Search

The Conditional Colour-Magnitude Distribution (CCMD) is a comprehensive formalism of the colour–magnitude–halo mass relation of galaxies. With joint modelling of a large sample of SDSS galaxies in fine bins of galaxy colour and luminosity, Xu et al. inferred parameters of a CCMD model that well reproduces colour- and luminosity-dependent abundance and clustering of present-day galaxies. In this work, we provide a test and investigation of the CCMD model by studying the colour and luminosity distribution of galaxies in galaxy groups. An apples-to-apples comparison of group galaxies is achieved by applying the same galaxy group finder to identify groups from the CCMD galaxy mocks and from the SDSS data, avoiding any systematic effect of group finding and mass assignment on the comparison. We find an overall nice agreement in the conditional luminosity function (CLF), the conditional colour function (CCF), and the CCMD of galaxies in galaxy groups inferred from CCMD mock and SDSS data. We also discuss the subtle differences revealed by the comparison. In addition, using two external catalogues constructed to only include central galaxies with halo mass measured through weak lensing, we find that their colour-magnitude distribution shows two distinct and orthogonal components, in line with the prediction of the CCMD model. Our results suggest that the CCMD model provides a good description of halo mass-dependent galaxy colour and luminosity distribution. The halo and CCMD mock catalogues are made publicly available to facilitate other investigations. [ABSTRACT FROM AUTHOR]

The far-ultraviolet (FUV) flare activity of low-mass stars has become a focus in our understanding of the exoplanet atmospheres and how they evolve. However, direct detection of FUV flares and measurements of their energies and rates are limited by the need for space-based observations. The difficulty of obtaining such observations may push some works to use widely available optical data to calibrate multiwavelength spectral models that describe UV and optical flare emission. These models either use single temperature blackbody curves to describe this emission, or combine a blackbody curve with archival spectra. These calibrated models would then be used to predict the FUV flare rates of low-mass stars of interest. To aid these works, we used TESS optical photometry and archival HST FUV spectroscopy to test the FUV predictions of literature flare models. We tested models for partially (M0–M2) and fully convective (M4–M5) stars, 40 Myr and field age stars, and optically quiet stars. We calculated FUV energy correction factors that can be used to bring the FUV predictions of tested models in line with observations. A flare model combining optical and NUV blackbody emission with FUV emission based on HST observations provided the best estimate of FUV flare activity, where others underestimated the emission at all ages, masses, and activity levels, by up to a factor of 104 for combined FUV continuum and line emission and greater for individual emission lines. We also confirmed previous findings that showed optically quiet low-mass stars exhibit regular FUV flares. [ABSTRACT FROM AUTHOR]

Motivation Despite an increase in protein modelling accuracy following the development of AlphaFold2, there remains an accuracy gap between predicted and observed model quality assessment (MQA) scores. In CASP15, variations in AlphaFold2 model accuracy prediction were noticed for quaternary models of very similar observed quality. In this study, we compare plDDT and pTM to their observed counterparts the local distance difference test (lDDT) and TM-score for both tertiary and quaternary models to examine whether reliability is retained across the scoring range under normal modelling conditions and in situations where AlphaFold2 functionality is customized. We also explore plDDT and pTM ranking accuracy in comparison with the published independent MQA programmes ModFOLD9 and ModFOLDdock. Results plDDT was found to be an accurate descriptor of tertiary model quality compared to observed lDDT-Cα scores (Pearson r  = 0.97), and achieved a ranking agreement true positive rate (TPR) of 0.34 with observed scores, which ModFOLD9 could not improve. However, quaternary structure accuracy was reduced (plDDT r  = 0.67, pTM r  = 0.70) and significant overprediction was seen with both scores for some lower quality models. Additionally, ModFOLDdock was able to improve upon AF2-Multimer model ranking compared to TM-score (TPR 0.34) and oligo-lDDT score (TPR 0.43). Finally, evidence is presented for increased variability in plDDT and pTM when using custom template recycling, which is more pronounced for quaternary structures. Availability and implementation The ModFOLD9 and ModFOLDdock quality assessment servers are available at https://www.reading.ac.uk/bioinf/ModFOLD/ and https://www.reading.ac.uk/bioinf/ModFOLDdock/ , respectively. A docker image is available at https://hub.docker.com/r/mcguffin/multifold. [ABSTRACT FROM AUTHOR]

Motivation Biomedical entity linking (BEL) is the task of grounding entity mentions to a given knowledge base (KB). Recently, neural name-based methods, system identifying the most appropriate name in the KB for a given mention using neural network (either via dense retrieval or autoregressive modeling), achieved remarkable results for the task, without requiring manual tuning or definition of domain/entity-specific rules. However, as name-based methods directly return KB names, they cannot cope with homonyms, i.e. different KB entities sharing the exact same name. This significantly affects their performance for KBs where homonyms account for a large amount of entity mentions (e.g. UMLS and NCBI Gene). Results We present BELHD (Biomedical Entity Linking with Homonym Disambiguation), a new name-based method that copes with this challenge. BELHD builds upon the BioSyn model with two crucial extensions. First, it performs pre-processing of the KB, during which it expands homonyms with a specifically constructed disambiguating string, thus enforcing unique linking decisions. Second, it introduces candidate sharing, a novel strategy that strengthens the overall training signal by including similar mentions from the same document as positive or negative examples, according to their corresponding KB identifier. Experiments with 10 corpora and 5 entity types show that BELHD improves upon current neural state-of-the-art approaches, achieving the best results in 6 out of 10 corpora with an average improvement of 4.55pp recall@1. Furthermore, the KB preprocessing is orthogonal to the prediction model and thus can also improve other neural methods, which we exemplify for GenBioEL, a generative name-based BEL approach. Availability and implementation The code to reproduce our experiments can be found at: https://github.com/sg-wbi/belhd. [ABSTRACT FROM AUTHOR]

Background PREDICT is a web-based tool for forecasting breast cancer outcomes. PREDICT version 3.0 was recently released. This study aimed to validate this tool for a large population in mainland China and compare v3.0 with v2.2. Methods Women who underwent surgery for nonmetastatic primary invasive breast cancer between 2010 and 2020 from the First Affiliated Hospital of Wenzhou Medical University were selected. Predicted and observed 5-year overall survival (OS) for both v3.0 and v2.2 were compared. Discrimination was compared using receiver-operator curves and DeLong test. Calibration was evaluated using calibration plots and chi-squared test. A difference greater than 5% was deemed clinically relevant. Results A total of 5424 patients were included, with median follow-up time of 58 months (IQR 38-89 months). Compared to v2.2, v3.0 did not show improved discriminatory accuracy for 5-year OS (AUC: 0.756 vs 0.771), same as ER-positive and ER-negative patients. However, calibration was significantly improved in v3.0, with predicted 5-year OS deviated from observed by −2.0% for the entire cohort, −2.9% for ER-positive and −0.0% for ER-negative patients, compared to −7.3%, −4.7% and −13.7% in v2.2. In v3.0, 5-year OS was underestimated by 9.0% for patients older than 75 years, and 5.8% for patients with micrometastases. Patients with distant metastases postdiagnosis was overestimated by 10.6%. Conclusions PREDICT v3.0 reliably predicts 5-year OS for the majority of Chinese patients with breast cancer. PREDICT v3.0 significantly improved the predictive accuracy for ER-negative groups. Furthermore, caution is advised when interpreting 5-year OS for patients aged over 70, those with micrometastases or metastases postdiagnosis. [ABSTRACT FROM AUTHOR]

The article offers a perspective on variants of unknown significance (VUS) in precision oncology and their impact on treatment choice. It presents clinical cases of patients with pancreatic cancer, a family history of cancer, and germline or somatic VUS, to illustrate the challenges of VUS in clinical practice. It considers pathogenic, germline mutations as loss-of-function mutations in tumor suppressors and presents data regarding pathogenic TET3 mutations and VUS.

Background Few studies have assessed the comprehensive associations among comorbid diseases in elderly patients with nasopharyngeal carcinoma (NPC). This study sought to identify potential comorbidity patterns and explore the relationship of comorbidity patterns with the mortality risk in elderly patients with NPC. Methods A total of 452 elderly patients with NPC were enrolled in the study. The network analysis and latent class analysis were applied to mine comorbidity patterns. Propensity score matching was used for adjusting confounders. A restricted cubic spline model was used to analyze the nonlinear association between age and the risk of all-cause mortality. Results We identified 2 comorbidity patterns, metabolic disease-related comorbidity (MDRC) and organ disease-related comorbidity (ODRC) in elderly patients with NPC. Patients in MDRC showed a significantly higher risk of all-cause mortality (71.41% vs 87.97%, HR 1.819 [95% CI, 1.106-2.994], P  = .031) and locoregional relapse (68.73% vs 80.88%, HR 1.689 [95% CI, 1.055-2.704], P  = .042). Moreover, in patients with MDRC pattern, we observed an intriguing inverted S-shaped relationship between age and all-cause mortality among patients aged 68 years and older. The risk of mortality up perpetually with age increasing in ODRC group, specifically within the age range of 68-77 years (HR 4.371, 1.958-9.757). Conclusion Our study shed light on the potential comorbidity patterns in elderly patients with NPC, thereby providing valuable insights into the development of comprehensive health management strategies for this specific population. [ABSTRACT FROM AUTHOR]

Motivation Predicting cancer drug response requires a comprehensive assessment of many mutations present across a tumor genome. While current drug response models generally use a binary mutated/unmutated indicator for each gene, not all mutations in a gene are equivalent. Results Here, we construct and evaluate a series of predictive models based on leading methods for quantitative mutation scoring. Such methods include VEST4 and CADD, which score the impact of a mutation on gene function, and CHASMplus, which scores the likelihood a mutation drives cancer. The resulting predictive models capture cellular responses to dabrafenib, which targets BRAF-V600 mutations, whereas models based on binary mutation status do not. Performance improvements generalize to other drugs, extending genetic indications for PIK3CA, ERBB2, EGFR, PARP1, and ABL1 inhibitors. Introducing quantitative mutation features in drug response models increases performance and mechanistic understanding. Availability and implementation Code and example datasets are available at https://github.com/pgwall/qms. [ABSTRACT FROM AUTHOR]

Motivation Short-read single-cell RNA-sequencing (scRNA-seq) has been used to study cellular heterogeneity, cellular fate, and transcriptional dynamics. Modeling splicing dynamics in scRNA-seq data is challenging, with inherent difficulty in even the seemingly straightforward task of elucidating the splicing status of the molecules from which sequenced fragments are drawn. This difficulty arises, in part, from the limited read length and positional biases, which substantially reduce the specificity of the sequenced fragments. As a result, the splicing status of many reads in scRNA-seq is ambiguous because of a lack of definitive evidence. We are therefore in need of methods that can recover the splicing status of ambiguous reads which, in turn, can lead to more accuracy and confidence in downstream analyses. Results We develop Forseti , a predictive model to probabilistically assign a splicing status to scRNA-seq reads. Our model has two key components. First, we train a binding affinity model to assign a probability that a given transcriptomic site is used in fragment generation. Second, we fit a robust fragment length distribution model that generalizes well across datasets deriving from different species and tissue types. Forseti combines these two trained models to predict the splicing status of the molecule of origin of reads by scoring putative fragments that associate each alignment of sequenced reads with proximate potential priming sites. Using both simulated and experimental data, we show that our model can precisely predict the splicing status of many reads and identify the true gene origin of multi-gene mapped reads. Availability and implementation Forseti and the code used for producing the results are available at https://github.com/COMBINE-lab/forseti under a BSD 3-clause license. [ABSTRACT FROM AUTHOR]

Recent advances in sequencing, mass spectrometry, and cytometry technologies have enabled researchers to collect multiple 'omics data types from a single sample. These large datasets have led to a growing consensus that a holistic approach is needed to identify new candidate biomarkers and unveil mechanisms underlying disease etiology, a key to precision medicine. While many reviews and benchmarks have been conducted on unsupervised approaches, their supervised counterparts have received less attention in the literature and no gold standard has emerged yet. In this work, we present a thorough comparison of a selection of six methods, representative of the main families of intermediate integrative approaches (matrix factorization, multiple kernel methods, ensemble learning, and graph-based methods). As non-integrative control, random forest was performed on concatenated and separated data types. Methods were evaluated for classification performance on both simulated and real-world datasets, the latter being carefully selected to cover different medical applications (infectious diseases, oncology, and vaccines) and data modalities. A total of 15 simulation scenarios were designed from the real-world datasets to explore a large and realistic parameter space (e.g. sample size, dimensionality, class imbalance, effect size). On real data, the method comparison showed that integrative approaches performed better or equally well than their non-integrative counterpart. By contrast, DIABLO and the four random forest alternatives outperform the others across the majority of simulation scenarios. The strengths and limitations of these methods are discussed in detail as well as guidelines for future applications. [ABSTRACT FROM AUTHOR]

Field-based phenomic prediction employs novel features, like vegetation indices (VIs) from drone images, to predict key agronomic traits in maize, despite challenges in matching biomarker measurement time points across years or environments. This study utilized functional principal component analysis (FPCA) to summarize the variation of temporal VIs, uniquely allowing the integration of this data into phenomic prediction models tested across multiple years (2018–2021) and environments. The models, which included 1 genomic, 2 phenomic, 2 multikernel, and 1 multitrait type, were evaluated in 4 prediction scenarios (CV2, CV1, CV0, and CV00), relevant for plant breeding programs, assessing both tested and untested genotypes in observed and unobserved environments. Two hybrid populations (415 and 220 hybrids) demonstrated the visible atmospherically resistant index's strong temporal correlation with grain yield (up to 0.59) and plant height. The first 2 FPCAs explained 59.3 ± 13.9% and 74.2 ± 9.0% of the temporal variation of temporal data of VIs, respectively, facilitating predictions where flight times varied. Phenomic data, particularly when combined with genomic data, often were comparable to or numerically exceeded the base genomic model in prediction accuracy, particularly for grain yield in untested hybrids, although no significant differences in these models' performance were consistently observed. Overall, this approach underscores the effectiveness of FPCA and combined models in enhancing the prediction of grain yield and plant height across environments and diverse agricultural settings. [ABSTRACT FROM AUTHOR]

Background Resilience of national health systems in Europe remains a major concern in times of multiple crises and as more evidence is emerging relating to the indirect effects of the COVID-19 pandemic on health care utilization (HCU), resulting from de-prioritization of regular, non-pandemic healthcare services. Most extant studies focus on regional, disease specific or early pandemic HCU creating difficulties in comparing across multiple countries. We provide a comparatively broad definition of HCU across multiple countries, with potential to expand across regions and timeframes. Methods Using a cross-country federated research infrastructure (FRI), we examined HCU for acute cardiovascular events, elective surgeries and serious trauma. Aggregated data were used in forecast modelling to identify changes from predicted European age-standardized counts via fitted regressions (2017–19), compared against post-pandemic data. Results We found that elective surgeries were most affected, universally falling below predicted levels in 2020. For cardiovascular HCU, we found lower-than-expected cases in every region for heart attacks and displayed large sex differences. Serious trauma was the least impacted by the COVID-19 pandemic. Conclusion The strength of this study comes from the use of the European Population Health Information Research Infrastructure's (PHIRI) FRI, allowing for rapid analysis of regional differences to assess indirect impacts of events such as pandemics. There are marked differences in the capacity of services to return to normal in terms of elective surgery; additionally, we found considerable differences between men and women which requires further research on potential sex or gender patterns of HCU during crises. [ABSTRACT FROM AUTHOR]

