VESPAl Prediction of the human proteome (downloaded 22/01/17)

VESPAl Prediction of the human proteome (downloaded 22/01/17) generated with https://github.com/Rostlab/VESPA.

For details on VESPAl see

Marquet, C., Heinzinger, M., Olenyi, T. et al. Embeddings from protein language models predict conservation and variant effects. Hum Genet (2021). https://doi.org/10.1007/s00439-021-02411-y

3 proteins (Q8WZ42,Q8WXI7,Q8NF91) of the human proteome were too long to generate ProtT5 embeddings (Elnaggar et al. 2021). VESPAl predictions are therefore available for 20357 proteins.