CellMemory: hierarchical interpretation of out-of-distribution cells using bottlenecked transformer

Machine learning methods, especially Transformer architectures, have been widely employed in single-cell omics studies. However, interpretability and accurate representation of out-of-distribution (OOD) cells remains challenging. Inspired by the global workspace theory in cognitive neuroscience, we...

Full description

Saved in:
Bibliographic Details
Published inGenome Biology Vol. 26; no. 1; pp. 178 - 37
Main Authors Wang, Qifei, Zhu, He, Hu, Yiwen, Chen, Yanjie, Wang, Yuwei, Li, Guochao, Li, Yun, Chen, Jinfeng, Zhang, Xuegong, Zou, James, Kellis, Manolis, Li, Yue, Liu, Dianbo, Jiang, Lan
Format Journal Article
LanguageEnglish
Published England BioMed Central 23.06.2025
BMC
Subjects
Accuracy
Annotations
Cell culture
Cells
Consciousness
Datasets
Genes
Humans
Information dissemination
Lung cancer
Machine Learning
Memory
Methodology
Neurosciences
Single-Cell Analysis - methods
Transcriptome
Transcriptomics
Online AccessGet full text
ISSN1474-760X
1474-7596
1474-760X
DOI10.1186/s13059-025-03638-y

Cover

Abstract Machine learning methods, especially Transformer architectures, have been widely employed in single-cell omics studies. However, interpretability and accurate representation of out-of-distribution (OOD) cells remains challenging. Inspired by the global workspace theory in cognitive neuroscience, we introduce CellMemory, a bottlenecked Transformer with improved generalizability designed for the hierarchical interpretation of OOD cells. Without pre-training, CellMemory outperforms existing single-cell foundation models and accurately deciphers spatial transcriptomics at high resolution. Leveraging its robust representations, we further elucidate malignant cells and their founder cells across patients, providing reliable characterizations of the cellular changes caused by the disease.
AbstractList Machine learning methods, especially Transformer architectures, have been widely employed in single-cell omics studies. However, interpretability and accurate representation of out-of-distribution (OOD) cells remains challenging. Inspired by the global workspace theory in cognitive neuroscience, we introduce CellMemory, a bottlenecked Transformer with improved generalizability designed for the hierarchical interpretation of OOD cells. Without pre-training, CellMemory outperforms existing single-cell foundation models and accurately deciphers spatial transcriptomics at high resolution. Leveraging its robust representations, we further elucidate malignant cells and their founder cells across patients, providing reliable characterizations of the cellular changes caused by the disease.
Abstract Machine learning methods, especially Transformer architectures, have been widely employed in single-cell omics studies. However, interpretability and accurate representation of out-of-distribution (OOD) cells remains challenging. Inspired by the global workspace theory in cognitive neuroscience, we introduce CellMemory, a bottlenecked Transformer with improved generalizability designed for the hierarchical interpretation of OOD cells. Without pre-training, CellMemory outperforms existing single-cell foundation models and accurately deciphers spatial transcriptomics at high resolution. Leveraging its robust representations, we further elucidate malignant cells and their founder cells across patients, providing reliable characterizations of the cellular changes caused by the disease.
Machine learning methods, especially Transformer architectures, have been widely employed in single-cell omics studies. However, interpretability and accurate representation of out-of-distribution (OOD) cells remains challenging. Inspired by the global workspace theory in cognitive neuroscience, we introduce CellMemory, a bottlenecked Transformer with improved generalizability designed for the hierarchical interpretation of OOD cells. Without pre-training, CellMemory outperforms existing single-cell foundation models and accurately deciphers spatial transcriptomics at high resolution. Leveraging its robust representations, we further elucidate malignant cells and their founder cells across patients, providing reliable characterizations of the cellular changes caused by the disease.Machine learning methods, especially Transformer architectures, have been widely employed in single-cell omics studies. However, interpretability and accurate representation of out-of-distribution (OOD) cells remains challenging. Inspired by the global workspace theory in cognitive neuroscience, we introduce CellMemory, a bottlenecked Transformer with improved generalizability designed for the hierarchical interpretation of OOD cells. Without pre-training, CellMemory outperforms existing single-cell foundation models and accurately deciphers spatial transcriptomics at high resolution. Leveraging its robust representations, we further elucidate malignant cells and their founder cells across patients, providing reliable characterizations of the cellular changes caused by the disease.
