Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/598870

Prediction of the Effect of Naturally Occurring Missense Mutations on Cellular N-Acetyl-Glucosaminidase Enzymatic Activity

Ford, C. T.·Nodzak, C. M.·Uppal, A.·Shi, X.
View original source ↗Export metadata ↓

Abstract

In 2015, the Critical Assessment of Genome Interpretation (CAGI) proposed a challenge to devise a computational method for predicting the phenotypic consequences of genetic variants of a lysosomal hydrolase enzyme known as -N-acetylglucosaminidase (NAGLU). In 2014, the Human Gene Mutation Database released that 153 NAGLU mutations associated with MPS IIIB and 90 of them are missense mutations. The ExAC dataset catalogued 189 missense mutations NAGLU based on exome sequence data from about 60,000 individual and 24 of them are known to be disease associated. Biotechnology company, BioMarin, has quantified the relative functionality of NAGLU for the remaining subset of 165 missense mutations. For this particular challenge, we examined the subset missense mutations within the ExAC dataset and predicted the probability of a given mutation being deleterious and relating this measure to the capacity of enzymatic activity. In doing so, we hoped to learn the degree to which changes in amino acid physicochemical properties are tolerable for NAGLU function.\n\nAmino acid substitution (AAS) prediction methods are mainly based on the sequence and structure information. Simple comparisons between different AAS methods are not only difficult, but also irrational because each method was tested on various datasets and based on varied versions of databases. Currently, several AAS prediction methods have been introduced. PolyPhen-2, an updated version of PolyPhen, is a tool used to predict possible impacts of an amino acid substitution on the structure and function. Users are required to provide protein or SNP identifiers, protein sequences, substitution positions, etc. A score is provided, ranging from 0 to 1, corresponding to the probability of a mutation resulting in no functionality for the enzyme\n\nOnce the probability scores were generated, the dataset was then run through multiple machine learning algorithms to generate an applicable model for predicting the enzymatic activity of MPS IIIB-related mutations. This prediction was generated using the PolyPhen-2 probability score and other information about the mutation (amino acid type, location, allele frequency, etc.) as input feature variables. This generated a predicted aggregate score for each mutation, which was then reported back to CAGI. The results of the analysis are significant enough to hold confidence that the scores are decent predictors of enzymatic activity given a mutation in the NAGLU amino acid sequence.

Explore related subjects

bioinformaticsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Ford, C. T., Nodzak, C. M., Uppal, A., Shi, X.. 2019-04-05. Prediction of the Effect of Naturally Occurring Missense Mutations on Cellular N-Acetyl-Glucosaminidase Enzymatic Activity. https://doi.org/10.1101/598870

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Deducing splicing events from transcript sets with splicelogic

Long-read RNA sequencing captures a greater proportion of full-length transcripts, enabling more accurate isoform identification, discovery of novel isoforms, and more precise differential transcript usage analysis. However, comparing transcripts, whether between conditions or between sets such as novel and annotated isoforms, yields complex isoform changes that are hard to manipulate, summarize, and visualize. This is compounded by vertical integration of some tools, where downstream analysis depends on the specific output of a particular upstream tool. To address this gap, we have developed splicelogic, an R/Bioconductor package that makes transcript-set comparisons biologically interpretable by turning them into discrete splicing events, such as exon skipping, alternative splice sites, intron retention, and alternative transcription start and end sites. We designed splicelogic to integrate easily with existing RNA-seq workflows and tools. The splicelogic functions are modular, readable, and extensible, making it easy for users to adapt core logic to their own custom scientific questions or novel splicing definitions. By obtaining interpretable splicing events from transcript changes, splicelogic enables downstream analyses, including annotation of RNA-binding protein recognition sites, alongside summary statistics and visualization. The splicelogic package is publicly available and distributed through Bioconductor.

bioinformatics↗
bioRxiv2026

Contrastive Learning Improves Generalization on M2OR Olfactory Binding Dataset

Olfaction-based biosensors stand to have profound impacts in fields such as medical diagnostics, national security, and drug discovery. A promising mode of vapor phase biodetection mimics volatile organic compound-olfactory receptor (VOC-OR) interactions with target-specific protein or peptide probes; however, lack of experimental coverage remains a core bottleneck. Current computational approaches aim to improve prediction of VOC-OR binding to reduce experimental burden, and current machine learning approaches fail to demonstrate a level of generalization that addresses current engineering challenges. Here, using the Molecular to Olfactory Dataset (M2OR) and Insect Olfactory Binding Protein Database (iOBPdb) datasets, data partitioning methods and their performance are evaluated on a neural network and contrastive learning framework on such VOC-OR binding datasets, varying: model training, architecture, and structure of the input data distribution. It was found that holding out certain chemical or proteomic motifs from the training data diminished model performance with a two layer neural network model. The model was able to generalize to state of the art performance (0.88 AUCROC) on every data split by applying a contrastive learning objective defined by shared molecular constituents and a stochastic sampler. This suggests the contrastive objective provides a strong inductive bias for neural networks to predict novel VOC-OR pairs. These findings highlight that model performance on pairwise biological interaction datasets can be inflated through identity leakage from constituent overlap, and emphasize the need for more robust evaluation protocols. Furthermore, we show contrastive regularization mitigates dataset degeneracy through enforcement of compatibility in the models latent geometry that may extend to other binder target-datasets where identity leakage confounds evaluation.

bioinformatics↗
bioRxiv2026

Plate design confounds donor variation and model evaluation in single-cell perturbation screens

Single-cell screens of immune cells from many donors are used to study why individuals respond differently and to benchmark response models. Each donor-perturbation combination typically occupies one well, controls are grouped, and donors share one layout, so technical effects can look biological. Using a 90-cytokine screen, two compound screens, four cohorts and simulations, we show that well effects explain most replicate-control variation in abundant cell types, controls carry a shared offset, and identical control wells differ by hundreds of differentially expressed genes at a standard threshold, about as many as two receptor-negative proteins do. Negative controls, design-aware estimators and perturbation-specific evaluation change the interpretation of four recent analyses. A deep-learning model that scores below a perturbation-agnostic predictor under standard evaluation outperforms a simple baseline on perturbation-specific differences in two of three cell types (significantly in one with stricter controls), but predicts less well the component shared with inert wells.

bioinformatics↗