AI-Driven Design of High Affinity Biomolecule-Drug Conjugates for Gynecological Cancer Therapy: An Up-to-Date...

Background: Gynecological cancers include collections of cancers with diverse cellular and molecular characteristics that often develop drug resistance, making them treatment-resistant. Biomolecule-drug conjugates (BDCs), especially antibody-drug conjugates (ADCs), have revolutionized the targeted therapy of cancer; however, the creation of these entities has so far been achieved by empirical, resource-intensive design methods. Objective: The aim of this review is to critically analyze how AI can be used for the rational design and optimization of high-affinity BDCs for gynecological cancer treatment. Methods and discussion: Recent advances in machine learning (ML)- and deep learning (DL)-based methods to predict biomolecule-target binding affinity, structural compatibility, linker stability, payload selection, trafficking in the cell, and biomolecule resistance mechanisms are summarized. The review also explores the possibilities for incorporation of structural, chemical, biological, and multi-omics data to enhance specificity, efficacy, and safety of conjugates. Besides antibody-based systems, AI-assisted design approaches with peptides, aptamers, and hybrid biomolecular systems are also included. This review also highlights parameters and experimental/numerical validation restrictions related to data quality, interpretability of models, regulatory aspects, etc. Conclusions: AI-based conjugate engineering is increasingly moving BDC development from a largely 'trial and error' approach to a more predictive and data-driven approach. While there are still challenges to be addressed in terms of translations and validations, the potential of AI approaches in the field of precision oncology and the development of more personalized treatment is promising in the context of gynecological cancers.