Anomaly detection for high-content image-based phenotypic cell profiling
High-content image-based phenotypic profiling combines automated microscopy and analysis to identify phenotypic alterations in cell morphology and provide insight into the cell's physiological state. Classical representations of the phenotypic profile can not capture the full underlying complex...
Uložené v:
| Vydané v: | bioRxiv |
|---|---|
| Hlavní autori: | , , , , |
| Médium: | Journal Article Paper |
| Jazyk: | English |
| Vydavateľské údaje: |
United States
Cold Spring Harbor Laboratory
03.06.2024
|
| Vydanie: | 1.1 |
| Predmet: | |
| ISSN: | 2692-8205, 2692-8205 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | High-content image-based phenotypic profiling combines automated microscopy and analysis to identify phenotypic alterations in cell morphology and provide insight into the cell's physiological state. Classical representations of the phenotypic profile can not capture the full underlying complexity in cell organization, while recent weakly machine-learning based representation-learning methods are hard to biologically interpret. We used the abundance of control wells to learn the in-distribution of control experiments and use it to formulate a self-supervised reconstruction anomaly-based representation that encodes the intricate morphological inter-feature dependencies while preserving the representation interpretability. The performance of our anomaly-based representations was evaluated for downstream tasks with respect to two classical representations across four public Cell Painting datasets. Anomaly-based representations improved reproducibility, Mechanism of Action classification, and complemented classical representations. Unsupervised explainability of autoencoder-based anomalies identified specific inter-feature dependencies causing anomalies. The general concept of anomaly-based representations can be adapted to other applications in cell biology. |
|---|---|
| AbstractList | High-content image-based phenotypic profiling combines automated microscopy and analysis to identify phenotypic alterations in cell morphology and provide insight into the cell's physiological state. Classical representations of the phenotypic profile can not capture the full underlying complexity in cell organization, while recent weakly machine-learning based representation-learning methods are hard to biologically interpret. We used the abundance of control wells to learn the in-distribution of control experiments and use it to formulate a self-supervised reconstruction anomaly-based representation that encodes the intricate morphological inter-feature dependencies while preserving the representation interpretability. The performance of our anomaly-based representations was evaluated for downstream tasks with respect to two classical representations across four public Cell Painting datasets. Anomaly-based representations improved reproducibility, Mechanism of Action classification, and complemented classical representations. Unsupervised explainability of autoencoder-based anomalies identified specific inter-feature dependencies causing anomalies. The general concept of anomaly-based representations can be adapted to other applications in cell biology.High-content image-based phenotypic profiling combines automated microscopy and analysis to identify phenotypic alterations in cell morphology and provide insight into the cell's physiological state. Classical representations of the phenotypic profile can not capture the full underlying complexity in cell organization, while recent weakly machine-learning based