RESISTANCE IN UNCOMMON GENETIC DISORDERS: UNLOCKING THE POTENTIAL OF AI-DRIVEN PHARMACOGENOMICS
Multidrug resistance continues to be the principal barrier to the clinical treatment of uncommon genetic illnesses, severely impeding therapeutic outcomes. Traditional drug development models as well as treatment models do not take into account patient-specific genomic differences. The convergence of AI with pharmacogenomics demonstrates a strong base that can be leveraged to promote therapeutic precision and resistance. Reflecting the current individual-treatment-strategy focus necessary for patients with rare diseases, this review discusses the potential paradigm-shifting impact of AI-facilitated pharmacogenomic approaches in drug discovery. We describe how computational methods—such as machine learning and deep learning—can be used to predict pharmacologic performance, to discover new therapeutic targets, and to understand molecular mechanisms of multidrug resistance (MDR) in rare genetic diseases. Even with much advancement, significant barriers still exist in producing precision therapeutics that can effectively counter MDR, becoming rigorously clinically validated, and translating AI platforms to span diverse genomic datatypes. In stating these unmet gaps, we outline focused research directions that can address these gaps and enable the development of more effective, genomically informed therapeutic strategies bridging computational modeling and clinical translation. This review emphasizes how crucial interdisciplinary cooperation is to the development of AI-driven precision medicine for uncommon diseases, which has the potential to significantly enhance patient outcomes and therapeutic efficacy.
Authors
- Navroop Kaur (ORCID: https://orcid.org/0000-0002-8414-1534)
- Arshdeep Singh (ORCID: https://orcid.org/0009-0006-7998-8155)
- Upasana
- Saksham
Institutions
- Guru Nanak Dev University (IN)
- Government Medical College, Amritsar (IN)
- Indian Institute of Management Amritsar (IN)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-18
- DOI
- https://doi.org/10.5281/zenodo.24333594
- Primary Topic
- Computational Drug Discovery Methods
- Type
- article
- Field-Weighted Citation Impact
- 0.00