By harnessing the representational capacity of pre-trained protein models and guiding them with conformation information, we can achieve more accurate predictions of protein folding behavior. This has implications for both basic research and drug discovery efforts, as accurate folding prediction can aid i...
PromptProtein The official implementation of the ICLR'2023 paper Multi-level Protein Structure Pre-training with Prompt Learning. PromptProtein is an effective method that leverages prompt-guided pre-training and fine-tuning framework to learn multi-level protein sturcture. Overview In this work we pr...
PROMPT: a protein mapping and comparison tool - Schmidt, Frishman - 2006 () Citation Context ...ily to 5 for the H3 family. Gene density values were logarithmized (natural logarithm) as they grow polynominally with increasing isochore family number. Statistical tests were performed using PROMPT...
In the context of protein folding prediction, transformers are used to encode amino acid sequences into embedding vectors that capture the crucial features of the sequence at both the residue and secondary structure levels. These embedding vectors are then injected into pre-trained protein models to ...
p pBackground/p pComparison of large protein datasets has become a standard task in bioinformatics. Typically researchers wish to know whether one group of proteins is significantly enriched in certain annotation attributes or sequence properties compared to another group, and whether this enrichment is...
Deng, J., Gu, M., Zhang, P., Dong, M., Liu, T., Zhang, Y., & Liu, M. (2024). Nanobody–antigen interaction prediction with ensemble deep learning and prompt-based protein language models.Nature Machine Intelligence, 1-11.
Deng, J., Gu, M., Zhang, P., Dong, M., Liu, T., Zhang, Y., & Liu, M. (2024). Nanobody–antigen interaction prediction with ensemble deep learning and prompt-based protein language models. Nature Machine Intelligence, 1-11.
The toolbox contains a set of functions to create and process coarse-grained models of protein conformational motion. The model implemented in the toolbox is described in the following paper: Tamazian, G., Ho Chang, J., Knyazev, S., Stepanov, E., Kim, K. J., & Porozov, Y. (2015...
然而,如何将预训练模型的应用到广泛的的结构和动力学性质预测任务中,仍是一个具有挑战性的问题。在此,我们提出了一种新的方法——“Prompt-Guided Injection of Conformation to Pre-trained protein Model”(PG-ICP),该方法旨在解决上述问题。 背景知识
Multifaceted protein–protein interaction prediction based on Siamese residual RCNN. Bioinformatics 35, i305–i314 (2019). Article Google Scholar Richoux, F. et al. Comparing two deep learning sequence-based models for protein–protein interaction prediction. Preprint at https://doi.org/10.48550/...