search

WangX-Lab / PreMSIm

6 stars 2 forks source link

input data type and result interpretation #3

Open zyh4482 opened 2 years ago

zyh4482 commented 2 years ago

I have two questions.

  1. I notice that you input data is log2(RSEM+1) transformed and scale to [0,1]. May I ask how to scale the data? BTW, RSEM seems to be the only normalization method for PreMSIm input. Can I change it to FPKM or TPM?
  2. The example output shows 0 or 1. May I ask what kind of MSI status do 0 and 1 refer to? Do you mind adding it in your README in the next update. Thanks
zyh4482 commented 2 years ago

I see, "scale" here means calculate the respective Z-score?

WangX-Lab commented 2 years ago

Hello!

Thank you for your interest in our tool. I am happy to answer your questions.

  1. You can use the function data_pre() to scale the data before prediction. For input data, we recommend the users using RPKM/FPKM/TPM/RSEM normalized values, RSEM is not the only normalization method for PreMSIm input.

  2. "1" indicates MSI-high, and "0" indicates MSI-low/microsatellite stability. The related interpretation is given in the help documentation of function msi_pre().

  3. The "scale" here means the "min-max scaling" normalization method.

With the best regards,

Xiaosheng Wang, MD, PhD

China Pharmaceutical University

发件人: @. @.> 代表 zyh4482 发送时间: Sunday, October 24, 2021 3:49 PM 收件人: WangX-Lab/PreMSIm @.> 抄送: Subscribed @.> 主题: [WangX-Lab/PreMSIm] input data type and result interpretation (Issue #3)

I have two questions.

  1. I notice that you input data is log2(RSEM+1) transformed and scale to [0,1]. May I ask how to scale the data? BTW, RSEM seems to be the only normalization method for PreMSIm input. Can I change it to FPKM or TPM?
  2. The example output shows 0 or 1. May I ask what kind of MSI status do 0 and 1 refer to? Do you mind adding it in your README in the next update.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/WangX-Lab/PreMSIm/issues/3 , or unsubscribe https://github.com/notifications/unsubscribe-auth/ANDDKVE4HDHO5YLBCGXTLN3UIO3ARANCNFSM5GTFAA7A . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub .