Evaluating and clustering retrosynthesis pathways with learned strategy.
Ontology highlight
ABSTRACT:
SUBMITTER: Mo Y
PROVIDER: S-EPMC8179211 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Infusing "chemical wisdom" should improve the data-driven approaches that rely exclusively on historical synthetic data for automatic retrosynthesis planning. For this purpose, we designed a chemistry-informed molecular graph (CIMG) to describe chemical reactions. A collection of key information that is most relevant to chemical reactions is integrated in CIMG:NMR chemical shifts as vertex features, bond dissociation energies as edge features, and solvent/catalyst information as global features. For any given compound as a target, a product CIMG is generated and exploited by a graph neural network (GNN) model to choose reaction template(s) leading to this product. A reactant CIMG is then inferred and used in two GNN models to select appropriate catalyst and solvent, respectively. Finally, a fourth GNN model compares the two CIMG descriptors to check the plausibility of the proposed reaction. A reaction vector is obtained for every molecule in training these models. The chemical wisdom of reaction propensity contained in the pretrained reaction vectors is exploited to autocategorize molecules/reactions and to accelerate Monte Carlo tree search (MCTS) for multistep retrosynthesis planning. Full synthetic routes with recommended catalysts/solvents are predicted efficiently using this CIMG-based approach.
| S-EPMC9564830 | biostudies-literature
Project description:Enzymes synthesize complex natural products effortlessly by catalyzing chemo-, regio-, and enantio-selective transformations. Further, biocatalytic processes are increasingly replacing conventional organic synthesis steps because they use mild solvents, avoid the use of metals, and reduce overall non-biodegradable waste. Here, we present a single-step retrosynthesis search algorithm to facilitate enzymatic synthesis of natural product analogs. First, we develop a tool, RDEnzyme, capable of extracting and applying stereochemically consistent enzymatic reaction templates, i.e., subgraph patterns that describe the changes in connectivity between a product molecule and its corresponding reactant(s). Using RDEnzyme, we demonstrate that molecular similarity is an effective metric to propose retrosynthetic disconnections based on analogy to precedent enzymatic reactions in UniProt/RHEA. Using ∼5500 reactions from RHEA as a knowledge base, the recorded reactants to the product are among the top 10 proposed suggestions in 71% of ∼700 test reactions. Second, we trained a statistical model capable of discriminating between reaction pairs belonging to homologous enzymes and evolutionarily distant enzymes using ∼30 000 reaction pairs from SwissProt as a knowledge base. This model is capable of understanding patterns in enzyme promiscuity to evaluate the likelihood of experimental evolution success. By recursively applying the similarity-based single-step retrosynthesis and evolution prediction workflow, we successfully plan the enzymatic synthesis routes for both active pharmaceutical ingredients (e.g. Islatravir, Molnupiravir) and commodity chemicals (e.g. 1,4-butanediol, branched-chain higher alcohols/biofuels), in a retrospective fashion. Through the development and demonstration of the single-step enzymatic retrosynthesis strategy using natural transformations, our approach provides a first step towards solving the challenging problem of incorporating both enzyme- and organic-chemistry based transformations into a computer aided synthesis planning workflow.
| S-EPMC9132021 | biostudies-literature
Project description:The problem of portfolio optimization is one of the most important issues in asset management. We here propose a new dynamic portfolio strategy based on the time-varying structures of MST networks in Chinese stock markets, where the market condition is further considered when using the optimal portfolios for investment. A portfolio strategy comprises two stages: First, select the portfolios by choosing central and peripheral stocks in the selection horizon using five topological parameters, namely degree, betweenness centrality, distance on degree criterion, distance on correlation criterion and distance on distance criterion. Second, use the portfolios for investment in the investment horizon. The optimal portfolio is chosen by comparing central and peripheral portfolios under different combinations of market conditions in the selection and investment horizons. Market conditions in our paper are identified by the ratios of the number of trading days with rising index to the total number of trading days, or the sum of the amplitudes of the trading days with rising index to the sum of the amplitudes of the total trading days. We find that central portfolios outperform peripheral portfolios when the market is under a drawup condition, or when the market is stable or drawup in the selection horizon and is under a stable condition in the investment horizon. We also find that peripheral portfolios gain more than central portfolios when the market is stable in the selection horizon and is drawdown in the investment horizon. Empirical tests are carried out based on the optimal portfolio strategy. Among all possible optimal portfolio strategies based on different parameters to select portfolios and different criteria to identify market conditions, 65% of our optimal portfolio strategies outperform the random strategy for the Shanghai A-Share market while the proportion is 70% for the Shenzhen A-Share market.
