TooT-BERT_ICAT

TooT-BERT-ICAT is a tool designed to predict and classify inorganic ion-specific transmembrane transporter proteins using the advanced transformer model, ProtBERT-BFD. The project consists of three main parts: data preparation, model definition, and training. Data preparation involves reading the dataset, splitting it into training, validation, and testing sets. The model uses the ProtBERT-BFD pre-trained model to obtain representations of the protein sequences, which are then passed through a linear classifier to predict the ion categories. The training process iteratively optimizes the model using the cross-entropy loss function and the Adam optimizer. This tool has been presented in the paper "Predicting the specific substrate for transmembrane transport proteins using BERT language model"