representation-learning methods are hard to biologically interpret. We used the abundance of control wells to learn the in-distribution of control experiments and use it to formulate a self-supervised reconstruction anomaly-based representation that encodes the intricate morphological inter-feature dependencies while preserving the representation interpretability. The performance of our anomaly-based representations was evaluated for downstream tasks with respect to two classical representations across four public Cell Painting datasets. Anomaly-based representations improved reproducibility, Mechanism of Action classification, and complemented classical representations. Unsupervised explainability of autoencoder-based anomalies identified specific inter-feature dependencies causing anomalies. The general concept of anomaly-based representations can be adapted to other applications in cell biology. High-content image-based phenotypic profiling combines automated microscopy and analysis to identify phenotypic alterations in cell morphology and provide insight into the cell’s physiological state. Classical representations of the phenotypic profile can not capture the full underlying complexity in cell organization, while recent weakly machine-learning based representation-learning methods are hard to biologically interpret. We used the abundance of control wells to learn the in-distribution of control experiments and use it to formulate a self-supervised reconstruction anomaly-based representation that encodes the intricate morphological inter-feature dependencies while preserving the representation interpretability. The performance of our anomaly-based representations was evaluated for downstream tasks with respect to two classical representations across four public Cell Painting datasets. Anomaly-based representations improved reproducibility, Mechanism of Action classification, and complemented classical representations. Unsupervised explainability of autoencoder-based anomalies identified specific inter-feature dependencies causing anomalies. The general concept of anomaly-based representations can be adapted to other applications in cell biology. |
| Author | Weisbart, Erin Golan, Shahar Kolet, Naor Shpigler, Alon Zaritsky, Assaf |
| Author_xml | – sequence: 1 givenname: Alon surname: Shpigler fullname: Shpigler, Alon organization: Department of Software and Information Systems Engineering, Ben-Gurion University of the Negev, Beer-Sheva 84105, Israel – sequence: 2 givenname: Naor surname: Kolet fullname: Kolet, Naor organization: Department of Software and Information Systems Engineering, Ben-Gurion University of the Negev, Beer-Sheva 84105, Israel – sequence: 3 givenname: Shahar surname: Golan fullname: Golan, Shahar organization: Department of Computer Science, Jerusalem College of Technology, 91160 Jerusalem, Israel – sequence: 4 givenname: Erin surname: Weisbart fullname: Weisbart, Erin organization: Imaging Platform, Broad Institute of MIT and Harvard, Cambridge (MA), USA – sequence: 5 givenname: Assaf orcidid: 0000-0002-1477-5478 surname: Zaritsky fullname: Zaritsky, Assaf organization: Department of Software and Information Systems Engineering, Ben-Gurion University of the Negev, Beer-Sheva 84105, Israel |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38895267$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkMtOwzAQRS1UREvpB7BBWbJJGNuxYy-rilKkSmxgHTm20xoldkhSRP-eRC2P1YxGR1dn7jWa-OAtQrcYEowBPxAgaQI8AZwwyQTjF2hGuCSxIMAm__YpWnTdOwAQyTHN0is0pUJIRng2Q5ulD7WqjpGxvdW9Cz4qQxvt3W4f6-B76_vI1Wpn40J11kTN3vrQHxunI22rKmraULrK-d0NuixV1dnFec7R2_rxdbWJty9Pz6vlNi6wEDzOTEmoZloSri01mRI4lWyUM4VmIsu4MqJUDGtpBoYPrwrOx1NJmE0VnaP7U27hQvvlPvOmHfzaYz72kQPPAeenPv7QQfLjYLs-r103Witvw6HLKWQggEIqB_TujB6K2prf0J-i6DeKkGra |
