A versatile active learning workflow for optimization of genetic and metabolic networks.
Ontology highlight
ABSTRACT:
SUBMITTER: Pandi A
PROVIDER: S-EPMC9256728 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Epigenetics helps define current cell states, yet also shapes how cells respond to external cues such as differentiation or stress. The epigenetic plasticity of a cell describes how flexible this regulation is. Bivalent chromatin is an exemplar of epigenetic plasticity. This co-occurrence of the active-associated H3K4me3 and inactive-associated H3K27me3 histone modifications on opposite tails of the same nucleosome was first described in mouse embryonic stem cells where it is found at promoters of key developmental genes. It has been postulated that bivalent chromatin poises these promoters, keeping them free from repressive DNAmethylation, enabling them to be transcriptionally upregulated upon differentiation. Bivalent chromatin has also been reported in other cell types including somatic cells and cancer cells, however we know little of the dynamics, resolution and regulation of this chromatin state. This is partly due to the technical challenges distinguishing bone-fide bivalent chromatin, where both marks are on the same nucleosome, from sample heterogeneity where some alleles have H3K4me3 and others H3K27me3. We developed a robust and sensitive reChIP method to accurately profile bivalent chromatin in as little as 2 million mouse embryonic stem cells. We validated the sensitivity of our method to detect changes in bivalent chromatin by profiling mouse ESCs lacking the epigenetic priming factors Dppa2 and Dppa4.
2024-02-26 | GSE242686 | GEO
Project description:Robotic arm assisted total knee arthroplasty (RTKA) has many potential benefits including advanced preoperative templating, restoration of mechanical alignment, accuracy of bony resection, robust safety mechanisms, and dynamic gap balancing. One of the most frequently quoted drawbacks preventing experienced surgeons from adopting this technology is the perceived increase in surgical time. This technique paper outlines the general concepts used to improve operating room efficiency as well as the step-by-step workflow to consistently perform RTKA with surgical times under 60 minutes. Although the clinical and functional results of RTKA are just beginning to be described in literature, this manuscript demonstrates that with proper technique and workflow, surgical time should not be a significant factor to deter surgeons from adopting this new technology.
| S-EPMC6921119 | biostudies-literature
Project description:The widespread natural ability of RNA to sense small molecules and regulate genes has become an important tool for synthetic biology in applications as diverse as environmental sensing and metabolic engineering. Previous work in RNA synthetic biology has engineered RNA mechanisms that independently regulate multiple targets and integrate regulatory signals. However, intracellular regulatory networks built with these systems have required proteins to propagate regulatory signals. In this work, we remove this requirement and expand the RNA synthetic biology toolkit by engineering three unique features of the plasmid pT181 antisense-RNA-mediated transcription attenuation mechanism. First, because the antisense RNA mechanism relies on RNA-RNA interactions, we show how the specificity of the natural system can be engineered to create variants that independently regulate multiple targets in the same cell. Second, because the pT181 mechanism controls transcription, we show how independently acting variants can be configured in tandem to integrate regulatory signals and perform genetic logic. Finally, because both the input and output of the attenuator is RNA, we show how these variants can be configured to directly propagate RNA regulatory signals by constructing an RNA-meditated transcriptional cascade. The combination of these three features within a single RNA-based regulatory mechanism has the potential to simplify the design and construction of genetic networks by directly propagating signals as RNA molecules.
| S-EPMC3102349 | biostudies-literature
Project description:Reverse-engineering of biological networks is a central problem in systems biology. The use of intervention data, such as gene knockouts or knockdowns, is typically used for teasing apart causal relationships among genes. Under time or resource constraints, one needs to carefully choose which intervention experiments to carry out. Previous approaches for selecting most informative interventions have largely been focused on discrete Bayesian networks. However, continuous Bayesian networks are of great practical interest, especially in the study of complex biological systems and their quantitative properties. In this work, we present an efficient, information-theoretic active learning algorithm for Gaussian Bayesian networks (GBNs), which serve as important models for gene regulatory networks. In addition to providing linear-algebraic insights unique to GBNs, leading to significant runtime improvements, we demonstrate the effectiveness of our method on data simulated with GBNs and the DREAM4 network inference challenge data sets. Our method generally leads to faster recovery of underlying network structure and faster convergence to final distribution of confidence scores over candidate graph structures using the full data, in comparison to random selection of intervention experiments.
| S-EPMC4773135 | biostudies-literature
Project description:To date, several independent methods and algorithms exist for exploiting constraint-based stoichiometric models to find metabolic engineering strategies that optimize microbial production performance. Optimization procedures based on metaheuristics facilitate a straightforward adaption and expansion of engineering objectives, as well as fitness functions, while being particularly suited for solving problems of high complexity. With the increasing interest in multi-scale models and a need for solving advanced engineering problems, we strive to advance genetic algorithms, which stand out due to their intuitive optimization principles and the proven usefulness in this field of research. A drawback of genetic algorithms is that premature convergence to sub-optimal solutions easily occurs if the optimization parameters are not adapted to the specific problem. Here, we conducted comprehensive parameter sensitivity analyses to study their impact on finding optimal strain designs. We further demonstrate the capability of genetic algorithms to simultaneously handle (i) multiple, non-linear engineering objectives; (ii) the identification of gene target-sets according to logical gene-protein-reaction associations; (iii) minimization of the number of network perturbations; and (iv) the insertion of non-native reactions, while employing genome-scale metabolic models. This framework adds a level of sophistication in terms of strain design robustness, which is exemplarily tested on succinate overproduction in Escherichia coli.
