Skip to content
DraconiticResearch
Search Sources API
189,280 studies31 sourcesUpdated 26 min ago
Peer-reviewedCC BY 4.0Cancers

Transcriptomic Profiles Carry Most of the Multi-Omics Signal for Drug Sensitivity Prediction in Cancer Cell Lines: A Cross-Lineage and Independent-Screen Evaluation of Twelve Anticancer Agents

  • Sultan A. Alfawaz1
  • Haifa Almukadi2
  • Thoraia Shinawi3
  • Dalal Alfawaz1
  • Dareen Alyousfi4
  • Khalda K. Nasser3
  • Ashraf A. El Harouni5
  • Noor A. Shaik5,6
  • Babajan Banaganapalli5,6,7
7 affiliations
  1. 1Department of Clinical Pharmacology, Faculty of Medicine, King Abdulaziz University, Jeddah 21589, Saudi Arabia
  2. 2Department of Pharmacology and Toxicology, Faculty of Pharmacy, King Abdulaziz University, Jeddah 21589, Saudi Arabia
  3. 3Department of Medical Laboratory Sciences, Faculty of Applied Medical Sciences, King Abdulaziz University, Jeddah 21589, Saudi Arabia
  4. 4Department of Clinical Biochemistry, Faculty of Medicine, King Abdulaziz University, Jeddah 21589, Saudi Arabia
  5. 5Department of Genetic Medicine, Faculty of Medicine, King Abdulaziz University, Jeddah 21589, Saudi Arabia
  6. 6Princess Al-Jawhara Al-Ibrahim Center of Excellence in Research of Hereditary Disorders, King Abdulaziz University, Jeddah 21589, Saudi Arabia
  7. 7Center of Excellence in High Performance Computing (Aziz), King Abdulaziz University, Jeddah 21589, Saudi Arabia
Open at sourceDOICite

Abstract

Background/Objectives: Combining omics layers is widely expected to improve cancer drug response prediction, but this is rarely tested under family-wise error control or on an independent screen. We measured what somatic mutation and copy number data add to gene expression, and how well models transfer to unseen lineages and an external screen. Methods: We linked the Cancer Dependency Map transcriptomic, somatic mutation and copy number profiles to GDSC2 dose–response data for twelve mechanistically diverse anticancer compounds in 509 cell lines. Lineage-only, single-modality, early-fusion and stacked late-fusion gradient-boosting models were compared by repeated cross-validation (DeLong tests, Holm adjustment), leave-one-lineage-out transfer across eleven solid tumour histologies, and external validation on 77-163 held-out PRISM cell lines per compound. Results: Gene expression models outperformed tissue-of-origin baselines for all twelve agents (AUC 0.69–0.84; gains 0.024–0.169; Holm-adjusted p < 0.001 for seven drugs). Adding mutation and copy number data changed AUC by −0.015 to +0.035, and no per-drug gain survived multiplicity correction. Pooled across compounds, early fusion added 0.008 AUC (95% CI 0.000–0.016), a gain that fold-level re-analysis did not support. Mixed-lineage cross-validation exceeded leave-one-lineage-out AUC by a median of 0.030 (p = 0.0005). External PRISM AUCs ranged from 0.46 to 0.76 and followed the concordance between the two screens (Spearman rho = 0.72, p = 0.008). TreeSHAP attributions recovered known determinants, including SLFN11, TP53, BRAF, PIK3CA and downstream MAPK transcriptional effectors. Conclusions: In this twelve-drug panel, gene expression captured most of the predictable response variation. Accuracy fell on held-out lineages and on an independent screen, which sets empirical limits on how far these models can generalise.

