DeepVF is a deep learning-based hybrid framework for accurate identification of VFs in Gram-negative bacteria. Seven popular machine learning algorithms consisting of four classical machine learning algorithms including random forest (RF), support vector machines (SVM), extreme gradient boosting (XGBoost) and multilayer perceptron (MLP), and three deep learning algorithms, including convolutional neural networks (CNN), long short-term memory networks (LSTM) and bi-directional long short-term memory networks (BiLSTM) are employed to train 62 single-method baseline models. By effectively combining these baseline models in a deep learning-based hybrid framework using the stacking strategy in order to integrate their individual prediction strengths.