| ContentType | Journal Article Paper |
| Copyright | 2024, Posted by Cold Spring Harbor Laboratory |
| Copyright_xml | – notice: 2024, Posted by Cold Spring Harbor Laboratory |
| DBID | NPM 7X8 FX. |
| DOI | 10.1101/2024.06.01.595856 |
| DatabaseName | PubMed MEDLINE - Academic bioRxiv |
| DatabaseTitle | PubMed MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Biology |
| EISSN | 2692-8205 |
| Edition | 1.1 |
| ExternalDocumentID | 2024.06.01.595856v1 38895267 |
| Genre | Journal Article Preprint |
| GrantInformation_xml | – fundername: NIGMS NIH HHS grantid: P41 GM135019 – fundername: Wellcome Trust |
| GroupedDBID | 8FE 8FH AFFHD AFKRA ALMA_UNASSIGNED_HOLDINGS BBNVY BENPR BHPHI CCPQU HCIFZ LK8 M7P NPM NQS PHGZM PHGZT PIMPY PQGLB PROAC RHI 7X8 PUEGO FX. |
| ID | FETCH-LOGICAL-b1886-7df23c5c926ce3d7a814950002dbc58776ad8fa51c9d9266110866d8faf25e4a3 |
| ISSN | 2692-8205 |
| IngestDate | Tue Jan 07 18:57:20 EST 2025 Thu Sep 04 17:30:09 EDT 2025 Sat Nov 22 01:41:03 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| License | This pre-print is available under a Creative Commons License (Attribution-NonCommercial 4.0 International), CC BY-NC 4.0, as described at http://creativecommons.org/licenses/by-nc/4.0 |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-b1886-7df23c5c926ce3d7a814950002dbc58776ad8fa51c9d9266110866d8faf25e4a3 |
| Notes | ObjectType-Working Paper/Pre-Print-3 ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 Competing Interest Statement: The authors have declared no competing interest. |
| ORCID | 0000-0002-1477-5478 |
| OpenAccessLink | https://www.biorxiv.org/content/10.1101/2024.06.01.595856 |
| PMID | 38895267 |
| PQID | 3070803049 |
| PQPubID | 23479 |
| PageCount | 35 |
| ParticipantIDs | biorxiv_primary_2024_06_01_595856 proquest_miscellaneous_3070803049 pubmed_primary_38895267 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-Jun-03 20240603 |
| PublicationDateYYYYMMDD | 2024-06-03 |
| PublicationDate_xml | – month: 06 year: 2024 text: 2024-Jun-03 day: 03 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | bioRxiv |
| PublicationTitleAlternate | bioRxiv |
| PublicationYear | 2024 |
| Publisher | Cold Spring Harbor Laboratory |
| Publisher_xml | – name: Cold Spring Harbor Laboratory |
| References | 41167192 - Cell Syst. 2025 Nov 19;16(11):101429. doi: 10.1016/j.cels.2025.101429. Way, Kost-Alimova, Shibue, Harrington, Gill, Piccioni, Becker, Shafqat-Abbasi, Hahn, Carpenter (2024.06.01.595856v1.51) 2021; 32 Kobayashi, Cheveralls, Leonetti, Royer (2024.06.01.595856v1.26) 2022; 19 Cohen, Valm, Lippincott-Schwartz (2024.06.01.595856v1.9) 2018; 53 Zaritsky, Tseng, Angeles Rabadán, Krishna, Overholtzer, Danuser, Hall (2024.06.01.595856v1.12) 2017; 216 Yang, Zhou, Li, Liu (2024.06.01.595856v1.42) 2021; 2110 Grys, Lo, Sahin, Kraus, Morris, Boone, Andrews (2024.06.01.595856v1.15) 2017; 216 Wu, Gilkes, Phillip, Narkar, Cheng, Marchand, Lee, Li, Wirtz (2024.06.01.595856v1.3) 2020; 6 Shai, Yifrach, van Roermund, Cohen, Bibi, IJlst, Cavellini, Meurisse, Schuster, Zada (2024.06.01.595856v1.7) 2018; 9 Ruff, Kauffmann, Vandermeulen, Montavon, Samek, Kloft, Dietterich, Müller (2024.06.01.595856v1.43) 2021; 109 van Dijk, Arevalo, Babadi, Carpenter, Singh (2024.06.01.595856v1.31) 2023 Moshkov, Becker, Yang, Horvath, Dancik, Wagner, Clemons, Singh, Carpenter, Caicedo (2024.06.01.595856v1.20) 2023; 14 Wong, Logan, Hariharan, Stanton, Clevert, Kiruluta (2024.06.01.595856v1.47) 2023; 2 Friedman, Lackner, West, DiBenedetto, Nunnari, Voeltz (2024.06.01.595856v1.4) 2020; 334 Marin Zapata, Méndez-Lucio, Le, Beese, Wichard, Rouquié, Clevert (2024.06.01.595856v1.53) 2023; 2 Breunig, Kriegel, Ng, Sander (2024.06.01.595856v1.38) 2000 Chandola, Banerjee, Kumar (2024.06.01.595856v1.33) 2009; 41 Fernando, Gammulle, Denman, Sridharan, Fookes (2024.06.01.595856v1.34) 2021; 54 Ramezani, Bauman, Singh, Weisbart, Yong, Lozada, Way, Kavari, Diaz, Haghighi (2024.06.01.595856v1.50) 2023 Keren, Pincus, Allen, Barnhart, Marriott, Mogilner, Theriot (2024.06.01.595856v1.2) 2008; 453 Antwarg, Miller, Shapira, Rokach (2024.06.01.595856v1.49) 2021; 186 Weisbart, Kumar, Arevalo, Carpenter, Cimini, Singh (2024.06.01.595856v1.46) 2024; 2402 Bray, Gustafsdottir, Rohban, Singh, Ljosa, Sokolnicki, Bittker, Bodycombe, Dancík, Hasaka (2024.06.01.595856v1.11) 2017; 6 Soelistyo, Vallardi, Charras, Lowe (2024.06.01.595856v1.54) 2022; 4 Way, Natoli, Adeboye, Litichevskiy, Yang, Lu, Caicedo, Cimini, Karhohs, Logan (2024.06.01.595856v1.14) 2022; 13 Chandrasekaran, Ceulemans, Boyd, Carpenter (2024.06.01.595856v1.13) 2021; 20 Gong, Liu, Le, Saha, Mansour, Venkatesh, van den Hengel (2024.06.01.595856v1.55) 2019 Bray, Singh, Han, Davis, Borgeson, Hartland, Kost-Alimova, Gustafsdottir, Gibson, Carpenter (2024.06.01.595856v1.16) 2016; 11 Pincus, Theriot (2024.06.01.595856v1.1) 2007; 227 Rohban, Singh, Wu, Berthet, Bray, Shrestha, Varelas, Boehm, Carpenter (2024.06.01.595856v1.44) 2017; 6 Arevalo, Su, van Dijk, Carpenter, Singh (2024.06.01.595856v1.52) 2023 Matters (2024.06.01.595856v1.18) 2010; 16 Caicedo, Arevalo, Piccioni, Bray, Hartland, Wu, Brooks, Berger, Boehm, Carpenter (2024.06.01.595856v1.22) 2022; 33 Molitor, Krispin, Van-Zuiden, Danino, Rudberg, Bar, Amzallag, Lubliner, Siany, Eitan (2024.06.01.595856v1.29) 2024 Viana, Chen, Knijnenburg, Vasan, Yan, Arakaki, Bailey, Berry, Borensztejn, Brown (2024.06.01.595856v1.24) 2023; 613 Lu, Kraus, Cooper, Moses (2024.06.01.595856v1.30) 2019; 15 Ohnuki, Ogawa, Itto-Nakama, Lu, Ranjan, Kabbage, Gebre, Yamashita, Li, Yashiroda (2024.06.01.595856v1.21) 2022; 3 Hautamaki, Karkkainen, Franti (2024.06.01.595856v1.39) 2004; 3 Wu, Carvalho, Voeltz (2024.06.01.595856v1.6) 2018; 361 Stirling, Swain-Bowden, Lucas, Carpenter, Cimini, Goodman (2024.06.01.595856v1.17) 2021; 22 Naidoo, Marivate (2024.06.01.595856v1.36) 2020; 12066 Haghighi, Caicedo, Cimini, Carpenter, Singh (2024.06.01.595856v1.19) 2022; 19 Scorrano, De Matteis, Emr, Giordano, Hajnóczky, Kornmann, Lackner, Levine, Pellegrini, Reinisch (2024.06.01.595856v1.8) 2019; 10 Kraus, Kenyon-Dean, Saberian, Fallah, McLean, Leung, Sharma, Khan, Balakrishnan, Celik (2024.06.01.595856v1.32) 2023; 2309 Lundberg, Lee (2024.06.01.595856v1.48) 2017; 30 Razdaibiedina, Brechalov, Friesen, Usaj, Masinas, Suresh, Wang, Boone, Ba, Andrews (2024.06.01.595856v1.28) 2024 Schaduangrat, Lampa, Simeon, Gleeson, Spjuth, Nantasenamat (2024.06.01.595856v1.45) 2020; 12 Singh, Wu, Ljosa, Bray, Piccioni, Root, Doench, Boehm, Carpenter (2024.06.01.595856v1.23) 2015; 10 Moshkov, Bornholdt, Benoit, Smith, McQuin, Goodman, Senft, Han, Babadi, Horvath (2024.06.01.595856v1.27) 2024; 15 Pang, Shen, Cao, Van Den Hengel (2024.06.01.595856v1.41) 2021; 54 Subramanian, Narayan, Corsello, Peck, Natoli, Lu, Gould, Davis, Tubelli, Asiedu (2024.06.01.595856v1.56) 2017; 171 Thudumu, Branch, Jin, Singh (2024.06.01.595856v1.25) 2020; 7 Serrano, Chandrasekaran, Bunten, Brewer, Tomkinson, Kern, Bornholdt, Fleming, Pei, Arevalo (2024.06.01.595856v1.57) 2023; 2311 Liu, Ting, Zhou (2024.06.01.595856v1.40) 2008 Meira, Andrade, Praça, Carneiro, Bolón-Canedo, Alonso-Betanzos, Marreirosi (2024.06.01.595856v1.37) 2020 Han, Rundo, Murao, Noguchi, Shimahara, Milacski, Koshino, Sala, Nakayama (2024.06.01.595856v1.35) 2021; 22 Kraus, Grys, Ba, Chong, Frey, Boone, Andrews (2024.06.01.595856v1.5) 2017; 13 Caicedo, Cooper, Heigwer, Warchal, Qiu, Molnar, Vasilevich, Barry, Bansal, Kraus (2024.06.01.595856v1.10) 2017; 14 |
