tessier-lab-umich / emi_pareto_opt_ml Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
1. Download the anaconda distribution of python from: https://www.anaconda.com/ 2. Open the anaconda command prompt, navigate to where the code for this paper is stored on your computer using: cd PATH\TO\CODE and use the following commands to activate the environment: conda env create -f environment.yml conda activate emi_env 3. The attached folder includes scripts to import data, fit LDA models to binary labeled data, and correlated those models to continuous measurements of sequences. Each model type (onehot, physchem, or unirep) is included as its own script. The physchem and unirep models scripts additionally correlate LDA models with out-of-library sequences. Scripts can be run using any development environment (ex: Spyder, included with anaconda) or by typing python SCRIPTNAME.py into the anaconda command prompt. For example: python onehot_models.py
Dear all, while reading the paper associated to this software, I wondered if the tool would also work for non-human Antibody design? E.g. if we design antibodies for dogs or cats, would the tool turn them more human than dog-like or cat-like? Would the software need retraining? And if so, how many dog-specific mAbs would it need to successfully retrain? Thx in advance.
I wish to implement and test this project. As you have mentioned in the Readme.md
I have tried creating the environment with the command,
conda env create -f environment.yml
But it fails to create an environment, by throwing the following error:
Collecting package metadata (repodata.json): ...working... done
Solving environment: ...working... failed
ResolvePackageNotFound:
- libspatialindex==1.9.3=h33f27b4_0
- win_unicode_console==0.5=py38_0
- blosc==1.20.1=h7bd577a_0
- libtiff==4.1.0=h56a325e_1
- pandocfilters==1.4.3=py38haa95532_1
- zeromq==4.3.2=ha925a31_3
- win_inet_pton==1.1.0=py38_0
- liblief==0.10.1=ha925a31_0
- pycurl==7.43.0.6=py38h7a1dbc1_0
- astropy==4.0.2=py38he774522_0
- libcurl==7.71.1=h2a8f88b_1
- llvmlite==0.34.0=py38h1a82afc_4
- lzo==2.10=he774522_2
- pyodbc==4.0.30=py38ha925a31_0
- scikit-image==0.17.2=py38h1e1f486_0
- pywin32-ctypes==0.2.0=py38_1000
- ujson==4.0.1=py38ha925a31_0
- numpy-base==1.19.2=py38ha3acd2a_0
- pip==20.2.4=py38haa95532_0
- distributed==2.30.1=py38haa95532_0
- matplotlib-base==3.3.2=py38hba9282a_0
- pyqt==5.9.2=py38ha925a31_4
- tornado==6.0.4=py38he774522_1
- msys2-conda-epoch==20160418=1
- hdf5==1.10.4=h7ebc959_0
- msgpack-python==1.0.0=py38h74a9793_1
- pywinpty==0.5.7=py38_0
- m2w64-gcc-libs-core==5.3.0=7
- ipython==7.19.0=py38hd4e2768_0
- krb5==1.18.2=hc04afaa_0
- powershell_shortcut==0.0.1=3
- python==3.8.5=h5fd99cc_1
- sqlalchemy==1.3.20=py38h2bbff1b_0
- numba==0.51.2=py38hf9181ef_1
- cytoolz==0.11.0=py38he774522_0
- pytables==3.6.1=py38ha5be198_0
- icu==58.2=ha925a31_3
- sqlite==3.33.0=h2a8f88b_0
- pillow==8.0.1=py38h4fa10fc_0
- sympy==1.6.2=py38haa95532_1
