Probabilistic Pocket Druggability Prediction via One-Class Learning
Ontology highlight
ABSTRACT:
SUBMITTER: Aguti R
PROVIDER: S-EPMC9278401 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Machine learning for materials discovery has largely focused on predicting an individual scalar rather than multiple related properties, where spectral properties are an important example. Fundamental spectral properties include the phonon density of states (phDOS) and the electronic density of states (eDOS), which individually or collectively are the origins of a breadth of materials observables and functions. Building upon the success of graph attention networks for encoding crystalline materials, we introduce a probabilistic embedding generator specifically tailored to the prediction of spectral properties. Coupled with supervised contrastive learning, our materials-to-spectrum (Mat2Spec) model outperforms state-of-the-art methods for predicting ab initio phDOS and eDOS for crystalline materials. We demonstrate Mat2Spec's ability to identify eDOS gaps below the Fermi energy, validating predictions with ab initio calculations and thereby discovering candidate thermoelectrics and transparent conductors. Mat2Spec is an exemplar framework for predicting spectral properties of materials via strategically incorporated machine learning techniques.
| S-EPMC8854636 | biostudies-literature
Project description:Reinforcement learning guides food decisions, yet how the brain learns from taste in humans is not fully understood. Existing research examines reinforcement learning from taste using passive condition paradigms, but response-dependent instrumental conditioning better reflects natural eating behavior. Here, we examined brain response during a taste-motivated reinforcement learning task and how measures of task-based network structure were related to behavioral outcomes. During a functional MRI scan, 85 participants completed a probabilistic selection task with feedback via sweet taste or bitter taste. Whole brain response and functional network topology measures, including identification of communities and community segregation, were examined during choice, sweet taste, and bitter taste conditions. Relative to the bitter taste, sweet taste was associated with increased whole brain response in the hippocampus, oral somatosensory cortex, and orbitofrontal cortex. Sweet taste was also related to differential community assignment of the ventromedial prefrontal cortex and ventrolateral prefrontal cortex compared to bitter taste. During choice, increasing segregation of a community containing the amygdala, hippocampus, and right fusiform gyrus was associated with increased sensitivity to punishment on the task's posttest. Further, normal BMI was associated with differential community structure compared to overweight and obese BMI, where high BMI reflected increased connectivity of visual regions. Together, results demonstrate that network topology of learning and memory regions during choice is related to avoiding a bitter taste, and that BMI is associated with increased connectivity of area involved in processing external stimuli. Network organization and topology provide unique insight into individual differences in brain response to instrumental conditioning via taste reinforcers.
| S-EPMC7425041 | biostudies-literature
Project description:Identification of ionic liquids with low toxicity is paramount for applications in various domains. Traditional approaches used for determining the toxicity of ionic liquids are often expensive, and can be labor intensive and time consuming. In order to mitigate these limitations, researchers have resorted to using computational models. This work presents a probabilistic model built from deep kernel learning with the aim of predicting the toxicity of ionic liquids in the leukemia rat cell line (IPC-81). Only open source tools, namely, RDKit and Mol2vec, are required to generate predictors for this model; as such, its predictions are solely based on chemical structure of the ionic liquids and no manual extraction of features is needed. The model recorded an RMSE of 0.228 and R2 of 0.943. These results indicate that the model is both reliable and accurate. Furthermore, this model provides an accompanying uncertainty level for every prediction it makes. This is important because discrepancies in experimental measurements that generated the dataset used herein are inevitable, and ought to be modeled. A user-friendly web server was developed as well, enabling researchers and practitioners ti make predictions using this model.
| S-EPMC9104997 | biostudies-literature
Project description:The antimicrobial activity of phenyl-thiazolylurea-sulfonamides against Staphylococcus aureus PheRS are dependent upon phenylalanine levels in the extracellular fluids. Inhibitor efficacy in animal models of infection is substantially diminished by dietary phenylalanine intake, thereby reducing the perceived clinical utility of this inhibitor class. The search for novel antibacterial compounds against Gram-negative pathogens led to a re-evaluation of this phenomenon, which is shown here to be unique to S. aureus. Inhibition of macromolecular syntheses and characterization of novel resistance mutations in Escherichia coli demonstrate that antimicrobial activity of phenyl-thiazolylurea-sulfonamides is mediated by PheRS inhibition, validating this enzyme as a viable drug discovery target for Gram-negative pathogens. A search for novel inhibitors of PheRS yielded three novel chemical starting points. NMR studies were used to confirm direct target engagement for phenylalanine-competitive hits. The crystallographic structure of Pseudomonas aeruginosa PheRS defined the binding modes of these hits and revealed an auxiliary hydrophobic pocket that is positioned adjacent to the phenylalanine binding site. Three viable inhibitor-resistant mutants were mapped to this pocket, suggesting that this region is a potential liability for drug discovery.
