OutSingle: a novel method of detecting and injecting outliers in RNA-Seq count data using the optimal hard threshold for singular values.

MOTIVATION: Finding outliers in RNA-sequencing (RNA-Seq) gene expression (GE) can help in identifying genes that are aberrant and cause Mendelian disorders. Recently developed models for this task rely on modeling RNA-Seq GE data using the negative binomial distribution (NBD). However, some of those models either rely on procedures for inferring NBD's parameters in a nonbiased way that are computationally demanding and thus make confounder control challenging, while others rely on less computationally demanding but biased procedures and convoluted confounder control approaches that hinder interpretability. RESULTS: In this article, we present OutSingle (Outlier detection using Singular Value Decomposition), an almost instantaneous way of detecting outliers in RNA-Seq GE data. It uses a simple log-normal approach for count modeling. For confounder control, it uses the recently discovered optimal hard threshold (OHT) method for noise detection, which itself is based on singular value decomposition (SVD). Due to its SVD/OHT utilization, OutSingle's model is straightforward to understand and interpret. We then show that our novel method, when used on RNA-Seq GE data with real biological outliers masked by confounders, outcompetes the previous state-of-the-art model based on an ad hoc denoising autoencoder. Additionally, OutSingle can be used to inject artificial outliers masked by confounders, which is difficult to achieve with previous approaches. We describe a way of using OutSingle for outlier injection and proceed to show how OutSingle outperforms its competition on 16 out of 18 datasets that were generated from three real datasets using OutSingle's injection procedure with different outlier types and magnitudes. Our methods are applicable to other types of similar problems involving finding outliers in matrices under the presence of confounders. AVAILABILITY AND IMPLEMENTATION: The code for OutSingle is available at https://github.com/esalkovic/outsingle.

Computational prediction and interpretation of both general and specific types of promoters in Escherichia coli by exploiting a stacked ensemble-learning framework.

Promoters are short consensus sequences of DNA, which are responsible for transcription activation or the repression of all genes. There are many types of promoters in bacteria with important roles in initiating gene transcription. Therefore, solving promoter-identification problems has important implications for improving the understanding of their functions. To this end, computational methods targeting promoter classification have been established; however, their performance remains unsatisfactory. In this study, we present a novel stacked-ensemble approach (termed SELECTOR) for identifying both promoters and their respective classification. SELECTOR combined the composition of k-spaced nucleic acid pairs, parallel correlation pseudo-dinucleotide composition, position-specific trinucleotide propensity based on single-strand, and DNA strand features and using five popular tree-based ensemble learning algorithms to build a stacked model. Both 5-fold cross-validation tests using benchmark datasets and independent tests using the newly collected independent test dataset showed that SELECTOR outperformed state-of-the-art methods in both general and specific types of promoter prediction in Escherichia coli. Furthermore, this novel framework provides essential interpretations that aid understanding of model success by leveraging the powerful Shapley Additive exPlanation algorithm, thereby highlighting the most important features relevant for predicting both general and specific types of promoters and overcoming the limitations of existing 'Black-box' approaches that are unable to reveal causal relationships from large amounts of initially encoded features.

Comparison and assessment of family- and population-based genotype imputation methods in large pedigrees.

Genotype imputation is widely used in genome-wide association studies to boost variant density, allowing increased power in association testing. Many studies currently include pedigree data due to increasing interest in rare variants coupled with the availability of appropriate analysis tools. The performance of population-based (subjects are unrelated) imputation methods is well established. However, the performance of family- and population-based imputation methods on family data has been subject to much less scrutiny. Here, we extensively compare several family- and population-based imputation methods on family data of large pedigrees with both European and African ancestry. Our comparison includes many widely used family- and population-based tools and another method, Ped_Pop, which combines family- and population-based imputation results. We also compare four subject selection strategies for full sequencing to serve as the reference panel for imputation: GIGI-Pick, ExomePicks, PRIMUS, and random selection. Moreover, we compare two imputation accuracy metrics: the Imputation Quality Score and Pearson's correlation R 2 for predicting power of association analysis using imputation results. Our results show that (1) GIGI outperforms Merlin; (2) family-based imputation outperforms population-based imputation for rare variants but not for common ones; (3) combining family- and population-based imputation outperforms all imputation approaches for all minor allele frequencies; (4) GIGI-Pick gives the best selection strategy based on the R 2 criterion; and (5) R 2 is the best measure of imputation accuracy. Our study is the first to extensively evaluate the imputation performance of many available family- and population-based tools on the same family data and provides guidelines for future studies.