| References_xml | – reference: 41167192 - Cell Syst. 2025 Nov 19;16(11):101429. doi: 10.1016/j.cels.2025.101429. – volume: 2402 start-page: 02203 year: 2024 ident: 2024.06.01.595856v1.46 article-title: Cell Painting Gallery: an open resource for image-based profiling publication-title: arXiv preprint arXiv – start-page: 1705 year: 2019 end-page: 1714 ident: 2024.06.01.595856v1.55 article-title: Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection publication-title: Proceedings of the IEEE/CVF international conference on computer vision – volume: 109 start-page: 756 issue: 5 year: 2021 end-page: 795 ident: 2024.06.01.595856v1.43 article-title: A unifying review of deep and shallow anomaly detection publication-title: Proceedings of the IEEE – start-page: 4477 year: 2020 end-page: 4489 ident: 2024.06.01.595856v1.37 article-title: “Performance evaluation of unsupervised techniques in cyber-attack anomaly detection” publication-title: Journal of ambient intelligence and humanized computing – volume: 19 start-page: 995 issue: 8 year: 2022 end-page: 1003 ident: 2024.06.01.595856v1.26 article-title: Self-supervised deep learning encodes high-resolution features of protein subcellular localization publication-title: Nature methods – volume: 11 start-page: 1757 issue: 9 year: 2016 end-page: 1774 ident: 2024.06.01.595856v1.16 article-title: Cell Painting, a high-content image-based assay for morphological profiling using multiplexed fluorescent dyes publication-title: Nature protocols – start-page: 2024 year: 2024 end-page: 01 ident: 2024.06.01.595856v1.29 article-title: “Organellomics: AI-driven deep organellar phenotyping of human neurons” publication-title: bioRxiv – volume: 16 start-page: 347 issue: 4 year: 2010 end-page: 347 ident: 2024.06.01.595856v1.18 article-title: Mechanism matters publication-title: Nature med – volume: 334 start-page: 358 year: 2020 end-page: 362 ident: 2024.06.01.595856v1.4 article-title: “ER tubules mark sites of mitochondrial division” publication-title: Science – volume: 20 start-page: 145 issue: 2 year: 2021 end-page: 159 ident: 2024.06.01.595856v1.13 article-title: Image-based profiling for drug discovery: due for a machine-learning upgrade? publication-title: Nature reviews drug discovery – volume: 12 start-page: 1 year: 2020 end-page: 30 ident: 2024.06.01.595856v1.45 article-title: Towards reproducible computational drug discovery publication-title: Journal of cheminformatics – volume: 14 start-page: 1967 issue: 1 year: 2023 ident: 2024.06.01.595856v1.20 article-title: Predicting compound activity from phenotypic profiles and chemical structures publication-title: Nature communications – volume: 3 start-page: 430 year: 2004 end-page: 433 ident: 2024.06.01.595856v1.39 article-title: “Outlier detection using k-nearest neighbour graph” publication-title: IEEE – volume: 216 start-page: 1543 issue: 6 year: 2017 end-page: 1556 ident: 2024.06.01.595856v1.12 article-title: Diverse roles of guanine nucleotide exchange factors in regulating collective cell migration publication-title: Journal of cell biology – volume: 186 start-page: 115736 year: 2021 ident: 2024.06.01.595856v1.49 article-title: Explaining anomalies detected by autoencoders using Shapley Additive Explanations publication-title: Expert systems with applications – start-page: 93 year: 