ArticleNumber 178
Author Jiang, Lan
Zhang, Xuegong
Hu, Yiwen
Li, Yun
Zou, James
Liu, Dianbo
Chen, Yanjie
Kellis, Manolis
Zhu, He
Wang, Qifei
Li, Guochao
Chen, Jinfeng
Li, Yue
Wang, Yuwei
Author_xml – sequence: 1
  givenname: Qifei
  surname: Wang
  fullname: Wang, Qifei
– sequence: 2
  givenname: He
  surname: Zhu
  fullname: Zhu, He
– sequence: 3
  givenname: Yiwen
  surname: Hu
  fullname: Hu, Yiwen
– sequence: 4
  givenname: Yanjie
  surname: Chen
  fullname: Chen, Yanjie
– sequence: 5
  givenname: Yuwei
  surname: Wang
  fullname: Wang, Yuwei
– sequence: 6
  givenname: Guochao
  surname: Li
  fullname: Li, Guochao
– sequence: 7
  givenname: Yun
  surname: Li
  fullname: Li, Yun
– sequence: 8
  givenname: Jinfeng
  surname: Chen
  fullname: Chen, Jinfeng
– sequence: 9
  givenname: Xuegong
  surname: Zhang
  fullname: Zhang, Xuegong
– sequence: 10
  givenname: James
  surname: Zou
  fullname: Zou, James
– sequence: 11
  givenname: Manolis
  surname: Kellis
  fullname: Kellis, Manolis
– sequence: 12
  givenname: Yue
  surname: Li
  fullname: Li, Yue
– sequence: 13
  givenname: Dianbo
  surname: Liu
  fullname: Liu, Dianbo
– sequence: 14
  givenname: Lan
  surname: Jiang
  fullname: Jiang, Lan
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40551223$$D View this record in MEDLINE/PubMed
BookMark eNpdkkuLFDEURoOMOA_9Ay6kwI2b0rxT5UaGxsfAiBsFdyGV3HSnrUraJCX0v7e6exxmXOV1cri5-S7RWUwREHpJ8FtCOvmuEIZF32IqWswk69r9E3RBuOKtkvjn2YP5ObosZYsx6TmVz9A5x0IQStkFsisYx68wpbx_32wCZJPtJlgzNiFWyLsM1dSQYpN8k-baJt-6UGoOw3zctsv10swlxHUzpFpHiGB_gWtqNrH4lCfIz9FTb8YCL-7GK_Tj08fvqy_t7bfPN6vr29aKTtR2IJJT5fpOSW487Yizkg3LYqDUU2Vtj00vGe57poyh2DtnhJMUMxAUG8yu0M3J65LZ6l0Ok8l7nUzQx42U19rkGuwIGhMAPyw61yuOgZgOrCV-EEooTkAurg8n124eJnAW4vKg8ZH08UkMG71OfzShpGOdPBje3Bly-j1DqXoK5dAuEyHNRbOl_5JxdkRf_4du05zj0qsDpaTAnHcL9ephSfe1_PvMBaAnwOZUSgZ_jxCsD4nRp8ToJTH6mBi9Z38BVUK1aA
Cites_doi 10.1038/s42256-022-00534-z
10.1038/s42255-022-00657-y
10.1038/s41580-024-00756-6
10.1038/s41467-019-09234-6
10.1038/s41588-021-00911-1
10.1038/s41592-024-02353-z
10.1038/s41587-019-0332-7
10.1101/2024.04.02.587824
10.1126/science.abl4896
10.1038/s42255-023-00876-x
10.1038/s41587-023-01657-3
10.1126/science.aah4573
10.1038/s41467-023-43630-3
10.1038/s41418-018-0202-8
10.1016/j.cell.2019.01.031
10.1038/s41592-018-0229-2
10.1038/s41587-021-01001-7
10.1038/s41467-023-43458-x
10.15252/msb.20209620
10.1038/s41467-022-32052-2
10.1038/s41586-018-0436-0
10.1038/s41590-022-01167-5
10.1038/s41586-022-05208-9
10.1016/j.cell.2021.04.048
10.1038/s41572-019-0063-6
10.1126/science.aaw1219
10.1126/science.abl5197
10.1126/science.1254257
10.1002/qub2.69
10.1016/j.ccell.2023.01.001
10.1002/cam4.4547
10.3892/etm.2021.9736
10.1016/j.cell.2022.04.003
10.1038/nmeth.2764
10.1016/j.ccell.2022.10.008
10.1126/science.ade9516
10.1084/jem.20232028
10.1038/s41586-019-1434-6
10.1038/s41586-022-04918-4
10.1126/science.aau5324
10.1145/3586074
10.1186/s13059-022-02683-1
10.1038/s41593-021-00872-y
10.1038/s41586-023-06252-9
10.1038/s41419-020-2488-y
10.1038/s42255-022-00531-x
10.5281/zenodo.15511926
10.1101/2023.11.28.568918
10.1038/s41592-021-01336-8
10.1182/asheducation-2015.1.225
10.1038/s41467-023-35923-4
10.1016/j.cell.2024.03.010
10.1016/j.cels.2021.05.006
10.1073/pnas.95.24.14529
10.1016/j.xcrm.2024.101489
10.1016/j.devcel.2022.04.016
10.1016/j.cell.2024.03.009
10.1038/s41588-023-01523-7
10.1038/s41588-019-0531-7
10.1038/s41591-023-02327-2
10.1038/35057062
10.1038/s41576-022-00532-2
10.1038/s41586-023-06812-z
10.1038/s41592-024-02201-0
10.1016/j.cell.2018.06.021
10.1038/s41587-022-01483-z
10.1038/s41392-021-00824-9
10.1101/2024.06.30.601119
10.1126/science.adg0934
10.5281/zenodo.15511819
10.1038/s41467-021-26770-2
10.1038/s41586-023-06139-9
10.1038/s41592-023-02035-2
10.1038/s42003-020-01464-5
10.1016/j.celrep.2021.109915
10.1038/s41587-021-00830-w
10.1038/s41592-021-01264-7
10.1038/s41586-023-06837-4
ContentType Journal Article
Copyright 2025. The Author(s).