Comprehensive review and assessment of computational methods for predicting RNA post-transcriptional modification sites from RNA sequences.

RNA post-transcriptional modifications play a crucial role in a myriad of biological processes and cellular functions. To date, more than 160 RNA modifications have been discovered; therefore, accurate identification of RNA-modification sites is fundamental for a better understanding of RNA-mediated biological functions and mechanisms. However, due to limitations in experimental methods, systematic identification of different types of RNA-modification sites remains a major challenge. Recently, more than 20 computational methods have been developed to identify RNA-modification sites in tandem with high-throughput experimental methods, with most of these capable of predicting only single types of RNA-modification sites. These methods show high diversity in their dataset size, data quality, core algorithms, features extracted and feature selection techniques and evaluation strategies. Therefore, there is an urgent need to revisit these methods and summarize their methodologies, in order to improve and further develop computational techniques to identify and characterize RNA-modification sites from the large amounts of sequence data. With this goal in mind, first, we provide a comprehensive survey on a large collection of 27 state-of-the-art approaches for predicting N1-methyladenosine and N6-methyladenosine sites. We cover a variety of important aspects that are crucial for the development of successful predictors, including the dataset quality, operating algorithms, sequence and genomic features, feature selection, model performance evaluation and software utility. In addition, we also provide our thoughts on potential strategies to improve the model performance. Second, we propose a computational approach called DeepPromise based on deep learning techniques for simultaneous prediction of N1-methyladenosine and N6-methyladenosine. To extract the sequence context surrounding the modification sites, three feature encodings, including enhanced nucleic acid composition, one-hot encoding, and RNA embedding, were used as the input to seven consecutive layers of convolutional neural networks (CNNs), respectively. Moreover, DeepPromise further combined the prediction score of the CNN-based models and achieved around 43% higher area under receiver-operating curve (AUROC) for m1A site prediction and 2-6% higher AUROC for m6A site prediction, respectively, when compared with several existing state-of-the-art approaches on the independent test. In-depth analyses of characteristic sequence motifs identified from the convolution-layer filters indicated that nucleotide presentation at proximal positions surrounding the modification sites contributed most to the classification, whereas those at distal positions also affected classification but to different extents. To maximize user convenience, a web server was developed as an implementation of DeepPromise and made publicly available at http://DeepPromise.erc.monash.edu/, with the server accepting both RNA sequences and genomic sequences to allow prediction of two types of putative RNA-modification sites.

BCrystal: an interpretable sequence-based protein crystallization predictor.

MOTIVATION: X-ray crystallography has facilitated the majority of protein structures determined to date. Sequence-based predictors that can accurately estimate protein crystallization propensities would be highly beneficial to overcome the high expenditure, large attrition rate, and to reduce the trial-and-error settings required for crystallization. RESULTS: In this study, we present a novel model, BCrystal, which uses an optimized gradient boosting machine (XGBoost) on sequence, structural and physio-chemical features extracted from the proteins of interest. BCrystal also provides explanations, highlighting the most important features for the predicted crystallization propensity of an individual protein using the SHAP algorithm. On three independent test sets, BCrystal outperforms state-of-the-art sequence-based methods by more than 12.5% in accuracy, 18% in recall and 0.253 in Matthew's correlation coefficient, with an average accuracy of 93.7%, recall of 96.63% and Matthew's correlation coefficient of 0.868. For relative solvent accessibility of exposed residues, we observed higher values to associate positively with protein crystallizability and the number of disordered regions, fraction of coils and tripeptide stretches that contain multiple histidines associate negatively with crystallizability. The higher accuracy of BCrystal enables it to accurately screen for sequence variants with enhanced crystallizability. AVAILABILITY AND IMPLEMENTATION: Our BCrystal webserver is at https://machinelearning-protein.qcri.org/ and source code is available at https://github.com/raghvendra5688/BCrystal. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Prediction of protein group function by iterative classification on functional relevance network.

