info_text = ("""
This application enables to inspect mutational effects on a predefined protein sequence.

It is built on the Prot-xLSTM backbone model, an xLSTM model specifically trained on protein sequences. Prot-xLSTM was trained using the Fill-In-the-Middle (FIM) objective, which allows it to perform sequence inpainting. Additionally, the model can be provided with a potentially large set of homologous sequences to enhance its predictions.

For further information please refer, to: https://openreview.net/forum?id=IjbXZdugdj.

This Hugging Face application is based on the following GitHub repository: https://github.com/ml-jku/Prot-xLSTM?tab=readme-ov-file.
The streamlit application was developed by Elias Bürger.
Please cite us as follows:
""") citation_text = """ @misc{ schmidinger2024bioxlstmgenerativemodelingrepresentation, title={Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences}, author={Niklas Schmidinger and Lisa Schneckenreiter and Philipp Seidl and Johannes Schimunek and Pieter-Jan Hoedt and Johannes Brandstetter and Andreas Mayr and Sohvi Luukkonen and Sepp Hochreiter and Günter Klambauer}, year={2024}, eprint={2411.04165}, archivePrefix={arXiv}, primaryClass={q-bio.BM}, url={https://arxiv.org/abs/2411.04165}, } """