kelly1210 / deepbind Goto Github PK
View Code? Open in Web Editor NEWThis project forked from kundajelab/deepbind
I have put my modified version of the deepbind code here.
License: BSD 3-Clause "New" or "Revised" License
This project forked from kundajelab/deepbind
I have put my modified version of the deepbind code here.
License: BSD 3-Clause "New" or "Revised" License
DEEPBIND v0.1 ------------- The deepbind command-line executable can be used to score DNA/RNA sequences according to any RBP/TF model listed in the DeepBind web repository: http://tools.genes.toronto.edu/deepbind For each input sequence, the deepbind executable scores each subsequence of a pre-determined length (e.g. 20) and returns only the maximum score over all positions. EXAMPLE ------- To generate predictions with DeepBind, you need two things: 1) a list of model IDs, and 2) a list of DNA/RNA sequences. The file example.ids contains 4 example model IDs, one on each line, reproduced here: D00210.001 # RBFOX1 (RNAcompete) D00120.001 # MBNL1 (RNAcompete) D00410.003 # GATA3 (SELEX) D00328.003 # CTCF (SELEX) The file example.seq contains 4 example sequences, which were chosen such that the nth sequence scores highly for the nth model. The file example.seq is reproduced here: AGGUAAUAAUUUGCAUGAAAUAACUUGGAGAGGAUAGC AGACAGAGCUUCCAUCAGCGCUAGCAGCAGAGACCAUU GAGGTTACGCGGCAAGATAA TACCACTAGGGGGCGCCACC To generate 16 predictions (4 models, 4 sequences), run the deepbind executable as follows: % deepbind example.ids < example.seq D00210.001 D00120.001 D00410.003 D00328.003 7.345649 -0.152710 -0.763340 -0.026180 -0.159393 3.663924 -0.196943 -0.026180 -0.143584 0.357632 5.885349 -0.026180 -0.161033 -0.081444 -0.379695 17.682623 To see details of each ID, use the --dump-info flag: % deepbind --dump-info example.ids ID Protein Type Species Family Class Experiment ... D00210.001 RBFOX1 RBP Homo sapiens RRM RNAcompete ... D00120.001 MBNL1 RBP Homo sapiens Znf RNAcompete ... D00410.003 GATA3 TF Homo sapiens GATA SELEX ... D00328.003 CTCF TF Homo sapiens znfC2H2 SELEX ...
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.