Back

Latent factor in Brain RNA-seq studies reflects cell type and clinical heterogeneity

Liu, Z.; Al-Ouran, R.; Liu, C.; Wang, L.; Wan, Y.; Li, X.; Milosavljevic, A.; Shulman, J.

2022-11-16 genomics
10.1101/2022.11.13.516360 bioRxiv
Show abstract

With the growing availability of Alzheimers disease (AD) transcriptomic data, several studies have nominated new therapeutic targets. However, a major challenge is accounting for latent (hidden) factors which affect the discovery of therapeutic targets. Using unsupervised machine learning, we identified a latent factor in brain tissue, and we validated the factor in AD and normal samples, across multiple studies, and different brain tissues. Moreover, significant metabolic differences were observed due to the latent factor. The latent factor was found to reflect cell-type heterogeneity in the brain and after adjusting for it, we were able to identify new biological pathways. The changes observed at both transcriptomic and metabolomic levels support the importance of identifying any latent factors before pursuing downstream analysis to accurately identify biomarkers.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

1
Nature Communications
○ 5641 papers in training set
Top 13%
13.3%
Similar papers in this journal
2
Alzheimer's & Dementia
177 papers in training set
Top 0.5%
12.9%
3
Scientific Reports
○ 3612 papers in training set
Top 9%
6.8%
Similar papers in this journal
4
Alzheimer's Research & Therapy
○ 57 papers in training set
Top 0.3%
4.9%
Similar papers in this journal
5
Communications Biology
○ 993 papers in training set
Top 3%
4.1%
Similar papers in this journal
6
Genome Biology
○ 637 papers in training set
Top 4%
3.3%
7
eLife
● 5828 papers in training set
Top 34%
3.3%
8
Genome Medicine
○ 183 papers in training set
Top 2%
2.7%
50% of probability mass above
9
npj Systems Biology and Applications
○ 125 papers in training set
Top 0.6%
2.7%
10
Molecular Neurodegeneration
○ 55 papers in training set
Top 0.9%
2.2%
11
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 2%
2.2%
12
Molecular Psychiatry
○ 282 papers in training set
Top 3%
2.1%
13
Genome Research
● 468 papers in training set
Top 3%
1.9%
14
Nature Aging
○ 60 papers in training set
Top 0.9%
1.8%
15
Human Genetics and Genomics Advances
○ 84 papers in training set
Top 1%
1.8%
16
Cell Reports
○ 1498 papers in training set
Top 18%
1.8%
17
iScience
○ 1154 papers in training set
Top 17%
1.8%
18
Nature Neuroscience
○ 252 papers in training set
Top 4%
1.4%
19
Briefings in Bioinformatics
◐ 354 papers in training set
Top 5%
1.4%
20
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 34%
1.1%
21
Frontiers in Genetics
○ 230 papers in training set
Top 4%
1.1%
22
Acta Neuropathologica Communications
○ 89 papers in training set
Top 2%
1.1%
23
Neurobiology of Disease
○ 148 papers in training set
Top 3%
1.0%
24
Human Genomics
○ 21 papers in training set
Top 0.4%
0.9%
25
PLOS Genetics
● 862 papers in training set
Top 11%
0.9%
26
Human Molecular Genetics
◐ 141 papers in training set
Top 3%
0.9%
27
Acta Neuropathologica
○ 58 papers in training set
Top 1%
0.9%
28
Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring
○ 42 papers in training set
Top 1.0%
0.6%
29
Alzheimer's & Dementia: Translational Research & Clinical Interventions
○ 17 papers in training set
Top 0.6%
0.6%
30
npj Aging
○ 22 papers in training set
Top 0.5%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.