2025. This work is licensed under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
The Author(s) 2025 2025
Copyright_xml – notice: 2025. The Author(s).
– notice: 2025. This work is licensed under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: The Author(s) 2025 2025
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
3V.
7X7
7XB
88E
8FE
8FH
8FI
8FJ
8FK
ABUWG
AFKRA
AZQEC
BBNVY
BENPR
BHPHI
CCPQU
DWQXO
FYUFA
GHDGH
GNUQQ
HCIFZ
K9.
LK8
M0S
M1P
M7P
PHGZM
PHGZT
PIMPY
PJZUB
PKEHL
PPXIY
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
7X8
5PM
DOA
DOI 10.1186/s13059-025-03638-y
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
ProQuest Central (Corporate)
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Medical Database (Alumni Edition)
ProQuest SciTech Collection
ProQuest Natural Science Collection
ProQuest Hospital Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest Central Essentials
Biological Science Database (Proquest)
ProQuest Central
Natural Science Collection
ProQuest One Community College
ProQuest Central
Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Central Student
SciTech Premium Collection
ProQuest Health & Medical Complete (Alumni)
Biological Sciences
ProQuest Health & Medical Collection
PML(ProQuest Medical Library)
Biological Science Database
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic
ProQuest One Academic UKI Edition
ProQuest Central China
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Publicly Available Content Database
ProQuest Central Student
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest One Health & Nursing
ProQuest Natural Science Collection
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Health & Medical Research Collection
Health Research Premium Collection
Health and Medicine Complete (Alumni Edition)
Natural Science Collection
ProQuest Central Korea
Health & Medical Research Collection
Biological Science Collection
ProQuest Central (New)
ProQuest Medical Library (Alumni)
ProQuest Biological Science Collection
ProQuest One Academic Eastern Edition
ProQuest Hospital Collection
Health Research Premium Collection (Alumni)
Biological Science Database
ProQuest SciTech Collection
ProQuest Hospital Collection (Alumni)
ProQuest Health & Medical Complete
ProQuest Medical Library
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList Publicly Available Content Database

MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Open Access Full Text
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 4
  dbid: BENPR
  name: ProQuest Central
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Biology
EISSN 1474-760X
EndPage 37
ExternalDocumentID oai_doaj_org_article_01eefba96d9740e1a8ecc1fb575741e6
PMC12183866
40551223
10_1186_s13059_025_03638_y
Genre Journal Article
GroupedDBID ---
0R~
29H
4.4
53G
5GY
5VS
7X7
88E
8FE
8FH
8FI
8FJ
AAFWJ
AAHBH
AAJSJ
AASML
AAYXX
ABUWG
ACGFO
ACGFS
ACJQM
ACPRK
ADBBV
ADUKV
AEGXH
AFKRA
AFPKN
AHBYD
AIAGR
ALIPV
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AMTXH
AOIAM
AOIJS
BAPOH
BAWUL
BBNVY
BCNDV
BENPR
BFQNJ
BHPHI
BMC
BPHCQ
BVXVI
C6C
CCPQU
CITATION
EBD
EBLON
EBS
EMOBN
FYUFA
GROUPED_DOAJ
GX1
HCIFZ
HMCUK
IAO
IGS
IHR
ISR
ITC
KPI
LK8
M1P
M7P
PHGZM
PHGZT
PIMPY
PQQKQ
PROAC
PSQYO
ROL
RPM
RSV
SJN
SOJ
SV3
UKHRP
CGR
CUY
CVF
ECM
EIF
NPM
3V.
7XB
8FK
AZQEC
DWQXO
GNUQQ
K9.
PJZUB
PKEHL
PPXIY
PQEST
PQGLB
PQUKI
PRINS
7X8
5PM
PUEGO
ID FETCH-LOGICAL-c585t-b16427d98764af281dc63b764b22f27cc90a96309937aa20fdda5d6203e520a03
IEDL.DBID DOA
ISSN 1474-760X
1474-7596
IngestDate Wed Aug 27 01:27:34 EDT 2025
Thu Aug 21 18:26:34 EDT 2025
Fri Jul 11 17:01:31 EDT 2025
Sat Aug 23 12:29:39 EDT 2025
Fri Jun 27 02:12:28 EDT 2025
Thu Jul 03 08:34:52 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License 2025. The Author(s).
