Predicting enzymatic reactions with a molecular transformer.
Ontology highlight
ABSTRACT:
SUBMITTER: Kreutter D
PROVIDER: S-EPMC8246114 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Organic synthesis methodology enables the synthesis of complex molecules and materials used in all fields of science and technology and represents a vast body of accumulated knowledge optimally suited for deep learning. While most organic reactions involve distinct functional groups and can readily be learned by deep learning models and chemists alike, regio- and stereoselective transformations are more challenging because their outcome also depends on functional group surroundings. Here, we challenge the Molecular Transformer model to predict reactions on carbohydrates where regio- and stereoselectivity are notoriously difficult to predict. We show that transfer learning of the general patent reaction model with a small set of carbohydrate reactions produces a specialized model returning predictions for carbohydrate reactions with remarkable accuracy. We validate these predictions experimentally with the synthesis of a lipid-linked oligosaccharide involving regioselective protections and stereoselective glycosylations. The transfer learning approach should be applicable to any reaction class of interest.
| S-EPMC7519051 | biostudies-literature
Project description:Delineating design principles of biological systems by reconstitution of purified components offers a platform to gauge the influence of critical physicochemical parameters on minimal biological systems of reduced complexity. Here we unravel the effect of strong reversible inhibitors on the spatiotemporal propagation of enzymatic reactions in a confined environment in vitro. We use micropatterned, enzyme-laden agarose gels which are stamped on polyacrylamide films containing immobilized substrates and reversible inhibitors. Quantitative fluorescence imaging combined with detailed numerical simulations of the reaction-diffusion process reveal that a shallow gradient of enzyme is converted into a steep product gradient by addition of strong inhibitors, consistent with a mathematical model of molecular titration. The results confirm that ultrasensitive and threshold effects at the molecular level can convert a graded input signal to a steep spatial response at macroscopic length scales.
| S-EPMC3752114 | biostudies-other
Project description:SKBR3 breast cancer cell extracts were digested with trypsin (or LysC) on short time scales (7min, 15min, 30min, 1h, and 18h), and the results were compared to overnight digestion protocols.
2018-09-24 | PXD010306 | Pride
Project description:Fusarium head blight (FHB) incited by Fusarium graminearum Schwabe is a devastating disease of barley and other cereal crops worldwide. Fusarium head blight is associated with trichothecene mycotoxins such as deoxynivalenol (DON), where contaminated grains are unfit for malting or animal feed industries. While genetically resistant cultivars offer the best economic and environmentally responsible means to mitigate disease, parent lines with adequate resistance are limited in barley. Resistancebreeding based upon quantitative genetic gains has been slow to date, due to intensive labour requirements of disease nurseries. The development of high throughput genome-wide molecular markers, allow application in genomic prediction models. A diverse genomic panel consisting of 400 two-row spring barley lines was assembled to focus on Canadian barley breeding programs. The panel was evaluated for FHB and DON content in three environments and over two years. Moreover, it was genotyped using an Illumina Infinium HTS iSelect custom beadchip array of single nucleotide polymorphic molecular markers (50K SNP), where over 23K molecular markers were polymorphic. Genomic prediction has been successfully demonstrated for reducing FHB and DON content in cereals using various statistically-based models of different underlying assumptions. Herein, we have studied an alternative method basedon machine learning and compare it with a statistical approach. Two encoding techniques were utilized (categorical or Hardy-Weinberg frequencies), followed by selecting essential genomic markers for phenotype prediction. Subsequently, we applied a transformer-based deep learning algorithm to predict FHB and DON. Apart from the transformer method, we also implemented a Residual Fully Connected Neural Network (RFCNN). Pearson correlation coefficients were calculated to compare true vs. predicted outputs. Under most model scenarios, the use of all markers vs. selected markers marginally improved prediction performance except for RFCNN method for FHB (27.6%). Hardy-Weinberg encoding generally improved correlation for FHB (6.9%) and DON (9.6%) for transformer. This study suggests the potential of the transformer based method for genomic prediction of complex traits such as FHB or DON, having performed better or equally compared with existing machine learning and statistical method. To genomic prediction in barley for Fusarium head blight and deoxynivalenol content using a custom Illumina Infinium array (BarleySNP50-JHI) (www.illumina.com). Sample types included leaves from 400 barley genotypes mostly of Canadian origin. This series includes 400 genotypes assayed on an Illumina infinium HTS platform 50K BeadChip.
2022-01-05 | GSE188791 | GEO
Project description:The prediction of chemical reaction pathways has been accelerated by the development of novel machine learning architectures based on the deep learning paradigm. In this context, deep neural networks initially designed for language translation have been used to accurately predict a wide range of chemical reactions. Among models suited for the task of language translation, the recently introduced molecular transformer reached impressive performance in terms of forward-synthesis and retrosynthesis predictions. In this study, we first present an analysis of the performance of transformer models for product, reactant, and reagent prediction tasks under different scenarios of data availability and data augmentation. We find that the impact of data augmentation depends on the prediction task and on the metric used to evaluate the model performance. Second, we probe the contribution of different combinations of input formats, tokenization schemes, and embedding strategies to model performance. We find that less stable input settings generally lead to better performance. Lastly, we validate the superiority of round-trip accuracy over simpler evaluation metrics, such as top-k accuracy, using a committee of human experts and show a strong agreement for predictions that pass the round-trip test. This demonstrates the usefulness of more elaborate metrics in complex predictive scenarios and highlights the limitations of direct comparisons to a predefined database, which may include a limited number of chemical reaction pathways.
