Machine learning (ML) systems can model quantitative structure-property relationships (QSPR) using existing experimental data and make property predictions for new molecules. With the advent of modalities such as targeted protein degraders (TPD), the applicability of QSPR models is questioned and ML usage in TPD-centric projects remains limited. Herein, ML models are developed and evaluated for TPDs’ property predictions, including passive permeability, metabolic clearance, cytochrome P450 inhibition, plasma protein binding, and lipophilicity. Interestingly, performance on TPDs is comparable to that of other modalities. Predictions for glues and heterobifunctionals often yield lower and higher errors, respectively. For permeability, CYP3A4 inhibition, and human and rat microsomal clearance, misclassification errors into high and low risk categories are lower than 4% for glues and 15% for heterobifunctionals. For all modalities, misclassification errors range from 0.8% to 8.1%. Investigated transfer learning strategies improve predictions for heterobifunctionals. This is the first comprehensive evaluation of ML for the prediction of absorption, distribution, metabolism, and excretion (ADME) and physicochemical properties of TPD molecules, including heterobifunctional and molecular glue sub-modalities. Taken together, our investigations show that ML-based QSPR models are applicable to TPDs and support ML usage for TPDs’ design, to potentially accelerate drug discovery.

Background: Maxillofacial bone defects present considerable challenges in oral and reconstructive surgery. While autologous bone grafts are the gold standard, their limitations, such as donor site morbidity and limited availability, have driven the search for alternative biomaterials. SmartBone^®, a xeno-hybrid graft, offers potential advantages due to its bioactivity and remodeling capacity. Methods: This analysis of a series of clinical cases, evaluated the performance of SmartBone^® in 10 patients presenting with various maxillofacial bone defects. The patient follow-up period spanned from 2017 to 2019, with a maximum duration of 30 months. Bone grafting was performed, and integration was monitored using Cone-Beam Computed Tomography at multiple timepoints. Bone density changes (ΔCT values) in selected anatomical sites were analyzed to assess graft transformation and integration. Results: SmartBone^® supported effective bone regeneration and selective remodeling in all cases. One patient required a revision procedure, after which successful integration was observed. Cellular colonization began within weeks, with complete remodeling into mature bone occurring between 6–12 months. Evidence of cortical wall resorption and reformation on the graft’s external surface confirmed this transformation. ΔCT values progressively aligned with native bone densities, indicating structural and functional integration. Conclusions: SmartBone^® demonstrates strong osteointegrative and site-specific remodeling capabilities, offering a reliable and predictable alternative for maxillofacial bone reconstruction. The study presents several limitations, including the small sample size, inter-patient variability, possible imaging artifacts due to metallic elements in Cone-Beam Computed Tomography scans and the lack of histological confirmation.