Multimodal protein representations across human brain cell types
Preprint
Abstract
The central nervous system (CNS) comprises diverse cell types whose molecular context shapes the roles of the proteins they express. Computational models offer a scalable way to study the roles of proteins across human brain cell types, with protein language models and interactome- or single-cell-based models capturing complementary information encoded in protein sequences and cellular network contexts. Human brain tissue is hard to access, so brain cell types make up a small fraction of the atlases single-cell models train on and of the benchmarks used for their evaluation. To capture these complementary sources of information in the CNS, we introduce SEMPER, a multimodal representation learning model that aligns protein language model representations with protein-protein interaction networks from 442 cell types of the adult human brain, giving each protein a sequence-informed representation in every cell type in which its gene is expressed. We show that SEMPER representations predict cell type-specific protein complexes and predict genes essential to the survival of dopaminergic neurons, measured in a genome-wide CRISPR screen. In zero-shot retrieval, SEMPER recovers clinically pursued drug targets for Parkinson’s disease, Alzheimer’s disease, multiple sclerosis, Huntington’s disease and amyotrophic lateral sclerosis at higher rates than cell type-specific models. To further improve target recovery, we combine SEMPER with a large language model that reasons over protein functional annotations. The combination recovers more targets, with SEMPER providing experimentally derived cellular context that complements literature-based reasoning of the large language model.Funding Information
- Aligning Science Across Parkinson's Initiative
- Collaborative Center for X-linked Dystonia-Parkinsonism at Massachusetts General Hospital
- NSF CAREER (2339524)
- Amazon Faculty Research
- Google Research Scholar Program
- AstraZeneca Research
- Roche Alliance with Distinguished Scientists (ROADS) Program
- Sanofi iDEA-iTECH Award
- GlaxoSmithKline Award
- Boehringer Ingelheim Award
- Merck Award
- Optum AI Research Collaboration Award
- Gates Foundation, INV (079038)
- Chan Zuckerberg Initiative
- John and Virginia Kaneb Fellowship at Harvard Medical School
- Biswas Computational Biology Initiative in partnership with the Milken Institute
- Harvard Medical School Dean’s Innovation Fund for the Use of Artificial Intelligence
- Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University
This publication has 156 references indexed in Scilit:
- Evaluating the Utilities of Foundation Models in Single‐Cell Data AnalysisAdvanced Science, 2026
- Astrocytes and Microglia in Alzheimer's Disease: Friends, Foes, or Both?Developmental Neurobiology, 2025
- Microtubules, Membranes, and Movement: New Roles for Stathmin‐2 in Axon IntegrityJournal of Neuroscience Research, 2024
- UniProtKB/Swiss-Prot, the Manually Annotated Section of the UniProt KnowledgeBase: How to Use the Entry View2016
- On Human Disease-Causing Amino Acid Variants: Statistical Study of Sequence and Structural PatternsHuman Mutation, 2015
- SQSTM1 Mutations in Familial and Sporadic Amyotrophic Lateral SclerosisArchives of Neurology, 2011
- The Human Protein Atlas—a tool for pathologyThe Journal of Pathology, 2008
- Biochemical abnormalities and excitotoxicity in Huntington's disease brainAnnals of Neurology, 1999
- Mitochondrial defect in Huntington's disease caudate nucleusAnnals of Neurology, 1996
- Basic Local Alignment Search ToolJournal of Molecular Biology, 1990