Identification of Interpretable Clusters and Associated Signatures in Breast Cancer Single-Cell Data: A Topic Modeling Approach
Topic modeling is a popular technique in machine learning and natural language processing, where a corpus of text documents is classified into themes or topics using word frequency analysis. This approach has proven successful in various biological data analysis applications, such as predicting canc...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-03-01
|
Series: | Cancers |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-6694/16/7/1350 |
_version_ | 1797212749233651712 |
---|---|
author | Gabriele Malagoli Filippo Valle Emmanuel Barillot Michele Caselle Loredana Martignetti |
author_facet | Gabriele Malagoli Filippo Valle Emmanuel Barillot Michele Caselle Loredana Martignetti |
author_sort | Gabriele Malagoli |
collection | DOAJ |
description | Topic modeling is a popular technique in machine learning and natural language processing, where a corpus of text documents is classified into themes or topics using word frequency analysis. This approach has proven successful in various biological data analysis applications, such as predicting cancer subtypes with high accuracy and identifying genes, enhancers, and stable cell types simultaneously from sparse single-cell epigenomics data. The advantage of using a topic model is that it not only serves as a clustering algorithm, but it can also explain clustering results by providing word probability distributions over topics. Our study proposes a novel topic modeling approach for clustering single cells and detecting topics (gene signatures) in single-cell datasets that measure multiple omics simultaneously. We applied this approach to examine the transcriptional heterogeneity of luminal and triple-negative breast cancer cells using patient-derived xenograft models with acquired resistance to chemotherapy and targeted therapy. Through this approach, we identified protein-coding genes and long non-coding RNAs (lncRNAs) that group thousands of cells into biologically similar clusters, accurately distinguishing drug-sensitive and -resistant breast cancer types. In comparison to standard state-of-the-art clustering analyses, our approach offers an optimal partitioning of genes into topics and cells into clusters simultaneously, producing easily interpretable clustering outcomes. Additionally, we demonstrate that an integrative clustering approach, which combines the information from mRNAs and lncRNAs treated as disjoint omics layers, enhances the accuracy of cell classification. |
first_indexed | 2024-04-24T10:47:20Z |
format | Article |
id | doaj.art-0b25ef683fe7460eb07cf09323e053ca |
institution | Directory Open Access Journal |
issn | 2072-6694 |
language | English |
last_indexed | 2024-04-24T10:47:20Z |
publishDate | 2024-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Cancers |
spelling | doaj.art-0b25ef683fe7460eb07cf09323e053ca2024-04-12T13:16:07ZengMDPI AGCancers2072-66942024-03-01167135010.3390/cancers16071350Identification of Interpretable Clusters and Associated Signatures in Breast Cancer Single-Cell Data: A Topic Modeling ApproachGabriele Malagoli0Filippo Valle1Emmanuel Barillot2Michele Caselle3Loredana Martignetti4Institut Curie, Inserm U900, Mines ParisTech, PSL Research University, 75248 Paris, FrancePhysics Department, University of Turin and INFN, 10125 Turin, ItalyInstitut Curie, Inserm U900, Mines ParisTech, PSL Research University, 75248 Paris, FrancePhysics Department, University of Turin and INFN, 10125 Turin, ItalyInstitut Curie, Inserm U900, Mines ParisTech, PSL Research University, 75248 Paris, FranceTopic modeling is a popular technique in machine learning and natural language processing, where a corpus of text documents is classified into themes or topics using word frequency analysis. This approach has proven successful in various biological data analysis applications, such as predicting cancer subtypes with high accuracy and identifying genes, enhancers, and stable cell types simultaneously from sparse single-cell epigenomics data. The advantage of using a topic model is that it not only serves as a clustering algorithm, but it can also explain clustering results by providing word probability distributions over topics. Our study proposes a novel topic modeling approach for clustering single cells and detecting topics (gene signatures) in single-cell datasets that measure multiple omics simultaneously. We applied this approach to examine the transcriptional heterogeneity of luminal and triple-negative breast cancer cells using patient-derived xenograft models with acquired resistance to chemotherapy and targeted therapy. Through this approach, we identified protein-coding genes and long non-coding RNAs (lncRNAs) that group thousands of cells into biologically similar clusters, accurately distinguishing drug-sensitive and -resistant breast cancer types. In comparison to standard state-of-the-art clustering analyses, our approach offers an optimal partitioning of genes into topics and cells into clusters simultaneously, producing easily interpretable clustering outcomes. Additionally, we demonstrate that an integrative clustering approach, which combines the information from mRNAs and lncRNAs treated as disjoint omics layers, enhances the accuracy of cell classification.https://www.mdpi.com/2072-6694/16/7/1350topic modelinghierarchical stochastic block modelingsingle-cell RNA-seqlong non-coding RNAsbreast cancer |
spellingShingle | Gabriele Malagoli Filippo Valle Emmanuel Barillot Michele Caselle Loredana Martignetti Identification of Interpretable Clusters and Associated Signatures in Breast Cancer Single-Cell Data: A Topic Modeling Approach Cancers topic modeling hierarchical stochastic block modeling single-cell RNA-seq long non-coding RNAs breast cancer |
title | Identification of Interpretable Clusters and Associated Signatures in Breast Cancer Single-Cell Data: A Topic Modeling Approach |
title_full | Identification of Interpretable Clusters and Associated Signatures in Breast Cancer Single-Cell Data: A Topic Modeling Approach |
title_fullStr | Identification of Interpretable Clusters and Associated Signatures in Breast Cancer Single-Cell Data: A Topic Modeling Approach |
title_full_unstemmed | Identification of Interpretable Clusters and Associated Signatures in Breast Cancer Single-Cell Data: A Topic Modeling Approach |
title_short | Identification of Interpretable Clusters and Associated Signatures in Breast Cancer Single-Cell Data: A Topic Modeling Approach |
title_sort | identification of interpretable clusters and associated signatures in breast cancer single cell data a topic modeling approach |
topic | topic modeling hierarchical stochastic block modeling single-cell RNA-seq long non-coding RNAs breast cancer |
url | https://www.mdpi.com/2072-6694/16/7/1350 |
work_keys_str_mv | AT gabrielemalagoli identificationofinterpretableclustersandassociatedsignaturesinbreastcancersinglecelldataatopicmodelingapproach AT filippovalle identificationofinterpretableclustersandassociatedsignaturesinbreastcancersinglecelldataatopicmodelingapproach AT emmanuelbarillot identificationofinterpretableclustersandassociatedsignaturesinbreastcancersinglecelldataatopicmodelingapproach AT michelecaselle identificationofinterpretableclustersandassociatedsignaturesinbreastcancersinglecelldataatopicmodelingapproach AT loredanamartignetti identificationofinterpretableclustersandassociatedsignaturesinbreastcancersinglecelldataatopicmodelingapproach |