Step 1: Upload your SCP data
Dataset format: the first column named ‘Protein’ represents the protein name, while the second column, ‘Peptide’, represents the corresponding constituent peptide sequence. The names of the remaining columns are unlimited, however, preferably please provide numbers of NA if the value is missing.
Click or drag file to this area to upload
Preview your input:
Don't know the file format?
Download Example!Step 2：Choosing the processing method
Step 2.1: Missing value imputation
Since different methods may have different requirements for input data, we provide two data imputation approaches: (i) the missing value ‘NA’ is replaced with ‘0’; and (ii) the Stage1 of scPROTEIN, which processes the data to obtain protein level data.
Fill Missing Values with Zero
Use SCPROTEIN Stage 1 for Processing
Step 2.2: Embedding generation
The processed data in Step 2.1 will be used to generate the embedding using one of the following methods.
SCPROTEIN
MAGIC
KNN-combat
BBKNN
Harmony
AutoClass
Scanorama
Step 3：Set parameters
This is only for using scPROTEIN Stage 1 to impute missing data. If you select ‘Fill Missing Values with Zero’, you can ignore this step.
Step 4: Enter Your Email (Optional)
Leave your email if you want to receive processing results via email