Related

  1. Integrated transcriptomic and clinical prediction model for malignant pulmonary nodules : Model development, external dataset evaluation, and single-center expression validation
    Xingshu Zhang, Jie Yang, Ming Gong +2
    MedicinePeer-reviewedCC BYFull textGeneral medicineEurope PMCPMC
  2. Molecular Mechanisms of the Anticancer Activity of Hinokitiol in C32 Melanoma Cells: Transcriptomic Analysis and Modulation by a Static Magnetic Field
    Agnieszka Synowiec-Wojtarowicz, Celina Kruszniewska-Rajs, Agata Krawczyk +1
    MoleculesPeer-reviewedCC BY 4.0Full textPhysiologyCrossrefEurope PMC
  3. Exploring Vitamin D Metabolism in Gynaecological Malignancies: Redox-Dependent and Redox-Independent Anticancer Mechanisms From Preclinical Models to Clinical Evidence.
    Hoi Ching Cherry Chan, Sachin Bhoora, Esther Zhou +2
    Cancer medicinePeer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMC
  4. Transcriptomic Profiling Reveals METTL26 as a Potential Biomarker in Head and Neck Squamous Cell Carcinoma with Independent Validation in Oral Squamous Cell Carcinoma
    Rossella Rotondo, Alessandro Polizzi, Sabrina Donati Zeppa +3
    Medical sciences (Basel, Switzerland)Peer-reviewedCC BYFull textGeneral medicineEurope PMC
  5. Ethnopharmacological evaluation of Irvingia gabonensis (Aubry-Lecomte ex O'Rorke) Baill. seed extract: integrated computational and in vitro assessment of antioxidant, antidiabetic, and anticancer activities with in vivo validation of antidiabetic activity
    Ahamefula Anslem Ahuchaogu, Cletus Anes Ukwubile, Ifeoma Uzoamaka Nwabekee +1
    In Silico PharmacologyPeer-reviewedLicence not statedFull textEndocrinology & metabolismPMC

Cite

BibTeXRIS
BibTeX
@article{alfawaz2026transcriptomic,
  title = {{Transcriptomic Profiles Carry Most of the Multi-Omics Signal for Drug Sensitivity Prediction in Cancer Cell Lines: A Cross-Lineage and Independent-Screen Evaluation of Twelve Anticancer Agents}},
  author = {Sultan A. Alfawaz and Haifa Almukadi and Thoraia Shinawi and Dalal Alfawaz and Dareen Alyousfi and Khalda K. Nasser and Ashraf A. El Harouni and Noor A. Shaik and Babajan Banaganapalli},
  journal = {Cancers},
  year = {2026},
  month = oct,
  doi = {10.3390/cancers18213503},
  url = {https://www.mdpi.com/2072-6694/18/21/3503},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Transcriptomic Profiles Carry Most of the Multi-Omics Signal for Drug Sensitivity Prediction in Cancer Cell Lines: A Cross-Lineage and Independent-Screen Evaluation of Twelve Anticancer Agents
AU  - Sultan A. Alfawaz
AU  - Haifa Almukadi
AU  - Thoraia Shinawi
AU  - Dalal Alfawaz
AU  - Dareen Alyousfi
AU  - Khalda K. Nasser
AU  - Ashraf A. El Harouni
AU  - Noor A. Shaik
AU  - Babajan Banaganapalli
PY  - 2026
DA  - 2026/10/30
JO  - Cancers
DO  - 10.3390/cancers18213503
UR  - https://www.mdpi.com/2072-6694/18/21/3503
AB  - Background/Objectives: Combining omics layers is widely expected to improve cancer drug response prediction, but this is rarely tested under family-wise error control or on an independent screen. We measured what somatic mutation and copy number data add to gene expression, and how well models transfer to unseen lineages and an external screen. Methods: We linked the Cancer Dependency Map transcriptomic, somatic mutation and copy number profiles to GDSC2 dose–response data for twelve mechanistically diverse anticancer compounds in 509 cell lines. Lineage-only, single-modality, early-fusion and stacked late-fusion gradient-boosting models were compared by repeated cross-validation (DeLong tests, Holm adjustment), leave-one-lineage-out transfer across eleven solid tumour histologies, and external validation on 77-163 held-out PRISM cell lines per compound. Results: Gene expression models outperformed tissue-of-origin baselines for all twelve agents (AUC 0.69–0.84; gains 0.024–0.169; Holm-adjusted p < 0.001 for seven drugs). Adding mutation and copy number data changed AUC by −0.015 to +0.035, and no per-drug gain survived multiplicity correction. Pooled across compounds, early fusion added 0.008 AUC (95% CI 0.000–0.016), a gain that fold-level re-analysis did not support. Mixed-lineage cross-validation exceeded leave-one-lineage-out AUC by a median of 0.030 (p = 0.0005). External PRISM AUCs ranged from 0.46 to 0.76 and followed the concordance between the two screens (Spearman rho = 0.72, p = 0.008). TreeSHAP attributions recovered known determinants, including SLFN11, TP53, BRAF, PIK3CA and downstream MAPK transcriptional effectors. Conclusions: In this twelve-drug panel, gene expression captured most of the predictable response variation. Accuracy fell on held-out lineages and on an independent screen, which sets empirical limits on how far these models can generalise.
SN  - 2072-6694
ER  -