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c585t-b16427d98764af281dc63b764b22f27cc90a96309937aa20fdda5d6203e520a03
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
OpenAccessLink https://doaj.org/article/01eefba96d9740e1a8ecc1fb575741e6
PMID 40551223
PQID 3227650448
PQPubID 2040232
PageCount 37
ParticipantIDs doaj_primary_oai_doaj_org_article_01eefba96d9740e1a8ecc1fb575741e6
pubmedcentral_primary_oai_pubmedcentral_nih_gov_12183866
proquest_miscellaneous_3223634366
proquest_journals_3227650448
pubmed_primary_40551223
crossref_primary_10_1186_s13059_025_03638_y
PublicationCentury 2000
PublicationDate 2025-06-23
PublicationDateYYYYMMDD 2025-06-23
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-06-23
  day: 23
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
– name: London
PublicationTitle Genome Biology
PublicationTitleAlternate Genome Biol
PublicationYear 2025
Publisher BioMed Central
BMC
Publisher_xml – name: BioMed Central
– name: BMC
References 3638_CR36
E Dann (3638_CR58) 2023; 55
3638_CR39
SZ Wu (3638_CR49) 2021; 53
QH Nguyen (3638_CR50) 2028; 2018
3638_CR33
AC Villani (3638_CR57) 2017; 356
F Yang (3638_CR18) 2022; 4
3638_CR100
H Chen (3638_CR42) 2021; 37
RC Jones (3638_CR2) 2022; 376
3638_CR25
3638_CR24
NL Jorstad (3638_CR30) 2023; 382
3638_CR23
3638_CR22
P van Galen (3638_CR63) 2019; 176
C Xu (3638_CR8) 2021; 17
T Kumar (3638_CR31) 2023; 620
S He (3638_CR40) 2022; 40
L Sikkema (3638_CR1) 2023; 29
G Novakovsky (3638_CR10) 2023; 24
3638_CR13
C De Donno (3638_CR6) 2023; 20
3638_CR16
Y Chen (3638_CR61) 2020; 11
3638_CR15
PA Northcott (3638_CR65) 2019; 5
3638_CR19
3638_CR94
3638_CR93
3638_CR96
3638_CR95
K Hrovatin (3638_CR29) 2023; 5
MD Luecken (3638_CR37) 2022; 19
3638_CR97
3638_CR12
3638_CR11
K Liu (3638_CR82) 2024; 187
3638_CR99
Y Chen (3638_CR72) 2022; 13
X Liu (3638_CR81) 2023; 41
RS Negrin (3638_CR62) 2015; 2015
Z Qin (3638_CR83) 2024; 221
Z Wang (3638_CR73) 2021; 12
ES Lander (3638_CR3) 2001; 409
R Sandberg (3638_CR4) 2014; 11
3638_CR85
3638_CR84
TC Lu (3638_CR32) 2023; 380
3638_CR87
3638_CR86
J Dohmen (3638_CR70) 2022; 23
3638_CR89
3638_CR88
JR Moffitt (3638_CR41) 2018; 362
R Lopez (3638_CR38) 2018; 15
3638_CR90
3638_CR92
D van Bruggen (3638_CR53) 2022; 57
V Hovestadt (3638_CR69) 2019; 572
A Janesick (3638_CR48) 2023; 14
S Jessa (3638_CR66) 2019; 51
SG Rodriques (3638_CR47) 2019; 363
Y Deng (3638_CR76) 2024; 5
XL Hao (3638_CR77) 2019; 26
X Liu (3638_CR79) 2020; 3
Z Yao (3638_CR56) 2023; 624
F Klein (3638_CR64) 2022; 23
L Zhang (3638_CR71) 2022; 7
S Dehaene (3638_CR21) 1998; 95
S Salcher (3638_CR34) 2022; 40
JM Granja (3638_CR60) 2019; 37
Y Zhou (3638_CR98) 2019; 10
H Aliee (3638_CR43) 2021; 12
T Biancalani (3638_CR44) 2021; 18
P Zhong (3638_CR51) 2021; 21
Y Hao (3638_CR7) 2021; 184
BJ Baars (3638_CR20) 1997; 4
A Szałata (3638_CR14) 2024; 21
KA Aldinger (3638_CR68) 2021; 24
J Chen (3638_CR26) 2023; 14
AP Patel (3638_CR75) 2014; 344
CV Theodoris (3638_CR17) 2023; 618
M Lotfollahi (3638_CR9) 2022; 40
S Mages (3638_CR46) 2023; 41
M Lotfollahi (3638_CR5) 2024; 187
A Zeisel (3638_CR55) 2018; 174
KS Smith (3638_CR67) 2022; 609
M Nomura (3638_CR80) 2023; 14
J Liang (3638_CR78) 2022; 11
TB Alexander (3638_CR59) 2018; 562
L Steuernagel (3638_CR35) 2022; 4
Q Fournier (3638_CR91) 2021; 55
DM Cable (3638_CR45) 2022; 40
AJC Russell (3638_CR52) 2024; 625
C Domínguez Conde (3638_CR27) 2022; 376
A Chen (3638_CR54) 2022; 185
M Fasolino (3638_CR28) 2022; 4
L Garcia-Alonso (3638_CR74) 2022; 607
References_xml – ident: 3638_CR90
– volume: 4
  start-page: 852