Experimental studies of the observables associated with |$b \rightarrow c$| transitions in semileptonic B -meson decays at BaBar, Belle, and LHCb have shown some deviations from the Standard Model predictions, consequently providing a handy tool to probe the possible new physics (NP). In this context, we first revisit the impact of recent measurements of |$R({D^{(*)}})$| and |$R(\Lambda _c)$| on the parametric space of the NP scenarios. In addition, we include the |$R(J/\psi)$| data in the analysis and find that their influence on the best-fit point and the parametric space is mild. Using the recent HFLAV data, after validating the well established sum rule of |$R(\Lambda _c)$|⁠ , we derive a similar sum rule for |$R(J/\psi)$|⁠. Furthermore, according to the updated data, we modify the correlation among the different observables, giving us their interesting interdependence. Finally, to discriminate the various NP scenarios, we plot the different angular observables and their ratios for |$B \rightarrow D^{*} \tau \nu _\tau$| against the transfer momentum square |$\left(q^2\right)$|⁠ , using the |$1\sigma$| and |$2\sigma$| parametric space of considered NP scenarios. By implementing the collider bounds on NP Wilson coefficients (WCs), we find that the parametric space of some NP WCs is significantly restrained. To see the clear influence of NP on the amplitude of the angular observables, we also calculate their numerical values in different |$q^2$| bins and show them through bar plots. We hope that their precise measurements will help to discriminate various NP scenarios. [ABSTRACT FROM AUTHOR]

With the plentiful information available in the Gaia BP/RP spectra, there is significant scope for applying discriminative models to extract stellar atmospheric parameters and abundances. We describe an approach to leverage an 'Uncertain Neural Network' model trained on APOGEE data to provide high-quality predictions with robust estimates for per-prediction uncertainty. We report median formal uncertainties of 0.068 dex, 69.1 K, 0.14 dex, 0.031 dex, 0.040 dex, and 0.029 dex for [Fe/H], T eff, log  g , [C/Fe], [N/Fe], and [α/M], respectively. We validate these predictions against our APOGEE training data, LAMOST, and Gaia GSP- phot stellar parameters, and see a strong correlation between our predicted parameters and those derived from these surveys. We investigate the information content of the spectra by considering the 'attention' our model pays to different spectral features compared to expectations from synthetic spectra calculations. Our model's predictions are applied to the Gaia data set, and we produce a publicly available catalogue of our model's predictions. [ABSTRACT FROM AUTHOR]

Motivation Accurately identifying the drug–target interactions (DTIs) is one of the crucial steps in the drug discovery and drug repositioning process. Currently, many computational-based models have already been proposed for DTI prediction and achieved some significant improvement. However, these approaches pay little attention to fuse the multi-view similarity networks related to drugs and targets in an appropriate way. Besides, how to fully incorporate the known interaction relationships to accurately represent drugs and targets is not well investigated. Therefore, there is still a need to improve the accuracy of DTI prediction models. Results In this study, we propose a novel approach that employs Multi-view similarity network fusion strategy and deep Interactive attention mechanism to predict Drug–Target Interactions (MIDTI). First, MIDTI constructs multi-view similarity networks of drugs and targets with their diverse information and integrates these similarity networks effectively in an unsupervised manner. Then, MIDTI obtains the embeddings of drugs and targets from multi-type networks simultaneously. After that, MIDTI adopts the deep interactive attention mechanism to further learn their discriminative embeddings comprehensively with the known DTI relationships. Finally, we feed the learned representations of drugs and targets to the multilayer perceptron model and predict the underlying interactions. Extensive results indicate that MIDTI significantly outperforms other baseline methods on the DTI prediction task. The results of the ablation experiments also confirm the effectiveness of the attention mechanism in the multi-view similarity network fusion strategy and the deep interactive attention mechanism. Availability and implementation https://github.com/XuLew/MIDTI. [ABSTRACT FROM AUTHOR]

Summary The increasing development of sequence-based machine learning models has raised the demand for manipulating sequences for this application. However, existing approaches to edit and evaluate genome sequences using models have limitations, such as incompatibility with structural variants, challenges in identifying responsible sequence perturbations, and the need for vcf file inputs and phased data. To address these bottlenecks, we present S equence M u tator for Pre dictive Mo dels (SuPreMo), a scalable and comprehensive tool for performing and supporting in silico mutagenesis experiments. We then demonstrate how pairs of reference and perturbed sequences can be used with machine learning models to prioritize pathogenic variants or discover new functional sequences. Availability and implementation SuPreMo was written in Python, and can be run using only one line of code to generate both sequences and 3D genome disruption scores. The codebase, instructions for installation and use, and tutorials are on the GitHub page: https://github.com/ketringjoni/SuPreMo. [ABSTRACT FROM AUTHOR]

Background In recent years, a number of predictive models have appeared to predict the risk of medium-term mortality in hemodialysis patients, but only one, limited to patients aged over 70 years, has undergone sufficiently powerful external validation. Recently, using a national learning database and an innovative approach based on Bayesian networks and 14 carefully selected predictors, we have developed a clinical prediction tool to predict all-cause mortality at 2 years in all incident hemodialysis patients. In order to generalize the results of this tool and propose its use in routine clinical practice, we carried out an external validation using an independent external validation database. Methods A regional, multicenter, observational, retrospective cohort study was conducted to externally validate the tool for predicting 2-year all-cause mortality in incident and prevalent hemodialysis patients. This study recruited a total of 142 incident and 697 prevalent adult hemodialysis patients followed up in one of the eight Association pour l'Utilisation du Rein Artificiel dans la région Lyonnaise (AURAL) Alsace dialysis centers. Results In incident patients, the 2-year all-cause mortality prediction tool had an area under the receiver curve (AUC-ROC) of 0.73, an accuracy of 65%, a sensitivity of 71% and a specificity of 63%. In prevalent patients, the performance for the external validation were similar in terms of AUC-ROC, accuracy and specificity, but was lower in term of sensitivity. Conclusion The tool for predicting all-cause mortality at 2 years, developed using a Bayesian network and 14 routinely available explanatory variables, obtained satisfactory external validation in incident patients, but sensitivity was insufficient in prevalent patients. [ABSTRACT FROM AUTHOR]

The immediate result of percutaneous balloon mitral commissurotomy is largely determined by the anatomy of the mitral valve complex. Several scores and models have been developed to assess anatomical suitability for percutaneous balloon mitral commissurotomy. Although none has an optimal predictive power, these models look at the valvular apparatus from different perspectives bearing the potential for a complementary role. [ABSTRACT FROM AUTHOR]

Developing prognostic tools specifically for patients themselves represents an important step in empowering patients to engage in shared decision-making. Incorporating patient-reported outcomes may improve the accuracy of these prognostic tools. We conducted a retrospective population-based study of transplant-ineligible (TIE) patients with multiple myeloma (MM) diagnosed between January 2007 and December 2018. A multivariable Cox regression model was developed to predict the risk of death within 1-year period from the index date. We identified 2356 patients with TIE MM. The following factors were associated with an increased risk of death within 1 year: age > 80 (HR 1.11), history of heart failure (HR 1.52), "CRAB" at diagnosis (HR 1.61), distance to cancer center (HR 1.25), prior radiation (HR 1.48), no proteosome inhibitor/immunomodulatory therapy usage (HR 1.36), recent emergency department (HR 1.55) or hospitalization (HR 2.13), poor performance status (ECOG 3-4 HR 1.76), and increasing number of severe symptoms (HR 1.56). Model discrimination was high with C-statistic of 0.74, and calibration was very good. To our knowledge, this represents one of the first prognostic models developed in MM incorporating patient-reported outcomes. This survival prognostic tool may improve communication regarding prognosis and shared decision-making among older adults with MM and their health care providers. [ABSTRACT FROM AUTHOR]

Background Accurate prognostic stratification of hepatocellular carcinoma (HCC) is vital for clinical trial enrollment and treatment allocation. Multiple scoring systems have been created to predict patient survival, but no standardized scoring systems account for radiologic tumor features. We sought to create a generalizable scoring system for HCC which incorporates standardized radiologic tumor features and more accurately predicts overall survival (OS) than established systems. Methods Clinicopathologic parameters were collected from a prospectively collected cohort of patients with HCC treated at a single institution. Imaging studies were evaluated for tumor characteristics. Patients were randomly divided into a training set for identification of covariates that impacted OS and a validation set. Cox models were used to determine the association of various factors with OS and a scoring system was created. Results We identified 383 patients with HCC with imaging and survival outcomes, n  = 255 in the training set and 128 in the validation cohort. Factors associated with OS on multivariate analysis included: tumor margin appearance on CT or MRI (hazard ratio [HR] 1.37, 95% CI, 1.01-1.88) with infiltrative margins portending worse outcomes than encapsulated margins, massive tumor morphology (HR 1.64, 95% CI, 1.06-2.54); >2 lesions (HR 2.06, 95% CI, 1.46-2.88), Child-Turcotte-Pugh class C (HR 3.7, 95% CI, 2.23-6.16), and portal vein thrombus (HR 2.41, 95% CI, 1.71-3.39). A new scoring system was developed and more predictive of OS than other well-established systems. Conclusions Incorporation of standardized imaging characteristics to established clinical and lab predictors of outcome resulted in an improved predictive scoring system for patients with HCC. [ABSTRACT FROM AUTHOR]

