Machine-learning a virus assembly fitness landscape.
Ontology highlight
ABSTRACT:
SUBMITTER: Dechant PP
PROVIDER: S-EPMC8099058 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Machine learning (ML) can aid in novel discoveries in the field of viral gene therapy. Specifically, big data gathered through next-generation sequencing (NGS) of complex capsid libraries is an especially prominent source of lost potential in data analysis and prediction. Furthermore, adeno-associated virus (AAV)-based capsid libraries are becoming increasingly popular as a tool to select candidates for gene therapy vectors. These higher complexity AAV capsid libraries have previously been created and selected in vivo; however, in silico analysis using ML computer algorithms may augment smarter and more robust libraries for selection. In this study, data of AAV capsid libraries gathered before and after viral assembly are used to train ML algorithms. We found that two ML computer algorithms, artificial neural networks (ANNs), and support vector machines (SVMs), can be trained to predict whether unknown capsid variants may assemble into viable virus-like structures. Using the most accurate models constructed, hypothetical mutation patterns in library construction were simulated to suggest the importance of N495, G546, and I554 in AAV2-derived capsids. Finally, two comparative libraries were generated using ML-derived data to biologically validate these findings and demonstrate the predictive power of ML in vector design.
| S-EPMC7809249 | biostudies-literature
Project description:Small proteins, encoded by small open reading frames, are only beginning to emerge with the current advancement of omics technology and bioinformatics. There is increasing evidence that small proteins play roles in diverse critical biological functions, such as adjusting cellular metabolism, regulating other protein activities, controlling cell cycles, and affecting disease physiology. In prokaryotes such as bacteria, the small proteins are largely unexplored for their sequence space and functional groups. For most bacterial species from a natural community, the sample cannot be easily isolated or cultured, and the bacterial peptides must be better characterized in a metagenomic manner. The bacterial peptides identified from metagenomic samples can not only enrich the pool of small proteins but can also reveal the community-specific microbe ecology information from a small protein perspective. In this study, metaBP (Bacterial Peptides for metagenomic sample) has been developed as a comprehensive toolkit to explore the small protein universe from metagenomic samples. It takes raw sequencing reads as input, performs protein-level meta-assembly, and computes bacterial peptide homolog groups with sample-specific mutations. The metaBP also integrates general protein annotation tools as well as our small protein-specific machine learning module metaBP-ML to construct a full landscape for bacterial peptides. The metaBP-ML shows advantages for discovering functions of bacterial peptides in a microbial community and increases the yields of annotations by up to five folds. The metaBP toolkit demonstrates its novelty in adopting the protein-level assembly to discover small proteins, integrating protein-clustering tool in a new and flexible environment of RBiotools, and presenting the first-time small protein landscape by metaBP-ML. Taken together, metaBP (and metaBP-ML) can profile functional bacterial peptides from metagenomic samples with potential diverse mutations, in order to depict a unique landscape of small proteins from a microbial community.
| S-EPMC9354662 | biostudies-literature
Project description:Viral fitness is determined by replication within hosts and transmission between them. We examine how pleiotropic mutations that have antagonistic effects (i.e., antibody evasion vs. receptor binding) on viral replication within hosts can impact viral immune escape in the host population. When the host population is vaccinated, the virus escapes from passive immunity by mutations in the antibody-binding region on the surface of the target protein. However, the reduced ability of the antibody to bind the virus is often accompanied by a reduced ability of the virus to bind the cell receptor because the antibody-binding region overlaps with the receptor-binding domain (RBD). The types of permitted mutations are limited. To investigate the causal relation between a mutation in a viral genome and adaptive evolution of a viral population, we developed a mathematical model that describes the population dynamics of viruses, antibodies, and normal/infected cells within a host. The coefficients describe the binding affinity between the virus and the induced antibody and that between the virus and its receptor. Our knowledge-based index enables us to estimate the effect of a mutation in a binding region on the binding affinity. Using population genetic theory, we evaluated the probability that a mutant is fixed in a host population. The mutations that can be fixed with high probabilities may determine how long a vaccine remains effective. We simulate the adaptive evolution of coronavirus, the etiological agent of severe acute respiratory syndrome, and show that some of mutations in the RBD may have high fixation probabilities in the vaccinated host population.
| S-EPMC7187634 | biostudies-literature
Project description:Here we show, at a high resolution (1%), the human immunodeficiency virus type 1 (HIV-1) protease gene quasispecies landscape from three infected naïve individuals. A huge range of genetic configurations was found (67%, 71%, and 80% of the nucleotide clones from the three individuals, respectively, were different), and these configurations created a dense net that linked different parts of the viral population. Similarly, a vast diversity of different protease activities was also found. Importantly, 65% of the analyzed enzymes had detectable protease activity, and 11% of the minority individual variants showed similar or better fitness than the master (most abundant) enzyme, suggesting that the viral complexity in this genomic region does not exclusively depend on the enzyme's catalytic efficiency. Several high-fitness minority variants had only one substitution compared to the master sequence, supporting the possibility that the rugged HIV-1 protease quasispecies fitness landscape may be formed by a continuous network that can be traversed by single mutational steps without passing through defective or less-adapted proteins.
