Skip to content
Contact us
  • There are no suggestions because the search field is empty.

How to run an Epitope Mapping Job

Overview of the steps required to launch the Epitope Mapping job and where to retrieve the results.

How to run an Epitope Mapping job

  • Step 1. On the LensAI™ Home Page, click "Run Analysis"
    LensAI Run Analysis

  • Step 2. Locate the Epitope Mapping analysis and click "Run Job"

  • Step 3. Select the input files from datasets for the binders, the target and the reference binder. The reference binder is optional and can be left empty if no reference binder needs to be analyzed.
    LensAI Epitope Mapping Dataset

Caution: For each input, a single file must be chosen from a dataset, not the dataset itself.

    • Step 3a. For the binders, choose either a .fasta file or a .csv file to represent the binder sequences. The content of the file can represent a single or multiple binders as follows.
      • If the input file is a .fasta file, the headers need to have following formatting:
        • Headers must end with _VH for heavy chains and _VL for light chains.
        • Both chains of the same antibody must share the same base name (e.g., antibody_1_VH and antibody_1_VL sharing antibody_1 as their basename in the example below

          c7479ac2-9539-49b8-a3fc-b634745f49db
      • If the input is a .csv file, the column names need to include
        • protein_name
        • chain_name (VH indicating heavy chain or VL indicating light chain)
        • chain_sequence (the sequence string)

        Each row represents a single chain of a protein. Sequences that share protein_name are taken together as a single (multimeric) protein.

        4970d09b-9c03-45b5-b8b4-a639196e483d
    • Step 3b. For the target, choose either a .fasta file or a .csv file to represent the target sequences. The content of the file can only represent a single target protein as follows.
      • If the input file is a .fasta file, the headers are ignored and all sequences in the file are taken as chains that constitute the (multimeric) target.
      • If the input is a .csv file, the column names need to include
        • protein_name
        • chain_name (VH indicating heavy chain or VL indicating light chain)
        • chain_sequence (the sequence string)

        Each row represents a single chain of a protein. Sequences that share protein_name are taken together as a single (multimeric) protein.

Caution: Since only a single target is allowed, all rows must have the same protein_name. If more than one protein is provided, the pipeline will fail.

    • Step 3c. For the reference binder, choose either a .fasta file or a .csv file to represent its sequences. The content of the file can only represent a single reference binder as follows.
      • If the input file is a .fasta file, the headers are ignored and all sequences in the file are taken as chains that constitute the (multimeric) reference binder.
      • If the input is a .csv file, the column names need to include
        • protein_name
        • chain_name (VH indicating heavy chain or VL indicating light chain)
        • chain_sequence (the sequence string)

        Each row represents a single chain of a protein. Sequences that share protein_name are taken together as a single (multimeric) protein.
         

 

Caution: Since only a single reference binder is allowed. all rows must have the same protein_name. If more than one reference binder is provided, the pipeline will only consider the first one defined in the file.

  • Step 4. Define the output dataset logical name
    dab82212-f301-446b-b925-5e8dd0ef453d

Caution: The name of the output dataset should not contain any space. Underscore is accepted.

  • Step 5. Optionally provide experiment details under the General Run Metadata Inputs
    a93ba125-efe6-4122-845f-6267822c538d
  • Step 6. Click "Run Job" to launch the application
  • Step 7. Monitor the state and the results of the analysis in the "Applications" page under the "History" tab
    LensAI Epitope Mapping Submitted