| S-EPMC5271336 | biostudies-literature
Project description:Experience-dependent formation of synaptic input clusters can occur in juvenile brains. Whether this also occurs in adults is largely unknown. We previously reconstructed the normal and learned circuits of prism-adapted barn owls and found that changes in clustering of axo-dendritic contacts (putative synapses) predicted functional circuit strength. Here we asked whether comparable changes occurred in normal and prism-removed adults. Across all anatomical zones, no systematic differences in the primary metrics for within-branch or between-branch clustering were observed: 95-99% of contacts resided within clusters (<10-20 μm from nearest neighbor) regardless of circuit strength. Bouton volumes, a proxy measure of synaptic strength, were on average larger in the functionally strong zones, indicating that changes in synaptic efficacy contributed to the differences in circuit strength. Bootstrap analysis showed that the distribution of inter-contact distances strongly deviated from random not in the functionally strong zones but in those that had been strong during the sensitive period (60-250 d), indicating that clusters formed early in life were preserved regardless of current value. While cluster formation in juveniles appeared to require the production of new synapses, cluster formation in adults did not. In total, these results support a model in which high cluster dynamics in juveniles sculpt a potential connectivity map that is refined in adulthood. We propose that preservation of clusters in functionally weak adult circuits provides a storage mechanism for disused but potentially useful pathways.
| S-EPMC4465939 | biostudies-literature
Project description:Inferential summaries of tree estimates are useful in the setting of evolutionary biology, where phylogenetic trees have been built from DNA data since the 1960s. In bioinformatics, psychometrics, and data mining, hierarchical clustering techniques output the same mathematical objects, and practitioners have similar questions about the stability and "generalizability" of these summaries. This article describes the implementation of the geometric distance between trees developed by Billera, Holmes, and Vogtmann (2001) equally applicable to phylogenetic trees and hierarchical clustering trees, and shows some of the applications in evaluating tree estimates. In particular, since Billera et al. (2001) have shown that the space of trees is negatively curved (called a CAT(0) space), a collection of trees can naturally be represented as a tree. We compare this representation to the Euclidean approximations of treespace made available through both a classical multidimensional scaling and a Kernel multidimensional scaling of the matrix of the distances between trees. We also provide applications of the distances between trees to hierarchical clustering trees constructed from microarrays. Our method gives a new way of evaluating the influence of both certain columns (positions, variables, or genes) and certain rows (species, observations, or arrays) on the construction of such trees. It also can provide a way of detecting heterogeneous mixtures in the input data. Supplementary materials for this article are available online.
| S-EPMC7518125 | biostudies-literature
Project description:Middle East respiratory syndrome coronavirus (MERS-CoV) is an emerging zoonotic pathogen with a broad host range. The extent of MERS-CoV in nature can be traced to its adaptable cell entry steps. The virus can bind host-cell carbohydrates as well as proteinaceous receptors. Following receptor interaction, the virus can utilize diverse host proteases for cleavage activation of virus-host cell membrane fusion and subsequent genome delivery. The fusion and genome delivery steps can be completed at variable times and places, either at or near cell surfaces or deep within endosomes. Investigators focusing on the CoVs have developed several methodologies that effectively distinguish these different cell entry pathways. Here we describe these methods, highlighting virus-cell entry factors, entry inhibitors, and viral determinants that specify the cell entry routes. While the specific methods described herein were utilized to reveal MERS-CoV entry pathways, they are equally suited for other CoVs, as well as other protease-dependent viral species.