  year: 2022
  ident: 3638_CR18
  publication-title: Nat Mach Intell
  doi: 10.1038/s42256-022-00534-z
– volume: 4
  start-page: 1402
  year: 2022
  ident: 3638_CR35
  publication-title: Nat Metab
  doi: 10.1038/s42255-022-00657-y
– ident: 3638_CR11
  doi: 10.1038/s41580-024-00756-6
– volume: 10
  start-page: 1523
  year: 2019
  ident: 3638_CR98
  publication-title: Nat Commun
  doi: 10.1038/s41467-019-09234-6
– volume: 53
  start-page: 1334
  year: 2021
  ident: 3638_CR49
  publication-title: Nat Genet
  doi: 10.1038/s41588-021-00911-1
– volume: 21
  start-page: 1430
  year: 2024
  ident: 3638_CR14
  publication-title: Nat Methods
  doi: 10.1038/s41592-024-02353-z
– volume: 37
  start-page: 1458
  year: 2019
  ident: 3638_CR60
  publication-title: Nat Biotechnol
  doi: 10.1038/s41587-019-0332-7
– ident: 3638_CR23
– ident: 3638_CR84
  doi: 10.1101/2024.04.02.587824
– volume: 376
  start-page: eabl4896
  year: 2022
  ident: 3638_CR2
  publication-title: Science
  doi: 10.1126/science.abl4896
– volume: 5
  start-page: 1615
  year: 2023
  ident: 3638_CR29
  publication-title: Nat Metab
  doi: 10.1038/s42255-023-00876-x
– volume: 41
  start-page: 1465
  year: 2023
  ident: 3638_CR46
  publication-title: Nat Biotechnol
  doi: 10.1038/s41587-023-01657-3
– ident: 3638_CR89
– volume: 356
  start-page: eaah4573
  year: 2017
  ident: 3638_CR57
  publication-title: Science
  doi: 10.1126/science.aah4573
– volume: 14
  start-page: 8095
  year: 2023
  ident: 3638_CR80
  publication-title: Nat Commun
  doi: 10.1038/s41467-023-43630-3
– ident: 3638_CR12
– volume: 26
  start-page: 1235
  year: 2019
  ident: 3638_CR77
  publication-title: Cell Death Differ
  doi: 10.1038/s41418-018-0202-8
– volume: 176
  start-page: 1265
  year: 2019
  ident: 3638_CR63
  publication-title: Cell
  doi: 10.1016/j.cell.2019.01.031
– ident: 3638_CR95
– volume: 15
  start-page: 1053
  year: 2018
  ident: 3638_CR38
  publication-title: Nat Methods
  doi: 10.1038/s41592-018-0229-2
– volume: 40
  start-page: 121
  year: 2022
  ident: 3638_CR9
  publication-title: Nat Biotechnol
  doi: 10.1038/s41587-021-01001-7
– volume: 14
  start-page: 8353
  year: 2023
  ident: 3638_CR48
  publication-title: Nat Commun
  doi: 10.1038/s41467-023-43458-x
– volume: 17
  start-page: e9620
  year: 2021
  ident: 3638_CR8
  publication-title: Mol Syst Biol
  doi: 10.15252/msb.20209620
– volume: 13
  start-page: 4557
  year: 2022
  ident: 3638_CR72
  publication-title: Nat Commun
  doi: 10.1038/s41467-022-32052-2
– volume: 4
  start-page: 292
  year: 1997
  ident: 3638_CR20
  publication-title: J Conscious Stud
– volume: 562
  start-page: 373
  year: 2018
  ident: 3638_CR59
  publication-title: Nature
  doi: 10.1038/s41586-018-0436-0
– volume: 23
  start-page: 505
  year: 2022
  ident: 3638_CR64
  publication-title: Nat Immunol
  doi: 10.1038/s41590-022-01167-5
– volume: 609
  start-page: 1012
  year: 2022
  ident: 3638_CR67
  publication-title: Nature
  doi: 10.1038/s41586-022-05208-9
– volume: 184
  start-page: 3573
  year: 2021
  ident: 3638_CR7
  publication-title: Cell
  doi: 10.1016/j.cell.2021.04.048
– volume: 5
  start-page: 11
  year: 2019
  ident: 3638_CR65
  publication-title: Nat Rev Dis Primers
  doi: 10.1038/s41572-019-0063-6
– volume: 363
  start-page: 1463
  year: 2019
  ident: 3638_CR47
  publication-title: Science
  doi: 10.1126/science.aaw1219
– volume: 376
  start-page: eabl5197
  year: 2022
  ident: 3638_CR27
  publication-title: Science
  doi: 10.1126/science.abl5197
– volume: 344
  start-page: 1396
