N-glycosylation has many essential biological roles, and is important for biotherapeutics as it can affect drug efficacy, duration of effect, and toxicity. The prediction of N-glycosylation and other important biopharmaceutical production values have mostly been limited to mechanistic modeling. We present a residual hybrid modeling approach that integrates mechanistic modeling with machine learning to produce significantly more accurate predictions for N-glycosylation and bioproduction. For the largest dataset, the residual hybrid models have an average 736-fold reduction in testing prediction error. Furthermore, the residual hybrid models have lower prediction errors than the mechanistic models for all of the predicted variables in the datasets. We provide the automatic machine learning software used in this work, allowing reproduction and use of our software for other tasks.

MOTIVATION: The accurate prediction of O-GlcNAcylation sites is crucial for understanding disease mechanisms and developing effective treatments. Previous machine learning (ML) models primarily relied on primary or secondary protein structural and related properties, which have limitations in capturing the spatial interactions of neighboring amino acids. This study introduces local environmental features as a novel approach that incorporates three-dimensional spatial information, significantly improving model performance by considering the spatial context around the target site. Additionally, we utilize sparse recurrent neural networks to effectively capture sequential nature of the proteins and to identify key factors influencing O-GlcNAcylation as an explainable ML model. RESULTS: Our findings demonstrate the effectiveness of our proposed features with the model achieving an F1 score of 28.3%, as well as feature selection capability with the model using only the top 20% of features achieving the highest F1 score of 32.02%, a 1.4-fold improvement over existing PTM models. Statistical analysis of the top 20 features confirmed their consistency with literature. This method not only boosts prediction accuracy but also paves the way for further research in understanding and targeting O-GlcNAcylation. AVAILABILITY AND IMPLEMENTATION: The entire code, data, features used in this study are available in the GitHub repository: https://github.com/pseokyoung/o-glcnac-prediction.

MOTIVATION: This work addresses two common issues in building classification models for biological or medical studies: learning a sparse model, where only a subset of a large number of possible predictors is used, and training in the presence of missing data. This work focuses on supervised generative binary classification models, specifically linear discriminant analysis (LDA). The parameters are determined using an expectation maximization algorithm to both address missing data and introduce priors to promote sparsity. The proposed algorithm, expectation-maximization sparse discriminant analysis (EM-SDA), produces a sparse LDA model for datasets with and without missing data. RESULTS: EM-SDA is tested via simulations and case studies. In the simulations, EM-SDA is compared with nearest shrunken centroids (NSCs) and sparse discriminant analysis (SDA) with k-nearest neighbors for imputation for varying mechanism and amount of missing data. In three case studies using published biomedical data, the results are compared with NSC and SDA models with four different types of imputation, all of which are common approaches in the field. EM-SDA is more accurate and sparse than competing methods both with and without missing data in most of the experiments. Furthermore, the EM-SDA results are mostly consistent between the missing and full cases. Biological relevance of the resulting models, as quantified via a literature search, is also presented. AVAILABILITY AND IMPLEMENTATION: A Matlab implementation published under GNU GPL v.3 license is available at http://web.mit.edu/braatzgroup/links.html . CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Referring to the above said paper by Narendra-Parthasarathy (ibid., vol.1, p4-27 (1990)), it is noted that the given Example 2 (p.15) has a third equilibrium state corresponding to the point (0.5, 0.5).