Motivation The quality scores data (QSD) account for 70% in compressed FastQ files obtained from the short and long reads sequencing technologies. Designing effective compressors for QSD that counterbalance compression ratio, time cost, and memory consumption is essential in scenarios such as large-scale genomics data sharing and long-term data backup. This study presents a novel parallel lossless QSD-dedicated compression algorithm named PQSDC, which fulfills the above requirements well. PQSDC is based on two core components: a parallel sequences-partition model designed to reduce peak memory consumption and time cost during compression and decompression processes, as well as a parallel four-level run-length prediction mapping model to enhance compression ratio. Besides, the PQSDC algorithm is also designed to be highly concurrent using multicore CPU clusters. Results We evaluate PQSDC and four state-of-the-art compression algorithms on 27 real-world datasets, including 61.857 billion QSD characters and 632.908 million QSD sequences. (1) For short reads, compared to baselines, the maximum improvement of PQSDC reaches 7.06% in average compression ratio, and 8.01% in weighted average compression ratio. During compression and decompression, the maximum total time savings of PQSDC are 79.96% and 84.56%, respectively; the maximum average memory savings are 68.34% and 77.63%, respectively. (2) For long reads, the maximum improvement of PQSDC reaches 12.51% and 13.42% in average and weighted average compression ratio, respectively. The maximum total time savings during compression and decompression are 53.51% and 72.53%, respectively; the maximum average memory savings are 19.44% and 17.42%, respectively. (3) Furthermore, PQSDC ranks second in compression robustness among the tested algorithms, indicating that it is less affected by the probability distribution of the QSD collections. Overall, our work provides a promising solution for QSD parallel compression, which balances storage cost, time consumption, and memory occupation primely. Availability and implementation The proposed PQSDC compressor can be downloaded from https://github.com/fahaihi/PQSDC. [ABSTRACT FROM AUTHOR]

N4-acetylcytidine (ac4C) is a modification found in ribonucleic acid (RNA) related to diseases. Expensive and labor-intensive methods hindered the exploration of ac4C mechanisms and the development of specific anti-ac4C drugs. Therefore, an advanced prediction model for ac4C in RNA is urgently needed. Despite the construction of various prediction models, several limitations exist: (1) insufficient resolution at base level for ac4C sites; (2) lack of information on species other than Homo sapiens ; (3) lack of information on RNA other than mRNA; and (4) lack of interpretation for each prediction. In light of these limitations, we have reconstructed the previous benchmark dataset and introduced a new dataset including balanced RNA sequences from multiple species and RNA types, while also providing base-level resolution for ac4C sites. Additionally, we have proposed a novel transformer-based architecture and pipeline for predicting ac4C sites, allowing for highly accurate predictions, visually interpretable results and no restrictions on the length of input RNA sequences. Statistically, our work has improved the accuracy of predicting specific ac4C sites in multiple species from less than 40% to around 85%, achieving a high AUC > 0.9. These results significantly surpass the performance of all existing models. [ABSTRACT FROM AUTHOR]

It is a vital step to recognize cyanobacteria promoters on a genome-wide scale. Computational methods are promising to assist in difficult biological identification. When building recognition models, these methods rely on non-promoter generation to cope with the lack of real non-promoters. Nevertheless, the factitious significant difference between promoters and non-promoters causes over-optimistic prediction. Moreover, designed for E. coli or B. subtilis , existing methods cannot uncover novel, distinct motifs among cyanobacterial promoters. To address these issues, this work first proposes a novel non-promoter generation strategy called phantom sampling, which can eliminate the factitious difference between promoters and generated non-promoters. Furthermore, it elaborates a novel promoter prediction model based on the Siamese network (SiamProm), which can amplify the hidden difference between promoters and non-promoters through a joint characterization of global associations, upstream and downstream contexts, and neighboring associations w.r.t. k-mer tokens. The comparison with state-of-the-art methods demonstrates the superiority of our phantom sampling and SiamProm. Both comprehensive ablation studies and feature space illustrations also validate the effectiveness of the Siamese network and its components. More importantly, SiamProm, upon our phantom sampling, finds a novel cyanobacterial promoter motif ('GCGATCGC'), which is palindrome-patterned, content-conserved, but position-shifted. [ABSTRACT FROM AUTHOR]

Phages can specifically recognize and kill bacteria, which lead to important application value of bacteriophage in bacterial identification and typing, livestock aquaculture and treatment of human bacterial infection. Considering the variety of human-infected bacteria and the continuous discovery of numerous pathogenic bacteria, screening suitable therapeutic phages that are capable of infecting pathogens from massive phage databases has been a principal step in phage therapy design. Experimental methods to identify phage–host interaction (PHI) are time-consuming and expensive; high-throughput computational method to predict PHI is therefore a potential substitute. Here, we systemically review bioinformatic methods for predicting PHI, introduce reference databases and in silico models applied in these methods and highlight the strengths and challenges of current tools. Finally, we discuss the application scope and future research direction of computational prediction methods, which contribute to the performance improvement of prediction models and the development of personalized phage therapy. [ABSTRACT FROM AUTHOR]

Vitamin A deficiency remains prevalent on a global scale, including in regions where maize constitutes a high percentage of human diets. One solution for alleviating this deficiency has been to increase grain concentrations of provitamin A carotenoids in maize (Zea mays ssp. mays L.)—an example of biofortification. The International Maize and Wheat Improvement Center (CIMMYT) developed a Carotenoid Association Mapping panel of 380 inbred lines adapted to tropical and subtropical environments that have varying grain concentrations of provitamin A and other health-beneficial carotenoids. Several major genes have been identified for these traits, 2 of which have particularly been leveraged in marker-assisted selection. This project assesses the predictive ability of several genomic prediction strategies for maize grain carotenoid traits within and between 4 environments in Mexico. Ridge Regression-Best Linear Unbiased Prediction, Elastic Net, and Reproducing Kernel Hilbert Spaces had high predictive abilities for all tested traits (β-carotene, β-cryptoxanthin, provitamin A, lutein, and zeaxanthin) and outperformed Least Absolute Shrinkage and Selection Operator. Furthermore, predictive abilities were higher when using genome-wide markers rather than only the markers proximal to 2 or 13 genes. These findings suggest that genomic prediction models using genome-wide markers (and assuming equal variance of marker effects) are worthwhile for these traits even though key genes have already been identified, especially if breeding for additional grain carotenoid traits alongside β-carotene. Predictive ability was maintained for all traits except lutein in between-environment prediction. The TASSEL (Trait Analysis by aSSociation, Evolution, and Linkage) Genomic Selection plugin performed as well as other more computationally intensive methods for within-environment prediction. The findings observed herein indicate the utility of genomic prediction methods for these traits and could inform their resource-efficient implementation in biofortification breeding programs. [ABSTRACT FROM AUTHOR]