| S-EPMC4118124 | biostudies-literature
Project description:Machine learning is increasingly applied to Earth Observation (EO) data to obtain datasets that contribute towards international accords. However, these datasets contain inherent uncertainty that needs to be quantified reliably to avoid negative consequences. In response to the increased need to report uncertainty, we bring attention to the promise of conformal prediction within the domain of EO. Unlike previous uncertainty quantification methods, conformal prediction offers statistically valid prediction regions while concurrently supporting any machine learning model and data distribution. To support the need for conformal prediction, we reviewed EO datasets and found that only 22.5% of the datasets incorporated a degree of uncertainty information, with unreliable methods prevalent. Current open implementations require moving large amounts of EO data to the algorithms. We introduced Google Earth Engine native modules that bring conformal prediction to the data and compute, facilitating the integration of uncertainty quantification into existing traditional and deep learning modelling workflows. To demonstrate the versatility and scalability of these tools we apply them to valued EO applications spanning local to global extents, regression, and classification tasks. Subsequently, we discuss the opportunities arising from the use of conformal prediction in EO. We anticipate that accessible and easy-to-use tools, such as those provided here, will drive wider adoption of rigorous uncertainty quantification in EO, thereby enhancing the reliability of downstream uses such as operational monitoring and decision-making.
| S-EPMC11246475 | biostudies-literature
Project description:In the paradigm of materials informatics for accelerated materials discovery, the choice of feature set (i.e. attributes that capture aspects of structure, chemistry and/or bonding) is critical. Ideally, the feature sets should provide a simple physical basis for extracting major structural and chemical trends and furthermore, enable rapid predictions of new material chemistries. Orbital radii calculated from model pseudopotential fits to spectroscopic data are potential candidates to satisfy these conditions. Although these radii (and their linear combinations) have been utilized in the past, their functional forms are largely justified with heuristic arguments. Here we show that machine learning methods naturally uncover the functional forms that mimic most frequently used features in the literature, thereby providing a mathematical basis for feature set construction without a priori assumptions. We apply these principles to study two broad materials classes: (i) wide band gap AB compounds and (ii) rare earth-main group RM intermetallics. The AB compounds serve as a prototypical example to demonstrate our approach, whereas the RM intermetallics show how these concepts can be used to rapidly design new ductile materials. Our predictive models indicate that ScCo, ScIr, and YCd should be ductile, whereas each was previously proposed to be brittle.
| S-EPMC4548442 | biostudies-literature
Project description:MicroRNAs (miRNAs) are small regulatory RNAs of approximately 22 nt. Although hundreds of miRNAs have been identified through experimental complementary DNA cloning methods and computational efforts, previous approaches could detect only abundantly expressed miRNAs or close homologs of previously identified miRNAs. Here, we introduce a probabilistic co-learning model for miRNA gene finding, ProMiR, which simultaneously considers the structure and sequence of miRNA precursors (pre-miRNAs). On 5-fold cross-validation with 136 referenced human datasets, the efficiency of the classification shows 73% sensitivity and 96% specificity. When applied to genome screening for novel miRNAs on human chromosomes 16, 17, 18 and 19, ProMiR effectively searches distantly homologous patterns over diverse pre-miRNAs, detecting at least 23 novel miRNA gene candidates. Importantly, the miRNA gene candidates do not demonstrate clear sequence similarity to the known miRNA genes. By quantitative PCR followed by RNA interference against Drosha, we experimentally confirmed that 9 of the 23 representative candidate genes express transcripts that are processed by the miRNA biogenesis enzyme Drosha in HeLa cells, indicating that ProMiR may successfully predict miRNA genes with at least 40% accuracy. Our study suggests that the miRNA gene family may be more abundant than previously anticipated, and confer highly extensive regulatory networks on eukaryotic cells.