| S-EPMC6027426 | biostudies-literature
Project description:Deep learning is one of the most advanced forms of machine learning. Most modern deep learning models are based on an artificial neural network, and benchmarking studies reveal that neural networks have produced results comparable to and in some cases superior to human experts. However, the generated neural networks are typically regarded as incomprehensible black-box models, which not only limits their applications, but also hinders testing and verifying. In this paper, we present an active learning framework to extract automata from neural network classifiers, which can help users to understand the classifiers. In more detail, we use Angluin's L* algorithm as a learner and the neural network under learning as an oracle, employing abstraction interpretation of the neural network for answering membership and equivalence queries. Our abstraction consists of value, symbol and word abstractions. The factors that may affect the abstraction are also discussed in the paper. We have implemented our approach in a prototype. To evaluate it, we have performed the prototype on a MNIST classifier and have identified that the abstraction with interval number 2 and block size 1 × 28 offers the best performance in terms of F1 score. We also have compared our extracted DFA against the DFAs learned via the passive learning algorithms provided in LearnLib and the experimental results show that our DFA gives a better performance on the MNIST dataset.
| S-EPMC8064235 | biostudies-literature
Project description:Tutorial tactics are policies for an Intelligent Tutoring System (ITS) to decide the next action when there are multiple actions available. Recent research has demonstrated that when the learning contents were controlled so as to be the same, different tutorial tactics would make difference in students' learning gains. However, the Reinforcement Learning (RL) techniques that were used in previous studies to induce tutorial tactics are insufficient when encountering large problems and hence were used in offline manners. Therefore, we introduced a Genetic-Based Reinforcement Learning (GBML) approach to induce tutorial tactics in an online-learning manner without basing on any preexisting dataset. The introduced method can learn a set of rules from the environment in a manner similar to RL. It includes a genetic-based optimizer for rule discovery task by generating new rules from the old ones. This increases the scalability of a RL learner for larger problems. The results support our hypothesis about the capability of the GBML method to induce tutorial tactics. This suggests that the GBML method should be favorable in developing real-world ITS applications in the domain of tutorial tactics induction.
| S-EPMC4439506 | biostudies-other
Project description:Ab initio protein docking represents a major challenge for optimizing a noisy and costly "black box"-like function in a high-dimensional space. Despite progress in this field, there is a lack of rigorous uncertainty quantification (UQ). To fill the gap, we introduce a novel algorithm, Bayesian active learning (BAL), for optimization and UQ of such black-box functions with applications to flexible protein docking. BAL directly models the posterior distribution of the global optimum (i.e., native structures) with active sampling and posterior estimation iteratively feeding each other. Furthermore, it uses complex normal modes to span a homogeneous, Euclidean conformation space suitable for high-dimensional optimization and constructs funnel-like energy models for quality estimation of encounter complexes. Over a protein-docking benchmark set and a CAPRI set including homology docking, we establish that BAL significantly improves against starting points from rigid docking and refinements by particle swarm optimization, providing a top-3 near-native prediction for one third targets. Quality assessment empowered with UQ leads to tight quality intervals with half range around 25% of the actual interface root-mean-square deviation and confidence level at 85%. BAL's estimated probability of a prediction being near-native achieves binary classification AUROC at 0.93 and area under the precision recall curve over 0.60 (compared to 0.50 and 0.14, respectively, by chance), which also improves ranking predictions. This study represents the first UQ solution for protein docking, with rigorous theoretical frameworks and comprehensive empirical assessments.
| S-EPMC7429362 | biostudies-literature
Project description:Metagenomics is currently the only generic method for pathogen detection. Starting from RNA allows the assessment of the whole sample community including RNA viruses. Here we present our modular concerted protocol for sample processing for diagnostic metagenomics analysis of human, animal, and food samples. The workflow does not rely on dedicated amplification steps at any stage in the process and, in contrast to published methods, libraries prepared accordingly will yield only minute amounts of unclassifiable reads. We confirmed the performance of the approach using a spectrum of pathogen/matrix-combinations showing it has the potential to become a commonly usable analytical framework.
| S-EPMC6117295 | biostudies-literature
Project description:SummaryDeepKG is an end-to-end deep learning-based workflow that helps researchers automatically mine valuable knowledge in biomedical literature. Users can utilize it to establish customized knowledge graphs in specified domains, thus facilitating in-depth understanding on disease mechanisms and applications on drug repurposing and clinical research, etc. To improve the performance of DeepKG, a cascaded hybrid information extraction framework (CHIEF) is developed for training model of 3-tuple extraction, and a novel AutoML-based knowledge representation algorithm (AutoTransX) is proposed for knowledge representation and inference. The system has been deployed in dozens of hospitals and extensive experiments strongly evidence the effectiveness. In the context of 144,900 COVID-19 scholarly full-text literature, DeepKG generates a high-quality knowledge graph with 7,980 entities and 43,760 3-tuples, a candidate drug list, and relevant animal experimental studies are being carried out. To accelerate more studies, we make DeepKG publicly available and provide an online tool including the data of 3-tuples, potential drug list, question answering system, visualization platform.AvailabilityFree to all users: http://covidkg.ai/.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC8689937 | biostudies-literature