Skip to main content

Table 1 Computational methods for RBP binding preference prediction

From: Prediction of RNA-protein sequence and structure binding preferences using deep convolutional and recurrent neural networks

Method

Sequence motif

Structure motif

Model

Code

Reference

MEMERIS

Yes

No

Maximum likelihood estimation

http://www.bioinf.uni-freiburg.de/~hiller/MEMERIS/

[2]

BEAM

No

Yes

Simulated annealing

http://beam.uniroma2.it/

[10]

CapR

No

Yes

Turner energy model

https://sites.google.com/site/fukunagatsu/software/capr

[11]

Li et al.

Yes

Yes

Iterative refinement

-

[3]

GraphProt

Yes

Yes

Graph encoding

http://www.bioinf.uni-freiburg.de/Software/GraphProt/

[13]

DeepBind

Yes

No

CNNs

http://tools.genes.toronto.edu/deepbind/

[19]

DeeperBind

Yes

No

CNNs and LSTMs

https://github.com/hassanzadeh/DeeperBind

[23]

RNAcontext

Yes

Yes

probabilistic models

http://www.cs.toronto.edu/~hilal/rnacontext/

[12]

Zeng et al.

Yes

No

CNNs

http://cnn.csail.mit.edu

[24]

iDeep

Yes

No

DBNs and CNNs

https://github.com/xypan1232/iDeep

[28]

iDeepV

No

No

CNNs

https://github.com/xypan1232/iDeepV

[22]

iDeepE

Yes

No

CNNs

https://github.com/xypan1232/iDeepE

[29]

iONMF

Yes

No

matrix factorization

https://github.com/mstrazar/iONMF

[14]

Deepnet-rbp

Yes

Yes

DBNs

https://github.com/thucombio/deepnet-rbp

[21]

DanQ

Yes

No

CNNs and LSTMs

http://github.com/uci-cbcl/DanQ

[27]