The shape of a molecule determines its physicochemical and biological properties. However, it is often underrepresented in standard molecular representation learning approaches. Here, we propose using the Euler Characteristic Transform (ECT) as a geometrical-topological descriptor. Computed directly from molecular graphs constructed using handcrafted atomic features, the ECT enables the extraction of multiscale structural features, offering a novel way to encode molecular shape in the feature space. We assess the predictive performance of this representation across nine benchmark regression datasets, all centered around predicting the inhibition constant \(K_i\) . In addition, we compare our proposed ECT-based descriptor against traditional molecular representations and methods, such as molecular fingerprints/descriptors and graph neural networks (GNNs). Our results show that our ECT-based representation achieves competitive performance, ranking among the best-performing methods on several datasets. More importantly, combining our descriptor with established representations, particularly with the AVALON fingerprint, significantly enhances predictive performance, outperforming other methods on most datasets. These findings highlight the complementary value of multiscale topological information and its potential for being combined with established techniques. Our study suggests that hybrid approaches incorporating explicit shape information can lead to more informative and robust molecular representations, enhancing and opening new avenues in molecular machine learning. To support reproducibility and foster open biomedical research, we provide open access to all experiments and code used in this work.