| S-EPMC1159118 | biostudies-literature
Project description:The role of prediction error (PE) in driving learning is well-established in fields such as classical and instrumental conditioning, reward learning and procedural memory; however, its role in human one-shot declarative encoding is less clear. According to one recent hypothesis, PE reflects the divergence between two probability distributions: one reflecting the prior probability (from previous experiences) and the other reflecting the sensory evidence (from the current experience). Assuming unimodal probability distributions, PE can be manipulated in three ways: (1) the distance between the mode of the prior and evidence, (2) the precision of the prior, and (3) the precision of the evidence. We tested these three manipulations across five experiments, in terms of peoples' ability to encode a single presentation of a scene-item pairing as a function of previous exposures to that scene and/or item. Memory was probed by presenting the scene together with three choices for the previously paired item, in which the two foil items were from other pairings within the same condition as the target item. In Experiment 1, we manipulated the evidence to be either consistent or inconsistent with prior expectations, predicting PE to be larger, and hence memory better, when the new pairing was inconsistent. In Experiments 2a-c, we manipulated the precision of the priors, predicting better memory for a new pairing when the (inconsistent) priors were more precise. In Experiment 3, we manipulated both visual noise and prior exposure for unfamiliar faces, before pairing them with scenes, predicting better memory when the sensory evidence was more precise. In all experiments, the PE hypotheses were supported. We discuss alternative explanations of individual experiments, and conclude the Predictive Interactive Multiple Memory Signals (PIMMS) framework provides the most parsimonious account of the full pattern of results.
| S-EPMC5381756 | biostudies-literature
Project description:BackgroundRecently, machine learning-based ligand activity prediction methods have been greatly improved. However, if known active compounds of a target protein are unavailable, the machine learning-based method cannot be applied. In such cases, docking simulation is generally applied because it only requires a tertiary structure of the target protein. However, the conformation search and the evaluation of binding energy of docking simulation are computationally heavy and thus docking simulation needs huge computational resources. Thus, if we can apply a machine learning-based activity prediction method for a novel target protein, such methods would be highly useful. Recently, Tsubaki et al. proposed an end-to-end learning method to predict the activity of compounds for novel target proteins. However, the prediction accuracy of the method was still insufficient because it only used amino acid sequence information of a protein as the input.ResultsIn this research, we proposed an end-to-end learning-based compound activity prediction using structure information of a binding pocket of a target protein. The proposed method learns the important features by end-to-end learning using a graph neural network both for a compound structure and a protein binding pocket structure. As a result of the evaluation experiments, the proposed method has shown higher accuracy than an existing method using amino acid sequence information.ConclusionsThe proposed method achieved equivalent accuracy to docking simulation using AutoDock Vina with much shorter computing time. This indicated that a machine learning-based approach would be promising even for novel target proteins in activity prediction.
| S-EPMC8555120 | biostudies-literature
Project description:Predicting protein pocket's ability to bind drug-like molecules with high affinity, i.e. druggability, is of major interest in the target identification phase of drug discovery. Therefore, pocket druggability investigations represent a key step of compound clinical progression projects. Currently computational druggability prediction models are attached to one unique pocket estimation method despite pocket estimation uncertainties. In this paper, we propose 'PockDrug-Server' to predict pocket druggability, efficient on both (i) estimated pockets guided by the ligand proximity (extracted by proximity to a ligand from a holo protein structure) and (ii) estimated pockets based solely on protein structure information (based on amino atoms that form the surface of potential binding cavities). PockDrug-Server provides consistent druggability results using different pocket estimation methods. It is robust with respect to pocket boundary and estimation uncertainties, thus efficient using apo pockets that are challenging to estimate. It clearly distinguishes druggable from less druggable pockets using different estimation methods and outperformed recent druggability models for apo pockets. It can be carried out from one or a set of apo/holo proteins using different pocket estimation methods proposed by our web server or from any pocket previously estimated by the user. PockDrug-Server is publicly available at: http://pockdrug.rpbs.univ-paris-diderot.fr.
| S-EPMC4489252 | biostudies-literature