  year: 2014
  ident: 3638_CR75
  publication-title: Science
  doi: 10.1126/science.1254257
– ident: 3638_CR15
  doi: 10.1002/qub2.69
– volume: 41
  start-page: 272
  year: 2023
  ident: 3638_CR81
  publication-title: Cancer Cell
  doi: 10.1016/j.ccell.2023.01.001
– volume: 11
  start-page: 2244
  year: 2022
  ident: 3638_CR78
  publication-title: Cancer Med
  doi: 10.1002/cam4.4547
– ident: 3638_CR96
– volume: 21
  start-page: 305
  year: 2021
  ident: 3638_CR51
  publication-title: Exp Ther Med
  doi: 10.3892/etm.2021.9736
– volume: 185
  start-page: 1777
  year: 2022
  ident: 3638_CR54
  publication-title: Cell
  doi: 10.1016/j.cell.2022.04.003
– volume: 11
  start-page: 22
  year: 2014
  ident: 3638_CR4
  publication-title: Nat Methods
  doi: 10.1038/nmeth.2764
– ident: 3638_CR19
– volume: 40
  start-page: 1503
  year: 2022
  ident: 3638_CR34
  publication-title: Cancer Cell
  doi: 10.1016/j.ccell.2022.10.008
– volume: 382
  start-page: eade9516
  year: 2023
  ident: 3638_CR30
  publication-title: Science
  doi: 10.1126/science.ade9516
– volume: 221
  start-page: e20232028
  year: 2024
  ident: 3638_CR83
  publication-title: J Exp Med
  doi: 10.1084/jem.20232028
– volume: 572
  start-page: 74
  year: 2019
  ident: 3638_CR69
  publication-title: Nature
  doi: 10.1038/s41586-019-1434-6
– volume: 607
  start-page: 540
  year: 2022
  ident: 3638_CR74
  publication-title: Nature
  doi: 10.1038/s41586-022-04918-4
– volume: 362
  start-page: eaau5324
  year: 2018
  ident: 3638_CR41
  publication-title: Science
  doi: 10.1126/science.aau5324
– volume: 55
  start-page: 1
  year: 2021
  ident: 3638_CR91
  publication-title: ACM Comput Surveys
  doi: 10.1145/3586074
– volume: 23
  start-page: 123
  year: 2022
  ident: 3638_CR70
  publication-title: Genome Biol
  doi: 10.1186/s13059-022-02683-1
– volume: 2018
  start-page: 9
  year: 2028
  ident: 3638_CR50
  publication-title: Nat Commun
– volume: 24
  start-page: 1163
  year: 2021
  ident: 3638_CR68
  publication-title: Nat Neurosci
  doi: 10.1038/s41593-021-00872-y
– ident: 3638_CR93
– ident: 3638_CR87
– ident: 3638_CR88
– ident: 3638_CR13
– volume: 620
  start-page: 181
  year: 2023
  ident: 3638_CR31
  publication-title: Nature
  doi: 10.1038/s41586-023-06252-9
– volume: 11
  start-page: 291
  year: 2020
  ident: 3638_CR61
  publication-title: Cell Death Dis
  doi: 10.1038/s41419-020-2488-y
– volume: 4
  start-page: 284
  year: 2022
  ident: 3638_CR28
  publication-title: Nat Metab
  doi: 10.1038/s42255-022-00531-x
– ident: 3638_CR36
– ident: 3638_CR94
– ident: 3638_CR100
  doi: 10.5281/zenodo.15511926
– ident: 3638_CR25
  doi: 10.1101/2023.11.28.568918
– volume: 19
  start-page: 41
  year: 2022
  ident: 3638_CR37
  publication-title: Nat Methods
  doi: 10.1038/s41592-021-01336-8
– volume: 2015
  start-page: 225
  year: 2015
  ident: 3638_CR62
  publication-title: Hematol Am Soc Hematol Educ Program
  doi: 10.1182/asheducation-2015.1.225
– ident: 3638_CR33
– volume: 14
  start-page: 223
  year: 2023
  ident: 3638_CR26
  publication-title: Nat Commun
  doi: 10.1038/s41467-023-35923-4
– volume: 187
  start-page: 2428
  year: 2024
  ident: 3638_CR82
  publication-title: Cell
  doi: 10.1016/j.cell.2024.03.010
– volume: 12
  start-page: 706
  year: 2021
  ident: 3638_CR43
  publication-title: Cell Syst
  doi: 10.1016/j.cels.2021.05.006
– volume: 95
  start-page: 14529
  year: 1998
  ident: 3638_CR21
  publication-title: Proc Natl Acad Sci U S A
  doi: 10.1073/pnas.95.24.14529
– volume: 5
  start-page: 101489
  year: 2024
