All Competitors

Protein-ligand binding site prediction that ranks pocket residues and pocket center coordinates, staying accurate on AlphaFold-predicted structures.

Cryo-EM and cryo-ET map enhancement model that sharpens density maps with a Mamba-based dual-branch UNet and local resolution-guided learning.

Protein dynamics model predicting per-residue covariances and residue-residue coupling from a static structure for fast RMSF and ensemble generation.

Coaxial-stacking prediction for RNA multi-way junctions from sequence and secondary structure, at ~0.87 mean accuracy across 2- to 7-way topologies.

Sequence-based protein-protein interaction predictor over ProtT5 embeddings that reaches 0.70 AUROC on the leakage-free gold standard benchmark.

Protein-protein interface prediction from 3D structure using face-centered surface fingerprints and geometric graph attention, at ROC AUC 0.89.

Surface-EMG wristband models that decode hand gestures, handwriting, and wrist movement, generalizing across users without per-person calibration.

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

Protein-protein interaction predictor that adds contact-guided dual attention and a geometric encoder to frozen protein language model embeddings.

De novo peptide sequencing from mirror-protease mass spectra, reading paired complementary spectra to recover near-complete fragment ion coverage.

GPCR peptide agonist screening with a graph neural network over AlphaFold-Multimer active-state complexes and interatomic contact graphs.

Cryo-ET tilt-series classifier that flags and removes tilts corrupted by drift, contamination, ice reflections, lamella edges, or thick lamellae.

Phylogenetic tree inference from unaligned nucleotide sequences, using a 2D genomic-footprint encoding and CNN classification of triplet topologies.

Enzyme turnover number (kcat) prediction from sequence and substrate SMILES, scaling to genome-wide kinetic parameters for metabolic modeling.

Protein inverse folding ensemble that fuses five pretrained sequence designers through a self-attention encoder, reaching 63.1% recovery on CATH4.2.

Protein language model fine-tuned on yeast-display directed evolution data to score rice immune receptor variants for fungal effector binding.

Base-pair resolution sequence-to-activity CNN predicting ATAC-seq Tn5 insertion profiles and accessibility across 90 mouse immune cell types.

Somatic copy-number alteration calling from tumor whole-genome sequencing, using Mamba and Hyena blocks over genome-scale inputs of about 1M loci.

Anti-phage defense gene classifier pairing protein language model embeddings with genomic features to find immune systems outside defense islands.

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

RNA modification classification from nanopore direct-RNA current, resolving m6A, inosine, pseudouridine, Gm, and m1A at single-base resolution.

Base-resolution chromatin accessibility model that factors out enzyme sequence bias to score regulatory variants and transcription factor footprints.

Graph neural network counting recurring cell-type neighborhood motifs in spatial transcriptomics and proteomics, linking topology to phenotype.