Virtual screening plays a critical role in modern drug discovery by enabling the identification of promising candidate molecules for experimental validation. Traditional machine learning methods, such as support vector machines (SVM) and XGBoost, rely on predefined molecular representations, often leading to information loss and potential bias. In contrast, deep learning approaches, particularly graph convolutional networks (GCNs), offer a more expressive and unbiased alternative by operating directly on molecular graphs. Meanwhile, large language models (LLMs) have recently demonstrated state-of-the-art performance in drug design thanks to their capacity to capture complex chemical patterns from large-scale data via attention mechanisms. In this paper, we propose a novel hybrid architecture that combines GCNs with LLM-derived embeddings, evaluated on both kinase-related data sets, which are well-established therapeutic targets of high biological significance, and non-kinase data sets such as the glucocorticoid receptor and PPARG, demonstrating the broader applicability of our approach. Our model introduces a layer-wise concatenation strategy, where LLM embeddings are injected after each GCN layer rather than solely at the final layer. This design enables progressive enrichment of the learned molecular representations with global chemical context throughout the network's depth. The LLM embeddings can be precomputed and stored in a molecular feature library, maintaining computational efficiency during training and inference. We conduct a comprehensive comparison against standalone GCN, Molformer, SVM, and XGBoost baselines, demonstrating that our method achieves superior performance, with an accuracy of 88.7%, compared to 86.8% for GCN, 85.1 for molformer, 85.0% for XGBoost, and 84.7% for SVM. These improvements are practically significant in real-world virtual screening scenarios, where even small gains can reduce false positives and accelerate candidate prioritization.