Back

Fine-scale cellular deconvolution via generalized maximum entropy on canonical correlation features

Kamm, J.

2024-10-22 bioinformatics
10.1101/2024.06.07.598010 bioRxiv
Show abstract

We propose a method for estimating probability distributions over single cells, which we apply to fine-scale cellular deconvolution, which quantifies the composition of external bulk RNAseq samples at high resolution (i.e. at the single-cell or neighborhood level). Our method is based on a computationally-efficient convex optimization problem, which is also generalization of the Maximum Entropy method. Our method has a much higher resolution than traditional approaches that require computing gene expression profiles at the cell-type level, and also compares favorably to recent high-resolution cellular deconvolution methods, with orders-of-magnitude speedup in computational efficiency. We implement this method in a Python package quipcell, available at https://github.com/genentech/quipcell.

Matching journals

The top 1 journal accounts for 50% of the predicted probability mass.

1
Bioinformatics
◐ 1204 papers in training set
Top 0.1%
64.8%
Similar papers in this journal
50% of probability mass above
2
Genome Biology
○ 637 papers in training set
Top 3%
3.5%
Similar papers in this journal
3
Biostatistics
◐ 24 papers in training set
Top 0.1%
3.4%
Similar papers in this journal
4
Bioinformatics Advances
◐ 203 papers in training set
Top 2%
3.2%
Similar papers in this journal
5
BMC Bioinformatics
○ 457 papers in training set
Top 3%
2.6%
Similar papers in this journal
6
Briefings in Bioinformatics
◐ 354 papers in training set
Top 4%
2.4%
7
PLOS Computational Biology
● 1863 papers in training set
Top 13%
2.1%
8
Nature Methods
○ 385 papers in training set
Top 4%
2.1%
9
Nature Biotechnology
○ 172 papers in training set
Top 2%
1.7%
10
Nature Communications
○ 5641 papers in training set
Top 44%
1.7%
11
Biometrics
◐ 23 papers in training set
Top 0.2%
1.7%
12
The Annals of Applied Statistics
● 19 papers in training set
Top 0.1%
1.5%
13
Cell Reports Methods
○ 165 papers in training set
Top 4%
0.8%
14
Patterns
○ 78 papers in training set
Top 3%
0.8%
15
Cell Systems
○ 201 papers in training set
Top 5%
0.6%
16
Journal of Computational Biology
○ 48 papers in training set
Top 1%
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.