ADpred

Prediction of acidic transcription activation domains (ADs) from protein sequence

What is ADpred?

ADpred is a deep learning model to predict acidic transcription activation domains (ADs) within protein sequences. It has been described in Erijman et al. from the Hahn lab and the Söding lab

How does ADpred webserver work?

A protein sequence OR protein ID can be provided. The protein ID is used to retrieve the sequence from uniprot, hence, make sure that your ID is unique and does not expand to different organisms. The secondary structure is retrieved from the psipred webserver and both sequence and secondary structure are the input of ADpred. ADpred uses a convolutional deep neural network to predict the probability of peptides having potential AD function. The practical length limits for ADs identified by ADpred is between ≥9 to ≤30 residues. We typically look for ADpred scores of ≥0.8 over ≥10-15 continuous residues as indicating a high propensity for AD function. However, we have found that not all peptides with potential AD function are in the proper protein context to work as transcription activators. See Erijman et al for details.

Once the results are ready, you should receive an email with a link to a file with the results.

Hint: If providing a protein ID, try to be specific (<Name>_<Specie>). Otherwise we will guess the ID from your input.
For protein sequences longer than 1500 amino-acids, please consider chopping it into smaller parts (domains or structural groups) or download adpred tool and use a local installation of psipred.

Local installation of ADpred

With a local installation of ADpred you can compute AD probabilities on a list of proteins. You can also compute in silico saturated mutagenesis for all fragments of interest.


Question or comments to: aerijman@neb.com or aerijman@fredhutch.org





Your job has been submitted!

Feel free to close this page, the results will be sent to you by email.
In case you can't find our email, check your junk mail!