Biology subjects

Nguyen, C. H.

Publications and source records attributed to Nguyen, C. H..

8 recordsLinked to original sources

bioRxiv2026

Improving Biological Sequence Prediction with AlphaFold2 Representation

MotivationAccurate prediction of functional sites from primary sequences is essential for elucidating biological mechanisms and advancing rational drug design. However, traditional sequence-based features are inherently unable to capture complex structural protein contexts. Recently, AlphaFold2 (AF2) revolutionized protein structure prediction, raising expectations of AF2 to serve as a feature extractor providing structure-rich representation, which can be useful for sequence-based prediction, particularly for unknown sequences. ResultsWe present a novel feature-engineering paradigm that leverages a high-dimensional latent representation matrix (of L x D, where L is the sequence length and D is the feature dimension size) extracted directly from the AF2 Evoformer module. We systematically evaluated the AF2 representation, comparing with conventional sequence-based features, such as hidden Markov model profiles, using a variety of machine learning models, on two structurally contrasting tasks, calpain cleavage site and nucleic-acid-binding site prediction. The AF2 representation outperformed conventional sequence-based features clearly and entirely, particularly for targets with low sequence homology to training data. Furthermore, interpretability analyses, using SHapley Additive exPlanations (SHAP) and Uniform MAnifoldapproximation and Projection (UMAP), showed more details behind the performance advantage of AF2 representation through feature importance ranking and visualization. Overall, these empirical results confirmed that AF2 representation could effectively bridge the sequence-to-structure gap as a feature input for sequence prediction, without increasing heavy computational burden. Availability and implementationSource code, pre-trained models, and datasets are freely available to non-commercial users at https://github.com/Lili-irtyd/Improve-biological-sequences-prediction-by-AlphaFold2. Contactmami@kuicr.kyoto-u.ac.jp

bioinformatics↗

bioRxiv2026

DeepKOALA: A Fast and Accurate Deep Learning Framework for KEGG Orthology Assignment

The KEGG Orthology (KO) system links DNA and protein sequences to biological functions and pathways, providing a curated, fundamental and consistent annotation framework across all domains of life. While accurate, traditional sequence alignment-based annotation methods are computationally expensive, which severely limits their application in large-scale datasets. To address this challenge, we introduce DeepKOALA, a deep learning approach based on Gated Recurrent Units (GRU), which frames KO annotation as an open-set recognition task. This design reduces false positives arising from out-of-scope sequences and, together with a lightweight GRU backbone, enables high-throughput annotation. The GRU-based model was benchmarked against four other deep learning architectures and showed the best balance between speed and accuracy. We further performed a cross-species evaluation of DeepKOALA in comparison with existing KO annotation tools, where it achieved an F1-score of 0.8653 and 37.5-fold acceleration compared with BlastKOALA. We also provide a specialized fragment model for handling incomplete sequences and an optional Multi-domain mode. Together, these features make DeepKOALA a scalable, efficient, and accurate solution for high-throughput function annotation. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=61 SRC="FIGDIR/small/698072v1_ufig1.gif" ALT="Figure 1"> View larger version (15K): org.highwire.dtl.DTLVardef@8c3b53org.highwire.dtl.DTLVardef@8acfa8org.highwire.dtl.DTLVardef@147398borg.highwire.dtl.DTLVardef@112d762_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2024

Antigen-specific T cell immunotherapy by in vivo mRNA delivery

Immunotherapy has shown promise for treating patients with autoimmune diseases or cancer, yet treatment is associated with adverse effects associated with global activation or suppression of T cell immunity. Here, we developed antigen-presenting nanoparticles (APNs) to selectively engineer disease antigen (Ag)-specific T cells by in vivo mRNA delivery. APNs consist of a lipid nanoparticle core functionalized with peptide-major histocompatibility complexes (pMHCs), facilitating antigen-specific T cell transfection through cognate T cell receptor-mediated endocytosis. In mouse models of type 1 diabetes and multiple myeloma, APNs selectively deplete autoreactive T cells leading to durable control of glycemia, and engineer virus-specific T cells with anti-cancer chimeric antigen receptors (CARs), achieving comparable therapeutic outcome as virally transduced ex vivo CAR. Overall, our work supports the use of APNs to engineer disease-relevant T cells in vivo as Ag-specific immunotherapy for autoimmune disorders and cancer.

bioengineering↗

bioRxiv2024

AMRomics: a scalable workflow to analyze large microbial genome collection

Whole genome analysis for microbial genomics is critical to studying and monitoring antimicrobial resistance strains. The exponential growth of microbial sequencing data necessitates a fast and scalable computational pipeline to generate the desired outputs in a timely and cost-effective manner. Recent methods have been implemented to integrate individual genomes into large collections of specific bacterial populations and are widely employed for systematic genomic surveillance. However, they do not scale well when the population expands and turnaround time remains the main issue for this type of analysis. Here, we introduce AMRomics, a minimalized microbial genomics pipeline that can work efficiently with big datasets. We use different bacterial data collections to compare AMRomics against competitive tools and show that our pipeline can generate similar results of interest but with better performance. The software is open source and is publicly available at https://github.com/amromics/amromics under an MIT license.

bioinformatics↗

bioRxiv2023

Pasa: Leverage population pangenome graph to scaffold prokaryote genome assemblies.

