Search

Abstract The prediction of interactions between novel drugs and biological targets is a vital step in the early stage of the drug discovery pipeline. Many deep learning approaches have been proposed over the last decade, with a substantial fraction of them sharing the same underlying two-branch architecture. Their distinction is limited to the use of different types of feature representations and branches (multi-layer perceptrons, convolutional neural networks, graph neural networks and transformers). In contrast, the strategy used to combine the outputs (embeddings) of the branches has remained mostly the same. The same general architecture has also been used extensively in the area of recommender systems, where the choice of an aggregation strategy is still an open question. In this work, we investigate the effectiveness of three different embedding aggregation strategies in the area of drug–target interaction (DTI) prediction. We formally define these strategies and prove their universal approximator capabilities. We then present experiments that compare the different strategies on benchmark datasets from the area of DTI prediction, showcasing conditions under which specific strategies could be the obvious choice.

Differentially private (DP) synthetic data has emerged as a potential solution for sharing sensitive individual-level biomedical data. DP generative models offer a promising approach for generating realistic synthetic data that aims to maintain the original data’s central statistical properties while ensuring privacy by limiting the risk of disclosing sensitive information about individuals. However, the issue regarding how to assess the expected real-world prediction performance of machine learning models trained on synthetic data remains an open question. In this study, we experimentally evaluate two different model evaluation protocols for classifiers trained on synthetic data. The first protocol employs solely synthetic data for downstream model evaluation, whereas the second protocol assumes limited DP access to a private test set consisting of real data managed by a data curator. We also propose a metric for assessing how well the evaluation results of the proposed protocols match the real-world prediction performance of the models. The assessment measures both the systematic error component indicating how optimistic or pessimistic the protocol is on average and the random error component indicating the variability of the protocol’s error. The results of our study suggest that employing the second protocol is advantageous, particularly in biomedical health studies where the precision of the research is of utmost importance. Our comprehensive empirical study offers new insights into the practical feasibility and usefulness of different evaluation protocols for classifiers trained on DP-synthetic data.

While the effectiveness of fog computing in Internet of Things (IoT) applications has been widely investigated in various studies, there is still a lack of techniques to efficiently utilize the computing resources in a fog platform to maximize Quality of Service (QoS) and Quality of Experience (QoE). This paper presents a resource management model for service placement of distributed multitasking applications in fog computing through mathematical modeling of such a platform. Our main design goal is to reduce communication between the candidate nodes hosting different task modules of an application by selecting a group of nodes near each other and as close to the source of the data as possible. We propose a method based on a greedy principle that demonstrates a highly scalable and near-optimal performance for resource mapping problems for multitasking applications in fog computing networks. Compared with the commercial Gurobi optimizer, our proposed algorithm provides a mapping solution that obtains 93% of the performance, attributed to a higher communication cost, while outperforming the reference method in terms of the computing speed, cutting the mapping execution time to less than 1% of that of the Gurobi optimizer.

Combinatorial treatments have become a standard of care for various complex diseases including cancers. Here, the authors show that combinatorial responses of two anticancer drugs can be accurately predicted using factorization machines trained on large-scale pharmacogenomic data for guiding precision oncology studies.

The automatic detection of facial expressions of pain is needed to ensure accurate pain assessment of patients who are unable to self-report pain. To overcome the challenges of automatic systems for determining pain levels based on facial expressions in clinical patient monitoring, a surface electromyography method was tested for feasibility in healthy volunteers. In the current study, two types of experimental gradually increasing pain stimuli were induced in thirty-one healthy volunteers who attended the study. We used a surface electromyography method to measure the activity of five facial muscles to detect facial expressions during pain induction. Statistical tests were used to analyze the continuous electromyography data, and a supervised machine learning was applied for pain intensity prediction model. Muscle activation of corrugator supercilii was most strongly associated with self-reported pain, and the levator labii superioris and orbicularis oculi showed a statistically significant increase in muscle activation when the pain stimulus reached subjects' self -reported pain thresholds. The two strongest features associated with pain, the waveform length of the corrugator supercilii and levator labii superioris, were selected for a prediction model. The performance of the pain prediction model resulted in a c-index of 0.64. In the study results, the most detectable difference in muscle activity during the pain experience was connected to eyebrow lowering, nose wrinkling and upper lip raising. As the performance of the prediction model remains modest, yet with a statistically significant ordinal classification, we suggest testing with a larger sample size to further explore the variables that affect variation in expressiveness and subjective pain experience.

PurposeTo develop and validate a classifier system for prediction of prostate cancer (PCa) Gleason score (GS) using radiomics and texture features of T2-weighted imaging (T2w), diffusion weighted imaging (DWI) acquired using high b values, and T2-mapping (T2).MethodsT2w, DWI (12 b values, 0-2000 s/mm2), and T2 data sets of 62 patients with histologically confirmed PCa were acquired at 3T using surface array coils. The DWI data sets were post-processed using monoexponential and kurtosis models, while T2w was standardized to a common scale. Local statistics and 8 different radiomics/texture descriptors were utilized at different configurations to extract a total of 7105 unique per-tumor features. Regularized logistic regression with implicit feature selection and leave pair out cross validation was used to discriminate tumors with 3+3 vs >3+3 GS.ResultsIn total, 100 PCa lesions were analysed, of those 20 and 80 had GS of 3+3 and >3+3, respectively. The best model performance was obtained by selecting the top 1% features of T2w, ADCm and K with ROC AUC of 0.88 (95% CI of 0.82-0.95). Features from T2 mapping provided little added value. The most useful texture features were based on the gray-level co-occurrence matrix, Gabor transform, and Zernike moments.ConclusionTexture feature analysis of DWI, post-processed using monoexponential and kurtosis models, and T2w demonstrated good classification performance for GS of PCa. In multisequence setting, the optimal radiomics based texture extraction methods and parameters differed between different image types.

