Super LeArner Prediction of NAb Panels (SLAPNAP): a containerized tool for predicting combination monoclonal broadly neutralizing antibody sensitivity

Williamson, Brian D.; Magaret, Craig A.; Gilbert, Peter B.; Nizam, Sohail; Simmons, Courtney; Benkeser, David

doi:10.1093/bioinformatics/btab398

Cited by 16 publications

(17 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we only compared learning algorithms applied on full Env sequences with neutralization data preprocessed similarly. We compared the LBUM to both RF and GBM models because both boosting trees and RF underlie recently published methods that do not use neural networks (5,7).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Learning patterns of HIV-1 co-resistance to broadly neutralizing antibodies with reduced subtype bias using multi-task learning

Igiraneza,

Zacharopoulou,

Hinch

et al. 2023

Preprint

View full text Add to dashboard Cite

The ability to predict HIV-1 resistance to broadly neutralizing antibodies (bnAbs) will increase bnAb therapeutic benefits. Machine learning is a powerful approach for such prediction. One challenge is that some HIV-1 subtypes in currently available training datasets are underrepresented, which likely affects models’ generalizability across subtypes. A second challenge is that combinations of bnAbs are required to avoid the inevitable resistance to a single bnAb, and computationally determining optimal combinations of bnAbs is an unsolved problem. Recently, machine learning models trained using resistance outcomes for multiple antibodies at once, a strategy called multi-task learning (MTL), have been shown to achieve better performance in several cases than previous approaches. We develop a new model and show that, beyond the boost in performance, MTL also helps address the previous two challenges. Specifically, we demonstrate empirically that MTL can mitigate bias from underrepresented subtypes, and that MTL allows the model to learn patterns of co-resistance between antibodies, thus providing tools to predict antibodies’ epitopes and to potentially select optimal bnAb combinations. Our analyses, publicly available athttps://github.com/iaime/LBUM, can be adapted to other infectious diseases that are treated with antibody therapy.

show abstract

Section: Discussionmentioning

confidence: 99%

“…A common modeling choice is to align Env sequences and treat a site in the alignment as a categorical variable (5)(6)(7)(8)10,11). However, Env is highly variable, thus making multiple sequence alignment very challenging.…”

Section: Model Rationalementioning

confidence: 99%

Learning patterns of HIV-1 co-resistance to broadly neutralizing antibodies with reduced subtype bias using multi-task learning

Igiraneza,

Zacharopoulou,

Hinch

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Alternative approaches may be desirable to augment these data. For example, data on HIV-1 Env sequences are abundant, so modeling precision could be improved using new techniques to predict IC50s from Env sequences [ 27 – 29 ].…”

Section: Discussionmentioning

confidence: 99%

Optimizing clinical dosing of combination broadly neutralizing antibodies for HIV prevention

et al. 2022

View full text Add to dashboard Cite

Broadly neutralizing antibodies (bNAbs) are promising agents to prevent HIV infection and achieve HIV remission without antiretroviral therapy (ART). As with ART, bNAb combinations are likely needed to cover HIV’s extensive diversity. Not all bNAbs are identical in terms of their breadth, potency, and in vivo longevity (half-life). Given these differences, it is important to optimally select the composition, or dose ratio, of combination bNAb therapies for future clinical studies. We developed a model that synthesizes 1) pharmacokinetics, 2) potency against a wide HIV diversity, 3) interaction models for how drugs work together, and 4) correlates that translate in vitro potency to clinical protection. We found optimization requires drug-specific balances between potency, longevity, and interaction type. As an example, tradeoffs between longevity and potency are shown by comparing a combination therapy to a bi-specific antibody (a single protein merging both bNAbs) that takes the better potency but the worse longevity of the two components. Then, we illustrate a realistic dose ratio optimization of a triple combination of VRC07, 3BNC117, and 10–1074 bNAbs. We apply protection estimates derived from both a non-human primate (NHP) challenge study meta-analysis and the human antibody mediated prevention (AMP) trials. In both cases, we find a 2:1:1 dose emphasizing VRC07 is nearly optimal. Our approach can be immediately applied to optimize the next generation of combination antibody prevention and cure studies.

show abstract

“…While the evaluation of the PhenoSense assay is ongoing across multiple studies, several new approaches are currently under development. These include outgrowth assays in the presence of the bnAbs for rapid selection, ultrasensitive binding assays that could rapidly infer neutralization sensitivity, and additional sequence-based prediction methods [54][55][56][57][58]. Advances in these technologies will allow the field to build on current methods available only as laboratory assays or prototype clinical screening assays.…”

Section: Future Directionsmentioning

confidence: 99%

Development of screening assays for use of broadly neutralizing antibodies in people with HIV

Lynch

Bar

2023

Current Opinion in HIV and AIDS

View full text Add to dashboard Cite

Purpose of reviewTreatment with combinations of complementary broadly neutralizing antibodies (bnAbs) has increased the proportion of participants for whom bnAbs can maintain virus suppression upon cessation of antiretroviral therapy (ART). There remains, however, a population of trial participants who experience virus rebound despite high plasma concentrations of bnAbs. Thus, baseline resistance remains a critical barrier to the efficacy of bnAbs for use in the treatment and cure of HIV, and the development of a screening assay to guide bnAb selection is a high priority.Recent findingsThere are two conceptual approaches to assess the putative rebound-competent HIV-1 reservoir for bnAb sensitivity: to assess neutralization sensitivity of reactivated virus in outgrowth assays and sequence-based approaches that include a selection for intact genomes and assessment of known resistance mutations within the env gene. Currently, the only phenotypic assay for bnAb screening that is clinical laboratory improvement amendments certified (CLIA certified) and available for clinical trial use is Monogram Biosciences’ PhenoSense HIV Neutralizing Antibody Assay.SummarySeveral new approaches for screening are currently under development and future screening methods must address three issues. First, complete sampling of the reservoir may be impossible, and determination of the relevance of partial sampling is needed. Second, multiple lines of evidence indicate that in vitro neutralization measures are at least one correlate of in vivo bnAb activity that should be included in screening, but more research is needed on how to use in vitro neutralization assays and other measures of antibody functions and measures of other antibody features. Third, the feasibility of screening assays must be a priority. A feasible, predictive bnAb screening assay will remain relevant until a time when bnAb combinations are substantially more broad and potent.

show abstract

Super LeArner Prediction of NAb Panels (SLAPNAP): a containerized tool for predicting combination monoclonal broadly neutralizing antibody sensitivity

Cited by 16 publications

References 28 publications

Learning patterns of HIV-1 co-resistance to broadly neutralizing antibodies with reduced subtype bias using multi-task learning

Learning patterns of HIV-1 co-resistance to broadly neutralizing antibodies with reduced subtype bias using multi-task learning

Optimizing clinical dosing of combination broadly neutralizing antibodies for HIV prevention

Development of screening assays for use of broadly neutralizing antibodies in people with HIV

Contact Info

Product

Resources

About