Investigating DNA-, RNA-, and protein-based features as a means to discriminate pathogenic synonymous variants.

Synonymous single-nucleotide variants (SNVs), although they do not alter the encoded protein sequences, have been implicated in many genetic diseases. Experimental studies indicate that synonymous SNVs can lead to changes in the secondary and tertiary structures of DNA and RNA, thereby affecting translational efficiency, cotranslational protein folding as well as the binding of DNA-/RNA-binding proteins. However, the importance of these various features in disease phenotypes is not clearly understood. Here, we have built a support vector machine (SVM) model (termed DDIG-SN) as a means to discriminate disease-causing synonymous variants. The model was trained and evaluated on nearly 900 disease-causing variants. The method achieves robust performance with the area under the receiver operating characteristic curve of 0.84 and 0.85 for protein-stratified 10-fold cross-validation and independent testing, respectively. We were able to show that the disease-causing effects in the immediate proximity to exon-intron junctions (1-3 bp) are driven by the loss of splicing motif strength, whereas the gain of splicing motif strength is the primary cause in regions further away from the splice site (4-69 bp). The method is available as a part of the DDIG server at http://sparks-lab.org/ddig.

Monitoring the environment and human sentiment on the Great Barrier Reef: Assessing the potential of collective sensing.

With the growth of smartphone usage the number of social media posts has significantly increased and represents potentially valuable information for management, including of natural resources and the environment. Already, evidence of using 'human sensor' in crises management suggests that collective knowledge could be used to complement traditional monitoring. This research uses Twitter data posted from the Great Barrier Reef region, Australia, to assess whether the extent and type of data could be used to Great Barrier Reef organisations as part of their monitoring program. The analysis reveals that large amounts of tweets, covering the geographic area of interest, are available and that the pool of information providers is greatly enhanced by the large number of tourists to this region. A keyword and sentiment analysis demonstrates the usefulness of the Twitter data, but also highlights that the actual number of Reef-related tweets is comparatively small and lacks specificity. Suggestions for further steps towards the development of an integrative data platform that incorporates social media are provided.

DDIG-in: detecting disease-causing genetic variations due to frameshifting indels and nonsense mutations employing sequence and structural properties at nucleotide and protein levels.

MOTIVATION: Frameshifting (FS) indels and nonsense (NS) variants disrupt the protein-coding sequence downstream of the mutation site by changing the reading frame or introducing a premature termination codon, respectively. Despite such drastic changes to the protein sequence, FS indels and NS variants have been discovered in healthy individuals. How to discriminate disease-causing from neutral FS indels and NS variants is an understudied problem. RESULTS: We have built a machine learning method called DDIG-in (FS) based on real human genetic variations from the Human Gene Mutation Database (inherited disease-causing) and the 1000 Genomes Project (GP) (putatively neutral). The method incorporates both sequence and predicted structural features and yields a robust performance by 10-fold cross-validation and independent tests on both FS indels and NS variants. We showed that human-derived NS variants and FS indels derived from animal orthologs can be effectively employed for independent testing of our method trained on human-derived FS indels. DDIG-in (FS) achieves a Matthews correlation coefficient (MCC) of 0.59, a sensitivity of 86%, and a specificity of 72% for FS indels. Application of DDIG-in (FS) to NS variants yields essentially the same performance (MCC of 0.43) as a method that was specifically trained for NS variants. DDIG-in (FS) was shown to make a significant improvement over existing techniques.

Feature-based multiple models improve classification of mutation-induced stability changes.

BACKGROUND: Reliable prediction of stability changes in protein variants is an important aspect of computational protein design. A number of machine learning methods that allow a classification of stability changes knowing only the sequence of the protein emerged. However, their performance on amino acid substitutions of previously unseen non-homologous proteins is rather limited. Moreover, the performance varies for different types of mutations based on the secondary structure or accessible surface area of the mutation site. RESULTS: We proposed feature-based multiple models with each model designed for a specific type of mutations. The new method is composed of five models trained for mutations in exposed, buried, helical, sheet, and coil residues. The classification of a mutation as stabilising or destabilising is made as a consensus of two models, one selected based on the predicted accessible surface area and the other based on the predicted secondary structure of the mutation site. We refer to our new method as Evolutionary, Amino acid, and Structural Encodings with Multiple Models (EASE-MM). Cross-validation results show that EASE-MM provides a notable improvement to our previous work reaching a Matthews correlation coefficient of 0.44. EASE-MM was able to correctly classify 73% and 75% of stabilising and destabilising protein variants, respectively. Using an independent test set of 238 mutations, we confirmed our results in a comparison with related work. CONCLUSIONS: EASE-MM not only outperformed other related methods but achieved more balanced results for different types of mutations based on the accessible surface area, secondary structure, or magnitude of stability changes. This can be attributed to using multiple models with the most relevant features selected for the given type of mutations. Therefore, our results support the presumption that different interactions govern stability changes in the exposed and buried residues or in residues with a different secondary structure.

