Back

An explainable map of human gastruloid morphospace reveals gastrulation failure modes and predicts teratogens

Rufo, J.; Qiu, C.; Han, D.; Baxter, N.; Daley, G.; Wilson, M. Z.

2024-09-23 developmental biology
10.1101/2024.09.20.614192 bioRxiv
Show abstract

Human gastrulation is a critical stage of development where many pregnancies fail due to poorly understood mechanisms. Using the 2D gastruloid, a stem cell model of human gastrulation, we combined high-throughput drug perturbations and mathematical modelling to create an explainable map of gastruloid morphospace. This map outlines patterning outcomes in response to diverse perturbations and identifies variations in canonical patterning and failure modes. We modeled morphogen dynamics to embed simulated gastruloids into experimentally-determined morphospace to explain how developmental parameters drive patterning. Our model predicted and validated the two greatest sources of patterning variance: cell density-based modulations in Wnt signaling and SOX2 stability. Assigning these parameters as axes of morphospace imparted interpretability. To demonstrate its utility, we predicted novel teratogens that we validated in zebrafish. Overall, we show how stem cell models of development can be used to build a comprehensive and interpretable understanding of the set of developmental outcomes.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Nature Communications
○ 5641 papers in training set
Top 15%
12.3%
Similar papers in this journal
2
Development
● 497 papers in training set
Top 1%
7.7%
Similar papers in this journal
3
eLife
● 5828 papers in training set
Top 18%
6.5%
Similar papers in this journal
4
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 7%
6.5%
Similar papers in this journal
5
Science Advances
● 1243 papers in training set
Top 3%
6.5%
Similar papers in this journal
6
Developmental Cell
○ 196 papers in training set
Top 0.5%
6.1%
7
Nature Physics
○ 45 papers in training set
Top 0.2%
5.0%
50% of probability mass above
8
Cell Systems
○ 201 papers in training set
Top 0.9%
4.7%
9
Cell
○ 431 papers in training set
Top 2%
4.7%
10
Cell Reports
○ 1498 papers in training set
Top 9%
4.2%
11
Science
● 477 papers in training set
Top 2%
3.4%
12
PLOS Computational Biology
● 1863 papers in training set
Top 10%
3.1%
13
Nature Cell Biology
○ 118 papers in training set
Top 1%
3.1%
14
iScience
○ 1154 papers in training set
Top 12%
2.4%
15
Current Biology
○ 665 papers in training set
Top 6%
2.1%
16
Nature
○ 645 papers in training set
Top 6%
2.1%
17
Stem Cell Reports
○ 130 papers in training set
Top 1%
1.9%
18
Advanced Science
○ 286 papers in training set
Top 5%
1.7%
19
Cell Stem Cell
○ 62 papers in training set
Top 1%
1.3%
20
Scientific Reports
○ 3612 papers in training set
Top 61%
1.3%
21
Nature Methods
○ 385 papers in training set
Top 6%
1.1%
22
Journal of Cell Biology
● 392 papers in training set
Top 3%
1.0%
23
Molecular Systems Biology
○ 162 papers in training set
Top 3%
0.8%
24
Cell Genomics
○ 172 papers in training set
Top 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.