AI-Assisted Cancer Biology: Mapping Non-Coding RNAs to Cancer Pathways

Cancer research is entering an era in which artificial intelligence, machine learning, and large-scale genomic data can be integrated with molecular biology to investigate increasingly complex questions in cancer. Our research focuses on understanding how non-coding RNAs, particularly long non-coding RNAs (lncRNAs) and microRNAs, contribute to cancer progression, tumor suppression, DNA-damage responses, and cellular stress pathways.

A major direction of our research involves the use of large-scale cancer genomic and clinical datasets to identify disease-associated molecular patterns. By integrating RNA-expression profiles with clinical characteristics and patient outcomes, we investigate cancer-associated RNA signatures, prognostic biomarkers, regulatory networks, and molecular pathways with potential biological and clinical relevance.

An emerging dimension of our work is the application of artificial intelligence and machine-learning approaches to cancer genomics. We explore computational methods including pattern recognition, clustering, feature selection, classification, and predictive modeling to identify meaningful relationships within complex cancer datasets. These approaches allow multiple molecular features to be examined collectively and provide a framework for identifying patterns that may not be apparent from conventional gene-by-gene analysis.

Our broader research direction therefore lies at the interface of Cancer Biology, Non-Coding RNA Biology, Genomics, Bioinformatics, and Artificial Intelligence. The objective is to connect computationally identified patterns with cancer biology, gene regulation, molecular pathways, and clinically relevant questions, providing new opportunities to understand the molecular complexity of cancer and identify candidate biomarkers and molecular signatures.

Selected Recent Publications

Sharma, M. et al. (2026).
DNA damage induces p53-dependent activation of the lncRNA TCERG1L-AS1 to regulate cell proliferation.
Biochimie.
Focus: p53 • DNA-damage response • lncRNA regulation • cell proliferation

Sharma, M. et al. (2026).
Clinical data analysis identifies prognostic long non-coding RNA signatures in lung adenocarcinoma.
Cancer Genomics & Proteomics, 23(3), 530–545.
Focus: Lung adenocarcinoma • lncRNA biomarkers • clinical data • survival analysis • cancer genomics

Sharma, M. et al. (2025).
Functional characterization of dysregulated lncRNAs in BRCA and CESC highlights their role in cancer prognosis.
Scientific Reports.
Focus: Breast and cervical cancers • lncRNAs • cancer prognosis • functional characterization

Representative Publications

Non-Coding RNA and Gene Regulation

Priyanka, P., Sharma, M., Das, S. & Saxena, S. (2022).
E2F1-induced lncRNA EMSLR regulates lncRNA LncPRESS1.
Scientific Reports, 12, 2548.

Priyanka, P., Sharma, M., Das, S. & Saxena, S. (2021).
The lncRNA HMS recruits RNA-binding protein HuR to stabilize the 3′-UTR of HOXC10 mRNA.
Journal of Biological Chemistry, 297, 100997.

microRNAs and Cancer

Shekhar, R., Priyanka, P., Kumar, P., Ghosh, T., Khan, M.M., Nagarajan, P. & Saxena, S. (2019).
The microRNAs miR-449a and miR-424 suppress osteosarcoma by targeting cyclin A2 expression.
Journal of Biological Chemistry, 294, 4381–4400.

Ghosh, T., Varshney, A., Kumar, P., Kaur, M., Kumar, V., Shekhar, R., Devi, R., Priyanka, P., Khan, M.M. & Saxena, S. (2017).
MicroRNA-874-mediated inhibition of the major G1/S phase cyclin, CCNE1, is lost in osteosarcomas.
Journal of Biological Chemistry, 292, 21264–21281.

Cell-Cycle and Cancer Biology

Kaur, M., Devi, R., Ghosh, T., Khan, M.M., Kumar, P., Priyanka, Kar, A., Sharma, A., Varshney, A., Kumar, V. & Saxena, S. (2018).
Sld5 ensures centrosomal resistance to congression forces by preserving centriolar satellites.
Molecular and Cellular Biology, 38(2), e00371-17.