| S-EPMC10091402 | biostudies-literature
Project description:The roles of cytochrome P450 monooxygenases (CYPs) from Streptomyces spp. which are called the "treasure islands" for natural products for medicine and antibiotics are not well understood. Substrate specificity studies on CYPs may give a solution for elucidation of their roles. Based on homology sequence information, the CYP105D7 of a soluble cytochrome P450 known as heme protein from Streptomyces avermitilis MA4680 was expressed using the T7 promoter of the bacterial expression vector pET24ma, over-expressed in Escherichia coli system and characterized. An engineered whole cell system for daidzein hydroxylation was constructed using an exogenous electron transport system from ferredoxin reductase (PdR) and ferredoxin (Pdx). Also, an in vitro reaction study showed the purified CYP105D7 enzyme, using NADH-dependent-reducing equivalents of a redox partner from Pseudomonas putida, hydroxylated daidzein at the 3' position of the B ring to produce 7,3,'4' trihydroxyisoflavone. The hydroxylated position was confirmed by GC-MS analysis. The turnover number of the enzyme was 0.69 μmol 7,3,'4'-trihydroxyisoflavone produced per μmol P450 per min. This enzyme CYP105D7 represents a novel type of 3'-hydroxylase for daidzein hydroxylation. A P450 inhibitor such as coumarin significantly (ca.98%) inhibited the daidzein hydroxylation activity.
| S-EPMC6270586 | biostudies-literature
Project description:The teleocidin B family members are terpene indole compounds isolated from Streptomyces bacteria, and they strongly activate protein kinase C (PKC). Their unique structures have attracted many researchers in the natural product chemistry and pharmacology fields, and numerous isolation and bioactivity studies have been conducted. The accumulated information has facilitated the identification of the enzymatic reactions in teleocidin biosynthesis, and new developments in structural biology have strongly aided efforts to clarify the finer points of these reactions. This review describes the recent biochemical and structural biological studies to reveal their reaction mechanisms, with a primary focus on the terpene cyclization triggered by the C-N bond formation by P450 oxygenase (TleB), the prenyltransferase (TleC), and the methyltransferase (TleD). This new knowledge will benefit future engineering studies to create unnatural PKC activators.
| S-EPMC8159823 | biostudies-literature
Project description:MotivationDrug-target interaction (DTI) prediction is a foundational task for in-silico drug discovery, which is costly and time-consuming due to the need of experimental search over large drug compound space. Recent years have witnessed promising progress for deep learning in DTI predictions. However, the following challenges are still open: (i) existing molecular representation learning approaches ignore the sub-structural nature of DTI, thus produce results that are less accurate and difficult to explain and (ii) existing methods focus on limited labeled data while ignoring the value of massive unlabeled molecular data.ResultsWe propose a Molecular Interaction Transformer (MolTrans) to address these limitations via: (i) knowledge inspired sub-structural pattern mining algorithm and interaction modeling module for more accurate and interpretable DTI prediction and (ii) an augmented transformer encoder to better extract and capture the semantic relations among sub-structures extracted from massive unlabeled biomedical data. We evaluate MolTrans on real-world data and show it improved DTI prediction performance compared to state-of-the-art baselines.Availability and implementationThe model scripts are available at https://github.com/kexinhuang12345/moltrans.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC8098026 | biostudies-literature
Project description:We present an extension of our Molecular Transformer model combined with a hyper-graph exploration strategy for automatic retrosynthesis route planning without human intervention. The single-step retrosynthetic model sets a new state of the art for predicting reactants as well as reagents, solvents and catalysts for each retrosynthetic step. We introduce four metrics (coverage, class diversity, round-trip accuracy and Jensen-Shannon divergence) to evaluate the single-step retrosynthetic models, using the forward prediction and a reaction classification model always based on the transformer architecture. The hypergraph is constructed on the fly, and the nodes are filtered and further expanded based on a Bayesian-like probability. We critically assessed the end-to-end framework with several retrosynthesis examples from literature and academic exams. Overall, the frameworks have an excellent performance with few weaknesses related to the training data. The use of the introduced metrics opens up the possibility to optimize entire retrosynthetic frameworks by focusing on the performance of the single-step model only.
| S-EPMC8152799 | biostudies-literature
Project description:Cell-sized vesicles have tremendous potential both as miniaturised pL reaction vessels and in bottom-up synthetic biology as chassis for artificial cells. In both these areas the introduction of light-responsive modules affords increased functionality, for example, to initiate enzymatic reactions in the vesicle interior with spatiotemporal control. Here we report a system composed of nested vesicles where the inner compartments act as phototransducers, responding to ultraviolet irradiation through diacetylene polymerisation-induced pore formation to initiate enzymatic reactions. The controlled release and hydrolysis of a fluorogenic ?-galactosidase substrate in the external compartment is demonstrated, where the rate of reaction can be modulated by varying ultraviolet exposure time. Such cell-like nested microreactor structures could be utilised in fields from biocatalysis through to drug delivery.
| S-EPMC5854585 | biostudies-literature