Background Chronic kidney disease (CKD) is a major global health problem and its early identification would allow timely intervention to reduce complications. We performed a systematic review and meta-analysis of multivariable prediction models derived and/or validated in community-based electronic health records (EHRs) for the prediction of incident CKD in the community. Methods Ovid Medline and Ovid Embase were searched for records from 1947 to 31 January 2024. Measures of discrimination were extracted and pooled by Bayesian meta-analysis, with heterogeneity assessed through a 95% prediction interval (PI). Risk of bias was assessed using Prediction model Risk Of Bias ASsessment Tool (PROBAST) and certainty in effect estimates by Grading of Recommendations, Assessment, Development and Evaluation (GRADE). Results Seven studies met inclusion criteria, describing 12 prediction models, with two eligible for meta-analysis including 2 173 202 patients. The Chronic Kidney Disease Prognosis Consortium (CKD-PC) (summary c-statistic 0.847; 95% CI 0.827–0.867; 95% PI 0.780–0.905) and SCreening for Occult REnal Disease (SCORED) (summary c-statistic 0.811; 95% CI 0.691–0.926; 95% PI 0.514–0.992) models had good model discrimination performance. Risk of bias was high in 64% of models, and driven by the analysis domain. No model met eligibility for meta-analysis if studies at high risk of bias were excluded, and certainty of effect estimates was 'low'. No clinical utility analyses or clinical impact studies were found for any of the models. Conclusions Models derived and/or externally validated for prediction of incident CKD in community-based EHRs demonstrate good prediction performance, but assessment of clinical usefulness is limited by high risk of bias, low certainty of evidence and a lack of impact studies. [ABSTRACT FROM AUTHOR]

Background Evidence has demonstrated that monitoring of the variable, diversity, and joining gene segments (VDJ) rearrangement of the immunoglobulin (Ig) genes in the circulating tumor DNA (ctDNA) is of value in predicting the outcomes of diffuse large B cell lymphoma (DLBCL). In this study, we investigated the role of VDJ rearrangement proportion in ctDNA for predicting DLBCL progression. Methods Patients diagnosed with newly diagnosed DLBCL were included in this study. The VDJ sequences of IgH were detected using next-generation sequencing (NGS) in formalin-fixed paraffin-embedded tissue and/or peripheral blood. The clonotype of the highest proportion in the peripheral blood was defined as the "dominant circulating clonotype," whilst the clonotype of the highest proportion in matched tissue that is detected in peripheral blood was defined as the "dominant tissue-matched clonotype." The decision tree, a machine learning-based methodology, was used to establish a progression-predicting model through a combination of "dominant tissue-matched clonotype" proportion or "dominant circulating clonotype" proportion, and the clinicopathological information, including age, sex, cell of origin, stage, international prognostic index, lactate dehydrogenase, number of extranodal involvements and β2-microglobulin. Results A total of 55 patients with eligible sequencing data were used for prognosis analysis, among which 36 patients had matched tissue samples. The concordance rate of "dominant circulating clonotype" and "dominant tissue-matched clonotype" was 19.44% (7/36). The decision tree model showed that the combination of extranodal involvement event and "dominant circulating clonotype" proportion (≥37%) had a clinical value in predicting the prognosis of DLBCL following combined chemotherapy (sensitivity, 0.63; specificity, 0.81; positive prediction value (PPV), 0.59; negative prediction value, 0.83; kappa value, 0.42). Noticeably, the combination of the "dominant tissue-matched clonotype" and extranodal involvement event showed a higher value in predicting the progression (sensitivity, 0.85; specificity, 0.78; PPV, 0.69; kappa value, 0.64). Conclusion IgH proportion detected in the ctDNA samples traced from tissue samples has a high clinical value in predicting the progression of DLBCL. [ABSTRACT FROM AUTHOR]

Motivation Recent advancements in sequencing technologies have led to the discovery of numerous variants in the human genome. However, understanding their precise roles in diseases remains challenging due to their complex functional mechanisms. Various methodologies have emerged to predict the pathogenic significance of these genetic variants. Typically, these methods employ an integrative approach, leveraging diverse data sources that provide important insights into genomic function. Despite the abundance of publicly available data sources and databases, the process of navigating, extracting, and pre-processing features for machine learning models can be highly challenging and time-consuming. Furthermore, researchers often invest substantial effort in feature extraction, only to later discover that these features lack informativeness. Results In this article, we introduce DrivR-Base , an innovative resource that efficiently extracts and integrates molecular information (features) related to single nucleotide variants. These features encompass information about the genomic positions and the associated protein positions of a variant. They are derived from a wide array of databases and tools, including structural properties obtained from AlphaFold , regulatory information sourced from ENCODE, and predicted variant consequences from Variant Effect Predictor. DrivR-Base is easily deployable via a Docker container to ensure reproducibility and ease of access across diverse computational environments. The resulting features can be used as input for machine learning models designed to predict the pathogenic impact of human genome variants in disease. Moreover, these feature sets have applications beyond this, including haploinsufficiency prediction and the development of drug repurposing tools. We describe the resource's development, practical applications, and potential for future expansion and enhancement. Availability and implementation DrivR-Base source code is available at https://github.com/amyfrancis97/DrivR-Base. [ABSTRACT FROM AUTHOR]

Motivation Molecular representation learning plays an indispensable role in crucial tasks such as property prediction and drug design. Despite the notable achievements of molecular pre-training models, current methods often fail to capture both the structural and feature semantics of molecular graphs. Moreover, while graph contrastive learning has unveiled new prospects, existing augmentation techniques often struggle to retain their core semantics. To overcome these limitations, we propose a gradient-compensated encoder parameter perturbation approach, ensuring efficient and stable feature augmentation. By merging enhancement strategies grounded in attribute masking and parameter perturbation, we introduce MoleMCL, a new MOLEcular pre-training model based on multi-level contrastive learning. Results Experimental results demonstrate that MoleMCL adeptly dissects the structure and feature semantics of molecular graphs, surpassing current state-of-the-art models in molecular prediction tasks, paving a novel avenue for molecular modeling. Availability and implementation The code and data underlying this work are available in GitHub at https://github.com/BioSequenceAnalysis/MoleMCL. [ABSTRACT FROM AUTHOR]

Standard models of structure formation allow us to predict the cosmic timescales relevant for the onset of star formation and the assembly history of galaxies at high redshifts (z > 10). The strength of the Balmer break represents a well-known diagnostic of the age and star formation history of galaxies, which enables us to compare observations with contemporary simulations – thus shedding light on the predictive power of our current models of star formation in the early Universe. Here, we measure the Balmer break strength for 23 spectroscopically confirmed galaxies at redshifts 6 ≲ z ≲ 12 using public JWST NIRSpec data from the cycle 1 GO 1433 and GO 2282 programmes (PI Coe), as well as public spectroscopic data from the JWST Deep Extragalactic Survey (JADES). We find that the range of observed Balmer break strengths agree well with that of current simulations given our measurement uncertainties. No cases of anomalously strong Balmer breaks are detected, and therefore no severe departures from the predictions of contemporary models of star formation. However, there are indications of a number of outliers in the observed distribution which have weaker Balmer breaks than predicted by simulations. [ABSTRACT FROM AUTHOR]

Multienvironment genomic prediction was applied to tetraploid potato using 147 potato varieties, tested for 2 years, in 3 locations representative of 3 distinct regions in Europe. Different prediction scenarios were investigated to help breeders predict genotypic performance in the regions from one year to the next, for genotypes that were tested this year (scenario 1), as well as new genotypes (scenario 3). In scenario 2, we predicted new genotypes for any one of the 6 trials, using all the information that is available. The choice of prediction model required assessment of the variance–covariance matrix in a mixed model that takes into account heterogeneity of genetic variances and correlations. This was done for each analyzed trait (tuber weight, tuber length, and dry matter) where examples of both limited and higher degrees of heterogeneity was observed. This explains why dry matter did not need complex multienvironment modeling to combine environments and increase prediction ability, while prediction in tuber weight, improved only when models were flexible enough to capture the heterogeneous variances and covariances between environments. We also found that the prediction abilities in a target trial condition decreased, if trials with a low genetic correlation to the target were included when training the model. Genomic prediction in tetraploid potato can work once there is clarity about the prediction scenario, a suitable training set is created, and a multienvironment prediction model is chosen based on the patterns of G×E indicated by the genetic variances and covariances. [ABSTRACT FROM AUTHOR]

