Alessandro Palma

Alessandro Palma

Auto-generated profile, based on publicly available information

Alessandro Palma

Department of Computational Health, Institute of Computational Biology, Helmholtz Zentrum München, Munich, Germany

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 January 2025 in Nature Communications
Verified
Journal Article
Open access
PDF file
APAlessandro Palma
Alessandro Palma
FTFabian J. Theis
Fabian J. Theis
MLMohammad Lotfollahi
Mohammad Lotfollahi
Advancements in high-throughput screenings enable the exploration of rich phenotypic readouts through high-content microscopy, expediting the development of phenotype-based drug discovery. However, analyzing large and complex high-content imaging screenings remains challenging due to incomplete sampling of perturbations and the presence of technical variations between experiments. To tackle these shortcomings, we present IMage Perturbation Autoencoder (IMPA), a generative style-transfer model predicting morphological changes of perturbations across genetic and chemical interventions. We show that IMPA accurately captures morphological and population-level changes of both seen and unseen perturbations on breast cancer and osteosarcoma cells. Additionally, IMPA accounts for batch effects and can model perturbations across various sources of technical variation, further enhancing its robustness in diverse experimental conditions. With the increasing availability of large-scale high-content imaging screens generated by academic and industrial consortia, we envision that IMPA will facilitate the analysis of microscopy data and enable efficient experimental design via in-silico perturbation prediction.

17 April 2025 in bioRxiv
Verified
Preprint
Open access
PDF file
DKDominik Klein
Dominik Klein
JFJonas Simon Fleck
Jonas Simon Fleck
DBDaniil Bobrovskiy
Daniil Bobrovskiy
LZLea Zimmermann
Lea Zimmermann
SBSören Becker
Sören Becker
FTFabian J. Theis
Fabian J. Theis
High-content phenotypic screens provide a powerful strategy for studying biological systems, but the scale of possible perturbations and cell states makes exhaustive experiments unfeasible. Computational models that are trained on existing data and extrapolate to correctly predict outcomes in unseen contexts have the potential to accelerate biological discovery. Here, we present CellFlow, a flexible framework based on flow matching that can model single cell phenotypes induced by complex perturbations. We apply CellFlow to various phenotypic screens, accurately predicting expression responses to a wide range of perturbations, including cytokine stimulation, drug treatments and gene knockouts. CellFlow successfully modeled developmental perturbations at the whole-embryo scale and guided cell fate and organoid engineering by predicting heterogeneous cell populations arising from combinatorial morphogen treatments and by performing a virtual organoid protocol screen. Taken together, CellFlow has the potential to accelerate discovery from phenotypic screens by learning from existing data and generating phenotypes induced by unseen conditions.

22 September 2025 in bioRxiv
Verified
Preprint
Open access
SMSophia C. Mädler
Sophia C. Mädler
NSNiklas A. Schmacke
Niklas A. Schmacke
APAlessandro Palma
Alessandro Palma
ANAltana Namsaraeva
Altana Namsaraeva
ACAli Oğuz Can
Ali Oğuz Can
MMMatthias Mann
Matthias Mann
Machine learning increasingly uncovers rules of biology directly from data, enabled by large, standardized datasets. Microscopy images provide rich information on cellular architecture and are accessible at scale across biological systems, making them an ideal foundation for modeling cell behavior. However, a standardized image format does not exist at the single-cell level. Here we present scPortrait, an scverse software package for generation, storage, and application of single-cell image datasets. scPortrait reads, stitches and segments raw fields of view with out-of-core computation scaling to larger-than-memory datasets. Parallelization enables rapid extraction of individual cells into a standardized single-cell image format with fast access to accelerate machine learning. scPortrait enables analysis across modalities including images, proteomics and transcriptomics, identifying cancer-associated macrophage subpopulations by morphology and embedding single-cell images into transcriptome atlases. scPortrait turns microscopy images into a reusable resource for integrative cell modeling, establishing single-cell images as a core modality in systems biology.