  ident: 3638_CR76
  publication-title: Cell Rep Med
  doi: 10.1016/j.xcrm.2024.101489
– volume: 57
  start-page: 1421
  year: 2022
  ident: 3638_CR53
  publication-title: Dev Cell
  doi: 10.1016/j.devcel.2022.04.016
– ident: 3638_CR22
– volume: 187
  start-page: 2343
  year: 2024
  ident: 3638_CR5
  publication-title: Cell
  doi: 10.1016/j.cell.2024.03.009
– ident: 3638_CR85
– volume: 55
  start-page: 1998
  year: 2023
  ident: 3638_CR58
  publication-title: Nat Genet
  doi: 10.1038/s41588-023-01523-7
– volume: 51
  start-page: 1702
  year: 2019
  ident: 3638_CR66
  publication-title: Nat Genet
  doi: 10.1038/s41588-019-0531-7
– volume: 29
  start-page: 1563
  year: 2023
  ident: 3638_CR1
  publication-title: Nat Med
  doi: 10.1038/s41591-023-02327-2
– volume: 409
  start-page: 860
  year: 2001
  ident: 3638_CR3
  publication-title: Nature
  doi: 10.1038/35057062
– volume: 24
  start-page: 125
  year: 2023
  ident: 3638_CR10
  publication-title: Nat Rev Genet
  doi: 10.1038/s41576-022-00532-2
– ident: 3638_CR92
– volume: 624
  start-page: 317
  year: 2023
  ident: 3638_CR56
  publication-title: Nature
  doi: 10.1038/s41586-023-06812-z
– ident: 3638_CR16
  doi: 10.1038/s41592-024-02201-0
– volume: 174
  start-page: 999
  year: 2018
  ident: 3638_CR55
  publication-title: Cell
  doi: 10.1016/j.cell.2018.06.021
– volume: 40
  start-page: 1794
  year: 2022
  ident: 3638_CR40
  publication-title: Nat Biotechnol
  doi: 10.1038/s41587-022-01483-z
– volume: 7
  start-page: 9
  year: 2022
  ident: 3638_CR71
  publication-title: Signal Transduct Target Ther
  doi: 10.1038/s41392-021-00824-9
– ident: 3638_CR39
  doi: 10.1101/2024.06.30.601119
– volume: 380
  start-page: eadg0934
  year: 2023
  ident: 3638_CR32
  publication-title: Science
  doi: 10.1126/science.adg0934
– ident: 3638_CR86
– ident: 3638_CR99
  doi: 10.5281/zenodo.15511819
– volume: 12
  start-page: 6500
  year: 2021
  ident: 3638_CR73
  publication-title: Nat Commun
  doi: 10.1038/s41467-021-26770-2
– volume: 618
  start-page: 616
  year: 2023
  ident: 3638_CR17
  publication-title: Nature
  doi: 10.1038/s41586-023-06139-9
– ident: 3638_CR97
– volume: 20
  start-page: 1683
  year: 2023
  ident: 3638_CR6
  publication-title: Nat Methods
  doi: 10.1038/s41592-023-02035-2
– volume: 3
  start-page: 728
  year: 2020
  ident: 3638_CR79
  publication-title: Commun Biol
  doi: 10.1038/s42003-020-01464-5
– volume: 37
  start-page: 109915
  year: 2021
  ident: 3638_CR42
  publication-title: Cell Rep
  doi: 10.1016/j.celrep.2021.109915
– volume: 40
  start-page: 517
  year: 2022
  ident: 3638_CR45
  publication-title: Nat Biotechnol
  doi: 10.1038/s41587-021-00830-w
– volume: 18
  start-page: 1352
  year: 2021
  ident: 3638_CR44
  publication-title: Nat Methods
  doi: 10.1038/s41592-021-01264-7
– ident: 3638_CR24
– volume: 625
  start-page: 101
  year: 2024
  ident: 3638_CR52
  publication-title: Nature
  doi: 10.1038/s41586-023-06837-4
SSID ssj0019426
ssj0017866
Score 2.4761412
Snippet Machine learning methods, especially Transformer architectures, have been widely employed in single-cell omics studies. However, interpretability and accurate...
Abstract Machine learning methods, especially Transformer architectures, have been widely employed in single-cell omics studies. However, interpretability and...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
StartPage 178
SubjectTerms Accuracy
Annotations
Cell culture
Cells
Consciousness
Datasets
Genes
Humans
Information dissemination
Lung cancer
Machine Learning
Memory
Methodology