Up to a half of couples seeking medical assistance for infertility are diagnosed with unexplained infertility, characterized by normal ovulation, tubal patency, and semen analysis results. This condition presents a challenge in determining the optimal treatment approach. Available treatments include IUI and IVF, but guidelines vary on when to offer each. Prognosis-based management is identified as a research priority, and various prediction models have been developed to guide treatment decisions. Prognostic factors include female age, duration of subfertility, and sperm parameters, among others. Prognosis-based strategies can enhance cost-effectiveness, safety, and patient outcomes, offering less invasive options to those with good prognoses and more aggressive interventions to those with poor prognoses. However, there is a gap between research evidence and its clinical application. In this article, we discuss the application of prognosis-based management in the context of unexplained infertility, highlighting its potential to improve clinical decision-making and patient outcomes. [ABSTRACT FROM AUTHOR]

The prediction of in situ stress based on azimuthal seismic data has extensive use in horizon crushability evaluation. Nonetheless, existing in situ stress seismic prediction models do not consider overburden pressure and tectonic strain, which limit the prediction accuracy. To this end, we propose a decoupled overburden pressure in situ stress prediction method under tectonic constraints. The key to this method is to consider that the overburden pressure could act on the rock skeleton and pore fluid, i.e. generating effective pressure and pore pressure; the pore pressure can be estimated using Eaton's method, and then the effective stress can be obtained. The relationship between tectonic strain and effective pressure is constructed based on Hooke's law, where tectonic strain can be calculated from curvature attributes extracted from seismic data. Introducing pore pressure and deriving a model for calculating the maximum and minimum horizontal stresses and the difference in horizontal stress ratio for orthotropic media (OA). When the Thomson anisotropy parameters and the pore pressure are neglected, the proposed model can be degraded to a conventional horizontal transverse isotropy medium in situ stress prediction model, which proves the validity of the model. The results of sensitivity analysis experiments affirm the need to decouple overburden pressure and account for tectonic strain when predicting in situ stress reasonably. Finally, single-well and azimuthal seismic prediction were carried out by using the a priori information from well logging and seismic data. [ABSTRACT FROM AUTHOR]

Aims Permanent pacemaker (PM) implantation is common after transcatheter aortic valve implantation (TAVI). Left ventricular mechanical dispersion (MeDi) by speckle tracking echocardiography is a marker of fibrosis that causes alterations in the conduction system. We hypothesized that MeDi can be a predictor of the need for PM implantation after TAVI. Methods and results Consecutively, 200 TAVI patients were enrolled. Transthoracic echocardiography and electrocardiography examinations were recorded before TAVI to evaluate global longitudinal strain (GLS), MeDi, and conduction disturbances. PM implantation information was obtained 3 months after TAVI. Patients were stratified into PM or no PM group. Mean age was 80 + 7 years (44% women). Twenty-nine patients (16%) received PM. MeDi, QRS duration, existence of right bundle branch abnormality (RBBB), and first-degree atrioventricular (AV) block were significantly different between groups. MeDi was 57 ± 15 ms and 48 ± 12 ms in PM and no PM groups, respectively (P < 0.001). In multivariate analysis, MeDi predicted the need for PM after TAVI independently of GLS, QRS duration, RBBB, and first-degree AV block [odds ratio (OR): 1.73, 95% confidence interval (CI): 1.22–2.45] with an area under the curve (AUC) of 0.68 in receiver operating characteristic (ROC) curves. Moreover, RBBB was an independent predictor of PM need after TAVI (OR: 8.98, 95% CI: 1.78–45.03). When added to RBBB, MeDi had an incremental predictive value with an AUC of 0.73 in ROC curves (P = 0.01). Conclusion MeDi may be used as an echocardiographic functional predictor of the need for PM after TAVI. [ABSTRACT FROM AUTHOR]

Aims Exercise-induced pulmonary hypertension (PH), defined by a mean pulmonary arterial pressure over cardiac output (mPAP/CO) slope >3 mmHg/L/min, has important diagnostic and prognostic implications. The aim of this study is to investigate the value of the mPAP/CO slope in patients with more than moderate primary mitral regurgitation (MR) with preserved ejection fraction and no or discordant symptoms. Methods and results A total of 128 consecutive patients were evaluated with exercise echocardiography and cardiopulmonary testing. Clinical outcome was defined as the composite of mitral valve intervention, new-onset atrial fibrillation, cardiovascular hospitalization, and all-cause mortality. The mean age was 63 years, 61% were male, and the mean LVEF was 66 ± 6%. The mPAP/CO slope correlated with peak VO2 (r = −0.52, P < 0.001), while the peak systolic pulmonary artery pressure (sPAP) did not (r = −0.06, P = 0.584). Forty-six per cent (n = 59) had peak exercise sPAP ≥60 mmHg, and 37% (n = 47) had mPAP/CO slope >3 mmHg/L/min. Event-free survival was 55% at 1 year and 46% at 2 years, with reduced survival in patients with mPAP/CO slope >3 mmHg/L/min (hazard ratio, 4.9; 95% confidence interval, 2.9–8.2; P < 0.001). In 53 cases (41%), mPAP/CO slope and peak sPAP were discordant: patients with slope >3 mmHg/L/mmHg and sPAP <60 mmHg (n = 21) had worse outcome vs. peak sPAP ≥60 mmHg and normal slope (n = 32, log-rank P = 0.003). The mPAP/CO slope improved predictive models for outcome, incremental to resting and exercise sPAP, and peak VO2. Conclusion Exercise PH defined by the mPAP/CO slope >3 mmHg/L/min is associated with decreased exercise capacity and a higher risk of adverse events in significant primary MR and no or discordant symptoms. The slope provides a greater prognostic value than single sPAP measures and peak VO2. [ABSTRACT FROM AUTHOR]

Aims Mammography, commonly used for breast cancer screening in women, can also predict cardiovascular disease. We developed mammography-based deep learning models for predicting coronary artery calcium (CAC) scores, an established predictor of coronary events. Methods and results We evaluated a subset of Korean adults who underwent image mammography and CAC computed tomography and randomly selected approximately 80% of the participants as the training dataset, used to develop a convolutional neural network (CNN) to predict detectable CAC. The sensitivity, specificity, area under the receiver operating characteristic curve (AUROC), and overall accuracy of the model's performance were evaluated. The training and validation datasets included 5235 and 1208 women, respectively [mean age, 52.6 (±10.2) years], including non-zero cases (46.8%). The CNN-based deep learning prediction model based on the Resnet18 model showed the best performance. The model was further improved using contrastive learning strategies based on positive and negative samples: sensitivity, 0.764 (95% CI, 0.667–0.830); specificity, 0.652 (95% CI, 0.614–0.710); AUROC, 0.761 (95% CI, 0.742–0.780); and accuracy, 70.8% (95% CI, 68.8–72.4). Moreover, including age and menopausal status in the model further improved its performance (AUROC, 0.776; 95% CI, 0.762–0.790). The Framingham risk score yielded an AUROC of 0.736 (95% CI, 0.712–0.761). Conclusion Mammography-based deep learning models showed promising results for predicting CAC, performing comparably to conventional risk models. This indicates mammography's potential for dual-risk assessment in breast cancer and cardiovascular disease. Further research is necessary to validate these findings in diverse populations, with a particular focus on representation from national breast screening programmes. [ABSTRACT FROM AUTHOR]

Geostatistical methods are powerful tools for understanding the spatial structure of the metallicity distribution of galaxies, and enable construction of accurate predictive models of the 2D metallicity distribution. However, so far these methods have only been applied to very high spatial resolution metallicity maps, leaving it uncertain if they will work on lower quality data. In this study, we apply geostatistical techniques to high-resolution spectroscopic maps of three local galaxies convolved to eight different spatial resolutions ranging from ∼40 pc to ∼1 kpc per pixel. We fit a geostatistical model to the data at all resolutions, and find that for metallicity maps where small-scale structure is visible by eye (with ≳10 resolution elements per R e), all parameters, including the metallicity correlation scale, can be recovered accurately. At all resolutions tested, we find that point metallicity predictions from such a geostatistical model outperform a circularly symmetric metallicity gradient model. We also explore dependence on the number of data points, and find that N ≳ 100 spatially resolved metallicity values are sufficient to train a geostatistical model that yields more accurate metallicity predictions than a radial gradient model. Finally, we investigate the potential detrimental effects of having spaxels smaller than an individual H  ii region by repeating our analysis with metallicities integrated over H  ii regions. We see that spaxel-based measurements have more noise, as expected, but the underlying spatial metallicity distribution can be recovered regardless of whether spaxels or integrated regions are used. [ABSTRACT FROM AUTHOR]

