frankligy / deepimmuno Goto Github PK
View Code? Open in Web Editor NEWDeep-learning empowered prediction and generation of immunogenic epitopes for T cell immunity
License: MIT License
Deep-learning empowered prediction and generation of immunogenic epitopes for T cell immunity
License: MIT License
Hello,
DeepImmuno might just be what I am looking for!
Unfortunately, I cannot clone the project without error, because some file names contain special characters:
new_imgt_scraping/new_imgt/new_imgt/spiders/hla_paratope/HLA-C*0102.json
I am having issues to download the hla_paratope json files because they have an "*" in the file name.
How important are these Files in order to run the code?
If they are really important would it be a possibility to change the file names so that they dont contain any special characters?
Best regards and thank you for sharing!
Hi, thank you for your great job!
But I have a question about the number of indices missing values for certain amino acids.
According to your description in the paper, there are 13 discarded indices, as below. However, when I check the source file of aaindex1, it seems that some missing values were filled by zero but not filled by "NA", such as ”H KOEP990101“, ”H ZASB820101“ and so on, which confuses me.
hi~
running deepimmuno-cnn on mode "multiple" returns this error:
UnboundLocalError: local variable 'encode' referenced before assignment
which can be traced back to line 156 of deepimmuno-cnn.py
when running peptide_data_aaindex
- specifically when running:
encode_pep = peptide_data_aaindex(peptide,after_pca)
replacing the function peptide_data_aaindex
in place solved the issue for me - so instead of running the line above I run instead:
# encode_pep = peptide_data_aaindex(peptide,after_pca) # [10,12]
length = len(peptide)
if length == 10:
encode = aaindex(peptide,after_pca)
elif length == 9:
peptide = peptide[:5] + '-' + peptide[5:]
encode = aaindex(peptide,after_pca)
encode = encode.reshape(encode.shape[0], encode.shape[1], -1)
encode_pep = encode
not sure whether anyone else can replicate this error, but am raising the issue in case this is actually a bug.
thanks for building this tool!
cheers,
Leda
Dear users,
It has been brought to my attention that there's a typo in my paper supplementary regarding the beta prior, so in the supplementary, it said:
But actually, Beta(32,1)
is used for positive-high, Beta(30,1)
is used for positive-intermediate and positive, it can be seen from the code:
https://github.com/frankligy/DeepImmuno/blob/main/src/immuno3_3.py#L17-L43
def assign_prior(label):
if label == 'Positive-High':
return (32,1) # beta(15,1) mean=0.93, std = 0.05
elif label == 'Positive' or label == 'Positive-Intermediate':
return (30,1) # beta(10,1) mean = 0.90 std = 0.08
elif label == 'Positive-Low':
return (28,1) # beta(5,1) mean = 0.83, std = 0.14
elif label == 'Negative':
return (3,3) # beta(3,4) mean = 0.42, std = 0.17
I apologize for any confusion caused by that, and please feel free to reach out for any questions!
Sincerely,
Frank
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.