Data-augmented machine learning redefines the effective concentration of eculizumab in complement blood disorders
Alfonso-Gonzalez, L.; Fernandez, F. J.; Praga, M.; Mikkelsen, K.; Vega, M. C.
Show abstract
Eculizumab, a humanized monoclonal antibody targeting the complement lytic pathway protein C5, has demonstrated high efficacy in the treatment of paroxysmal nocturnal hemoglobinuria, atypical hemolytic uremic syndrome, generalized myasthenia gravis, and neuromyelitis optica spectrum disorder. However, recent reports have highlighted patients who exhibit a lack of treatment response, necessitating an increase in the recommended dose or a reduction in the dosing interval. In this study, we employed machine-learning predictive models to identify the optimal blood concentration of eculizumab to inhibit the complement lytic pathway. Additionally, we examined the impact of data augmentation through the generation of artificial data on the predictive performance of these models. In conclusion, our machine learning model predicts that the target blood concentration of eculizumab should be increased to a minimum of 152-162 g mL-1 (up from 50-100 g mL-1) to achieve a more complete inhibition of the complement systems lytic pathway.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Nintedanib Targets KIT D816V Neoplastic Cells Derived from Induced Pluripotent Stem cells of Systemic Mastocytosis 91%
- Engineered coagulation factor VIII with enhanced secretion and coagulation potential for hemophilia A gene therapy 91%
- Mutant-SETBP1 activates transcription of Myc programs to accelerate CSF3R-driven myeloproliferative neoplasms 90%
Similar papers in this journal
- Clinical Knowledge Extraction via Sparse Embedding Regression (KESER) with Multi-Center Large Scale Electronic Health Record Data 91%
- Conformal prediction enables disease course prediction and allows individualized diagnostic uncertainty in multiple sclerosis 91%
- Federated Target Trial Emulation using Distributed Observational Data for Treatment Effect Estimation 90%
Similar papers in this journal
- Serological fingerprints link antiviral activity of therapeutic antibodies to affinity and concentration 93%
- Synergistic and antagonistic drug interactions are prevalent but not conserved across acute myeloid leukemia cell lines 93%
- Mebendazole for Differentiation Therapy of Acute Myeloid Leukemia Identified by a Lineage Maturation Index 92%
Similar papers in this journal
Similar papers in this journal
- Zero-shot drug repurposing with geometric deep learning and clinician centered design 92%
- Actionable druggable genome-wide Mendelian randomization identifies repurposing opportunities for COVID-19 90%
- Immunogenicity and reactogenicity of a heterologous COVID-19 prime-boost vaccination compared with homologous vaccine regimens 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.