Andrea Francesca Salvador
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Andrea Francesca Salvador has a total of 87 co-authors. Here are the top co-authors by number of shared publications:
Igor Smirnov
Center for Brain Immunology and Glia (BIG), Washington University in St. Louis, St. Louis, MO, USA
3 shared publications- Jonathan Kipnis
Department of Pathology and Immunology, Washington University School of Medicine, St. Louis, MO, USA
3 shared publications Morgan Wall
Department of Neuroscience, University of Virginia School of Medicine, Charlottesville, VA, USA
3 shared publications- Taitea Dykstra
Brain Immunology and Glia (BIG) Center, Washington University in St. Louis, St. Louis, USA
3 shared publications Dylan H. Goldman
Center for Brain Immunology and Glia (BIG), Washington University in St. Louis, St. Louis, MO, USA
2 shared publications- Jasmin Herz
Department of Pathology and Immunology, Washington University School of Medicine in St. Louis, St. Louis, USA
2 shared publications
Latest Publications
- Open Access
BioReason-Pro: Advancing Protein Function Prediction with Multimodal Biological Reasoning
Protein function annotation is fundamental to understanding biological mechanisms, designing therapeutics, and advancing biomedical research. Current computational methods either rely on shallow sequence similarity or treat function prediction as isolated classification tasks, failing to capture the integrative reasoning across sequence, structure, domains, and interactions that expert biologists perform to infer function. We introduce BioReason-Pro, the first multimodal reasoning large language model (LLM) for protein function prediction that integrates protein embeddings with biological context to generate structured reasoning traces. A key input into BioReason-Pro is the set of GO term predictions made by GO-GPT, our autoregressive transformer that captures hierarchical and cross-aspect dependencies of GO terms. BioReason-Pro is trained via supervised fine-tuning on synthetic reasoning traces generated by GPT-5 for over 130K proteins and further optimized through reinforcement learning. It achieves 73.6% F max on GO term prediction and an LLM judge score of 8/10 on functional summaries, substantially outperforming previous methods. Evaluations with human protein experts show that BioReason-Pro annotations are preferred over ground truth UniProt annotations in 79% of cases. Remarkably, BioReason-Pro de novo predicted experimentally confirmed binding partners with per-residue attention localizing to the exact contact residues resolved in cryo-EM structures of those complexes. Together, GO-GPT and BioReason-Pro establish a framework for protein function prediction that combines precise ontology modeling with interpretable biological reasoning.
Open AccessBioReason-Pro: Advancing Protein Function Prediction with Multimodal Biological Reasoning
Protein function annotation is fundamental to understanding biological mechanisms, designing therapeutics, and advancing biomedical research. Current computational methods either rely on shallow sequence similarity or treat function prediction as isolated classification tasks, failing to capture the integrative reasoning across sequence, structure, domains, and interactions that expert biologists perform to infer function. We introduce BioReason-Pro, the first multimodal reasoning large language model (LLM) for protein function prediction that integrates protein embeddings with biological context to generate structured reasoning traces. A key input into BioReason-Pro is the set of GO term predictions made by GO-GPT, our autoregressive transformer that captures hierarchical and cross-aspect dependencies of GO terms. BioReason-Pro is trained via supervised fine-tuning on synthetic reasoning traces generated by GPT-5 for over 130K proteins and further optimized through reinforcement learning. It achieves 73.6% F max on GO term prediction and an LLM judge score of 8/10 on functional summaries, substantially outperforming previous methods. Evaluations with human protein experts show that BioReason-Pro annotations are preferred over ground truth UniProt annotations in 79% of cases. Remarkably, BioReason-Pro de novo predicted experimentally confirmed binding partners with per-residue attention localizing to the exact contact residues resolved in cryo-EM structures of those complexes. Together, GO-GPT and BioReason-Pro establish a framework for protein function prediction that combines precise ontology modeling with interpretable biological reasoning.
- Top Cited Papers
- 28 April 2021
- Published by Springer Nature in Nature
- Vol. 593 (7858) , 255-260
Meningeal lymphatics affect microglia responses and anti-Aβ immunotherapy
Alzheimer’s disease (AD) is the most prevalent cause of dementia1. Although there is no effective treatment for AD, passive immunotherapy with monoclonal antibodies against amyloid beta (Aβ) is a promising therapeutic strategy2,3. Meningeal lymphatic drainage has an important role in the accumulation of Aβ in the brain4, but it is not known whether modulation of meningeal lymphatic function can influence the outcome of immunotherapy in AD. Here we show that ablation of meningeal lymphatic vessels in 5xFAD mice (a mouse model of amyloid deposition that expresses five mutations found in familial AD) worsened the outcome of mice treated with anti-Aβ passive immunotherapy by exacerbating the deposition of Aβ, microgliosis, neurovascular dysfunction, and behavioural deficits. By contrast, therapeutic delivery of vascular endothelial growth factor C improved clearance of Aβ by monoclonal antibodies. Notably, there was a substantial overlap between the gene signature of microglia from 5xFAD mice with impaired meningeal lymphatic function and the transcriptional profile of activated microglia from the brains of individuals with AD. Overall, our data demonstrate that impaired meningeal lymphatic drainage exacerbates the microglial inflammatory response in AD and that enhancement of meningeal lymphatic function combined with immunotherapies could lead to better clinical outcomes.
- 28 April 2021
- Published by Springer Nature in Nature
- Vol. 593 (7858) , 255-260
Top Cited PapersMeningeal lymphatics affect microglia responses and anti-Aβ immunotherapy
Alzheimer’s disease (AD) is the most prevalent cause of dementia1. Although there is no effective treatment for AD, passive immunotherapy with monoclonal antibodies against amyloid beta (Aβ) is a promising therapeutic strategy2,3. Meningeal lymphatic drainage has an important role in the accumulation of Aβ in the brain4, but it is not known whether modulation of meningeal lymphatic function can influence the outcome of immunotherapy in AD. Here we show that ablation of meningeal lymphatic vessels in 5xFAD mice (a mouse model of amyloid deposition that expresses five mutations found in familial AD) worsened the outcome of mice treated with anti-Aβ passive immunotherapy by exacerbating the deposition of Aβ, microgliosis, neurovascular dysfunction, and behavioural deficits. By contrast, therapeutic delivery of vascular endothelial growth factor C improved clearance of Aβ by monoclonal antibodies. Notably, there was a substantial overlap between the gene signature of microglia from 5xFAD mice with impaired meningeal lymphatic function and the transcriptional profile of activated microglia from the brains of individuals with AD. Overall, our data demonstrate that impaired meningeal lymphatic drainage exacerbates the microglial inflammatory response in AD and that enhancement of meningeal lymphatic function combined with immunotherapies could lead to better clinical outcomes.