MOTIVATION: Biological experiments including proteomics and transcriptomics approaches often reveal sets of proteins that are most likely to be involved in a disease/disorder. To understand the functional nature of a set of proteins, it is important to capture the function of the proteins as a group, even in cases where function of individual proteins is not known. In this work, we propose a model that takes groups of proteins found to work together in a certain biological context, integrates them into functional relevance networks, and subsequently employs an iterative inference on graphical models to identify group functions of the proteins, which are then extended to predict function of individual proteins. RESULTS: The proposed algorithm, iterative group function prediction (iGFP), depicts proteins as a graph that represents functional relevance of proteins considering their known functional, proteomics and transcriptional features. Proteins in the graph will be clustered into groups by their mutual functional relevance, which is iteratively updated using a probabilistic graphical model, the conditional random field. iGFP showed robust accuracy even when substantial amount of GO annotations were missing. The perspective of 'group' function annotation opens up novel approaches for understanding functional nature of proteins in biological systems.Availability and implementation: http://kiharalab.org/iGFP/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

DeepCrystal: a deep learning framework for sequence-based protein crystallization prediction.

MOTIVATION: Protein structure determination has primarily been performed using X-ray crystallography. To overcome the expensive cost, high attrition rate and series of trial-and-error settings, many in-silico methods have been developed to predict crystallization propensities of proteins based on their sequences. However, the majority of these methods build their predictors by extracting features from protein sequences, which is computationally expensive and can explode the feature space. We propose DeepCrystal, a deep learning framework for sequence-based protein crystallization prediction. It uses deep learning to identify proteins which can produce diffraction-quality crystals without the need to manually engineer additional biochemical and structural features from sequence. Our model is based on convolutional neural networks, which can exploit frequently occurring k-mers and sets of k-mers from the protein sequences to distinguish proteins that will result in diffraction-quality crystals from those that will not. RESULTS: Our model surpasses previous sequence-based protein crystallization predictors in terms of recall, F-score, accuracy and Matthew's correlation coefficient (MCC) on three independent test sets. DeepCrystal achieves an average improvement of 1.4, 12.1% in recall, when compared to its closest competitors, Crysalis II and Crysf, respectively. In addition, DeepCrystal attains an average improvement of 2.1, 6.0% for F-score, 1.9, 3.9% for accuracy and 3.8, 7.0% for MCC w.r.t. Crysalis II and Crysf on independent test sets. AVAILABILITY AND IMPLEMENTATION: The standalone source code and models are available at https://github.com/elbasir/DeepCrystal and a web-server is also available at https://deeplearning-protein.qcri.org. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

KinVis: a visualization tool to detect cryptic relatedness in genetic datasets.

MOTIVATION: It is important to characterize individual relatedness in terms of familial relationships and underlying population structure in genome-wide association studies for correct downstream analysis. The characterization of individual relatedness becomes vital if the cohort is to be used as reference panel in other studies for association tests and for identifying ethnic diversities. In this paper, we propose a kinship visualization tool to detect cryptic relatedness between subjects. We utilize multi-dimensional scaling, bar charts, heat maps and node-link visualizations to enable analysis of relatedness information. AVAILABILITY AND IMPLEMENTATION: Available online as well as can be downloaded at http://shiny-vis.qcri.org/public/kinvis/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

RGBM: regularized gradient boosting machines for identification of the transcriptional regulators of discrete glioma subtypes.

We propose a generic framework for gene regulatory network (GRN) inference approached as a feature selection problem. GRNs obtained using Machine Learning techniques are often dense, whereas real GRNs are rather sparse. We use a Tikonov regularization inspired optimal L-curve criterion that utilizes the edge weight distribution for a given target gene to determine the optimal set of TFs associated with it. Our proposed framework allows to incorporate a mechanistic active biding network based on cis-regulatory motif analysis. We evaluate our regularization framework in conjunction with two non-linear ML techniques, namely gradient boosting machines (GBM) and random-forests (GENIE), resulting in a regularized feature selection based method specifically called RGBM and RGENIE respectively. RGBM has been used to identify the main transcription factors that are causally involved as master regulators of the gene expression signature activated in the FGFR3-TACC3-positive glioblastoma. Here, we illustrate that RGBM identifies the main regulators of the molecular subtypes of brain tumors. Our analysis reveals the identity and corresponding biological activities of the master regulators characterizing the difference between G-CIMP-high and G-CIMP-low subtypes and between PA-like and LGm6-GBM, thus providing a clue to the yet undetermined nature of the transcriptional events among these subtypes.

