (2026). Interpretable Recurrent Neural Networks for Modeling Temporal Dynamics of Acquired Drug Resistance in Targeted Therapy. International Journal of Drug Delivery Technology, 16(32s). https://doi.org/10.25258/ijddt.16.32s.11
Vancouver
Pushpalatha V, I TK, Kamaleshwar DT, Jini AJ, Nagalakshmidevi J, Susmitha V, et al. Interpretable Recurrent Neural Networks for Modeling Temporal Dynamics of Acquired Drug Resistance in Targeted Therapy. International Journal of Drug Delivery Technology. 2026;16(32s). doi:10.25258/ijddt.16.32s.11
BibTeX
@article{Pushpalatha2026,
author = {Pushpalatha, V. and I, Thanvi Kuttaiah and Kamaleshwar, Dr. T. and Jini, Anat Jaslin and Nagalakshmidevi, Jakkapu and Susmitha, V. and Sathyaraju, Sathyaraju and Jayasudha, Dr. R. and Deepa, Dr. A.R. and Vengatesh, Dr. T.},
title = {Interpretable Recurrent Neural Networks for Modeling Temporal Dynamics of Acquired Drug Resistance in Targeted Therapy},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {32s},
doi = {10.25258/ijddt.16.32s.11}
}
EUVIMED