2000 end-page: 104 ident: 2024.06.01.595856v1.38 article-title: LOF: identifying density-based local outliers – volume: 14 start-page: 849 issue: 9 year: 2017 end-page: 863 ident: 2024.06.01.595856v1.10 article-title: Data-analysis strategies for image-based cell profiling publication-title: Nature methods – volume: 41 start-page: 1 issue: 3 year: 2009 end-page: 58 ident: 2024.06.01.595856v1.33 article-title: Anomaly detection: A survey publication-title: ACM computing surveys (CSUR – volume: 13 start-page: 911 issue: 11 year: 2022 end-page: 923 ident: 2024.06.01.595856v1.14 article-title: Morphology and gene expression profiling provide complementary information for mapping cell state publication-title: Cell systems – volume: 10 start-page: 7 year: 2015 ident: 2024.06.01.595856v1.23 article-title: Morphological profiles of RNAi-induced gene knockdown are highly reproducible but dominated by seed effects publication-title: PloS one – volume: 7 start-page: 1 year: 2020 end-page: 30 ident: 2024.06.01.595856v1.25 article-title: A comprehensive survey of anomaly detection techniques for high dimensional big data publication-title: Journal of big data – start-page: 1 year: 2024 end-page: 28 ident: 2024.06.01.595856v1.28 article-title: “PIFiA: self-supervised approach for protein functional annotation from single-cell imaging data” publication-title: Molecular systems biology – volume: 2 start-page: 91 issue: 1 year: 2023 end-page: 102 ident: 2024.06.01.595856v1.53 article-title: “Cell morphology-guided de novo hit design by conditioning GANs on phenotypic image features” publication-title: Digital discovery – volume: 13 start-page: 924 issue: 4 year: 2017 ident: 2024.06.01.595856v1.5 article-title: Automated analysis of high-content microscopy data with deep learning publication-title: Molecular systems biology – volume: 6 start-page: 12 year: 2017 ident: 2024.06.01.595856v1.11 article-title: A dataset of images and morphological profiles of 30,000 small-molecule treatments using the Cell Painting assay publication-title: Gigascience – year: 2023 ident: 2024.06.01.595856v1.50 article-title: A genome-wide atlas of human cell morphology publication-title: bioRxiv – volume: 6 year: 2017 ident: 2024.06.01.595856v1.44 article-title: Systematic morphological profiling of human gene and allele function via Cell Painting publication-title: Elife – volume: 30 year: 2017 ident: 2024.06.01.595856v1.48 article-title: A unified approach to interpreting model predictions publication-title: Advances in neural information processing systems – volume: 9 start-page: 1761 issue: 1 year: 2018 ident: 2024.06.01.595856v1.7 article-title: Systematic mapping of contact sites reveals tethers and a function for the peroxisome-mitochondria contact publication-title: Nature communications – volume: 10 start-page: 1287 issue: 1 year: 2019 ident: 2024.06.01.595856v1.8 article-title: Coming together to define membrane contact sites publication-title: Nature communications – volume: 53 start-page: 84 year: 2018 end-page: 91 ident: 2024.06.01.595856v1.9 article-title: Interacting organelles publication-title: Current opinion in cell biology – volume: 6 start-page: 4 year: 2020 ident: 2024.06.01.595856v1.3 article-title: Single-cell morphology encodes metastatic potential publication-title: Science advances – volume: 22 start-page: 1 year: 2021 end-page: 20 ident: 2024.06.01.595856v1.35 article-title: MADGAN: Unsupervised medical anomaly detection GAN using multiple adjacent brain MRI slice reconstruction publication-title: BMC bioinformatics – start-page: 413 year: 2008 end-page: 422 ident: 2024.06.01.595856v1.40 