Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 23 min ago
Peer-reviewedCC BY 4.0PLOS One

Mutation-resolved ABL1 inhibitor resistance prediction under mutation-disjoint and temporal cross-study validation

  • Mohanad A. Deif1,2
  • Mohamed A. Hafez3,4
  • Mohammad Khishe5
  • Ahmed Solyman6
  • Ismail A. M. Elhaty7
7 affiliations
  1. 1Research Institute of Sciences and Engineering, University of Sharjah, Sharjah, United Arab Emirates
  2. 2Department of Computer Science, College of Information Technology, Misr University for Science and Technology (MUST), Giza, Egypt
  3. 3Faculty of Engineering, INTI International University, Nilai, Malaysia
  4. 4Shinawatra University, Bangkok, Pathum Thani, Thailand
  5. 5Applied Science Research Center, Applied Science Private University, Amman, Jordan
  6. 6Department of Engineering, School of Science and Engineering, Glasgow Caledonian University, Glasgow, United Kingdom
  7. 7Istanbul Gelisim University, Istanbul, Turkey
Read full textPDFDOICite

Abstract

Computational prediction of ABL1 tyrosine-kinase inhibitor (TKI) resistance is difficult because available mutation–drug datasets are small, imbalanced, and heterogeneous. This study evaluates structure-aware resistance prediction under mutation-disjoint internal validation and temporal cross-study outcome validation. The development benchmark comprised 144 ABL1 mutation–TKI records (19 resistant and 125 susceptible) labelled by a ten-fold affinity-loss criterion. A fixed panel of 11 documented structural and energetic predictors was used to minimize data-adaptive feature selection within the validation framework. A calibrated ensemble combining Elastic-Net logistic regression, radial-basis-function support-vector machines, random forests, and XGBoost was evaluated using mutation-disjoint five-fold grouped out-of-fold prediction repeated ten times. Temporal validation used a later prime-editing resistance map, yielding 84 exact mutation–TKI matches across imatinib, nilotinib, bosutinib, and ponatinib; 61 had binary Sensitive/Resistant outcomes and 23 were retained as Intermediate. The 11-feature stack achieved grouped internal AUROC 0.645 (95% CI 0.429–0.830) and PR-AUC 0.230, with mean ± SD AUROC 0.583 ± 0.101 across repeated grouped splits. On the 61 binary later-study outcomes, AUROC was 0.605 (95% CI 0.431–0.874) and PR-AUC 0.835, modestly above the resistance-prevalence baseline of 0.770. External calibration was poor (Brier score 0.583; calibration slope 0.441). Elastic-Net showed somewhat higher temporal discrimination (AUROC 0.643; PR-AUC 0.877). These results indicate limited transportability across mutation identities and experimental platforms and support use of the framework for hypothesis-generating resistance screening rather than clinically calibrated treatment selection.

Related

  1. Anti-CRISPR prediction using deep learning reveals an inhibitor of Cas13b nucleases
    Katharina Wandera, Omer Alkhnbashi, Harris V.I. Bassett +5
    Molecular CellPeer-reviewedLicence not stated42 citedMolecular biology & gene regulationHAL
  2. Towards Accurate Prediction of Mutation-Induced Changes in Protein Structure
    Zhuoyi Liu, Alex Calabrese, Corey S. O'Hern
    arXivPreprintarXiv licenceFull textBiophysicsBiological & medical physicsarXiv
  3. SbWRKY62 Coordinates With SbERF096 to Activate Pterostilbene Biosynthesis and Targets a Xylanase Inhibitor Protein for Anthracnose Resistance in Sorghum
    Yajing Li, Bofu Deng, Yiming Gan +3
    Plant, Cell & EnvironmentPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationPMC
  4. A Dynamics-Informed Machine Learning Framework for Inhibitor Optimization Against Quickly Evolving Targets to Avoid Resistance
    L. E. Intravaia, J. Kaur, A. M. Shaqra +7
    bioRxivPreprintCC BY-NC-NDFull textBiophysicsbioRxiv
  5. DNA Repair Pathways as Determinants of PARP Inhibitor Resistance and Therapeutic Targets in Cancer
    Kousalya Lavudi, Malavika Sunita Renjith, Charan PSVV +3
    International Journal of Molecular SciencesPeer-reviewedCC BY 4.0General biochemistryCrossref

Cite

BibTeXRIS
BibTeX
@article{deif2026mutationresolved,
  title = {{Mutation-resolved ABL1 inhibitor resistance prediction under mutation-disjoint and temporal cross-study validation}},
  author = {Mohanad A. Deif and Mohamed A. Hafez and Mohammad Khishe and Ahmed Solyman and Ismail A. M. Elhaty},
  journal = {PLOS One},
  year = {2026},
  month = oct,
  doi = {10.1371/journal.pone.0353101},
  url = {https://doi.org/10.1371/journal.pone.0353101},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Mutation-resolved ABL1 inhibitor resistance prediction under mutation-disjoint and temporal cross-study validation
AU  - Mohanad A. Deif
AU  - Mohamed A. Hafez
AU  - Mohammad Khishe
AU  - Ahmed Solyman
AU  - Ismail A. M. Elhaty
PY  - 2026
DA  - 2026/10/27
JO  - PLOS One
DO  - 10.1371/journal.pone.0353101
UR  - https://doi.org/10.1371/journal.pone.0353101
AB  - Computational prediction of ABL1 tyrosine-kinase inhibitor (TKI) resistance is difficult because available mutation–drug datasets are small, imbalanced, and heterogeneous. This study evaluates structure-aware resistance prediction under mutation-disjoint internal validation and temporal cross-study outcome validation. The development benchmark comprised 144 ABL1 mutation–TKI records (19 resistant and 125 susceptible) labelled by a ten-fold affinity-loss criterion. A fixed panel of 11 documented structural and energetic predictors was used to minimize data-adaptive feature selection within the validation framework. A calibrated ensemble combining Elastic-Net logistic regression, radial-basis-function support-vector machines, random forests, and XGBoost was evaluated using mutation-disjoint five-fold grouped out-of-fold prediction repeated ten times. Temporal validation used a later prime-editing resistance map, yielding 84 exact mutation–TKI matches across imatinib, nilotinib, bosutinib, and ponatinib; 61 had binary Sensitive/Resistant outcomes and 23 were retained as Intermediate. The 11-feature stack achieved grouped internal AUROC 0.645 (95% CI 0.429–0.830) and PR-AUC 0.230, with mean ± SD AUROC 0.583 ± 0.101 across repeated grouped splits. On the 61 binary later-study outcomes, AUROC was 0.605 (95% CI 0.431–0.874) and PR-AUC 0.835, modestly above the resistance-prevalence baseline of 0.770. External calibration was poor (Brier score 0.583; calibration slope 0.441). Elastic-Net showed somewhat higher temporal discrimination (AUROC 0.643; PR-AUC 0.877). These results indicate limited transportability across mutation identities and experimental platforms and support use of the framework for hypothesis-generating resistance screening rather than clinically calibrated treatment selection.
SN  - 1932-6203
ER  -