Data Inquiries

[byeongchangsim]

@kmboehm Hello Professor, I am Shim Byung-chang, a researcher at the Catholic Medical Center in Korea.

I was impressed by the paper you published in the nature cancer, "Multimal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer".

Our lab wants to apply the cfRNA-seq data of AD patients, related H&E slide images, and CT images to the github code created by the professor.

However, in the code you presented in this process, the csv file named preprocessed_msk_os_h&e_cohort.csv, preprocessed_hne_df is not created or stored.

When I read the code, I think one of the two csf files is created through the connector.py file, but I don't have access to the Dremio used by the professor and the brilliant researchers.

I'm sorry that I couldn't use the code that great professors and researchers created. But I want to apply the code and data that you created without giving up on our research.

If you don't mind, can I get the two csv files I mentioned earlier, or even the slightest hint on how to access DREMIO?

Thank you. ByeongChang

[kmboehm]

Dear Byung-Chang,

Thank you for reaching out and for your interest in our work.

To use the code without Dremio, please use the commit from June 28, 2022 (https://github.com/kmboehm/onco-fusion/tree/ddc61ee9031b77dd27be54afa8126c886007fe72).

Thank you for pointing this out, and please let me know if you have any other issues.

[byeongchangsim]

Hello Dr. Kevin Boehm, I am ByungChang Sim, a researcher at the Catholic Medical Center in Korea.

Thank you so much for your response.

I was conducting the analysis with the git version you mentioned. Still, I cannot make the preprocessed_hne_df.csv entered in the 1_infer_tissue_types_and_extract_features.sh file, so it is difficult to analyze it later.

Is there a part that makes this file into the code in the git, but I'm not finding it? Or I'd like to ask you again if you didn't include it in the git for security reasons.

Thank you. ByeongChang

2024년 4월 19일 (금) 오전 9:17, Kevin Boehm @.***>님이 작성:

Dear Byung-Chang,Thank you for reaching out and for your interest in our work. To use the code without Dremio, please use the commit from June 28, 2022 ( https://github.com/kmboehm/onco-fusion/tree/ddc61ee9031b77dd27be54afa8126c886007fe72). Thank you for pointing this out, and please let me know if you have any other issues. Kevin BoehmOn Apr 18, 2024, at 4:05 PM, byeongchangsim @.***> wrote: @kmboehm Hello Professor, I am Shim Byung-chang, a researcher at the Catholic Medical Center in Korea. I was impressed by the paper you published in the nature cancer, "Multimal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer". Our lab wants to apply the cfRNA-seq data of AD patients, related H&E slide images, and CT images to the github code created by the professor. However, in the code you presented in this process, the csv file named preprocessed_msk_os_h&e_cohort.csv, preprocessed_hne_df is not created or stored. When I read the code, I think one of the two csf files is created through the connector.py file, but I don't have access to the Dremio used by the professor and the brilliant researchers. I'm sorry that I couldn't use the code that great professors and researchers created. But I want to apply the code and data that you created without giving up on our research. If you don't mind, can I get the two csv files I mentioned earlier, or even the slightest hint on how to access DREMIO? Thank you. ByeongChang

—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you were mentioned.Message ID: @.***>

— Reply to this email directly, view it on GitHub https://github.com/kmboehm/onco-fusion/issues/6#issuecomment-2065522062, or unsubscribe https://github.com/notifications/unsubscribe-auth/AS6YL24LFCNF7E63GCHJZNTY6BPBPAVCNFSM6AAAAABGMVE6PGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANRVGUZDEMBWGI . You are receiving this because you authored the thread.Message ID: @.***>

[kmboehm]

Hi ByeongChan, this line invoking preprocess.py in this script produces preprocessed_hne_df.csv: https://github.com/kmboehm/onco-fusion/blob/ddc61ee9031b77dd27be54afa8126c886007fe72/tissue-type-training/cross_validate_on_annotations.sh