article-title: Isolation forest – volume: 12066 start-page: 419 year: 2020 end-page: 430 ident: 2024.06.01.595856v1.36 – volume: 2110 start-page: 11334 year: 2021 ident: 2024.06.01.595856v1.42 article-title: Generalized out-of-distribution detection: A survey publication-title: arXiv preprint arXiv – volume: 22 start-page: 1 year: 2021 end-page: 11 ident: 2024.06.01.595856v1.17 article-title: CellProfiler 4: improvements in speed, utility and usability publication-title: BMC bioinformatics – volume: 19 start-page: 1550 issue: 12 year: 2022 end-page: 1557 ident: 2024.06.01.595856v1.19 article-title: High-dimensional gene expression and morphology profiles of cells across 28,000 genetic and chemical perturbations publication-title: Nature methods – volume: 2 start-page: 1354 issue: 5 year: 2023 end-page: 1367 ident: 2024.06.01.595856v1.47 article-title: Deep representation learning determines drug mechanism of action from cell painting images publication-title: Digital Discovery – start-page: 2023 year: 2023 end-page: 11 ident: 2024.06.01.595856v1.31 article-title: Capturing cell heterogeneity in representations of cell populations for image-based profiling using contrastive learning publication-title: bioRxiv – year: 2023 ident: 2024.06.01.595856v1.52 article-title: Evaluating batch correction methods for image-based cell profiling publication-title: bioRxiv – volume: 33 start-page: 6 year: 2022 ident: 2024.06.01.595856v1.22 article-title: Cell Painting predicts impact of lung cancer variants publication-title: Molecular biology of the cell – volume: 361 start-page: 6401 year: 2018 ident: 2024.06.01.595856v1.6 article-title: Here, there, and everywhere: The importance of ER membrane contact sites publication-title: Science – volume: 15 start-page: 1594 issue: 1 year: 2024 ident: 2024.06.01.595856v1.27 article-title: Learning representations for image-based profiling of perturbations publication-title: Nature communications – volume: 2311 start-page: 13417 year: 2023 ident: 2024.06.01.595856v1.57 article-title: Reproducible image-based profiling with Pycytominer publication-title: arXiv preprint arXiv – volume: 15 start-page: 9 year: 2019 ident: 2024.06.01.595856v1.30 article-title: Learning unsupervised feature representations for single cell microscopy images with paired cell inpainting publication-title: PLoS computational biology – volume: 32 start-page: 995 issue: 9 year: 2021 end-page: 1005 ident: 2024.06.01.595856v1.51 article-title: Predicting cell health phenotypes using image-based morphology profiling publication-title: Molecular biology of the cell – volume: 227 start-page: 140 issue: 2 year: 2007 end-page: 156 ident: 2024.06.01.595856v1.1 article-title: Comparison of quantitative methods for cell-shape analysis publication-title: Journal of microscopy – volume: 4 start-page: 636 issue: 7 year: 2022 end-page: 644 ident: 2024.06.01.595856v1.54 article-title: Learning biophysical determinants of cell fate with deep neural networks publication-title: Nature machine intelligence – volume: 613 start-page: 345 issue: 7943 year: 2023 end-page: 354 ident: 2024.06.01.595856v1.24 article-title: Integrated intracellular organization and its variations in human iPS cells publication-title: Nature – volume: 171 start-page: 1437 issue: 6 year: 2017 end-page: 1452 ident: 2024.06.01.595856v1.56 article-title: A next generation connectivity map: L1000 platform and the first 1,000,000 profiles publication-title: Cell – volume: 216 start-page: 65 issue: 1 year: 2017 end-page: 71 ident: 2024.06.01.595856v1.15 article-title: Machine learning and computer vision approaches for phenotypic