Motivation Retrosynthesis is a critical task in drug discovery, aimed at finding a viable pathway for synthesizing a given target molecule. Many existing approaches frame this task as a graph-generating problem. Specifically, these methods first identify the reaction center, and break a targeted molecule accordingly to generate the synthons. Reactants are generated by either adding atoms sequentially to synthon graphs or by directly adding appropriate leaving groups. However, both of these strategies have limitations. Adding atoms results in a long prediction sequence that increases the complexity of generation, while adding leaving groups only considers those in the training set, which leads to poor generalization. Results In this paper, we propose a novel end-to-end graph generation model for retrosynthesis prediction, which sequentially identifies the reaction center, generates the synthons, and adds motifs to the synthons to generate reactants. Given that chemically meaningful motifs fall between the size of atoms and leaving groups, our model achieves lower prediction complexity than adding atoms and demonstrates superior performance than adding leaving groups. We evaluate our proposed model on a benchmark dataset and show that it significantly outperforms previous state-of-the-art models. Furthermore, we conduct ablation studies to investigate the contribution of each component of our proposed model to the overall performance on benchmark datasets. Experiment results demonstrate the effectiveness of our model in predicting retrosynthesis pathways and suggest its potential as a valuable tool in drug discovery. Availability and implementation All code and data are available at https://github.com/szu-ljh2020/MARS. [ABSTRACT FROM AUTHOR]

Pharmacogenomics aims to provide personalized therapy to patients based on their genetic variability. However, accurate prediction of cancer drug response (CDR) is challenging due to genetic heterogeneity. Since clinical data are limited, most studies predicting drug response use preclinical data to train models. However, such models might not be generalizable to external clinical data due to differences between the preclinical and clinical datasets. In this study, a Precision Medicine Prediction using an Adversarial Network for Cancer Drug Response (PANCDR) model is proposed. PANCDR consists of two sub-models, an adversarial model and a CDR prediction model. The adversarial model reduces the gap between the preclinical and clinical datasets, while the CDR prediction model extracts features and predicts responses. PANCDR was trained using both preclinical data and unlabeled clinical data. Subsequently, it was tested on external clinical data, including The Cancer Genome Atlas and brain tumor patients. PANCDR outperformed other machine learning models in predicting external test data. Our results demonstrate the robustness of PANCDR and its potential in precision medicine by recommending patient-specific drug candidates. The PANCDR codes and data are available at https://github.com/DMCB-GIST/PANCDR. [ABSTRACT FROM AUTHOR]

Herbs applicability in disease treatment has been verified through experiences over thousands of years. The understanding of herb–disease associations (HDAs) is yet far from complete due to the complicated mechanism inherent in multi-target and multi-component (MTMC) botanical therapeutics. Most of the existing prediction models fail to incorporate the MTMC mechanism. To overcome this problem, we propose a novel dual-channel hypergraph convolutional network, namely HGHDA, for HDA prediction. Technically, HGHDA first adopts an autoencoder to project components and target protein onto a low-dimensional latent space so as to obtain their embeddings by preserving similarity characteristics in their original feature spaces. To model the high-order relations between herbs and their components, we design a channel in HGHDA to encode a hypergraph that describes the high-order patterns of herb-component relations via hypergraph convolution. The other channel in HGHDA is also established in the same way to model the high-order relations between diseases and target proteins. The embeddings of drugs and diseases are then aggregated through our dual-channel network to obtain the prediction results with a scoring function. To evaluate the performance of HGHDA, a series of extensive experiments have been conducted on two benchmark datasets, and the results demonstrate the superiority of HGHDA over the state-of-the-art algorithms proposed for HDA prediction. Besides, our case study on Chuan Xiong and Astragalus membranaceus is a strong indicator to verify the effectiveness of HGHDA, as seven and eight out of the top 10 diseases predicted by HGHDA for Chuan-Xiong and Astragalus-membranaceus, respectively, have been reported in literature. [ABSTRACT FROM AUTHOR]

Lysine lactylation (Kla) is a newly discovered posttranslational modification that is involved in important life activities, such as glycolysis-related cell function, macrophage polarization and nervous system regulation, and has received widespread attention due to the Warburg effect in tumor cells. In this work, we first design a natural language processing method to automatically extract the 3D structural features of Kla sites, avoiding potential biases caused by manually designed structural features. Then, we establish two Kla prediction frameworks, Attention-based feature fusion Kla model (ABFF-Kla) and EBFF-Kla, to integrate the sequence features and the structure features based on the attention layer and embedding layer, respectively. The results indicate that ABFF-Kla and Embedding-based feature fusion Kla model (EBFF-Kla), which fuse features from protein sequences and spatial structures, have better predictive performance than that of models that use only sequence features. Our work provides an approach for the automatic extraction of protein structural features, as well as a flexible framework for Kla prediction. The source code and the training data of the ABFF-Kla and the EBFF-Kla are publicly deposited at: https://github.com/ispotato/Lactylation_model. [ABSTRACT FROM AUTHOR]

Poor fit between models of sequence or trait evolution and empirical data is known to cause biases and lead to spurious conclusions about evolutionary patterns and processes. Bayesian posterior prediction is a flexible and intuitive approach for detecting such cases of poor fit. However, the expected behavior of posterior predictive tests has never been characterized for evolutionary models, which is critical for their proper interpretation. Here, we show that the expected distribution of posterior predictive P -values is generally not uniform, in contrast to frequentist P -values used for hypothesis testing, and extreme posterior predictive P -values often provide more evidence of poor fit than typically appreciated. Posterior prediction assesses model adequacy under highly favorable circumstances, because the model is fitted to the data, which leads to expected distributions that are often concentrated around intermediate values. Nonuniform expected distributions of P -values do not pose a problem for the application of these tests, however, and posterior predictive P -values can be interpreted as the posterior probability that the fitted model would predict a dataset with a test statistic value as extreme as the value calculated from the observed data. [ABSTRACT FROM AUTHOR]

Aims Bicuspid aortic valve (BAV) is a common congenital condition that is frequently associated with aortic stenosis (AS) and aortic regurgitation (AR), as well as aortic aneurysms, but specific outcome data are scarce. The present study sought to assess outcomes in a large cohort of consecutive patients with BAV. Methods and results A total of 581 consecutive patients (median age 29 years, 157 female) with BAV were included in the study and followed prospectively in a heart valve clinic follow-up programme. The overall survival rate after 10 years was 94.5%. During follow-up, 158 patients developed an indication for surgery. Event-free survival rates were 97%, 94%, 87%, and 73% at 1, 2, 5, and 10 years, respectively. In the multivariable analysis, event rates were independently predicted by AS [subdistribution hazard ratio (SHR) 2.3 per degree of severity], AR (SHR 1.5 per degree of severity), baseline aortic dilatation ≥ 40 mm (SHR 1.9), and age (SHR 1.3) (P < 0.001). Conclusion BAV disease is associated with a high rate of cardiac events, but state-of-the-art care results in good survival with low rates of infective endocarditis, aortic dissection, and sudden death. Incremental degrees of AS and regurgitation, the presence of aortic dilatation, and age are predictive of cardiac events. [ABSTRACT FROM AUTHOR]

Motivation A patient's disease phenotype can be driven and determined by specific groups of cells whose marker genes are either unknown or can only be detected at late-stage using conventional bulk assays such as RNA-Seq technology. Recent advances in single-cell RNA sequencing (scRNA-seq) enable gene expression profiling in cell-level resolution, and therefore have the potential to identify those cells driving the disease phenotype even while the number of these cells is small. However, most existing methods rely heavily on accurate cell type detection, and the number of available annotated samples is usually too small for training deep learning predictive models. Results Here, we propose the method ScRAT for phenotype prediction using scRNA-seq data. To train ScRAT with a limited number of samples of different phenotypes, such as coronavirus disease (COVID) and non-COVID, ScRAT first applies a mixup module to increase the number of training samples. A multi-head attention mechanism is employed to learn the most informative cells for each phenotype without relying on a given cell type annotation. Using three public COVID datasets, we show that ScRAT outperforms other phenotype prediction methods. The performance edge of ScRAT over its competitors increases as the number of training samples decreases, indicating the efficacy of our sample mixup. Critical cell types detected based on high-attention cells also support novel findings in the original papers and the recent literature. This suggests that ScRAT overcomes the challenge of missing marker genes and limited sample number with great potential revealing novel molecular mechanisms and/or therapies. Availability and implementation The code of our proposed method ScRAT is published at https://github.com/yuzhenmao/ScRAT. [ABSTRACT FROM AUTHOR]

