Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386469202> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4386469202 abstract "Abstract Bias in neural network model training datasets has been observed to decrease prediction accuracy for groups underrepresented in training data. Thus, investigating the composition of training datasets used in machine learning models with health-care applications is vital to ensure equity. Two such machine learning models are NetMHCpan-4.1 and NetMHCIIpan-4.0, used to predict antigen binding scores to major histocompatibility complex class I and II molecules, respectively. As antigen presentation is a critical step in mounting the adaptive immune response, previous work has used these or similar predictions models in a broad array of applications, from explaining asymptomatic viral infection to cancer neoantigen prediction. However, these models have also been shown to be biased toward hydrophobic peptides, suggesting the network could also contain other sources of bias. Here, we report the composition of the networks’ training datasets are heavily biased toward European Caucasian individuals and against Asian and Pacific Islander individuals. We test the ability of NetMHCpan-4.1 and NetMHCpan-4.0 to distinguish true binders from randomly generated peptides on alleles not included in the training datasets. Unexpectedly, we fail to find evidence that the disparities in training data lead to a meaningful difference in prediction quality for alleles not present in the training data. We attempt to explain this result by mapping the HLA sequence space to determine the sequence diversity of the training dataset. Furthermore, we link the residues which have the greatest impact on NetMHCpan predictions to structural features for three alleles (HLA-A*34:01, HLA-C*04:03, HLA-DRB1*12:02)." @default.
- W4386469202 created "2023-09-07" @default.
- W4386469202 creator A5002253225 @default.
- W4386469202 creator A5016755964 @default.
- W4386469202 creator A5021419381 @default.
- W4386469202 creator A5046024173 @default.
- W4386469202 creator A5054665537 @default.
- W4386469202 date "2023-09-06" @default.
- W4386469202 modified "2023-09-27" @default.
- W4386469202 title "Geographically Biased Composition of NetMHCpan Training Datasets and Evaluation of MHC-Peptide Binding Prediction Accuracy on Novel Alleles" @default.
- W4386469202 cites W1968426398 @default.
- W4386469202 cites W1973192023 @default.
- W4386469202 cites W1999283569 @default.
- W4386469202 cites W2002030144 @default.
- W4386469202 cites W2021935957 @default.
- W4386469202 cites W2037918327 @default.
- W4386469202 cites W2132262459 @default.
- W4386469202 cites W2531587846 @default.
- W4386469202 cites W2605830019 @default.
- W4386469202 cites W2721701181 @default.
- W4386469202 cites W2783102765 @default.
- W4386469202 cites W2886283492 @default.
- W4386469202 cites W2922534626 @default.
- W4386469202 cites W2970480306 @default.
- W4386469202 cites W2971041153 @default.
- W4386469202 cites W2981869278 @default.
- W4386469202 cites W3024570138 @default.
- W4386469202 cites W3042910002 @default.
- W4386469202 cites W3189842962 @default.
- W4386469202 cites W4229451133 @default.
- W4386469202 cites W4282960557 @default.
- W4386469202 cites W4308447027 @default.
- W4386469202 cites W4376133743 @default.
- W4386469202 cites W4384820308 @default.
- W4386469202 doi "https://doi.org/10.1101/2023.09.03.556092" @default.
- W4386469202 hasPublicationYear "2023" @default.
- W4386469202 type Work @default.
- W4386469202 citedByCount "0" @default.
- W4386469202 crossrefType "posted-content" @default.
- W4386469202 hasAuthorship W4386469202A5002253225 @default.
- W4386469202 hasAuthorship W4386469202A5016755964 @default.
- W4386469202 hasAuthorship W4386469202A5021419381 @default.
- W4386469202 hasAuthorship W4386469202A5046024173 @default.
- W4386469202 hasAuthorship W4386469202A5054665537 @default.
- W4386469202 hasBestOaLocation W43864692021 @default.
- W4386469202 hasConcept C104317684 @default.
- W4386469202 hasConcept C119857082 @default.
- W4386469202 hasConcept C147483822 @default.
- W4386469202 hasConcept C154945302 @default.
- W4386469202 hasConcept C180754005 @default.
- W4386469202 hasConcept C188280979 @default.
- W4386469202 hasConcept C207936829 @default.
- W4386469202 hasConcept C41008148 @default.
- W4386469202 hasConcept C50644808 @default.
- W4386469202 hasConcept C54355233 @default.
- W4386469202 hasConcept C70721500 @default.
- W4386469202 hasConcept C86803240 @default.
- W4386469202 hasConceptScore W4386469202C104317684 @default.
- W4386469202 hasConceptScore W4386469202C119857082 @default.
- W4386469202 hasConceptScore W4386469202C147483822 @default.
- W4386469202 hasConceptScore W4386469202C154945302 @default.
- W4386469202 hasConceptScore W4386469202C180754005 @default.
- W4386469202 hasConceptScore W4386469202C188280979 @default.
- W4386469202 hasConceptScore W4386469202C207936829 @default.
- W4386469202 hasConceptScore W4386469202C41008148 @default.
- W4386469202 hasConceptScore W4386469202C50644808 @default.
- W4386469202 hasConceptScore W4386469202C54355233 @default.
- W4386469202 hasConceptScore W4386469202C70721500 @default.
- W4386469202 hasConceptScore W4386469202C86803240 @default.
- W4386469202 hasLocation W43864692021 @default.
- W4386469202 hasOpenAccess W4386469202 @default.
- W4386469202 hasPrimaryLocation W43864692021 @default.
- W4386469202 hasRelatedWork W1989613103 @default.
- W4386469202 hasRelatedWork W1990329984 @default.
- W4386469202 hasRelatedWork W1991211153 @default.
- W4386469202 hasRelatedWork W1997924220 @default.
- W4386469202 hasRelatedWork W2021502563 @default.
- W4386469202 hasRelatedWork W2057739827 @default.
- W4386469202 hasRelatedWork W2067167938 @default.
- W4386469202 hasRelatedWork W2070922469 @default.
- W4386469202 hasRelatedWork W2091857464 @default.
- W4386469202 hasRelatedWork W2223919059 @default.
- W4386469202 isParatext "false" @default.
- W4386469202 isRetracted "false" @default.
- W4386469202 workType "article" @default.