bojarlab / lectinoracle Goto Github PK
View Code? Open in Web Editor NEWDeep learning model to predict interactions between proteins and glycans [LEGACY; use glycowork implementation]
License: MIT License
Deep learning model to predict interactions between proteins and glycans [LEGACY; use glycowork implementation]
License: MIT License
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
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'
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.