DeepReac+: deep active learning for quantitative modeling of organic chemical reactions.
Ontology highlight
ABSTRACT:
SUBMITTER: Gong Y
PROVIDER: S-EPMC8580052 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Being able to predict the course of arbitrary chemical reactions is essential to the theory and applications of organic chemistry. Approaches to the reaction prediction problems can be organized around three poles corresponding to: (1) physical laws; (2) rule-based expert systems; and (3) inductive machine learning. Previous approaches at these poles, respectively, are not high throughput, are not generalizable or scalable, and lack sufficient data and structure to be implemented. We propose a new approach to reaction prediction utilizing elements from each pole. Using a physically inspired conceptualization, we describe single mechanistic reactions as interactions between coarse approximations of molecular orbitals (MOs) and use topological and physicochemical attributes as descriptors. Using an existing rule-based system (Reaction Explorer), we derive a restricted chemistry data set consisting of 1630 full multistep reactions with 2358 distinct starting materials and intermediates, associated with 2989 productive mechanistic steps and 6.14 million unproductive mechanistic steps. And from machine learning, we pose identifying productive mechanistic steps as a statistical ranking, information retrieval problem: given a set of reactants and a description of conditions, learn a ranking model over potential filled-to-unfilled MO interactions such that the top-ranked mechanistic steps yield the major products. The machine learning implementation follows a two-stage approach, in which we first train atom level reactivity filters to prune 94.00% of nonproductive reactions with a 0.01% error rate. Then, we train an ensemble of ranking models on pairs of interacting MOs to learn a relative productivity function over mechanistic steps in a given system. Without the use of explicit transformation patterns, the ensemble perfectly ranks the productive mechanism at the top 89.05% of the time, rising to 99.86% of the time when the top four are considered. Furthermore, the system is generalizable, making reasonable predictions over reactants and conditions which the rule-based expert does not handle. A web interface to the machine learning based mechanistic reaction predictor is accessible through our chemoinformatics portal ( http://cdb.ics.uci.edu) under the Toolkits section.
| S-EPMC3193800 | biostudies-literature
Project description:BACKGROUND:Adverse drug reactions (ADRs) are unintended and harmful reactions caused by normal uses of drugs. Predicting and preventing ADRs in the early stage of the drug development pipeline can help to enhance drug safety and reduce financial costs. METHODS:In this paper, we developed machine learning models including a deep learning framework which can simultaneously predict ADRs and identify the molecular substructures associated with those ADRs without defining the substructures a-priori. RESULTS:We evaluated the performance of our model with ten different state-of-the-art fingerprint models and found that neural fingerprints from the deep learning model outperformed all other methods in predicting ADRs. Via feature analysis on drug structures, we identified important molecular substructures that are associated with specific ADRs and assessed their associations via statistical analysis. CONCLUSIONS:The deep learning model with feature analysis, substructure identification, and statistical assessment provides a promising solution for identifying risky components within molecular structures and can potentially help to improve drug safety evaluation.
| S-EPMC6300887 | biostudies-other
Project description:Efficient and reproducible construction of signaling and sorting complexes, both on the surface and within the living cell, is contingent on local regulation of biochemical reactions by the cellular milieu. We propose that in many cases this spatiotemporal regulation can be mediated by interaction with components of the dynamic cytoskeleton. We show how the interplay between active contractility and remodeling of the cytoskeleton can result in transient focusing of passive molecules to form clusters, leading to a dramatic increase in the reaction efficiency and output levels. The dynamic cytoskeletal elements that drive focusing behave as quasienzymes catalyzing the chemical reaction. These ideas are directly applicable to the cortical actin-dependent clustering of cell surface proteins such as lipid-tethered GPI-anchored proteins, Ras proteins, as well as many proteins that have domains that confer the ability to interact with the actin cytoskeleton. In general such cytoskeletal driven clustering of proteins could be a cellular mechanism to spatiotemporally regulate and amplify local chemical reaction rates in a variety of contexts such as signaling, transcription, sorting, and endocytosis.
