top of page



SiFT (Signal FilTering)

A computational framework that aims to uncover the underlying structure in single-cell data by filtering out previously exposed biological signals. SiFT can be applied to a wide range of tasks, from (i) the removal of unwanted variation as a pre-processing step, through (ii) revealing hidden biological structure by utilizing prior knowledge with respect to existing signal, to (iii) uncovering trajectories of interest using reference data to remove unwanted variation.

Piran, Z. and Nitzan, M. 2024. Uncovering hidden biological processes by probabilistic filtering of single-cell data, Nature Communications.

The code is available on github and here are documentation and tutorials.

Biolord (biological representation disentanglement)

Biolord is a deep generative method for disentangling single-cell multi-omic data to known and unknown attributes, including spatial, temporal, and disease state, used to reveal the decoupled biological signatures over diverse single-cell modalities and biological systems. By virtually shifting cells across states, biolord generates experimentally-inaccessible samples, outperforming state-of-the-art methods in predictions of cellular response to unseen drugs and genetic perturbations.

Piran, Z., Cohen, N., Hoshen, Y. and Nitzan, M. 2024. Disentanglement of single-cell data with biolord. Nature Biotechnology.

The code is available on github and here are documentation and tutorials.


scPrisma is a spectral analysis method, for pseudotime reconstruction, informative genes inference, filtering, and enhancement of underlying topological signals in scRNA-seq data.

Karin, J., Bornfeld, Y. and Nitzan, M., 2022. scPrisma: inference, filtering and enhancement of periodic signals in single-cell data using spectral template matching. Nature Biotechnology

The code, documentation and tutorials are available on github.

TACCO (Transfer of Annotations to Cells and their COmbinations)

TACCO is a python framework for working with categorical and compositional annotations for high-dimensional observations, in particular for transferring annotations from single cell to spatial transcriptomics data. 

Mages, S.*, Moriel, N.*, Avraham-Davidi, I.*, Murray, E., Chen, F., Rozenblatt-Rosen, O., Klughammer, J., Regev, A. and Nitzan, M., 2023. TACCO: Unified annotation transfer and decomposition of cell identities for single-cell and spatial omics. Nature Biotechnology.

The code is available on github and here are documentation and a set of example notebooks.


Time-warp-attend is a deep-learning framework that classifies dynamical regimes and detects bifurcation boundaries by learning topologically invariant features in systems ranging from electrical circuits to chemical oscillators. We demonstrate its effectiveness on real-world data including single-cell gene expression dynamics in pancreatic development.

Moriel* N., Ricci* M., Nitzan M. 2024. Let’s do the time-warp-attend: learning topological invariants of dynamical systems, ICLR.

The code is available on


Phase2vec, a universal embedder of dynamical systems, is trained via a self-supervised auxiliary task of governing equation prediction. Learned representations enable accurate classification of simulated systems into key physical classes (e.g., by stability, energy conservation), as well as clustering of real meteorological data.


Matthew R., Moriel N., Piran Z., Nitzan M. 2023. Phase2vec: dynamical systems embedding with a physics-informed convolutional network, ICLR.


The code is available on

NovoSpaRc (de novo spatial reconstruction)

Embedding single cells (or, their single-cell RNA sequencing expression profile representation) into their original spatial context, or tissue of origin, based on structural similarities between the cells in high dimensional gene expression space and the cellular locations in physical space (and, if available, an imaging reference atlas), based on generalized optimal transport.

Nitzan, M.*, Karaiskos, N.*, Friedman, N. and Rajewsky, N. 2019. Gene expression cartography.

Nature, 576(7785), pp.132-137.

Moriel, N.*, Senel, E.*, Friedman, N., Rajewsky, N., Karaiskos, N., and Nitzan, M. 2021. NovoSpaRc: flexible spatial reconstruction of single-cell gene expression with optimal transport. Nature Protocols, pp. 1-24.

The code is available on github and here are documentation a tutorial.

bottom of page