PMID- 37105115
OWN - NLM
STAT- MEDLINE
DCOM- 20230509
LR  - 20230512
IS  - 1879-0534 (Electronic)
IS  - 0010-4825 (Linking)
VI  - 159
DP  - 2023 Jun
TI  - MLSpatial: A machine-learning method to reconstruct the spatial distribution of 
      cells from scRNA-seq by extracting spatial features.
PG  - 106873
LID - S0010-4825(23)00338-4 [pii]
LID - 10.1016/j.compbiomed.2023.106873 [doi]
AB  - MOTIVATION: Single-cell RNA sequencing (scRNA-seq) technologies allow us to 
      interrogate the state of an individual cell within its microenvironment. However, 
      prior to sequencing, cells should be dissociated first, making it difficult to 
      obtain their spatial information. Since the spatial distribution of cells is 
      critical in a few circumstances such as cancer immunotherapy, we present 
      MLSpatial, a novel computational method to learn the relationship between gene 
      expression patterns and spatial locations of cells, and then predict cell-to-cell 
      distance distribution based on scRNA-seq data alone. RESULTS: We collected the 
      drosophila embryo dataset, which contains both the fluorescence in situ 
      hybridization (FISH) data and single cell RNA-seq (scRNA-seq) data of drosophila 
      embryo. The FISH data provided the spatial position of 3039 cells and the 
      expression of 84 genes for each cell. The scRNA-seq data contains the expressions 
      of 8924 genes in 1297 high-quality cells with cell location unknown. For a 
      comparison, we also collected the MERFISH data of 645 osteosarcoma cells with 
      cell location and the expression status of 10,050 genes known. For each data, the 
      cells were randomly divided into a training set and a test set, in the ratio of 
      7:3. The cell-to-cell distances our model extracted had a higher correspondence 
      (i.e., correlation coefficient 0.99) with those of the real situation than those 
      of existing methods in the FISH data of drosophila embryo. However, in the 
      osteosarcoma data, our model captured the spatial relationship between cells, 
      with a correlation of 0.514 to that of the real situation. We also applied the 
      model trained using the FISH data of drosophila embryo into the single cell data 
      of drosophila embryo, for which the real location of cells are unknown. The 
      reconstructed pseudo drosophila embryo and the real embryo (as shown by the FISH 
      data) had a high similarity in the spatial distribution of gene expression. 
      CONCLUSION: MLSpatial can accurately restore the relative position of cells from 
      scRNA-seq data; however, the performance depends on the type of cells. The 
      trained model might be useful in reconstructing the spatial distributions of 
      single cells with only scRNA-seq data, provided that the scRNA-seq data and the 
      FISH data are under similar background (i.e., the same tissue with similar 
      disease background).
CI  - Copyright (c) 2023 Elsevier Ltd. All rights reserved.
FAU - Zhu, Mengbo
AU  - Zhu M
AD  - Department of Mathematics, Ocean University of China, Qingdao, 266100, China; 
      Geneis Beijing Co., Ltd., Beijing, 100102, China.
FAU - Li, Changjun
AU  - Li C
AD  - Department of Mathematics, Ocean University of China, Qingdao, 266100, China. 
      Electronic address: licj@ouc.edu.cn.
FAU - Lv, Kebo
AU  - Lv K
AD  - Department of Mathematics, Ocean University of China, Qingdao, 266100, China.
FAU - Guo, Hongzhe
AU  - Guo H
AD  - Geneis Beijing Co., Ltd., Beijing, 100102, China. Electronic address: 
      guohz@geneis.cn.
FAU - Hou, Rui
AU  - Hou R
AD  - Geneis Beijing Co., Ltd., Beijing, 100102, China; Qingdao Geneis Institute of Big 
      Data Mining and Precision Medicine, Qingdao, 266000, China.
FAU - Tian, Geng
AU  - Tian G
AD  - Geneis Beijing Co., Ltd., Beijing, 100102, China; Qingdao Geneis Institute of Big 
      Data Mining and Precision Medicine, Qingdao, 266000, China.
FAU - Yang, Jialiang
AU  - Yang J
AD  - Geneis Beijing Co., Ltd., Beijing, 100102, China; Qingdao Geneis Institute of Big 
      Data Mining and Precision Medicine, Qingdao, 266000, China; Chifeng Municipal 
      Hospital, Chifeng, Inner Mongolia, 024000, China; Academician Workstation, 
      Changsha Medical University, Changsha, 410219, China. Electronic address: 
      yangjl@geneis.cn.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20230418
PL  - United States
TA  - Comput Biol Med
JT  - Computers in biology and medicine
JID - 1250250
SB  - IM
MH  - *Software
MH  - *Gene Expression Profiling/methods
MH  - Sequence Analysis, RNA/methods
MH  - In Situ Hybridization, Fluorescence
MH  - Single-Cell Gene Expression Analysis
MH  - Single-Cell Analysis/methods
MH  - Machine Learning
COIS- Declaration of competing interest Mengbo Zhu, Rui Hou, Geng Tian and Jialiang are 
      employed in Geneis Beijing Co., Ltd., Beijing; Other authors declare that they 
      have no competing interests.
EDAT- 2023/04/28 00:42
MHDA- 2023/05/09 06:42
CRDT- 2023/04/27 18:10
PHST- 2023/02/01 00:00 [received]
PHST- 2023/03/03 00:00 [revised]
PHST- 2023/03/30 00:00 [accepted]
PHST- 2023/05/09 06:42 [medline]
PHST- 2023/04/28 00:42 [pubmed]
PHST- 2023/04/27 18:10 [entrez]
AID - S0010-4825(23)00338-4 [pii]
AID - 10.1016/j.compbiomed.2023.106873 [doi]
PST - ppublish
SO  - Comput Biol Med. 2023 Jun;159:106873. doi: 10.1016/j.compbiomed.2023.106873. Epub 
      2023 Apr 18.