University of Missouri

Post-translational modification site prediction over frozen ProtT5 embeddings, sharing one model across six PTM types via anchor-based flow matching.

Protein structure tokenizer that maps 3D backbones to discrete tokens with an SE(3)-equivariant encoder preserving orientation and chirality.

Sequence-based protein-ligand binding site predictor pairing a protein language model with a SMILES chemical language model for zero-shot ligands.

Transcription factor binding site prediction fusing DNA sequence with TF protein embeddings by cross-attention, generalizing zero-shot to unseen TFs.

Automated cryo-EM structure determination that fuses density maps with AlphaFold3 predictions, averaging a TM-score of 0.93 on high-resolution maps.

Structure-aware protein language model aligning sequence and 3D structure by contrastive learning, with adapter and LoRA fine-tuning tools.

Multitask binding site prediction across protein, DNA/RNA, ligand, lipid, and ion partners, combining protein language models with equivariant GNNs.

RNA 3D structure reconstruction from cryo-EM density maps, using a 3D U-Net that predicts 18 atom types and assigns sequence by global alignment.

Cryo-EM density-map-to-atomic-structure modeling that fuses protein language model embeddings with density voxels, then refines with AlphaFold3.

Protein complex structure prediction system combining AlphaFold2 and AlphaFold3 with stoichiometry prediction, MSA engineering, and model ranking.

Graph transformer that scores the accuracy of predicted protein complex structures, ranking model pools using pairwise structural similarity graphs.

Gene regulatory network inference from single-cell or bulk RNA-seq with a graph transformer. One checkpoint transfers across species and cell types.

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

Multi-task protein framework recasting function, binding site, and structure prediction as autoregressive next-token prediction over ESM2 embeddings.