TY - JOUR U1 - Zeitschriftenartikel, wissenschaftlich - nicht begutachtet (unreviewed) A1 - Balabin, Helena A1 - Hoyt, Charles Tapley A1 - Birkenbihl, Colin A1 - Gyori, Benjamin M. A1 - Bachman, John A1 - Tom Kodamullil, Alpha A1 - Plöger, Paul G. A1 - Hofmann-Apitius, Martin A1 - Domingo-Fernández, Daniel T1 - STonKGs: A Sophisticated Transformer Trained on Biomedical Text and Knowledge Graphs T2 - bioRxiv N2 - The majority of biomedical knowledge is stored in structured databases or as unstructured text in scientific publications. This vast amount of information has led to numerous machine learning-based biological applications using either text through natural language processing (NLP) or structured data through knowledge graph embedding models (KGEMs). However, representations based on a single modality are inherently limited. To generate better representations of biological knowledge, we propose STonKGs, a Sophisticated Transformer trained on biomedical text and Knowledge Graphs. This multimodal Transformer uses combined input sequences of structured information from KGs and unstructured text data from biomedical literature to learn joint representations. First, we pre-trained STonKGs on a knowledge base assembled by the Integrated Network and Dynamical Reasoning Assembler (INDRA) consisting of millions of text-triple pairs extracted from biomedical literature by multiple NLP systems. Then, we benchmarked STonKGs against two baseline models trained on either one of the modalities (i.e., text or KG) across eight different classification tasks, each corresponding to a different biological application. Our results demonstrate that STonKGs outperforms both baselines, especially on the more challenging tasks with respect to the number of classes, improving upon the F1-score of the best baseline by up to 0.083. Additionally, our pre-trained model as well as the model architecture can be adapted to various other transfer learning applications. Finally, the source code and pre-trained STonKGs models are available at https://github.com/stonkgs/stonkgs and https://huggingface.co/stonkgs/stonkgs-150k. KW - Knowledge Graphs KW - Natural Language Processing KW - Transformers KW - Bioinformatics KW - Machine Learning U6 - https://doi.org/10.1101/2021.08.17.456616 DO - https://doi.org/10.1101/2021.08.17.456616 SP - 16 S1 - 16 PB - Cold Spring Harbor Laboratory ER -