Pollock: fishing for cell states

Erik P. Storrs; Daniel Cui Zhou; Michael C. Wendl; Matthew A. Wyczalkowski; Alla Karpova; Liang Bo Wang; Yize Li; Austin Southard-Smith; Reyka G. Jayasinghe; Lijun Yao; Ruiyang Liu; Yige Wu; Nadezhda V. Terekhanova; Houxiang Zhu; John M. Herndon; Sid Puram; Feng Chen; William E. Gillanders; Ryan C. Fields; Li Ding

doi:10.1093/bioadv/vbac028

Pollock: fishing for cell states

Erik P. Storrs, Daniel Cui Zhou, Michael C. Wendl, Matthew A. Wyczalkowski, Alla Karpova, Liang Bo Wang, Yize Li, Austin Southard-Smith, Reyka G. Jayasinghe, Lijun Yao, Ruiyang Liu, Yige Wu, Nadezhda V. Terekhanova, Houxiang Zhu, John M. Herndon, Sid Puram, Feng Chen, William E. Gillanders, Ryan C. Fields, Li Ding

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

1 Scopus citations

Abstract

Motivation: The use of single-cell methods is expanding at an ever-increasing rate. While there are established algorithms that address cell classification, they are limited in terms of cross platform compatibility, reliance on the availability of a reference dataset and classification interpretability. Here, we introduce Pollock, a suite of algorithms for cell type identification that is compatible with popular single-cell methods and analysis platforms, provides a set of pretrained human cancer reference models, and reports interpretability scores that identify the genes that drive cell type classifications. Results: Pollock performs comparably to existing classification methods, while offering easily deployable pretrained classification models across a wide variety of tissue and data types. Additionally, it demonstrates utility in immune pan-cancer analysis.

Original language	English
Article number	vbac028
Journal	Bioinformatics Advances
Volume	2
Issue number	1
DOIs	https://doi.org/10.1093/bioadv/vbac028
State	Published - 2022

Access to Document

10.1093/bioadv/vbac028

Cite this

Storrs, E. P., Zhou, D. C., Wendl, M. C., Wyczalkowski, M. A., Karpova, A., Wang, L. B., Li, Y., Southard-Smith, A., Jayasinghe, R. G., Yao, L., Liu, R., Wu, Y., Terekhanova, N. V., Zhu, H., Herndon, J. M., Puram, S., Chen, F., Gillanders, W. E., Fields, R. C., & Ding, L. (2022). Pollock: fishing for cell states. Bioinformatics Advances, 2(1), Article vbac028. https://doi.org/10.1093/bioadv/vbac028

@article{9378946375cf4328a0d4e1c07df3ffbb,

title = "Pollock: fishing for cell states",

abstract = "Motivation: The use of single-cell methods is expanding at an ever-increasing rate. While there are established algorithms that address cell classification, they are limited in terms of cross platform compatibility, reliance on the availability of a reference dataset and classification interpretability. Here, we introduce Pollock, a suite of algorithms for cell type identification that is compatible with popular single-cell methods and analysis platforms, provides a set of pretrained human cancer reference models, and reports interpretability scores that identify the genes that drive cell type classifications. Results: Pollock performs comparably to existing classification methods, while offering easily deployable pretrained classification models across a wide variety of tissue and data types. Additionally, it demonstrates utility in immune pan-cancer analysis.",

author = "Storrs, {Erik P.} and Zhou, {Daniel Cui} and Wendl, {Michael C.} and Wyczalkowski, {Matthew A.} and Alla Karpova and Wang, {Liang Bo} and Yize Li and Austin Southard-Smith and Jayasinghe, {Reyka G.} and Lijun Yao and Ruiyang Liu and Yige Wu and Terekhanova, {Nadezhda V.} and Houxiang Zhu and Herndon, {John M.} and Sid Puram and Feng Chen and Gillanders, {William E.} and Fields, {Ryan C.} and Li Ding",

note = "Publisher Copyright: {\textcopyright} 2022 The Author(s). Published by Oxford University Press.",

year = "2022",

doi = "10.1093/bioadv/vbac028",

language = "English",

volume = "2",

journal = "Bioinformatics Advances",

issn = "2635-0041",

number = "1",

}

TY - JOUR

T1 - Pollock

T2 - fishing for cell states

AU - Storrs, Erik P.

AU - Zhou, Daniel Cui

AU - Wendl, Michael C.

AU - Wyczalkowski, Matthew A.

AU - Karpova, Alla

AU - Wang, Liang Bo

AU - Li, Yize

AU - Southard-Smith, Austin

AU - Jayasinghe, Reyka G.

AU - Yao, Lijun

AU - Liu, Ruiyang

AU - Wu, Yige

AU - Terekhanova, Nadezhda V.

AU - Zhu, Houxiang

AU - Herndon, John M.

AU - Puram, Sid

AU - Chen, Feng

AU - Gillanders, William E.

AU - Fields, Ryan C.

AU - Ding, Li

PY - 2022

Y1 - 2022

N2 - Motivation: The use of single-cell methods is expanding at an ever-increasing rate. While there are established algorithms that address cell classification, they are limited in terms of cross platform compatibility, reliance on the availability of a reference dataset and classification interpretability. Here, we introduce Pollock, a suite of algorithms for cell type identification that is compatible with popular single-cell methods and analysis platforms, provides a set of pretrained human cancer reference models, and reports interpretability scores that identify the genes that drive cell type classifications. Results: Pollock performs comparably to existing classification methods, while offering easily deployable pretrained classification models across a wide variety of tissue and data types. Additionally, it demonstrates utility in immune pan-cancer analysis.

AB - Motivation: The use of single-cell methods is expanding at an ever-increasing rate. While there are established algorithms that address cell classification, they are limited in terms of cross platform compatibility, reliance on the availability of a reference dataset and classification interpretability. Here, we introduce Pollock, a suite of algorithms for cell type identification that is compatible with popular single-cell methods and analysis platforms, provides a set of pretrained human cancer reference models, and reports interpretability scores that identify the genes that drive cell type classifications. Results: Pollock performs comparably to existing classification methods, while offering easily deployable pretrained classification models across a wide variety of tissue and data types. Additionally, it demonstrates utility in immune pan-cancer analysis.

UR - http://www.scopus.com/inward/record.url?scp=85148567495&partnerID=8YFLogxK

U2 - 10.1093/bioadv/vbac028

DO - 10.1093/bioadv/vbac028

M3 - Article

C2 - 35603231

AN - SCOPUS:85148567495

SN - 2635-0041

VL - 2

JO - Bioinformatics Advances

JF - Bioinformatics Advances

IS - 1

M1 - vbac028

ER -

Pollock: fishing for cell states

Abstract

Access to Document

Other files and links

Fingerprint

Cite this