Inserm

Genomic variant effect prediction from a bidirectional absorbing-diffusion model over human DNA, pretrained with entropy-guided span masking.

Skeletal CT reconstruction from two orthogonal X-ray projections, using conditional latent diffusion that classifies scoliosis as the volume forms.

Dense self-supervised pretraining that learns pixel- and voxel-level features for segmenting cardiac MRI and abdominal CT from very few labels.

Physiological time-series classification model bringing in-context learning to ECG, EEG, and ICU signals with temporal and channel-aware encodings.

Anti-phage defense gene predictor fusing protein language model embeddings with a contrastive genomic-context transformer over 64-gene windows.

Histopathology classifier separating atypical from normal mitotic figures, LoRA-adapting a DINOv3 vision transformer with 1.3M trainable parameters.

End-to-end protein structure alignment from 3D coordinates, matching TM-align quality at LDDT 0.56 and beating Foldseek on SCOPe40 search.

Cell segmentation for image-based spatial transcriptomics that fuses RNA point clouds with any number of membrane and nuclear staining channels.

Retinal encoding models that predict ganglion cell responses to visual stimuli, with pretrained checkpoints across four species and two modalities.

Liquid-liquid phase separation predictor that scores proteins and residues from sequence and designs phase-separating peptides by gradient descent.

Genomic language model reading bacterial gene neighborhoods as sentences of protein-family tokens to predict anti-phage defense function.

Protein language model fine-tuned to score any bacterial protein for anti-phage defense function, detecting homology too remote for HMM profiles.

Codon optimization model designing host-specific coding DNA for a target protein, conditioned on any of 164 organisms across all domains of life.

Graph attention foundation model for spatial transcriptomics that assigns spatial domains zero-shot across gene panels, tissues, and technologies.

Missense variant effect predictor that distills GEMME evolutionary scores into a small head over frozen protein language model embeddings.

Structure-based RNA virtual screening that scores small molecules against a binding site's base-pairing graph, around 10,000x faster than docking.