Neurosciences
Single-Cell Analysis - methods
Transcriptome
Transcriptomics
SummonAdditionalLinks – databaseName: Health & Medical Collection
  dbid: 7X7
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3Ni9UwEA-6InhZ1u-6q0TwJmHTpE1TL6KLyyLoyYV3C_nqurC063t9h_ff70yaPq2It7YJZZiv_CaZzBDyTkRZBoAFrHVBscoBhmud5MzZWvLAvdU-ZVt8VxeX1ddVvcobbpucVjn7xOSow-Bxj_wUFK8BNAHRxMfbXwy7RuHpam6hcZ88wNJlGHw1q33AVTYasUp-aSsxXTXCBMS6VfMNGq1ON-DI65ZhZ1c819Rst1ilUjH_fyHQvxMp_1iZzo_IYYaU9NOkA4_Jvdg_IQ-nJpO7p8SfxZubb5hQu_tAsfN1OjsA0dDrRcIhHTo6bEc2dCxgNd3cCIvi1v6GYn78FcW-Y7BMRTD9QMcZ88b1M3J5_uXH2QXLrRWYh_hgZA6iJNGEFnxhZTsBoNUr6eDFCdGJxvuWWzBNjujFWsG7EGwdlOAy1oJbLp-Tg37o40tCY6g6J-vYSIg1ta4B0rXedSIKeNaxLMj7mZXmdqqgYVLkoZWZGG-A8SYx3uwK8hm5vZ-J1a_Th2F9ZbIxGV7G2DkgMEA0xGNpNShi2TmAngCQoirIySwrk01yY34rUEHe7ofBmJCNto_DNs0BMiqp4BcvJtHuKQFkC-BIyILohdAXpC5H-uufqWB3iTgUdPHV_-k6Jo9E0kHFhDwhB-N6G18D5Bndm6TXd9Bk_rw
  priority: 102
  providerName: ProQuest
Title CellMemory: hierarchical interpretation of out-of-distribution cells using bottlenecked transformer
URI https://www.ncbi.nlm.nih.gov/pubmed/40551223
https://www.proquest.com/docview/3227650448
https://www.proquest.com/docview/3223634366
https://pubmed.ncbi.nlm.nih.gov/PMC12183866
https://doaj.org/article/01eefba96d9740e1a8ecc1fb575741e6
Volume 26
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Na9wwEB3ahEIvpUk_4jZZVOitiMiSLcu9dUNCKDSU0MDSi5AsqQ0Eu2S9h_33Hcn2EpdCL70Y2zL2-I2keWONZwDecy9yh7SA1tZJWljkcLUVjFpTCuZYY1SToi2u5OVN8XlVrh6U-ooxYUN64AG4U5Z7H6yppUPmy3xuFD40DxZpBhpDn5Jto82bnKlx_aBGwzP9IqPk6Rpn6rKmsXRrXLhUdDszQylb_98o5p-Rkg9Mz8VzeDZyRvJpkPUAHvn2EJ4MVSS3L6A583d3X2LE7PYjiaWt0-IAYk9uZxGFpAuk2_S0C9TFdLljpSsSv92vSQyA_0FiYTG0Qx7HtiP9RGr9_Uu4uTj_dnZJx9oJtEEHoKcW3SBeuRonu8IEjqy0kcLigeU88KppaoaYChbpiTGcBedM6SRnwpecGSZewV7btf4IiHdFsKL0lUBnUqkSOVvd2MA9x33l8ww-TFDqX0OKDJ1cCyX1ALxG4HUCXm8zWEa0d1fG9NbpBCpdj0rX_1J6BseTrvQ45tYap6YK-Sb6mxm82zXjaIkwmtZ3m3QNilEIibd4Pah2JwlSV2Q_XGSgZkqfiTpvaW9_pozceSSaSso3_-Pl3sJTnnqqpFwcw15_v_EnyHx6u4DH1apawP7y_Orr9SJ1edxeL7__BoMaBwk
linkProvider Directory of Open Access Journals
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Nb9QwEB2VIgQXxDcpBYwEJ2TVsRPHQUIICtWWfpxaaW8mjp1SqUra3axQ_hS_kbGTLAQhbr0lcRSNxs-eN_HYD-A1dyK2SAtobqykiUEOlxvBqClSwSwrC1WGaotjOTtNvs7T-Qb8HPfC-LLKcU4ME7VtSv-PfAeBlyGbwGziw-UV9apRfnV1lNDoYXHguh-Ysi3f73_G_n3D-d6Xk90ZHVQFaInUuKUGEwSeWcy1ZVJUHPlaKYXBG8N5xbOyzFmBqGQ-cBcFZ5W1RWolZ8KlnBVM4HdvwE0MvMyXEGbzdYIXZ8pzo-EmT3i_tckXPKa5HHfsKLmzxMCR5tQryfp1VEW7SVQM4gH_Yrx_F27-EQn37sHdgcKSjz3m7sOGqx_ArV7UsnsI5a67uDjyBbzdO-KVtsNaBUKBnE8KHElTkWbV0qai1p_eOwhvEb-UsCS-Hv-MeJ0zDIsOpxpL2pFju8UjOL0Wpz-Gzbqp3VMgziaVEanLBOa2SqVIIfPSVNxxvFYujuDt6Ep92Z_YoUOmo6TuHa_R8To4XncRfPLeXr_pT9sOD5rFmR4Gr2axc5VBAy1mX8zFhULgx5VBqouEzMkItse-0sMUsNS_ARvBq3UzDl7vxqJ2zSq8g2YkQuInnvRdu7YEmTSSMS4iUJNOn5g6banPv4cDwmPPexGLW_-36yXcnp0cHerD_eODZ3CHBzxKysU2bLaLlXuOdKs1LwLGCXy77kH1C315Ojw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=CellMemory%3A+hierarchical+interpretation+of+out-of-distribution+cells+using+bottlenecked+transformer&rft.jtitle=Genome+biology&rft.au=Qifei+Wang&rft.au=He+Zhu&rft.au=Yiwen+Hu&rft.au=Yanjie+Chen&rft.date=2025-06-23&rft.pub=BMC&rft.eissn=1474-760X&rft.volume=26&rft.issue=1&rft.spage=1&rft.epage=37&rft_id=info:doi/10.1186%2Fs13059-025-03638-y&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_01eefba96d9740e1a8ecc1fb575741e6
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1474-760X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1474-760X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1474-760X&client=summon