DeepSol: a deep learning framework for sequence-based protein solubility prediction.

Motivation: Protein solubility plays a vital role in pharmaceutical research and production yield. For a given protein, the extent of its solubility can represent the quality of its function, and is ultimately defined by its sequence. Thus, it is imperative to develop novel, highly accurate in silico sequence-based protein solubility predictors. In this work we propose, DeepSol, a novel Deep Learning-based protein solubility predictor. The backbone of our framework is a convolutional neural network that exploits k-mer structure and additional sequence and structural features extracted from the protein sequence. Results: DeepSol outperformed all known sequence-based state-of-the-art solubility prediction methods and attained an accuracy of 0.77 and Matthew's correlation coefficient of 0.55. The superior prediction accuracy of DeepSol allows to screen for sequences with enhanced production capacity and can more reliably predict solubility of novel proteins. Availability and implementation: DeepSol's best performing models and results are publicly deposited at https://doi.org/10.5281/zenodo.1162886 (Khurana and Mall, 2018). Supplementary information: Supplementary data are available at Bioinformatics online.

Correction: Exploring new approaches towards the formability of mixed-ion perovskites by DFT and machine learning.

Correction for 'Exploring new approaches towards the formability of mixed-ion perovskites by DFT and machine learning' by Heesoo Park et al., Phys. Chem. Chem. Phys., 2019, DOI: 10.1039/c8cp06528d.

Exploring new approaches towards the formability of mixed-ion perovskites by DFT and machine learning.

Recent years have witnessed a growing effort in engineering and tuning the properties of hybrid halide perovskites as light absorbers. These have led to the successful enhancement of their stability, a feature that is often counterbalanced by a reduction of their power-conversion efficiency. In order to provide a systematic analysis of the structure-property relationships of this class of compounds we have performed density functional theory calculations exploring fully inorganic ABC3 chalcogenide (I-V-VI3), halide (I-II-VII3) and hybrid perovskites. Special attention has been given to structures featuring three-dimensional BC6 octahedral networks because of their efficient carrier transport properties. In particular we have carefully analyzed the role of BC6 octahedral deformations, rotations and tilts in the thermodynamic stability and optical properties of the compounds. By using machine learning algorithms we have estimated the relations between the octahedral deformation and the bandgap, and established a similarity map among all the calculated compounds.

Learn-and-Match Molecular Cations for Perovskites.

Forecasting the structural stability of hybrid organic/inorganic compounds, where polyatomic molecules replace atoms, is a challenging task; the composition space is vast, and the reference structure for the organic molecules is ambiguously defined. In this work, we use a range of machine-learning algorithms, constructed from state-of-the-art density functional theory data, to conduct a systematic analysis on the likelihood of a given cation to be housed in the perovskite structure. In particular, we consider both ABC3 chalcogenide (I-V-VI3) and halide (I-II-VII3) perovskites. We find that the effective atomic radius and the number of lone pairs residing on the A-site cation are sufficient features to describe the perovskite phase stability. Thus, the presented machine-learning approach provides an efficient way to map the phase stability of the vast class of compounds, including situations where a cation mixture replaces a single A-site cation. This work demonstrates that advanced electronic structure theory combined with machine-learning analysis can provide an efficient strategy superior to the conventional trial-and-error approach in materials design.

Correction to: Harnessing Qatar Biobank to understand type 2 diabetes and obesity in adult Qataris from the First Qatar Biobank Project.

Following publication of the original article [1], the authors reported that one of the authors' names was processed incorrectly. In this Correction the incorrect and correct author name are shown. The original publication of this article has been corrected.

Harnessing Qatar Biobank to understand type 2 diabetes and obesity in adult Qataris from the First Qatar Biobank Project.

