Comments (3)
Thanks @rubenalv for the help. I included your instructions in the install instructions of the main README file (commit ba651aa).
I will look into creating a docker image as well.
from pesto.
Hi!
Sorry, I just noticed now that you submitted an issue.
I also noticed a few other people having similar problems with the .yml install.
There are not many dependencies and it shouldn't be too sensitive to the exact version.
The main packages are:
- pytorch (deep learning framework)
- gemmi (for parsing pdb files)
- numpy, scipy, pandas, matplotlib, scikit-learn (the usual tools for numerical analysis)
The optional packages are:
- h5py (storage format for the dataset)
- mdtraj (trajectory files parser)
- tensorboard (visualization toolkit)
The most complicated to install is pytorch. If you want to install it with GPU support, follow the instructions there: https://pytorch.org/
I will push now a new environment file that should be working.
from pesto.
The current .yml file contains a hard-coded path at the end:
prefix: /home/khaos/miniconda3/envs/pesto
Harmless though, see https://stackoverflow.com/questions/41274007/anaconda-export-environment-file.
The current .yml file does not solve the environment for me either, when running
conda env create -f pesto.yml python=3.9
I could create a working conda environment that meets dependencies and runs model.py with:
conda create -n pestocus python=3.9
# python 3.9 to be supported by gemmi
conda activate pestocus
conda install pytorch=2.0.1 pytorch-cuda=11.8 -c pytorch -c nvidia
# pytorch with CUDA support
conda install conda-forge::gemmi
conda install conda-forge::tensorboard
conda install numpy scipy pandas matplotlib scikit-learn conda-forge::tqdm
conda install anaconda::h5py
from pesto.
Related Issues (12)
- interface_ppi_benchmark.ipynb, incorrect paths and missing benchmark data HOT 1
- interface_ppi_profiling_analysis.ipynb, missing
- interface_ppi_confidence.ipynb, missing data and incorrect module calling HOT 6
- PeSTo/md_analysis/data_manager /data_manager.py, "meta" does not exist HOT 2
- Datasets about protien-lipid interactions HOT 1
- AttributeError: module 'numpy' has no attribute 'object' HOT 4
- missing files HOT 1
- Is there a ready-made docker image ? HOT 3
- Question: which prediction file(s) to use HOT 1
- Questions about training
- The longe range context seems to affect local interface prediction scores
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pesto.