xiaoqiongxia / dleps Goto Github PK
View Code? Open in Web Editor NEWThis project forked from kekegg/dleps
A Deep Learning based Efficacy Prediction System for drug discovery
This project forked from kekegg/dleps
A Deep Learning based Efficacy Prediction System for drug discovery
# DLEPS A Deep Learning based Efficacy Prediction System for Drug Discovery # Setup - ## Install package This package requires the **rdkit**, **tensorflow >=1.15.0** and **Keras >=2.3.0**. conda install -c rdkit rdkit apt-get update apt install libxrender1 apt install libxext6 pip install nltk pip install tensorflow==1.15.0 pip install keras==2.3.0 - ## On Code ocean The supporting files and sample input files for the model locates in the data folder. Results were saved in results folder. # Run the model - **Script options** input files 1. The csv file with all the chemical SMILES in the column with string SMILES as the header, other columns will be copied to the output file and an efficacy score column will be appended. 2. The upregulated gene signatures using ENTREZGENE_ACC in a file without header, each gene occupy a row 3. The downregulated gene signatures using the same format Conversion of gene names can be accomplished at https://biit.cs.ut.ee/gprofiler/convert A sample command is as followed: python driv_DLEPS.py --input=../../data/Brief_Targetmol_natural_product_2719 --output=../../results/np2719_Browning.csv --upset=../../data/BROWNING_up --downset=../../data/BROWNING_down --reverse=False Batch jobs were put into run_script Other options include: '--input', default=INPUTFILE, 'Brief format of chemicals: contains SMILES column. ' '--use_onehot', default=True, 'If use pre-stored one hot array to save time.' '--use_l12k', default=None, 'Use pre-calculated L12k' '--upset', default=None, 'Up set of genes' '--downset', default=None, 'Down set of genes. ' '--reverse', default=True, 'If the drug Reverse the Up / Down set of genes. ' '--output', default='out.csv', 'Output file name. ' Jupyter notebook users may run DLEPS_tutorial.ipynb for better iterative computing and analysis.
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.