BACKGROUND: Human tissues are invaluable resources for researchers worldwide. Biobanks are repositories of such human tissues and can have a strategic importance for genetic research, clinical care, and future discoveries and treatments. One of the aims of Qatar Biobank is to improve the understanding and treatment of common diseases afflicting Qatari population such as obesity and diabetes. METHODS: In this study we apply a panorama of state-of-the-art statistical methods and machine learning algorithms to investigate associations and risk factors for diabetes and obesity on a sample of 1000 Qatari population. RESULTS: Regarding diabetes, we identified pronounced associations and risk factors in Qatari population including magnesium, chloride, c-peptide of insulin, insulin, and uric acid. Similarly, for obesity, significant associations and risk factors include insulin, c-peptide of insulin, albumin, and uric acid. Moreover, our study has revealed interactions of hypomagnesemia with HDL-C, triglycerides, and free thyroxine. CONCLUSIONS: Our study strongly confirms known associations and risk factors associated with diabetes and obesity in Qatari population as previously found in other population studies in different parts of the world. Moreover, interactions of hypomagnesemia with other associations and risk factors merit further investigations.

COUSCOus: improved protein contact prediction using an empirical Bayes covariance estimator.

BACKGROUND: The post-genomic era with its wealth of sequences gave rise to a broad range of protein residue-residue contact detecting methods. Although various coevolution methods such as PSICOV, DCA and plmDCA provide correct contact predictions, they do not completely overlap. Hence, new approaches and improvements of existing methods are needed to motivate further development and progress in the field. We present a new contact detecting method, COUSCOus, by combining the best shrinkage approach, the empirical Bayes covariance estimator and GLasso. RESULTS: Using the original PSICOV benchmark dataset, COUSCOus achieves mean accuracies of 0.74, 0.62 and 0.55 for the top L/10 predicted long, medium and short range contacts, respectively. In addition, COUSCOus attains mean areas under the precision-recall curves of 0.25, 0.29 and 0.30 for long, medium and short contacts and outperforms PSICOV. We also observed that COUSCOus outperforms PSICOV w.r.t. Matthew's correlation coefficient criterion on full list of residue contacts. Furthermore, COUSCOus achieves on average 10% more gain in prediction accuracy compared to PSICOV on an independent test set composed of CASP11 protein targets. Finally, we showed that when using a simple random forest meta-classifier, by combining contact detecting techniques and sequence derived features, PSICOV predictions should be replaced by the more accurate COUSCOus predictions. CONCLUSION: We conclude that the consideration of superior covariance shrinkage approaches will boost several research fields that apply the GLasso procedure, amongst the presented one of residue-residue contact prediction as well as fields such as gene network reconstruction.

Systems biology analysis reveals NFAT5 as a novel biomarker and master regulator of inflammatory breast cancer.

BACKGROUND: Inflammatory breast cancer (IBC) is the most rare and aggressive variant of breast cancer (BC); however, only a limited number of specific gene signatures with low generalization abilities are available and few reliable biomarkers are helpful to improve IBC classification into a molecularly distinct phenotype. We applied a network-based strategy to gain insight into master regulators (MRs) linked to IBC pathogenesis. METHODS: In-silico modeling and Algorithm for the Reconstruction of Accurate Cellular Networks (ARACNe) on IBC/non-IBC (nIBC) gene expression data (n = 197) was employed to identify novel master regulators connected to the IBC phenotype. Pathway enrichment analysis was used to characterize predicted targets of candidate genes. The expression pattern of the most significant MRs was then evaluated by immunohistochemistry (IHC) in two independent cohorts of IBCs (n = 39) and nIBCs (n = 82) and normal breast tissues (n = 15) spotted on tissue microarrays. The staining pattern of non-neoplastic mammary epithelial cells was used as a normal control. RESULTS: Using in-silico modeling of network-based strategy, we identified three top enriched MRs (NFAT5, CTNNB1 or ß-catenin, and MGA) strongly linked to the IBC phenotype. By IHC assays, we found that IBC patients displayed a higher number of NFAT5-positive cases than nIBC (69.2% vs. 19.5%; p-value = 2.79 10(-7)). Accordingly, the majority of NFAT5-positive IBC samples revealed an aberrant nuclear expression in comparison with nIBC samples (70% vs. 12.5%; p-value = 0.000797). NFAT5 nuclear accumulation occurs regardless of WNT/ß-catenin activated signaling in a substantial portion of IBCs, suggesting that NFAT5 pathway activation may have a relevant role in IBC pathogenesis. Accordingly, cytoplasmic NFAT5 and membranous ß-catenin expression were preferentially linked to nIBC, accounting for the better prognosis of this phenotype. CONCLUSIONS: We provide evidence that NFAT-signaling pathway activation could help to identify aggressive forms of BC and potentially be a guide to assignment of phenotype-specific therapeutic agents. The NFAT5 transcription factor might be developed into routine clinical practice as a putative biomarker of IBC phenotype.