| S-EPMC7121971 | biostudies-literature
Project description:Data-driven approaches to retrosynthesis are limited in user interaction, diversity of their predictions, and recommendation of unintuitive disconnection strategies. Herein, we extend the notions of prompt-based inference in natural language processing to the task of chemical language modeling. We show that by using a prompt describing the disconnection site in a molecule we can steer the model to propose a broader set of precursors, thereby overcoming training data biases in retrosynthetic recommendations and achieving a 39% performance improvement over the baseline. For the first time, the use of a disconnection prompt empowers chemists by giving them greater control over the disconnection predictions, which results in more diverse and creative recommendations. In addition, in place of a human-in-the-loop strategy, we propose a two-stage schema consisting of automatic identification of disconnection sites, followed by prediction of reactant sets, thereby achieving a considerable improvement in class diversity compared with the baseline. The approach is effective in mitigating prediction biases derived from training data. This provides a wider variety of usable building blocks and improves the end user's digital experience. We demonstrate its application to different chemistry domains, from traditional to enzymatic reactions, in which substrate specificity is critical.
| S-EPMC10390024 | biostudies-literature
Project description:We demonstrate molecular similarity to be a surprisingly effective metric for proposing and ranking one-step retrosynthetic disconnections based on analogy to precedent reactions. The developed approach mimics the retrosynthetic strategy defined implicitly by a corpus of known reactions without the need to encode any chemical knowledge. Using 40 000 reactions from the patent literature as a knowledge base, the recorded reactants are among the top 10 proposed precursors in 74.1% of 5000 test reactions, providing strong quantitative support for our methodology. Extension of the one-step strategy to multistep pathway planning is demonstrated and discussed for two exemplary drug products.
| S-EPMC5746854 | biostudies-literature
Project description:Crystal engineering of metal-organic frameworks (MOFs) has allowed the construction of complex structures at atomic precision, but has yet to reach the same level of sophistication as organic synthesis. The synthesis of complex MOFs with multiple organic and/or inorganic components is ultimately limited by the lack of control over framework assembly in one-pot reactions. Herein, we demonstrate that multi-component MOFs with unprecedented complexity can be constructed in a predictable and stepwise manner under simple kinetic guidance, which conceptually mimics the retrosynthetic approach utilized to construct complicated organic molecules. Four multi-component MOFs were synthesized by the subsequent incorporation of organic linkers and inorganic clusters into the cavity of a mesoporous MOF, each composed of up to three different metals and two different linkers. Furthermore, we demonstrated the utility of such a retrosynthetic design through the construction of a cooperative bimetallic catalytic system with two collaborative metal sites for three-component Strecker reactions.
| S-EPMC5824804 | biostudies-literature
Project description:Racquet sports can provide positive benefits for human healthcare. A reliable detection device that can effectively distinguish movement with similar sub-features is therefore needed. In this paper, a racquet sports recognition wristband system and a multilayer hybrid clustering model are proposed to achieve reliable activity recognition and perform number counting. Additionally, a Bluetooth mesh network enables communication between a phone and wristband, and sets-up the connection between multiple devices. This allows users to track their exercise through the phone and share information with other players and referees. Considering the complexity of the classification algorithm and the user-friendliness of the measurement system, the improved multi-layer hybrid clustering model applies three-level K-means clustering to optimize feature extraction and segmentation and then uses the density-based spatial clustering of applications with noise (DBSCAN) algorithm to determine the feature center of different movements. The model can identify unlabeled and noisy data without data calibration and is suitable for smartwatches to recognize multiple racquet sports. The proposed system shows better recognition results and is verified in practical experiments.
| S-EPMC7146345 | biostudies-literature