Lightnews — Scholar-powered news

Khushi Desai @khushipde.bsky.social · 14d

End/ Read our full paper for a full preview of our method and findings! www.biorxiv.org/content/10.1...

AMICI: Attention Mechanism Interpretation of Cell-cell Interactions

Spatial transcriptomic data enable study of cell-cell communication, yet current analysis tools often fail to provide dynamic, interpretable estimates of interactions and their spatial range across ti...

www.biorxiv.org

2

Khushi Desai @khushipde.bsky.social · 14d

16/ Source code for AMICI can be found at github.com/azizilab/amici, installable with pip install amici-st with documentation and tutorials on the way!

GitHub - azizilab/amici: Cross-attention-based cell-cell interaction inference from ST data.

Cross-attention-based cell-cell interaction inference from ST data. - azizilab/amici

github.com

1 2

Khushi Desai @khushipde.bsky.social · 14d

15/ We invite you to apply AMICI on your single-cell spatial transcriptomics data 🗺️! Thanks to @canergen.bsky.social , Nathan Levy (Yosef Lab) for data wrangling help, and special thanks to my co-authors @justjhong.bsky.social and @elhamazizi.bsky.social for an incredible learning experience.

1 1

Khushi Desai @khushipde.bsky.social · 14d

14/ To put a cherry on top, AMICI discovered a spatial population of CD8 T cells influencing Invasive tumor cells towards ER-dependence (beyond known intrinsic cell cycles ‼️), explaining worse prognosis for immune-infiltrated ER+ tumors.

1 1 2

Khushi Desai @khushipde.bsky.social · 14d

13/ With AMICI, we even redefined static niche composition into communication hubs across tissues where cells actively influence each other's phenotypes, capturing dynamic functional interactions 📊.

1 1

Khushi Desai @khushipde.bsky.social · 14d

12/ AMICI revealed that immune-immune signaling occurs at shorter distances than immune-tumor communication, aligning with known biology of local immune synapses 🧩versus distant cytokine signaling 📡.

1 3

Khushi Desai @khushipde.bsky.social · 14d

11/ When we brought even more complexity with a Xenium breast cancer sample, AMICI presented a complex story 📖of CD4 T cell-driven activation of CD8 T cells as well as M1 → M2 macrophage polarization driven by Invasive tumor cells 💥.

1 1 2

Khushi Desai @khushipde.bsky.social · 14d

10/ Leveling up, AMICI recovered known interactions and downstream genes modulating these interactions between astrocytes and oligodendrocytes in MERFISH mouse cortex 🐁 🧠 data.

1 1

Khushi Desai @khushipde.bsky.social · 14d

9/ Not only did AMICI capture the true interactions and their corresponding length scales, but it surpassed other methods on 3 different tasks: predicting mediating genes ♺, predicting the interacting senders 🔊, and predicting the interacting receivers 📞!

1 1

Khushi Desai @khushipde.bsky.social · 14d

8/ We constructed semi-synthetic spatial data from PBMC cells with defined ground-truth interactions, where receiver subpopulations express distinct gene programs 🧪only when within specific ranges of their sender cell types 👯.

1 1

Khushi Desai @khushipde.bsky.social · 14d

7/ However, AMICI is not just a regular attention model – we re-parametrized attention as a monotonically decreasing function of distance 📐 to reflect the biological principle that closer cells will have stronger influence 💪.

1 1

Khushi Desai @khushipde.bsky.social · 14d

6/ How does AMICI work? It redefines attention for spatial transcriptomics where receiver cells attend to neighboring senders, and their aggregated weights determine a receiver’s phenotype 🧬. AMICI masks the receiver’s expression and learns to reconstruct it 🏗️from its spatial neighbors.

1 2

Khushi Desai @khushipde.bsky.social · 14d

5/ With this we present AMICI, an attention-based framework that adaptively learns cell interactions across spatial scales, resolves context-dependent subpopulations, and uses sparsity regularization to pinpoint 🎯 specific neighbors driving transcriptional changes.

1 1

Khushi Desai @khushipde.bsky.social · 14d

4/ Other graph-based methods rely on rigid 🗿distance definitions and broad cell-type labels, missing multi-scale interactions and dynamic subpopulations that transition under local environmental influences.

1 1

Khushi Desai @khushipde.bsky.social · 14d

3/ Current methods for modeling cell-cell communication rely on spatial co-localization or ligand-receptor co-expression, but miss the dynamic dialogue 🗣️where specific cell subpopulations drive context-dependent phenotypic shifts in an interacting cell.

1 1

Khushi Desai @khushipde.bsky.social · 14d

2/ How does complex cell-cell communication contribute to tissue function and disease? 🤝 Spatial transcriptomics at single-cell resolution offers an unprecedented opportunity to understand these interactions in their native context.

1 1

Khushi Desai @khushipde.bsky.social · 14d

1/ I’m excited to share recent work on inferring cell-cell interactions using attention by @justjhong.bsky.social and me, supervised by @elhamazizi.bsky.social . Open the thread 🧵 for a brief overview of our method. bioRxiv link: www.biorxiv.org/content/10.1....

1 6 14

Khushi Desai @khushipde.bsky.social · 14d

End/ Read our full paper for a full preview of our method and findings! www.biorxiv.org/content/10.1...

AMICI: Attention Mechanism Interpretation of Cell-cell Interactions

Spatial transcriptomic data enable study of cell-cell communication, yet current analysis tools often fail to provide dynamic, interpretable estimates of interactions and their spatial range across ti...

www.biorxiv.org

Khushi Desai @khushipde.bsky.social · 14d

16/ Source code for AMICI can be found at github.com/azizilab/amici, installable with pip install amici-st with documentation and tutorials on the way!

GitHub - azizilab/amici: Cross-attention-based cell-cell interaction inference from ST data.

Cross-attention-based cell-cell interaction inference from ST data. - azizilab/amici

github.com

1

Khushi Desai @khushipde.bsky.social · 14d

15/ We invite you to apply AMICI on your single-cell spatial transcriptomics data! Thanks to @canergen.bsky.social, Nathan Levy (Yosef Lab) for data wrangling help, and special thanks to my co-authors @justjhong.bsky.social and @elhamazizi.bsky.social for an incredible learning experience.

1

Khushi Desai @khushipde.bsky.social · 14d

14/ To put a cherry on top, AMICI discovered a spatial population of CD8 T cells influencing Invasive tumor cells towards ER-dependence (beyond known intrinsic cell cycles ‼️), explaining worse prognosis for immune-infiltrated ER+ tumors.

1

Khushi Desai @khushipde.bsky.social · 14d

13/ With AMICI, we even redefined static niche composition into communication hubs across tissues where cells actively influence each other's phenotypes, capturing dynamic functional interactions 📊.

1

Khushi Desai @khushipde.bsky.social · 14d

12/ AMICI revealed that immune-immune signaling occurs at shorter distances than immune-tumor communication, aligning with known biology of local immune synapses 🧩versus distant cytokine signaling 📡.

1

Khushi Desai @khushipde.bsky.social · 14d

11/ When we brought even more complexity with a Xenium breast cancer sample, AMICI presented a complex story 📖of CD4 T cell-driven activation of CD8 T cells as well as M1 → M2 macrophage polarization driven by Invasive tumor cells 💥.

1

Khushi Desai @khushipde.bsky.social · 14d

10/ Leveling up, AMICI recovered known interactions and downstream genes modulating these interactions between astrocytes and oligodendrocytes in MERFISH mouse cortex 🐁🧠data.

1