AI-driven drug repurposing and binding pose meta dynamics identifies novel targets for monkeypox virus.

Monkeypox virus (MPXV) was confirmed in May 2022 and designated a global health emergency by WHO in July 2022. MPX virions are big, enclosed, brick-shaped, and contain a linear, double-stranded DNA genome as well as enzymes. MPXV particles bind to the host cell membrane via a variety of viral-host protein interactions. As a result, the wrapped structure is a potential therapeutic target. DeepRepurpose, an artificial intelligence-based compound-viral proteins interaction framework, was used via a transfer learning setting to prioritize a set of FDA approved and investigational drugs which can potentially inhibit MPXV viral proteins. To filter and narrow down the lead compounds from curated collections of pharmaceutical compounds, we used a rigorous computational framework that included homology modeling, molecular docking, dynamic simulations, binding free energy calculations, and binding pose metadynamics. We identified Elvitegravir as a potential inhibitor of MPXV virus using our comprehensive pipeline.

The triglyceride glucose-waist-to-height ratio outperforms obesity and other triglyceride-related parameters in detecting prediabetes in normal-weight Qatari adults: A cross-sectional study.

Introduction: The triglyceride-glucose (TyG)-driven indices, incorporating obesity indices, have been proposed as reliable markers of insulin resistance and related comorbidities such as diabetes. This study evaluated the effectiveness of these indices in detecting prediabetes in normal-weight individuals from a Middle Eastern population. Methods: Using the data of 5,996 adult Qatari participants from the Qatar Biobank cohort, we employed adjusted logistic regression to assess the ability of various obesity and triglyceride-related indices to detect prediabetes in normal-weight (18.5 ≤ BMI <25 kg/m2) adults (≥18 years). Results: Of the normal-weight adults, 13.62% had prediabetes. TyG-waist-to-height ratio (TyG-WHTR) was significantly associated with prediabetes among normal-weight men [OR per 1-SD 2.68; 95% CI (1.67-4.32)] and women [OR per 1-SD 2.82; 95% CI (1.61-4.94)]. Compared with other indices, TyG-WHTR had the highest area under the curve (AUC) value for prediabetes in men [AUC: 0.76, 95% CI (0.70-0.81)] and women [AUC: 0.73, 95% CI (0.66-0.80)], and performed significantly higher than other indices (p < 0.05) in detecting prediabetes in men. Tyg-WHTR shared similar diagnostic values as fasting plasma glucose (FPG). Discussion: Our findings suggest that the TyG-WHTR index could be a better indicator of prediabetes for general clinical usage in normal weight Qatari adult men than other obesity and TyG-related indices. TyG-WHTR can help identify a person's risk for developing prediabetes in both men and women when combined with FPG results.

Multi-omics and machine learning reveal context-specific gene regulatory activities of PML::RARA in acute promyelocytic leukemia.

The PML::RARA fusion protein is the hallmark driver of Acute Promyelocytic Leukemia (APL) and disrupts retinoic acid signaling, leading to wide-scale gene expression changes and uncontrolled proliferation of myeloid precursor cells. While known to be recruited to binding sites across the genome, its impact on gene regulation and expression is under-explored. Using integrated multi-omics datasets, we characterize the influence of PML::RARA binding on gene expression and regulation in an inducible PML::RARA cell line model and APL patient ex vivo samples. We find that genes whose regulatory elements recruit PML::RARA are not uniformly transcriptionally repressed, as commonly suggested, but also may be upregulated or remain unchanged. We develop a computational machine learning implementation called Regulatory Element Behavior Extraction Learning to deconvolute the complex, local transcription factor binding site environment at PML::RARA bound positions to reveal distinct signatures that modulate how PML::RARA directs the transcriptional response.