18 June 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
XFXiaotong Fu
Xiaotong Fu
DKDominik Klein
Dominik Klein
EAEgor Antipov
Egor Antipov
APAlessandro Palma
Alessandro Palma
ATAlejandro Tejada-Lapuerta
Alejandro Tejada-Lapuerta
FTFabian J. Theis
Fabian J. Theis
Single-cell transcriptomics is typically modeled in low-dimensional latent representations that improve the signal-to-noise ratio of the data. Such representations underpin data integration, cell state discovery, and perturbation prediction, with applications ranging from large-scale organ atlases to latent trajectory modeling. Recent virtual cell approaches further leverage these representations to predict cellular responses as distributional shifts in latent space. Each of these applications ultimately requires faithful gene expression reconstruction from latent spaces for biological interpretation, enabling gene-level analysis of predicted perturbed or batch-corrected cells. Yet representation choice is typically treated as an implementation detail rather than a primary modeling decision, with no systematic evaluation of how well latent representations support gene expression reconstruction. Here, we introduce ReconEval, a benchmark for evaluating gene expression reconstruction from single-cell latent spaces. We benchmark two classes of latent representations: end-to-end trained models such as PCA, autoencoders, and variational autoencoders, and pretrained single-cell foundation model embeddings coupled to newly trained decoders. Reconstruction is evaluated both directly and after latent-space perturbation prediction. Across perturbational and observational datasets totaling over 100 million cells, our metric suite quantifies statistical fidelity; biological signal preservation, including differential expression, coexpression, cell-cycle structure, cytokine response and pathway activity; and perturbation-specific effects. We find that autoencoders achieve the strongest stand-alone reconstruction at low dimensionality, while variational regularization does not improve generalization in reconstruction. Frozen foundation model embeddings retain recoverable gene-level information, with reconstruction quality depending strongly on decoder architecture and pretraining objective. In latent perturbation modeling, high-dimensional PCA matches foundation model embeddings, while low-dimensional AE embeddings are optimal for flow-based generative models. Overall, reconstruction depends critically on the interplay between representation and downstream model, and simpler representations can outperform complex alternatives given appropriate capacity. Our benchmark establishes reconstruction as a critical evaluation axis for single-cell foundation models. We envision it improving the biological interpretability of latent-space modeling, a prerequisite for future virtual cell models to be validated by domain experts and grounded in biology.

9 October 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
LPLicyel Paulas-Condori
Licyel Paulas-Condori
APAlessandro Palma
Alessandro Palma
LCLorenzo Consoli
Lorenzo Consoli
JRJuan Antonio Rubio-Lara
Juan Antonio Rubio-Lara
OHOlivia Hidajat
Olivia Hidajat
FTFabian J. Theis
Fabian J. Theis
Summary: Inverse design has advanced the discovery of molecules and materials. Yet it remains largely unexplored for steering cell fate, where inputs are continuous, combinatorial culture conditions and outputs are distributions of cell states. Human hematopoiesis, in which combinations and doses of growth factors steer stem cells toward each blood lineage, is a demanding test case. While forward models can evaluate discrete conditions, the vast combinatorial space renders searching for a specific, target-producing design an intractable inverse problem. Here, we introduce LabCompass, an inverse-modeling framework that optimizes experimental designs toward candidates expected to produce specified target cell states, using a flow-matching generative model guided by cellular phenotypes predicted by a forward surrogate. We applied LabCompass to primary human CD34+ in vitro cultures, where continuous cytokine and small-molecule parameters govern hematopoietic cell fate. In a lab-in-the-loop setting, we experimentally validated model-driven designs and used these measurements to update the model across four successive loops. LabCompass recovered established lineage-inducing designs, improved predictions with new data, and enriched target populations across lineages. Incorporating new parameters expanded the design space and enriched rare populations beyond initial reach. Across loops, we generated a 78-million-cell spectral flow cytometry dataset and identified distinct culture conditions converging on the same target cell states. Our results establish generative inverse modeling as a compelling paradigm for navigating high-dimensional, continuous experimental spaces, and demonstrate that virtual cell models should be judged not only by how accurately they predict cellular responses, but also by how effectively they guide experiments toward desired biological outcomes.