CoCoNat

CoCoNat is a novel deep-learning based method for predicting coiled-coil regions, register annotation and oligomenrization state. CoCoNat adopts a sequence encoding based on two state-of-the-art protein language models and a deep-learning architetcure to perform prediction.


Input

From the CoCoNat home page, a single sequence in fasta format can be submitted for coiled-coil analysis by copying the text in the panel or uploading a FASTA file, and pressing the button "Submit". Valid inputs include an ID line starting with a '>' character, followed by the protein sequence, that can have between 40 and 700 valid residues (including the 20 standard amino acids ARNDCQEGHILKMFPSTWYV, non-standard residues UZB, and undetermined residue X).

By default, CoCoNat works in abinitio mode: given an input sequence, it firstly detects the coiled-coil segments and then performs oligomerization state prediction on predicted segments. If you already have coiled-coil segments (either experimentally verified or predicted), you can also run CoCoNat in state prediction mode only, providing the annoatation of available segments along the input sequence. To do so, you need to check the "Provide precomputed coiled-coils segments" flag. By this, a new text area will appear where you can provide your annotation.

The format for the is straightforward, namely a string of the same length of the protein, specifying, for each residue position, one of eigth possibile labels: abcdef for coiled-coils heptad repeat registers, i for non-coiled coils residues.


Output

The results page will display different information. On top, protein ID is shown, as well as buttons to copy the results page (for future access), or download results in TSV or JSON formats. Then a panel reports information about predicted segments in tabular format, including: segment start and end, length, heptad repeat register annotation, pedicted oligomerization state. Clicking on the button of each segment, you can zoom-in on it in the feature viewer (see below). A second panel visualize the predicted coiled-coil segments, registers and oligomerization state along the sequence using an inteactive feature viewer. Three tracks are shown corresponding to coiled-coil segment annotation (coloured by oligomenrization state), corresponding heptad repeat register annotation, and coiled-coil probability. If you hover the mouse over the graphs, the position of the residue will be shown. If you select a rectangular area, you can zoom on a part of the sequence. You can always right click on the graph to reset the zoom back to normal. Alternatively, you can make use of the buttons on the top-right of the viewer to zoom-in, zoom-out, move along the sequence or take a screenshot of the selected area.