search

saws-lab / SAP_H3N2_ML

Seasonal antigenic prediction of influenza A H3N2 using machine learning
GNU General Public License v3.0
1 stars 1 forks source link

could you provide the training and testing data for the model? #6

Open feinianyu0218 opened 2 weeks ago

feinianyu0218 commented 2 weeks ago

such as sequences of virus-antiserum, as well as data on virus affinity and antiserum potency.

saws-lab commented 2 weeks ago

Thank you for reviewing our work and bringing this to our attention. The dataset is included with the published paper here (see Supplementary Data 1). It outlines the specific HI data from the Crick Worldwide Influenza Centre reports and the HA protein sequences from GISAID and IVR. This data can be used to build the training and test sets using the provided source codes. The model further estimates virus avidity and antiserum potency based on name and passage information available in Supplementary Data 1.

feinianyu0218 commented 1 week ago

Thank you for your reply, and I apologize for the previous question. However, when I ran the program using Supplementary Data 1, it indicated that the "nht" metric was missing. I checked Supplementary Data 1, but it doesn't contain the "nht" values either. Could you please provide data that includes the "nht" values?

saws-lab commented 1 week ago

Thank you for bringing this to our attention. The NHT values can be computed using the equation provided in the subsection "Antigenic and Genetic Datasets of IAV H3N2" under the "Methods" section. You can derive these values from the HI titer data found in the Crick reports, as referenced in the "Source" column of Supplementary Data 1. Unfortunately, we are unable to provide the NHT values directly due to restrictions from source data providers.

feinianyu0218 commented 5 days ago

thank you for the response