PON-P3 was developed by Muhammad Kabir and Mauno Vihinen. Manuscript describing the method has been submitted. Submitted...
In the meantime, cite the URL of the predictor.
There are two input methods: interactively via a text box or by uploading a file. The platform offers three interfaces for processing data:
Each of these interfaces requires inputs in a specific format, variations have to be described in MANE-compliant references. Results are provided with e-mail in both text and PDF formats.
You can input data via the text box by first entering refseq_ids
followed by a ">" symbol.
There one or several variation_ids
are provided. For uploading a file, the
file must contain
two columns with header names as refseq_ids
and variation_ids
. Please refer to
the format examples below:
>NP_000005.3
V1292F
W436E
>NP_000008.1
Y382W
S412N
Use either the box where transcript varitiations can be pasted or typed or download the example file and make a similar file for submission via a file.
NM_000016.6:c.613G>C
NM_000016.6:c.653C>G
NM_000017.4:c.319C>T
Use either the box where genomic varitiations can be pasted or typed or download the example file and make a similar file for submission via a file.
chr1:g.75745819G>C
chr2:g.47789620T>A
chr3:g.12156789A>G
Datasets were obtained with extensive data mining.
Dataset type | variations | Pathogenic | Benign |
---|---|---|---|
Training dataset | 11567 | 11478 | 23045 |
Blind Test dataset | 2581 | 1246 | 1335 |
Training dataset can be download from here. Download
Blind Test dataset can be download from here. Download
PON-P3 excluded 400 protein IDs for which we do not provide results. These proteins did not have all the necessary data available. Download
All predictions from PON-P3 are available for download in a single file. DownloadIf you have any problems, please contact Muhammad Kabir (muhammad.kabir@med.lu.se) or Prof. Mauno Vihinen (mauno.vihinen@med.lu.se).