The lectinoracle from bojarlab

documentation for applying to to a new protein

Dear LectinOracle,

Thank you for your software

I would like to apply your method to a new protein I have been asked to look into. Would it be possible for more indepth how to guide? I see in you .ipynb there is a section "Legacy: Getting ESM-1b representations for new lectins"

Would this section apply to a new protein? If so, what would be the input file and format for a new protein? Which line of code could I alter to input my new protein of interest?

Regards,

Pete

Error: glycan_to_graph() got an unexpected keyword argument 'libr'

When running the cell below, I got the error regarding the use of glycan_tograph(k, libr = lib). I checked the glycowork code and saw that libr = lib is as the default argument. The code cell runs successfully when no second argument is given, such that glycan_to_graph(k) is all that there is but I later got errors that were confusing and I would like to discuss on a different issue thread once this is resolved as to make sure that this 'fix' isn't causing later errors.

#split into train/validation sets
train2 = pd.DataFrame(train, columns = ['seq', 'glycan', 'match'])
val2 = pd.DataFrame(val, columns = ['seq', 'glycan', 'match'])
#the extension of lib was done for unrelated downstream analyses and is needed to use the trained LectinOracle file but does not need to be there if you train a new LectinOracle model
lib = get_lib(list(set(train2.glycan.values.tolist()+val2.glycan.values.tolist()))) + ['GlcNAcOS', 'GalOS', 'HexNAc']
X_train = list(zip(train2.seq.values.tolist(), [glycan_to_graph(k, libr = lib) for k in train2.glycan.values.tolist()]))
y_train = train2.match.values.tolist()
X_val = list(zip(val2.seq.values.tolist(), [glycan_to_graph(k, libr = lib) for k in val2.glycan.values.tolist()]))
y_val = val2.match.values.tolist()

TypeError                                 Traceback (most recent call last)
[<ipython-input-42-9c6f3b4eef97>](https://localhost:8080/#) in <module>()
      4 #the extension of lib was done for unrelated downstream analyses and is needed to use the trained LectinOracle file but does not need to be there if you train a new LectinOracle model
      5 lib = get_lib(list(set(train2.glycan.values.tolist()+val2.glycan.values.tolist()))) + ['GlcNAcOS', 'GalOS', 'HexNAc']
----> 6 X_train = list(zip(train2.seq.values.tolist(), [glycan_to_graph(k, libr = lib) for k in train2.glycan.values.tolist()]))
      7 #X_train = list(zip(train2.seq.values.tolist(), [glycan_to_graph(k) for k in train2.glycan.values.tolist()]))
      8 y_train = train2.match.values.tolist()

[<ipython-input-42-9c6f3b4eef97>](https://localhost:8080/#) in <listcomp>(.0)
      4 #the extension of lib was done for unrelated downstream analyses and is needed to use the trained LectinOracle file but does not need to be there if you train a new LectinOracle model
      5 lib = get_lib(list(set(train2.glycan.values.tolist()+val2.glycan.values.tolist()))) + ['GlcNAcOS', 'GalOS', 'HexNAc']
----> 6 X_train = list(zip(train2.seq.values.tolist(), [glycan_to_graph(k, libr = lib) for k in train2.glycan.values.tolist()]))
      7 #X_train = list(zip(train2.seq.values.tolist(), [glycan_to_graph(k) for k in train2.glycan.values.tolist()]))
      8 y_train = train2.match.values.tolist()

TypeError: glycan_to_graph() got an unexpected keyword argument 'libr'

bojarlab / lectinoracle Goto Github PK

lectinoracle's People

Contributors

Stargazers

Watchers

Forkers

lectinoracle's Issues

documentation for applying to to a new protein

Error: glycan_to_graph() got an unexpected keyword argument 'libr'

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent