The Ohio State University

Multimodal pre-training distils 3D, text and biochemical knowledge into a 2D molecular graph encoder, so downstream prediction needs only SMILES.

Ice-binding protein classifiers over frozen ESM-2 embeddings, separating antifreeze from ice-nucleation proteins across bacterial proteomes.

Spatial proteomics foundation model, marker-aware and panel-agnostic, pretrained on 47 million multiplexed tissue-imaging patches from 175 markers.

Instruction-tuned LLM series for multi-property molecule optimization that improves named drug properties while preserving those already in range.

Agent-based pathology model that navigates whole-slide images by zooming and panning like a pathologist, scoring 88.6% on the PathMMU-HR2 benchmark.

Structure-constrained molecular generation using reinforcement learning over reaction templates, trained without any external property metric.

Instruction-tuned LLMs for multi-property molecule optimization, rewriting a hit compound to improve three or more drug properties at once.

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

Histopathology vision-language model handling image patches and gigapixel slides in one 15B checkpoint, across classification, VQA, and captioning.

Multimodal large language model that interprets 12-lead electrocardiogram images, answering open-ended clinical questions and generating ECG reports.

Multimodal vision-language copilot for pathology that answers open-ended questions about histology images and reasons about differential diagnoses.

Histopathology multimodal assistant answering questions about H&E patches, pairing a pathology-trained CLIP tower with a 13B Vicuna language model.

Histopathology vision-language model classifying H&E patches zero-shot from text prompts, trained on 1.6M captions written for whole-slide crops.

Multimodal pathology assistant that answers questions about histology and cytology images, pairing the PathCLIP vision encoder with a Vicuna-13B LLM.