| S-EPMC3169122 | biostudies-literature
Project description:DNA-Encoded Chemical Libraries (DELs) have emerged as efficient and cost-effective ligand discovery tools, which enable the generation of protein-ligand interaction data of unprecedented size. In this article, we present an approach that combines DEL screening and instance-level deep learning modeling to identify tumor-targeting ligands against carbonic anhydrase IX (CAIX), a clinically validated marker of hypoxia and clear cell renal cell carcinoma. We present a new ligand identification and hit-to-lead strategy driven by machine learning models trained on DELs, which expand the scope of DEL-derived chemical motifs. CAIX-screening datasets obtained from three different DELs were used to train machine learning models for generating novel hits, dissimilar to elements present in the original DELs. Out of the 152 novel potential hits that were identified with our approach and screened in an in vitro enzymatic inhibition assay, 70% displayed submicromolar activities (IC50 < 1 μM). To generate lead compounds that are functionalized with anticancer payloads, analogues of top hits were prioritized for synthesis based on the predicted CAIX affinity and synthetic feasibility. Three lead candidates showed accumulation on the surface of CAIX-expressing tumor cells in cellular binding assays. The best compound displayed an in vitro KD of 5.7 nM and selectively targeted tumors in mice bearing human renal cell carcinoma lesions. Our results demonstrate the synergy between DEL and machine learning for the identification of novel hits and for the successful translation of lead candidates for in vivo targeting applications.
| S-EPMC10357458 | biostudies-literature
Project description:Most of the current object detection approaches deliver competitive results with an assumption that a large number of labeled data are generally available and can be fed into a deep network at once. However, due to expensive labeling efforts, it is difficult to deploy the object detection systems into more complex and challenging real-world environments, especially for defect detection in real industries. In order to reduce the labeling efforts, this study proposes an active learning framework for defect detection. First, an Uncertainty Sampling is proposed to produce the candidate list for annotation. Uncertain images can provide more informative knowledge for the learning process. Then, an Average Margin method is designed to set the sampling scale for each defect category. In addition, an iterative pattern of training and selection is adopted to train an effective detection model. Extensive experiments demonstrate that the proposed method can render the required performance with fewer labeled data.
| S-EPMC7146140 | biostudies-literature
Project description:Active matter comprises individual units that convert energy into mechanical motion. In many examples, such as bacterial systems and biofilament assays, constituent units are elongated and can give rise to local nematic orientational order. Such "active nematics" systems have attracted much attention from both theorists and experimentalists. However, despite intense research efforts, data-driven quantitative modeling has not been achieved, a situation mainly due to the lack of systematic experimental data and to the large number of parameters of current models. Here, we introduce an active nematics system made of swarming filamentous bacteria. We simultaneously measure orientation and velocity fields and show that the complex spatiotemporal dynamics of our system can be quantitatively reproduced by a type of microscopic model for active suspensions whose important parameters are all estimated from comprehensive experimental data. This provides unprecedented access to key effective parameters and mechanisms governing active nematics. Our approach is applicable to different types of dense suspensions and shows a path toward more quantitative active matter research.
