A machine learning model for predicting serum neutralizing activity against Omicron SARS-CoV-2 BA.2 and BA.4/5 sublineages in the general population.

Supervised machine learning (ML) methods have been used to predict antibody responses elicited by COVID-19 vaccines in a variety of clinical settings. Here, we explored the reliability of a ML approach to predict the presence of detectable neutralizing antibody responses (NtAb) against Omicron BA.2 and BA.4/5 sublineages in the general population. Anti-SARS-CoV-2 receptor-binding domain (RBD) total antibodies were measured by the Elecsys® Anti-SARS-CoV-2 S assay (Roche Diagnostics) in all participants. NtAbs against Omicron BA.2 and BA4/5 were measured using a SARS-CoV-2 S pseudotyped neutralization assay in 100 randomly selected sera. A ML model was built using the variables of age, vaccination (number of doses) and SARS-CoV-2 infection status. The model was trained in a cohort (TC) comprising 931 participants and validated in an external cohort (VC) including 787 individuals. Receiver operating characteristics analysis indicated that an anti-SARS-CoV-2 RBD total antibody threshold of 2300 BAU/mL best discriminated between participants either exhibiting or not detectable Omicron BA.2 and Omicron BA.4/5-Spike targeted NtAb responses (87% and 84% precision, respectively). The ML model correctly classified 88% (793/901) of participants in the TC: 717/749 (95.7%) of those displaying ≥2300 BAU/mL and 76/152 (50%) of those exhibiting antibody levels <2300 BAU/mL. The model performed better in vaccinated participants, either with or without prior SARS-CoV-2 infection. The overall accuracy of the ML model in the VC was comparable. Our ML model, based upon a few easily collected parameters for predicting neutralizing activity against Omicron BA.2 and BA.4/5 (sub)variants circumvents the need to perform not only neutralization assays, but also anti-S serological tests, thus potentially saving costs in the setting of large seroprevalence studies.

A performance comparison of two (electro) chemiluminescence immunoassays for detection and quantitation of serum anti-spike antibodies according to SARS-CoV-2 vaccination and infections status.

The information provided by SARS-CoV-2 spike (S)-targeting immunoassays can be instrumental in clinical-decision making. We compared the performance of the Elecsys® Anti-SARS-CoV-2 S assay (Roche Diagnostics) and the LIAISON® SARS-CoV-2 TrimericS IgG assay (DiaSorin) using a total of 1176 sera from 797 individuals, of which 286 were from vaccinated-SARS-CoV-2/experienced (Vac-Ex), 581 from vaccinated/naïve (Vac-N), 147 from unvaccinated/experienced (Unvac-Ex), and 162 from unvaccinated/naïve (Unvac-N) individuals. The Roche assay returned a higher number of positive results (907 vs. 790; p = 0.45; overall sensitivity: 89.3% vs. 77.6%). The concordance between results provided by the two immunoassays was higher for sera from Vac-N (Ï°: 0.58; interquartile ranges [IQR]: 0.50-0.65) than for sera from Vac-Ex (Ï°: 0.19; IQR: -0.14 to 0.52) or Unvac-Ex (Ï°: 0.18; IQR: 0.06-0.30). Discordant results occurred more frequently among sera from Unvac-Ex (34.7%) followed by Vac-N (14.6%) and Vac-Ex (2.7%). Antibody levels quantified by both immunoassays were not significantly different when <250 (p = 0.87) or <1000 BAU/ml (p = 0.13); in contrast, for sera ≥1000 BAU/ml, the Roche assay returned significantly higher values than the DiaSorin assay (p < 0.008). Neutralizing antibody titers (NtAb) were measured in 127 sera from Vac-Ex or Vac-N using a S-pseudotyped virus neutralization assay of Wuhan-Hu-1, Omicron BA.1, and Omicron BA.2. The correlation between antibody levels and NtAb titers was higher for sera from Vac-N than those from Vac-Ex, irrespective of the (sub)variant considered. In conclusion, neither qualitative nor quantitative results returned by both immunoassays are interchangeable. The performance of both assays was found to be greatly influenced by the vaccination and SARS-CoV-2 infection status of individuals.