All Competitors

Protein language model using a multiplicative LSTM over 24 million UniRef50 sequences to produce fixed-length embeddings for protein engineering.

3D convolutional network that predicts subcellular fluorescence labels from transmitted-light microscopy, enabling label-free imaging of living cells.

Antibody paratope prediction model that identifies antigen-contacting residues from heavy and light CDR sequences alone, using CNN and RNN layers.

Dilated convolutional network that predicts cell-type-specific epigenetic and transcriptional profiles from DNA sequence across mammalian genomes.

Visible neural network simulating eukaryotic cell growth by embedding the Gene Ontology into its architecture for interpretable phenotype prediction.

Attention-based model predicting gene expression from histone modification signals across 56 cell types, with interpretable attention scores.

Convolutional neural network that predicts DNA accessibility from sequence across 164 DNase-seq cell types, enabling variant effect prediction.