Whole genome sequencing has increasingly become the essential method for studying the genetic mechanisms of antimicrobial resistance and for surveillance of drug-resistant bacterial pathogens. The majority of bacterial genomes sequenced to date have been sequenced with Illumina sequencing technology, owing to its high-throughput, excellent sequence accuracy, and low cost. However, because of the short-read nature of the technology, these assemblies are fragmented into large numbers of contigs, hindering the obtaining of full information of the genome. We develop Pasa, a graph-based algorithm that utilizes the pangenome graph and the assembly graph information to improve scaffolding quality. By leveraging the population information of the bacteria species, Pasa is able to utilize the linkage information of the gene families of the species to resolve the contig graph of the assembly. We show that our method outperforms the current state of the art in terms of accuracy, and at the same time, is computationally efficient to be applied to a large number of existing draft assemblies.

bioinformatics↗

bioRxiv2023

PanTA: An ultra-fast method for constructing large and growing microbial pangenomes

Pangenome analysis is an indispensable step in bacterial genomics to address the high variability of bacteria genomes. However, speed and scalability remain a challenge for pangenome inference software tools to cope with the fast-growing genomic collections. We present PanTA, a software package for constructing the pangenomes of large bacterial collections. We show that PanTA exhibits an unprecedented multiple times more efficient than the current state-of-the-arts while maintaining a similar pangenome accuracy. In addition, PanTA introduces a novel mechanism to construct the pangenome progressively where new samples are added into an existing pangenome without rebuilding the accumulated collection from scratch. In the progressive mode, PanTA is demonstrated to consume orders of magnitude less computational resource than existing solutions in managing the pangenomes of growing microbial datasets. We further show that PanTA can build the pangenome of the entire collection of >28000 Escherichia coli genomes from the RefSeq database on a laptop computer in 32 hours, highlighting the scalability and practicality of PanTA.The software is open source and is publicly available at https://github.com/amromics/panta under an MIT license.

bioinformatics↗

bioRxiv2020

XGSEA: CROSS-species Gene Set Enrichment Analysis via domain adaptation

Gene set enrichment analysis (GSEA) has been widely used to identify gene sets with statistically significant difference between cases and controls against a large gene set. GSEA needs both phenotype labels and expression of genes. However, gene expression are assessed more often for model organisms than minor species. More importantly, gene expression could not be measured under specific conditions for human, due to high healthy risk of direct experiments, such as non-approved treatment or gene knockout, and then often substituted by mouse. Thus predicting enrichment significance (on a phenotype) of a given gene set of a species (target, say human), by using gene expression measured under the same phenotype of the other species (source, say mouse) is a vital and challenging problem, which we call CROSS-species Gene Set Enrichment Problem (XGSEP). For XGSEP, we propose XGSEA (Cross-species Gene Set Enrichment Analysis), with three steps of: 1) running GSEA for a source species to obtain enrichment scores and p-values of source gene sets; 2) representing the relation between source and target gene sets by domain adaptation; and 3) using regression to predict p-values of target gene sets, based on the representation in 2). We extensively validated XGSEA by using four real data sets under various settings, proving that XGSEA significantly outperformed three baseline methods. A case study of identifying important human pathways for T cell dysfunction and reprogramming from mouse ATAC-Seq data further confirmed the reliability of XGSEA. Source code is available through https://github.com/LiminLi-xjtu/XGSEA Author summaryGene set enrichment analysis (GSEA) is a powerful tool in the gene sets differential analysis given a ranked gene list. GSEA requires complete data, gene expression with phenotype labels. However, gene expression could not be measured under specific conditions for human, due to high risk of direct experiments, such as non-approved treatment or gene knockout, and then often substituted by mouse. Thus no availability of gene expression leads to more challenging problem, CROSS-species Gene Set Enrichment Problem (XGSEP), in which enrichment significance (on a phenotype) of a given gene set of a species (target, say human) is predicted by using gene expression measured under the same phenotype of the other species (source, say mouse). In this work, we propose XGSEA (Cross-species Gene Set Enrichment Analysis) for XGSEP, with three steps of: 1) GSEA; 2) domain adaptation; and 3) regression. The results of four real data sets and a case study indicate that XGSEA significantly outperformed three baseline methods and confirmed the reliability of XGSEA.

bioinformatics↗

bioRxiv2019

Viruses of the eukaryotic plankton are predicted to increase carbon export efficiency in the global sunlit ocean

The biological carbon pump, in which carbon fixed by photosynthesis is exported to the deep ocean through sinking, is a major process in Earths carbon cycle. The proportion of primary production that is exported is termed the carbon export efficiency (CEE). Based on in-lab or regional scale observations, viruses were previously suggested to affect the CEE (i.e., viral "shunt" and "shuttle"). In this study, we tested associations between viral community composition and CEE measured at a global scale. A regression model based on relative abundance of viral marker genes explained 67% of the variation in CEE. Viruses with high importance in the model were predicted to infect ecologically important hosts. These results are consistent with the view that the viral shunt and shuttle functions at a large scale and further imply that viruses likely act in this process in a way dependent on their hosts and ecosystem dynamics.

ecology↗