| S-EPMC1865935 | biostudies-literature
Project description:Viral evolutionary pathways are determined by the fitness landscape, which maps viral genotype to fitness. However, a quantitative description of the landscape and the evolutionary forces on it remain elusive. Here, we apply a biophysical fitness model based on capsid folding stability and antibody binding affinity to predict the evolutionary pathway of norovirus escaping a neutralizing antibody. The model is validated by experimental evolution in bulk culture and in a drop-based microfluidics that propagates millions of independent small viral subpopulations. We demonstrate that along the axis of binding affinity, selection for escape variants and drift due to random mutations have the same direction, an atypical case in evolution. However, along folding stability, selection and drift are opposing forces whose balance is tuned by viral population size. Our results demonstrate that predictable epistatic tradeoffs between molecular traits of viral proteins shape viral evolution.
| S-EPMC6188569 | biostudies-literature
Project description:Cardiopulmonary exercise testing (CPET) is a non-invasive approach to measure the maximum oxygen uptake ([Formula: see text]), which is an index to assess cardiovascular fitness (CF). However, CPET is not available to all populations and cannot be obtained continuously. Thus, wearable sensors are associated with machine learning (ML) algorithms to investigate CF. Therefore, this study aimed to predict CF by using ML algorithms using data obtained by wearable technologies. For this purpose, 43 volunteers with different levels of aerobic power, who wore a wearable device to collect unobtrusive data for 7 days, were evaluated by CPET. Eleven inputs (sex, age, weight, height, and body mass index, breathing rate, minute ventilation, total hip acceleration, walking cadence, heart rate, and tidal volume) were used to predict the [Formula: see text] by support vector regression (SVR). Afterward, the SHapley Additive exPlanations (SHAP) method was used to explain their results. SVR was able to predict the CF, and the SHAP method showed that the inputs related to hemodynamic and anthropometric domains were the most important ones to predict the CF. Therefore, we conclude that the cardiovascular fitness can be predicted by wearable technologies associated with machine learning during unsupervised activities of daily living.
| S-EPMC9980797 | biostudies-literature
Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status. RNA was isolated from 199 primary breast cancer patients. A machine learning classifier was built to predict ER status using only three gene features.
2013-01-01 | E-GEOD-29210 | biostudies-arrayexpress
Project description:Adeno-associated virus (AAV) capsids can deliver transformative gene therapies, but our understanding of AAV biology remains incomplete. We generated the complete first-order AAV2 capsid fitness landscape, characterizing all single-codon substitutions, insertions, and deletions across multiple functions relevant for in vivo delivery. We discovered a frameshifted gene in the VP1 region that expresses a membrane-associated accessory protein that limits AAV production through competitive exclusion. Mutant biodistribution revealed the importance of both surface-exposed and buried residues, with a few phenotypic profiles characterizing most variants. Finally, we algorithmically designed and experimentally verified a diverse in vivo targeted capsid library with viability far exceeding random mutagenesis approaches. These results demonstrate the power of systematic mutagenesis for deciphering complex genomes and the potential of empirical machine-guided protein engineering.
| S-EPMC7197022 | biostudies-literature
Project description:An Adeno-Associated Virus capsid fitness landscape reveals a frameshifted viral gene and in vivo design principles, enabling machine-guided engineering.
2019-11-29 | GSE139657 | GEO
Project description:Evolutionary rescue describes a situation where adaptive evolution prevents the extinction of a population facing a stressing environment. Models of evolutionary rescue could in principle be used to predict the level of stress beyond which extinction becomes likely for species of conservation concern, or, conversely, the treatment levels most likely to limit the emergence of resistant pests or pathogens. Stress levels are known to affect both the rate of population decline (demographic effect) and the speed of adaptation (evolutionary effect), but the latter aspect has received less attention. Here, we address this issue using Fisher's geometric model of adaptation. In this model, the fitness effects of mutations depend both on the genotype and the environment in which they arise. In particular, the model introduces a dependence between the level of stress, the proportion of rescue mutants, and their costs before the onset of stress. We obtain analytic results under a strong-selection-weak-mutation regime, which we compare to simulations. We show that the effect of the environment on evolutionary rescue can be summarized into a single composite parameter quantifying the effective stress level, which is amenable to empirical measurement. We describe a narrow characteristic stress window over which the rescue probability drops from very likely to very unlikely as the level of stress increases. This drop is sharper than in previous models, as a result of the decreasing proportion of stress-resistant mutations as stress increases. We discuss how to test these predictions with rescue experiments across gradients of stress.
| S-EPMC5937192 | biostudies-other