Deep learning improves prediction of CRISPR-Cpf1 guide RNA activity

Hui Kwon Kim; Seonwoo Min; Myungjae Song; Soobin Jung; Jae Woo Choi; Younggwang Kim; Sangeun Lee; Sungroh Yoon; Hyongbum Kim

doi:10.1038/nbt.4061

Deep learning improves prediction of CRISPR-Cpf1 guide RNA activity

Hui Kwon Kim
, Seonwoo Min
, Myungjae Song
, Soobin Jung
, Jae Woo Choi
, Younggwang Kim
, Sangeun Lee
, Sungroh Yoon
, Hyongbum Kim

Research output: Contribution to journal › Article › peer-review

283 Scopus citations

Abstract

We present two algorithms to predict the activity of AsCpf1 guide RNAs. Indel frequencies for 15,000 target sequences were used in a deep-learning framework based on a convolutional neural network to train Seq-deepCpf1. We then incorporated chromatin accessibility information to create the better-performing DeepCpf1 algorithm for cell lines for which such information is available and show that both algorithms outperform previous machine learning algorithms on our own and published data sets.

Original language	English
Pages (from-to)	239-241
Number of pages	3
Journal	Nature Biotechnology
Volume	36
Issue number	3
DOIs	https://doi.org/10.1038/nbt.4061
State	Published - 1 Mar 2018
Externally published	Yes

Access to Document

10.1038/nbt.4061

Cite this

@article{4be282d06c8c487eb9f77bb3dbf8cb79,

title = "Deep learning improves prediction of CRISPR-Cpf1 guide RNA activity",

abstract = "We present two algorithms to predict the activity of AsCpf1 guide RNAs. Indel frequencies for 15,000 target sequences were used in a deep-learning framework based on a convolutional neural network to train Seq-deepCpf1. We then incorporated chromatin accessibility information to create the better-performing DeepCpf1 algorithm for cell lines for which such information is available and show that both algorithms outperform previous machine learning algorithms on our own and published data sets.",

author = "Kim, \{Hui Kwon\} and Seonwoo Min and Myungjae Song and Soobin Jung and Choi, \{Jae Woo\} and Younggwang Kim and Sangeun Lee and Sungroh Yoon and Hyongbum Kim",

year = "2018",

month = mar,

day = "1",

doi = "10.1038/nbt.4061",

language = "English",

volume = "36",

pages = "239--241",

journal = "Nature Biotechnology",

issn = "1087-0156",

publisher = "Nature Research",

number = "3",

}

TY - JOUR

T1 - Deep learning improves prediction of CRISPR-Cpf1 guide RNA activity

AU - Kim, Hui Kwon

AU - Min, Seonwoo

AU - Song, Myungjae

AU - Jung, Soobin

AU - Choi, Jae Woo

AU - Kim, Younggwang

AU - Lee, Sangeun

AU - Yoon, Sungroh

AU - Kim, Hyongbum

PY - 2018/3/1

Y1 - 2018/3/1

N2 - We present two algorithms to predict the activity of AsCpf1 guide RNAs. Indel frequencies for 15,000 target sequences were used in a deep-learning framework based on a convolutional neural network to train Seq-deepCpf1. We then incorporated chromatin accessibility information to create the better-performing DeepCpf1 algorithm for cell lines for which such information is available and show that both algorithms outperform previous machine learning algorithms on our own and published data sets.

AB - We present two algorithms to predict the activity of AsCpf1 guide RNAs. Indel frequencies for 15,000 target sequences were used in a deep-learning framework based on a convolutional neural network to train Seq-deepCpf1. We then incorporated chromatin accessibility information to create the better-performing DeepCpf1 algorithm for cell lines for which such information is available and show that both algorithms outperform previous machine learning algorithms on our own and published data sets.

UR - https://www.scopus.com/pages/publications/85042934649

U2 - 10.1038/nbt.4061

DO - 10.1038/nbt.4061

M3 - Article

C2 - 29431740

AN - SCOPUS:85042934649

SN - 1087-0156

VL - 36

SP - 239

EP - 241

JO - Nature Biotechnology

JF - Nature Biotechnology

IS - 3

ER -

Deep learning improves prediction of CRISPR-Cpf1 guide RNA activity

Abstract

Access to Document

Other files and links

Fingerprint

Cite this