| S-EPMC6338848 | biostudies-other
Project description:Predictive biogeochemical modeling requires data-model integration that enables explicit representation of the sophisticated roles of microbial processes that transform substrates. Data from high-resolution organic matter (OM) characterization are increasingly available and can serve as a critical resource for this purpose, but their incorporation into biogeochemical models is often prohibited due to an over-simplified description of reaction networks. To fill this gap, we proposed a new concept of biogeochemical modeling-termed substrate-explicit modeling-that enables parameterizing OM-specific oxidative degradation pathways and reaction rates based on the thermodynamic properties of OM pools. Based on previous developments in the literature, we characterized the resulting kinetic models by only two parameters regardless of the complexity of OM profiles, which can greatly facilitate the integration with reactive transport models for ecosystem simulations by alleviating the difficulty in parameter identification. The two parameters include maximal growth rate (μmax) and harvest volume (Vh) (i.e., the volume that a microbe can access for harvesting energy). For every detected organic molecule in a given sample, our approach provides a systematic way to formulate reaction kinetics from chemical formula, which enables the evaluation of the impact of OM character on biogeochemical processes across conditions. In a case study of two sites with distinct OM thermodynamics using ultra high-resolution metabolomics datasets derived from Fourier transform ion cyclotron resonance mass spectrometry analyses, our method predicted how oxidative degradation is primarily driven by thermodynamic efficiency of OM consistent with experimental rate measurements (as shown by correlation coefficients of up to 0.61), and how biogeochemical reactions can vary in response to carbon and/or oxygen limitations. Lastly, we showed that incorporation of enzymatic regulations into substrate-explicit models is critical for more reasonable predictions. This result led us to present integrative biogeochemical modeling as a unifying framework that can ideally describe the dynamic interplay among microbes, enzymes, and substrates to address advanced questions and hypotheses in future studies. Altogether, the new modeling concept we propose in this work provides a foundational platform for unprecedented predictions of biogeochemical and ecosystem dynamics through enhanced integration with diverse experimental data and extant modeling approaches.
| S-EPMC7644784 | biostudies-literature
Project description:Reaction condition recommendation is an essential element for the realization of computer-assisted synthetic planning. Accurate suggestions of reaction conditions are required for experimental validation and can have a significant effect on the success or failure of an attempted transformation. However, de novo condition recommendation remains a challenging and under-explored problem and relies heavily on chemists' knowledge and experience. In this work, we develop a neural-network model to predict the chemical context (catalyst(s), solvent(s), reagent(s)), as well as the temperature most suitable for any particular organic reaction. Trained on ∼10 million examples from Reaxys, the model is able to propose conditions where a close match to the recorded catalyst, solvent, and reagent is found within the top-10 predictions 69.6% of the time, with top-10 accuracies for individual species reaching 80-90%. Temperature is accurately predicted within ±20 °C from the recorded temperature in 60-70% of test cases, with higher accuracy for cases with correct chemical context predictions. The utility of the model is illustrated through several examples spanning a range of common reaction classes. We also demonstrate that the model implicitly learns a continuous numerical embedding of solvent and reagent species that captures their functional similarity.
| S-EPMC6276053 | biostudies-literature
Project description:The "creativity" of Artificial Intelligence (AI) in terms of generating de novo molecular structures opened a novel paradigm in compound design, weaknesses (stability & feasibility issues of such structures) notwithstanding. Here we show that "creative" AI may be as successfully taught to enumerate novel chemical reactions that are stoichiometrically coherent. Furthermore, when coupled to reaction space cartography, de novo reaction design may be focused on the desired reaction class. A sequence-to-sequence autoencoder with bidirectional Long Short-Term Memory layers was trained on on-purpose developed "SMILES/CGR" strings, encoding reactions of the USPTO database. The autoencoder latent space was visualized on a generative topographic map. Novel latent space points were sampled around a map area populated by Suzuki reactions and decoded to corresponding reactions. These can be critically analyzed by the expert, cleaned of irrelevant functional groups and eventually experimentally attempted, herewith enlarging the synthetic purpose of popular synthetic pathways.
| S-EPMC7862614 | biostudies-literature
Project description:A cross ELF-NCI analysis is tested over prototypical organic reactions. The synergetic use of ELF and NCI enables the understanding of reaction mechanisms since each method can respectively identify regions of strong and weak electron pairing. Chemically intuitive results are recovered and enriched by the identification of new features. Non covalent interactions are found to foresee the evolution of the reaction from the initial steps. Within NCI, no topological catastrophe is observed as changes are continuous to such an extent that future reaction steps can be predicted from the evolution of the initial NCI critical points. Indeed, strong convergences through the reaction paths between ELF and NCI critical points enable to identify key interactions at the origin of the bond formation. VMD scripts enabling the automatic generation of movies depicting the cross NCI/ELF analysis along a reaction path (or following a Born-Oppenheimer molecular dynamics trajectory) are provided as S.I.
| S-EPMC3505119 | biostudies-literature