profiling publication-title: Journal of cell biology – volume: 2309 start-page: 16064 year: 2023 ident: 2024.06.01.595856v1.32 article-title: Masked autoencoders are scalable learners of cellular morphology publication-title: arXiv preprint arXiv – volume: 3 year: 2022 ident: 2024.06.01.595856v1.21 article-title: High-throughput platform for yeast morphological profiling predicts the targets of bioactive compounds publication-title: npj systems biology and applications – volume: 453 start-page: 475 issue: 7194 year: 2008 end-page: 480 ident: 2024.06.01.595856v1.2 article-title: Mechanism of shape determination in motile cells publication-title: Nature – volume: 54 start-page: 1 issue: 2 year: 2021 end-page: 38 ident: 2024.06.01.595856v1.41 article-title: Deep learning for anomaly detection: A review publication-title: ACM computing surveys (CSUR – volume: 54 start-page: 1 issue: 7 year: 2021 end-page: 37 ident: 2024.06.01.595856v1.34 article-title: Deep learning for medical anomaly detection–a survey publication-title: ACM Computing Surveys (CSUR |
| SSID | ssj0002961374 |
| Score | 1.8720495 |
| SecondaryResourceType | preprint |
| Snippet | High-content image-based phenotypic profiling combines automated microscopy and analysis to identify phenotypic alterations in cell morphology and provide... |
| SourceID | biorxiv proquest pubmed |
| SourceType | Open Access Repository Aggregation Database Index Database |
| SubjectTerms | Bioinformatics |
| Title | Anomaly detection for high-content image-based phenotypic cell profiling |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/38895267 https://www.proquest.com/docview/3070803049 https://www.biorxiv.org/content/10.1101/2024.06.01.595856 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 2692-8205 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002961374 issn: 2692-8205 databaseCode: M7P dateStart: 20131107 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2692-8205 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002961374 issn: 2692-8205 databaseCode: BENPR dateStart: 20131107 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2692-8205 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002961374 issn: 2692-8205 databaseCode: PIMPY dateStart: 20131107 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLbYBhIviDsbUBkJ8VIFEudmPw7UMaQRoqmTylPkOM4aqUtC203tv-ec2EsrFaTxwEvUWI2TnC86Pjefj5D3bqQjX3q5g83MnUAJ1xEMvVZRKq3CXIuw7Mgm4iThk4lILWf7oqMTiOuar1ai_a9QwxiAjVtn_wHuflIYgN8AOhwBdjjeCXhw6K_kbD0s9FKrvpIQ2xI7WJeOuf_qCrSIgwtYMcQar2a5bis1xCD-0JB43y5o1mzNq-Z8Vd304ZhpW13aLYTHs61EfjMzuY1ENn3R71dwnk2QdSqnclMLrMG9lGbDECjjejv8wIKuTMrfaCkWCVCpzDWpab07tqujO24AnKvrnOp9DAX4LH_oh538yE4uzs6y8Wgy_tD-cpAqDFPqljdljxywOBSgyg4-j5L0vA-tMQE2Std_u38Qm8-GW3_auTF4PiDFOUjx715GZ22MH5NH1k2gxwbeJ-Serp-SB4Y4dP2MnFqQaQ8yBZDpNsh0C2S6AZkiyLQH-Tm5OBmNv5w6lhPDyT3OIycuSuarUAkWKe0XseTo4uJLF7kKeRxHsuClDD0lCoHGFzJpRThUslAH0n9B9uum1q8I9TxdMjcoJViBQa4UF2Xe8WMErp97WhySd1YuWWs6n2QouwwLIb3MyA7-cyuxDPQSvoKsdXO9yHAt4Zh3h3leGlH20_ici5BF8dEdrn5NHm4-uzdkfzm_1m_JfXWzrBbzAdmLJ3xgP4ABFu6mcJZ--57-_A0VtWKi |
| linkProvider | ProQuest |
| 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=Anomaly+detection+for+high-content+image-based+phenotypic+cell+profiling&rft.jtitle=bioRxiv&rft.au=Shpigler%2C+Alon&rft.au=Kolet%2C+Naor&rft.au=Golan%2C+Shahar&rft.au=Weisbart%2C+Erin&rft.date=2024-06-03&rft.issn=2692-8205&rft.eissn=2692-8205&rft_id=info:doi/10.1101%2F2024.06.01.595856&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2692-8205&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2692-8205&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2692-8205&client=summon |