Background The molecular mechanisms mediating postnatal loss of cardiac regeneration in mammals are not fully understood. We aimed to provide an integrated resource of mRNA, protein, and metabolite changes in the neonatal heart for identification of metabolism‐related mechanisms associated with cardiac regeneration. Methods and Results Mouse ventricular tissue samples taken on postnatal day 1 (P01), P04, P09, and P23 were analyzed with RNA sequencing and global proteomics and metabolomics. Gene ontology analysis, KEGG pathway analysis, and fuzzy c‐means clustering were used to identify up‐ or downregulated biological processes and metabolic pathways on all 3 levels, and Ingenuity pathway analysis (Qiagen) was used to identify upstream regulators. Differential expression was observed for 8547 mRNAs and for 1199 of 2285 quantified proteins. Furthermore, 151 metabolites with significant changes were identified. Differentially regulated metabolic pathways include branched chain amino acid degradation (upregulated at P23), fatty acid metabolism (upregulated at P04 and P09; downregulated at P23) as well as the HMGCS (HMG‐CoA [hydroxymethylglutaryl‐coenzyme A] synthase)–mediated mevalonate pathway and ketogenesis (transiently activated). Pharmacological inhibition of HMGCS in primary neonatal cardiomyocytes reduced the percentage of BrdU‐positive cardiomyocytes, providing evidence that the mevalonate and ketogenesis routes may participate in regulating the cardiomyocyte cell cycle. Conclusions This study is the first systems‐level resource combining data from genomewide transcriptomics with global quantitative proteomics and untargeted metabolomics analyses in the mouse heart throughout the early postnatal period. These integrated data of molecular changes associated with the loss of cardiac regeneration may open up new possibilities for the development of regenerative therapies.

Due to relatively high costs and labor required for experimental profiling of the full target space of chemical compounds, various machine learning models have been proposed as cost-effective means to advance this process in terms of predicting the most potent compound-target interactions for subsequent verification. However, most of the model predictions lack direct experimental validation in the laboratory, making their practical benefits for drug discovery or repurposing applications largely unknown. Here, we therefore introduce and carefully test a systematic computational-experimental framework for the prediction and pre-clinical verification of drug-target interactions using a well-established kernel-based regression algorithm as the prediction model. To evaluate its performance, we first predicted unmeasured binding affinities in a large-scale kinase inhibitor profiling study, and then experimentally tested 100 compound-kinase pairs. The relatively high correlation of 0.77 (p < 0.0001) between the predicted and measured bioactivities supports the potential of the model for filling the experimental gaps in existing compound-target interaction maps. Further, we subjected the model to a more challenging task of predicting target interactions for such a new candidate drug compound that lacks prior binding profile information. As a specific case study, we used tivozanib, an investigational VEGF receptor inhibitor with currently unknown off-target profile. Among 7 kinases with high predicted affinity, we experimentally validated 4 new off-targets of tivozanib, namely the Src-family kinases FRK and FYN A, the non-receptor tyrosine kinase ABL1, and the serine/threonine kinase SLK. Our sub-sequent experimental validation protocol effectively avoids any possible information leakage between the training and validation data, and therefore enables rigorous model validation for practical applications. These results demonstrate that the kernel-based modeling approach offers practical benefits for probing novel insights into the mode of action of investigational compounds, and for the identification of new target selectivities for drug repurposing applications.

The rut formation during forest operations is an undesirable phenomenon. A methodology is being proposed to measure the rut depth distribution of a logging site by photogrammetric point clouds produced by unmanned aerial vehicles (UAV). The methodology includes five processing steps that aim at reducing the noise from the surrounding trees and undergrowth for identifying the trails. A canopy height model is produced to focus the point cloud on the open pathway around the forest machine trail. A triangularized ground model is formed by a point cloud filtering method. The ground model is vectorized using the histogram of directed curvatures (HOC) method to produce an overall ground visualization. Finally, a manual selection of the trails leads to an automated rut depth profile analysis. The bivariate correlation (Pearson’s r) between rut depths measured manually and by UAV photogrammetry is r = 0.67 . The two-class accuracy a of detecting the rut depth exceeding 20 cm is a = 0.65 . There is potential for enabling automated large-scale evaluation of the forestry areas by using autonomous drones and the process described.

Three methods to estimate the presence of ground surface stones from publicly available Airborne Laser Scanning (ALS) point clouds are presented. The first method approximates the local curvature by local linear multi-scale fitting, and the second method uses Discrete-Differential Gaussian curvature based on the ground surface triangulation. The third baseline method applies Laplace filtering to Digital Elevation Model (DEM) in a 2 m regular grid data. All methods produce an approximate Gaussian curvature distribution which is then vectorized and classified by logistic regression. Two training data sets consisted of 88 and 674 polygons of mass-flow deposits, respectively. The locality of the polygon samples is a sparse canopy boreal forest, where the density of ALS ground returns is sufficiently high to reveal information about terrain micro-topography. The surface stoniness of each polygon sample was categorized for supervised learning by expert observation on the site. The leave-pair-out (L2O) cross-validation of the local linear fit method results in the area under curve A U C = 0 . 74 and A U C = 0 . 85 on two data sets, respectively. This performance can be expected to suit real world applications such as detecting coarse-grained sediments for infrastructure construction. A wall-to-wall predictor based on the study was demonstrated.