Scott H. Soderling

Reward-guided inference-time search over the Proteína-Complexa sequence-structure codesign model yields validated binders across 127 targets, kinases and a free carbohydrate, with codesigned sequences outperforming ProteinMPNN redesign.

The paper uses in vivo proteomics and CRISPR screening to identify STXBP1 as a protective factor against α-synuclein toxicity in dopamine neurons in Parkinson's disease models.

PLMNovo improves de novo peptide sequencing by aligning spectrum and peptide embeddings using pre-trained protein language models.

The paper identifies new ciliary signaling pathways in the mouse brain using iBioID and links them to neurological disorders.

The paper introduces KolossuS, a deep learning framework for kinase-substrate prediction, integrated with CRISPR-based proximity proteomics to identify kinase substrates in vivo, including novel substrates associated with sleep deprivation.

Raygun is a generative AI framework that miniaturizes, modifies, and expands proteins while preserving function and structural integrity, validated through cell-based experiments.

This study shows that presynaptic Rac1 signaling selectively regulates spatial working memory, with distinct effects on synaptic vesicles and morphology compared to postsynaptic Rac1 inhibition.

This study shows that the LRRK2 G2019S mutation impairs astrocyte morphology and synapse maintenance by hyperphosphorylating ERM proteins, which disrupts the Ezrin/Atg7 interaction and autophagy.

The paper develops a proximity proteomics method in mice to identify protein interactions relevant to autism, revealing new genetic risk factors and functional interactions.

The paper identifies a prefrontal to lateral entorhinal pathway that disrupts memory by showing silencing improves memory and activation impairs it.

This study shows that training-induced excitatory synaptogenesis in the ACC->DMS circuit is required for effort control, not learning, and is mediated by the 2{delta}-1 protein.

This study identifies Rac1 and Arp2/3 as key regulators of presynaptic plasticity through proteomic analysis and shows their coupling to action potentials via calcium influx.

The paper identifies a brain network encoding reward anticipation through multi-region electrical recordings and machine learning analysis in mice.

This study shows that restoring WAVE-1 in GluN1 knockdown mice rescues striatal spine density and improves maze exploration behavior.