CanSeer: A Method for Development and Clinical Translation of Personalized Cancer Therapeutics
Butt, R. N.; Amina, B.; Sultan, M. U.; Tanveer, Z. B.; Hussain, R.; Akbar, R.; Khan, S.; Gondal, M. N.; Khalid, M. F.; Faisal, A.; Shoaib, M.; Chaudhary, S. U.
Show abstract
Computational modeling and analysis of biomolecular network models annotated with cancer patient-specific multi-omics data can enable the development of personalized therapies. Current endeavors aimed at employing in silico models towards personalized cancer therapeutics remain to be fully translated. In this work, we present "CanSeer" a novel multi-stage methodology for developing in silico models towards clinical translation of personalized cancer therapeutics. The proposed methodology integrates state-of-the-art dynamical analysis of biomolecular network models with patient-specific genomic and transcriptomic data to assess the individualized therapeutic responses to targeted drugs and their combinations. CanSeers translational approach employs transcriptomic data (RNA-seq based gene expressions) with genomic profile (CNVs, SMs, and SVs). Specifically, patient-specific cancer driver genes are identified, followed by the selection of druggable and/or clinically actionable targets for therapeutic interventions. To exemplify CanSeer, we have designed three case studies including (i) lung squamous cell carcinoma, (ii) breast invasive carcinoma, and (iii) ovarian serous cystadenocarcinoma. The case study on lung squamous cell carcinoma concluded that restoration of Tp53 activity together with an inhibition of EGFR as an efficacious combinatorial treatment for patients with Tp53 and EGFR cancer driver genes. The findings from the cancer case study helped identify personalized treatments including APR-246, APR-246+palbociclib, APR-246+osimertinib, APR-246+afatinib, APR-246+osimertinib+dinaciclib, and APR-246+afatinib+dinaciclib. The second case study on breast invasive carcinoma revealed CanSeers potential to elucidate drug resistance against targeted drugs and their combinations including KU-55933, afuresertib, ipatasertib, and KU-55933+afuresertib. Lastly, the ovarian cancer case study revealed the combinatorial efficacy of APR-246+carmustine, and APR-246+dinaciclib for treating ovarian serous cystadenocarcinoma. Taken together, CanSeer outlines a novel method for systematic identification of optimal tailored treatments with mechanistic insights into patient-to-patient variability of therapeutic response, drug resistance mechanism, and cytotoxicity profiling towards personalized medicine.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Network-driven cancer cell avatars for combination discovery and biomarker identification for DNA Damage Response inhibitors 94%
- Stratification and prediction of drug synergy based on target functional similarity 93%
- SwarmMAP: Swarm Learning for Decentralized Cell Type Annotation in Single Cell Sequencing Data 93%
Similar papers in this journal
- Tissue-guided LASSO for prediction of clinical drug response using preclinical samples 95%
- Inferring latent temporal progression and regulatory networks from cross-sectional transcriptomic data of cancer samples 95%
- HELP: A computational framework for labelling and predicting human common and context-specific essential genes 95%
Similar papers in this journal
- Identifying potential risk genes for clear cell renal cell carcinoma with deep reinforcement learning 96%
- Teacher-student collaborated multiple instance learning for pan-cancer PDL1 expression prediction from histopathology slides 94%
- MORONET: Multi-omics Integration via Graph Convolutional Networks for Biomedical Data Classification 94%
Similar papers in this journal
Similar papers in this journal
- Cell graph neural networks enable the digital staging of tumor microenvironment and precise prediction of patient survival in gastric cancer 94%
- Overcoming Resistance to BRAFV600E Inhibition in Melanoma by Deciphering and Targeting Personalized Protein Network Alterations 94%
- Cancer drug sensitivity prediction from routine histology images 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.