Unified Model to Predict gRNA Efficiency across Diverse Cell Lines and CRISPR-Cas9 Systems
Computationally predicting the efficiency of a guide RNA (gRNA) from its sequence is crucial to designing the CRISPR-Cas9 system. Currently, machine learning (ML)-based models are widely used for such predictions. However, these ML models often show performance imbalance when applied to multiple data sets from diverse sources, hindering the practical utilization of these tools. To address this issue, we propose a Michaelis-Menten theoretical framework that integrates information from multiple data sets. We demonstrate that the binding free energy can serve as a useful invariant that bridges the data from different experimental setups. Building upon this framework, we develop a new ML model called Uni-deepSG. This model exhibits broad applicability on 27 data sets with different cell types, Cas9 variants, and gRNA designs. Our work confirms the existence of a generalized model for predicting gRNA efficiency and lays the theoretical groundwork necessary to finalize such a model.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:63 |
---|---|
Enthalten in: |
Journal of chemical information and modeling - 63(2023), 23 vom: 11. Dez., Seite 7320-7329 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Zhong, Zhicheng [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 16.12.2023 Date Revised 16.12.2023 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1021/acs.jcim.3c01339 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM364748850 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM364748850 | ||
003 | DE-627 | ||
005 | 20231227133740.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1021/acs.jcim.3c01339 |2 doi | |
028 | 5 | 2 | |a pubmed24n1231.xml |
035 | |a (DE-627)NLM364748850 | ||
035 | |a (NLM)37983481 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Zhong, Zhicheng |e verfasserin |4 aut | |
245 | 1 | 0 | |a Unified Model to Predict gRNA Efficiency across Diverse Cell Lines and CRISPR-Cas9 Systems |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 16.12.2023 | ||
500 | |a Date Revised 16.12.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Computationally predicting the efficiency of a guide RNA (gRNA) from its sequence is crucial to designing the CRISPR-Cas9 system. Currently, machine learning (ML)-based models are widely used for such predictions. However, these ML models often show performance imbalance when applied to multiple data sets from diverse sources, hindering the practical utilization of these tools. To address this issue, we propose a Michaelis-Menten theoretical framework that integrates information from multiple data sets. We demonstrate that the binding free energy can serve as a useful invariant that bridges the data from different experimental setups. Building upon this framework, we develop a new ML model called Uni-deepSG. This model exhibits broad applicability on 27 data sets with different cell types, Cas9 variants, and gRNA designs. Our work confirms the existence of a generalized model for predicting gRNA efficiency and lays the theoretical groundwork necessary to finalize such a model | ||
650 | 4 | |a Journal Article | |
650 | 7 | |a RNA, Guide, CRISPR-Cas Systems |2 NLM | |
700 | 1 | |a Li, Zeying |e verfasserin |4 aut | |
700 | 1 | |a Yang, Jie |e verfasserin |4 aut | |
700 | 1 | |a Wang, Qian |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Journal of chemical information and modeling |d 2005 |g 63(2023), 23 vom: 11. Dez., Seite 7320-7329 |w (DE-627)NLM153268735 |x 1549-960X |7 nnns |
773 | 1 | 8 | |g volume:63 |g year:2023 |g number:23 |g day:11 |g month:12 |g pages:7320-7329 |
856 | 4 | 0 | |u http://dx.doi.org/10.1021/acs.jcim.3c01339 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 63 |j 2023 |e 23 |b 11 |c 12 |h 7320-7329 |