- gevent==20.9.0=py38he774522_0
- vs2015_runtime==14.16.27012=hf0eaf9b_3
- setuptools==50.3.1=py38haa95532_1
- zope.interface==5.1.2=py38he774522_0
- argon2-cffi==20.1.0=py38he774522_1
- conda-package-handling==1.7.2=py38h76e460a_0
- m2w64-gcc-libs==5.3.0=7
- pandas==1.1.3=py38ha925a31_0
- pynacl==1.4.0=py38h62dcd97_1
- scipy==1.5.2=py38h14eb087_0
- brotlipy==0.7.0=py38he774522_1000
- numexpr==2.7.1=py38h25d0782_0
- libxml2==2.9.10=hb89e7f3_3
- m2w64-gcc-libgfortran==5.3.0=6
- xz==5.2.5=h62dcd97_0
- kiwisolver==1.3.0=py38hd77b12b_0
- bottleneck==1.3.2=py38h2a96729_1
- pywavelets==1.1.1=py38he774522_2
- py-lief==0.10.1=py38ha925a31_0
- pywin32==227=py38he774522_1
- six==1.15.0=py38haa95532_0
- get_terminal_size==1.0.0=h38e98db_0
- qt==5.9.7=vc14h73c81de_0
- psutil==5.7.2=py38he774522_0
- pyyaml==5.3.1=py38he774522_1
- m2w64-libwinpthread-git==5.0.0.4634.697f757=2
- conda==4.10.1=py38haa244fe_0
- ruamel_yaml==0.15.87=py38he774522_1
- libssh2==1.9.0=h7a1dbc1_1
- winpty==0.4.3=4
- xlwings==0.20.8=py38_0
- wincertstore==0.2=py38_0
- vc==14.1=h0510ff6_4
- freetype==2.10.4=hd328e21_0
- mkl_fft==1.2.0=py38h45dec08_0
- fastcache==1.1.0=py38he774522_0
- mkl_random==1.1.1=py38h47e9c7a_0
- yaml==0.2.5=he774522_0
- numpy==1.19.2=py38hadc3359_0
- bitarray==1.6.1=py38h2bbff1b_0
- menuinst==1.4.16=py38he774522_1
- libpng==1.6.37=h2a8f88b_0
- markupsafe==1.1.1=py38he774522_0
- comtypes==1.1.7=py38_1001
- mistune==0.8.4=py38he774522_1000
- pandoc==2.11=h9490d1a_0
- scikit-learn==0.23.2=py38h47e9c7a_0
- zlib==1.2.11=h62dcd97_4
- rtree==0.9.4=py38h21ff451_1
- pyzmq==19.0.2=py38ha925a31_1
- jpeg==9b=hb83a4c4_2
- zstd==1.4.5=h04227a9_0
- lazy-object-proxy==1.4.3=py38he774522_0
- openssl==1.1.1h=he774522_0
- lxml==4.6.1=py38h1350720_0
- lz4-c==1.9.2=hf4a77e7_3
- cffi==1.14.3=py38h7a1dbc1_0
- greenlet==0.4.17=py38he774522_0
- pycosat==0.6.3=py38he774522_0
- libxslt==1.1.34=he774522_0
- mkl-service==2.3.0=py38hb782905_0
- libiconv==1.15=h1df5818_7
- curl==7.71.1=h2a8f88b_1
- pyrsistent==0.17.3=py38he774522_0
- icc_rt==2019.0.0=h0cc432a_1
- bcrypt==3.2.0=py38he774522_0
- console_shortcut==0.1.1=4
- tk==8.6.10=he774522_0
- regex==2020.10.15=py38he774522_0
- m2w64-gmp==6.1.0=2
- cryptography==3.1.1=py38h7a1dbc1_0
- sip==4.19.13=py38ha925a31_0
- libsodium==1.0.18=h62dcd97_0
- statsmodels==0.12.0=py38he774522_0
- pyreadline==2.1=py38_1
- pkginfo==1.6.1=py38haa95532_0
- tifffile==2020.10.1=py38h8c2d366_2
- biopython==1.78=py38h294d835_2
- cython==0.29.21=py38ha925a31_0
- bzip2==1.0.8=he774522_0
- libarchive==3.4.2=h5e25573_0
I went and looked into the content of the environment.yml
file. It had a line
....
....
....
- umap-learn==0.5.1
- wrapt==1.12.1
- xgboost==1.5.0
prefix: C:\Users\makow\anaconda3
I commented on the last line and tried again. But still throws the same error.
I request the creators to provide the correct YAML file, with only necessary packages.
Thankyou.
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.