Skip to main content

Table 1 The main ideas of ANMDA and 6 published methods

From: AttCRISPR: a spacetime interpretable model for prediction of sgRNA on-target activity

Method

Neural

End2end

Description

CNN*

Yes

Yes

Naive CNN

RNN*

Yes

Yes

Bidirectional long short-term memory neural network

XGBoost*

No

Yes

Extreme Gradient Boosting regression tree

MLP*

Yes

Yes

Multilayer perceptron

DeepHF*

Yes

No

Bidirectional long short-term memory neural network (with hand-crafted biological features)

CRISPRpred#

No

No

A conventional machine learning pipeline

SpAC

Yes

Yes

Spatial AttCRISPR

TAC

Yes

Yes

Temporal AttCRISPR

EnAC

Yes

Yes

Ensemble AttCRISPR (without hand-crafted biological features)

StAC

Yes

No

Standard AttCRISPR

  1. The method with superscript of * and # have been reported respectively [15, 17]. Especially, CRISPRpred takes another set of hand-crafted sequence-based features to improve performance