Deciphering Context-Specific Axitinib Escape Pathways via Multi-Omics and Explainable Machine Learning

In this study, we conducted a comprehensive, high-throughput analysis using supervised machine learning classifiers applied to transcriptomic and proteomic data from pan cancer cell lines classified as resistant or sensitive to FDA-approved targeted drugs. Among the evaluated drugs, Axitinib demonstrated particularly high predictive accuracy.

To uncover the molecular determinants of resistance, we employed explainable AI algorithm: LIME, identifying key molecular players associated with resistance. Further, to understand various mechanisms of resistance, unsupervised clustering was performed. Enrichment analysis further revealed the biological pathways in which these resistance mediators are overrepresented, and pathway cross-talk was examined to elucidate the perturbed biological processes.

Axitinib Resistance Mechanism

Repository Organisation

📂 Axitinib_Codes_2025_may/
    ├── 📂 1_DataProcessing/
    │   ├── 📂 1_GDSC_Drugs_Preprocessing/
    │       └── 📄 GDSC_Processing_and_EDA.ipynb
    │   ├── 📂 2_Data_Representation_Transcriptomics_TPM/
    │       └── 📄 Data_Representation_Transcriptomics_TPM.ipynb
    │   ├── 📂 3_Data_Representation_Protein_Intensity/
    │       └── 📄 Data_Representation_Protein_Intensity.ipynb
    │   └── 📂 4_Targeted_Drugs_FDA_Approved/
    │       └── 📄 Targeted_Drugs_Processing.ipynb
    │
    ├── 📂 2_AutomatedFeatureEnggAndML/
    │   ├── 📂 Proteomics/
    │   │   ├── 📂 Prot_BatchA/
    │   │       ├── 📄 Result_Post-processing.ipynb
    │   │       └── 📄 automationbatchcode_protbatchA.py
    │   │   └── 📂 Prot_BatchB/
    │   │       ├── 📄 Result_Post-processing.ipynb
    │   │       └── 📄 automationbatchcode_protbatchB.py
    │   └── 📂 Transcriptomics/
    │       ├── 📂 Trans_BatchA/
    │       │   ├── 📄 Result_Processing.ipynb
    │       │   └── 📄 automationbatchcode_transBatchA.py
    │       └── 📂 Trans_BatchB/
    │           ├── 📄 Result_Processing.ipynb
    │           └── 📄 automationbatchcode_transbatchb.py
    │
    ├── 📂 3_BestPerformingDrugProcessing/
    │   └── 📄 ComparisonofAllAutomatedvsSelectedDrugs_MLScores.ipynb
    │
    ├── 📂 4_ExplainableAI_LIME/
    │   ├── 📄 Transcriptomics_Lime.ipynb
    │   └── 📄 Proteomics_Lime.ipynb
    │
    ├── 📂 5_Correlation/
    │   ├── 📄 Correlation_Resistancecell_Lines_T.ipynb
    │   └── 📄 Correlation_Resistancecell_Lines_P.ipynb
    │
    └── 📂 6_Clustering_and_StatisticalAnalysis/
        ├── 📄 Clustering.ipynb
        ├── 📄 Same_Clusters.ipynb
        ├── 📄 Variance_Analysis.ipynb
        └── 📄 Mean_Analysis.ipynb

==================================================
TOTAL CODE FILES: 21
==================================================
            
Download Analysis Pipeline & Datasets

Contact Us

Indraprastha Institute of Information Technology Delhi (IIIT-Delhi)

Okhla Industrial Estate, Phase III, New Delhi, Delhi 110020, India

Research Team

Samriddhi Gupta
Khyati Patni
Simarpreet Kaur

Principal Investigator

Dr. Jaspreet Kaur Dhanjal

Assistant Professor, Computational Biology