Helmholtz Munich

Tissue reconstruction model placing dissociated single cells into spatial coordinates by predicting pairwise distances in a learned embedding space.

RNA foundation model pretrained on 223 eCLIP experiments to predict base-resolution RBP binding, with frozen embeddings that transfer downstream.

Open-weights pathology foundation models pairing a 1.1B-parameter ViT-g/8 tile encoder with distilled 86M and 22M variants for H&E histology.

Spatial transcriptomics foundation model giving gene-, cell- and neighborhood-scale embeddings zero-shot, plus in-silico gene knockout in tissue.

Hierarchy-aware self-supervised model for single-cell microscopy that preserves morphological structure suppressed by imaging-modality confounders.

Contrastive multimodal model for perturbation screens, aligning transcriptomic signatures with text and cell-painting image embeddings.

Self-supervised 3D masked autoencoder for volumetric fluorescence microscopy, aligned to ESM2 embeddings to predict protein localization.

Genetically aligned foundation model for blood smear cytology that links single-cell morphology to the chromosomal aberrations behind AML and APL.

Virtual spatial transcriptomics foundation model predicting pan-cancer, spatially-resolved single-cell gene expression from H&E histology slides.

Protein language model that predicts per-residue local energetic frustration directly from sequence, covering whole proteomes and disordered regions.

LoRA adapter on ProstT5 predicting per-residue distributions over Foldseek 3Di tokens, capturing conformational flexibility from MD trajectories.

Single-cell foundation model adapting LLaMA-3.1-8B with LoRA, recasting transcriptomes and protein interaction networks as natural-language Q&A pairs.

Multi-modal contrastive model that aligns H&E histopathology with spatial transcriptomics across tissue scales to predict gene expression from images.

Self-supervised foundation model for human cortical cytoarchitecture, encoding histological brain sections into anatomically meaningful features.

Single-cell foundation model learning technology-agnostic cell embeddings by contrasting cell views rather than reconstructing gene expression counts.

SE(3)-equivariant flow-matching model for pocket-aware 3D ligand generation, predicting binding affinity and confidence in the same network.

Predicts single-cell scRNA-seq coverage and scATAC-seq insertion profiles from DNA sequence, adapting the Borzoi trunk with a cell-specific decoder.

Red blood cell morphology foundation model pretrained on 1.25 million single-cell crops, released as small, base, and large ViT feature extractors.

Splicing variant effect prediction across 49 human tissues and 15 developmental stages, from four weeks post conception to adulthood.

Sparse autoencoder for blood-cell microscopy that decomposes hematology foundation model embeddings into expert-validated sub-cellular concepts.

Histopathology patch encoder turning 512x512 tiles into 768-dimensional features, trained with a CoCa objective on 1.26 million captioned images.

Slide-level pathology foundation model turning whole-slide images into reusable embeddings for classification, retrieval, and report generation.

Enhancer-promoter interaction prediction from DNA sequence and ATAC-seq alone. Spearman above 0.90 on cell types unseen during training.

Tissue-specific histological aging clocks that read biological age and per-organ age gaps from H&E whole-slide images and from blood gene expression.

Aligns structure, binding-pocket, text and molecular-dynamics encoders to a protein sequence anchor, giving frozen embeddings that transfer widely.

Spot detection and quantification in 5D fluorescence microscopy. Pretrained 2D and 3D U-Nets segment foci, then Gaussian fitting measures each one.

Transformer foundation model pretrained on 110M single-cell and spatial transcriptomics profiles, transferring spatial context to dissociated cells.

Cryo-electron tomography membrane analysis pipeline pairing generalizable U-Net membrane segmentation with mesh-based particle localization.

Predicts CLIP-seq crosslink counts along an RNA sequence base by base, separating protein-specific signal from experimental background.