Motivation Utilizing both purebred and crossbred data in animal genetics is widely recognized as an optimal strategy for enhancing the predictive accuracy of breeding values. Practically, the different genetic background among several purebred populations and their crossbred offspring populations limits the application of traditional prediction methods. Several studies endeavor to predict the crossbred performance via the partial relationship, which divides the data into distinct sub-populations based on the common genetic background, such as one single purebred population and its corresponding crossbred descendant. However, this strategy makes prediction inaccurate due to ignoring half of the parental information of crossbreed animals. Furthermore, dominance effects, although playing a significant role in crossbreeding systems, cannot be modeled under such a prediction model. Results To overcome this weakness, we developed a novel multi-breed single-step model using metafounders to assess ancestral relationships across diverse breeds under a unified framework. We proposed to use multi-breed dominance combined relationship matrices to model additive and dominance effects simultaneously. Our method provides a straightforward way to evaluate the heterosis of crossbreeds and the breeding values of purebred parents efficiently and accurately. We performed simulation and real data analyses to verify the potential of our proposed method. Our proposed model improved prediction accuracy under all scenarios considered compared to commonly used methods. Availability and implementation The software for implementing our method is available at https://github.com/CAU-TeamLiuJF/MAGE. [ABSTRACT FROM AUTHOR]

Toward the identification of genetic basis of complex traits, transcriptome-wide association study (TWAS) is successful in integrating transcriptome data. However, TWAS is only applicable for common variants, excluding rare variants in exome or whole-genome sequences. This is partly because of the inherent limitation of TWAS protocols that rely on predicting gene expressions. Our previous research has revealed the insight into TWAS: the 2 steps in TWAS, building and applying the expression prediction models, are essentially genetic feature selection and aggregations that do not have to involve predictions. Based on this insight disentangling TWAS, rare variants' inability of predicting expression traits is no longer an obstacle. Herein, we developed "rare variant TWAS," or rvTWAS, that first uses a Bayesian model to conduct expression-directed feature selection and then uses a kernel machine to carry out feature aggregation, forming a model leveraging expressions for association mapping including rare variants. We demonstrated the performance of rvTWAS by thorough simulations and real data analysis in 3 psychiatric disorders, namely schizophrenia, bipolar disorder, and autism spectrum disorder. We confirmed that rvTWAS outperforms existing TWAS protocols and revealed additional genes underlying psychiatric disorders. Particularly, we formed a hypothetical mechanism in which zinc finger genes impact all 3 disorders through transcriptional regulations. rvTWAS will open a door for sequence-based association mappings integrating gene expressions. [ABSTRACT FROM AUTHOR]

Error-correcting codes (ECCs) employed in the state-of-the-art DNA digital storage (DDS) systems suffer from a trade-off between error-correcting capability and the proportion of redundancy. To address this issue, in this study, we introduce soft-decision decoding approach into DDS by proposing a DNA-specific error prediction model and a series of novel strategies. We demonstrate the effectiveness of our approach through a proof-of-concept DDS system based on Reed-Solomon (RS) code, named as Derrick. Derrick shows significant improvement in error-correcting capability without involving additional redundancy in both in vitro and in silico experiments, using various sequencing technologies such as Illumina, PacBio and Oxford Nanopore Technology (ONT). Notably, in vitro experiments using ONT sequencing at a depth of 7× reveal that Derrick, compared with the traditional hard-decision decoding strategy, doubles the error-correcting capability of RS code, decreases the proportion of matrices with decoding-failure by 229-fold, and amplifies the potential maximum storage volume by impressive 32 388-fold. Also, Derrick surpasses 'state-of-the-art' DDS systems by comprehensively considering the information density and the minimum sequencing depth required for complete information recovery. Crucially, the soft-decision decoding strategy and key steps of Derrick are generalizable to other ECCs' decoding algorithms. [ABSTRACT FROM AUTHOR]

Background The E.U.'s lack of racially disaggregated data impedes the formulation of effective interventions, and crises such as Covid-19 may continue to impact minorities more severely. Our predictive model offers insight into the disparate ways in which Covid-19 has likely impacted E.U. minorities and allows for the inference of differences in Covid-19 infection and death rates between E.U. minority and non-minority populations. Methods Data covering Covid-19, social determinants of health and minority status were included from 1 March 2020 to 28 February 2021. A systematic comparison of US and E.U. states enabled the projection of Covid-19 infection and death rates for minorities and non-minorities in E.U. states. Results The model predicted Covid-19 infection rates with 95–100% accuracy for 23 out of 28 E.U. states. Projections for Covid-19 infection and mortality rates among E.U. minority groups illustrate parallel trends to US rates. Conclusions Disparities in Covid-19 infection and death rates by minority status likely exist in patterns similar to those observed in US data. Policy Implications : Collecting data by race/ethnicity in the E.U. would help document health disparities and craft more targeted health interventions and mitigation strategies. [ABSTRACT FROM AUTHOR]

Aims To evaluate the incremental value of positron emission tomography (PET) myocardial perfusion imaging (MPI) over coronary computed tomography angiography (CCTA) in predicting short- and long-term outcome using machine learning (ML) approaches. Methods and results A total of 2411 patients with clinically suspected coronary artery disease (CAD) underwent CCTA, out of whom 891 patients were admitted to downstream PET MPI for haemodynamic evaluation of obstructive coronary stenosis. Two sets of Extreme Gradient Boosting (XGBoost) ML models were trained, one with all the clinical and imaging variables (including PET) and the other with only clinical and CCTA-based variables. Difference in the performance of the two sets was analysed by means of area under the receiver operating characteristic curve (AUC). After the removal of incomplete data entries, 2284 patients remained for further analysis. During the 8-year follow-up, 210 adverse events occurred including 59 myocardial infarctions, 35 unstable angina pectoris, and 116 deaths. The PET MPI data improved the outcome prediction over CCTA during the first 4 years of the observation time and the highest AUC was at the observation time of Year 1 (0.82, 95% confidence interval 0.804–0.827). After that, there was no significant incremental prognostic value by PET MPI. Conclusion PET MPI variables improve the prediction of adverse events beyond CCTA imaging alone for the first 4 years of follow-up. This illustrates the complementary nature of anatomic and functional information in predicting the outcome of patients with suspected CAD. [ABSTRACT FROM AUTHOR]

Background Retinoblastoma is the most common intraocular malignant tumor occurring among children, with an incidence rate of 1/15 000. This study built a joinpoint regression model to assess the incidence trend of retinoblastoma from 2004 to 2015 and constructed a nomogram to predict the overall survival (OS) in children. Materials and Methods Patients less than 19 years diagnosed with retinoblastoma from 2004 to 2015 were selected from the SEER database. Joinpoint regression analysis (version 4.9.0.0) was performed to evaluate the trends in retinoblastoma incidence rates from 2004 to 2015. Cox Regression Analysis was applied to investigate prognostic risk factors that influence OS. Results Joinpoint regression revealed that retinoblastoma incidence exhibited no significant increase or decrease from 2004 to 2015. As per the multiple Cox regression, tumor size, laterality, and residence (rural-urban continuum code) were correlated with OS and were used to construct a nomogram. The nomogram exhibited a good C-index of 0.71 (95% CI, 0.63 to 0.79), and the calibration curve for survival probability demonstrated that the predictions corresponded well with actual observations. Conclusions and Relevance A prognostic nomogram integrating the risk factors for retinoblastoma was constructed to provide comparatively accurate individual survival predictions. If validated, this type of assessment could be used to guide therapy in patients with retinoblastoma. [ABSTRACT FROM AUTHOR]