Towards sequence-based prediction of mutation-induced stability changes in unseen non-homologous proteins.

BACKGROUND: Reliable prediction of stability changes induced by a single amino acid substitution is an important aspect of computational protein design. Several machine learning methods capable of predicting stability changes from the protein sequence alone have been introduced. Prediction performance of these methods is evaluated on mutations unseen during training. Nevertheless, different mutations of the same protein, and even the same residue, as encountered during training are commonly used for evaluation. We argue that a faithful evaluation can be achieved only when a method is tested on previously unseen proteins with low sequence similarity to the training set. RESULTS: We provided experimental evidence of the limitations of the evaluation commonly used for assessing the prediction performance. Furthermore, we demonstrated that the prediction of stability changes in previously unseen non-homologous proteins is a challenging task for currently available methods. To improve the prediction performance of our previously proposed method, we identified features which led to over-fitting and further extended the model with new features. The new method employs Evolutionary And Structural Encodings with Amino Acid parameters (EASE-AA). Evaluated with an independent test set of more than 600 mutations, EASE-AA yielded a Matthews correlation coefficient of 0.36 and was able to classify correctly 66% of the stabilising and 74% of the destabilising mutations. For real-value prediction, EASE-AA achieved the correlation of predicted and experimentally measured stability changes of 0.51. CONCLUSIONS: Commonly adopted evaluation with mutations in the same protein, and even the same residue, randomly divided between the training and test sets lead to an overestimation of prediction performance. Therefore, stability changes prediction methods should be evaluated only on mutations in previously unseen non-homologous proteins. Under such an evaluation, EASE-AA predicts stability changes more reliably than currently available methods.

Sequence-only evolutionary and predicted structural features for the prediction of stability changes in protein mutants.

BACKGROUND: Even a single amino acid substitution in a protein sequence may result in significant changes in protein stability, structure, and therefore in protein function as well. In the post-genomic era, computational methods for predicting stability changes from only the sequence of a protein are of importance. While evolutionary relationships of protein mutations can be extracted from large protein databases holding millions of protein sequences, relevant evolutionary features for the prediction of stability changes have not been proposed. Also, the use of predicted structural features in situations when a protein structure is not available has not been explored. RESULTS: We proposed a number of evolutionary and predicted structural features for the prediction of stability changes and analysed which of them capture the determinants of protein stability the best. We trained and evaluated our machine learning method on a non-redundant data set of experimentally measured stability changes. When only the direction of the stability change was predicted, we found that the best performance improvement can be achieved by the combination of the evolutionary features mutation likelihood and SIFT score in conjunction with the predicted structural feature secondary structure. The same two evolutionary features in the combination with the predicted structural feature accessible surface area achieved the lowest error when the prediction of actual values of stability changes was assessed. Compared to similar studies, our method achieved improvements in prediction performance. CONCLUSION: Although the strongest feature for the prediction of stability changes appears to be the vector of amino acid identities in the sequential neighbourhood of the mutation, the most relevant combination of evolutionary and predicted structural features further improves prediction performance. Even the predicted structural features, which did not perform well on their own, turn out to be beneficial when appropriately combined with evolutionary features. We conclude that a high prediction accuracy can be achieved knowing only the sequence of a protein when the right combination of both structural and evolutionary features is used.

Mitochondrial targeting of vitamin E succinate enhances its pro-apoptotic and anti-cancer activity via mitochondrial complex II.

Mitochondrial complex II (CII) has been recently identified as a novel target for anti-cancer drugs. Mitochondrially targeted vitamin E succinate (MitoVES) is modified so that it is preferentially localized to mitochondria, greatly enhancing its pro-apoptotic and anti-cancer activity. Using genetically manipulated cells, MitoVES caused apoptosis and generation of reactive oxygen species (ROS) in CII-proficient malignant cells but not their CII-dysfunctional counterparts. MitoVES inhibited the succinate dehydrogenase (SDH) activity of CII with IC(50) of 80 µM, whereas the electron transfer from CII to CIII was inhibited with IC(50) of 1.5 µM. The agent had no effect either on the enzymatic activity of CI or on electron transfer from CI to CIII. Over 24 h, MitoVES caused stabilization of the oxygen-dependent destruction domain of HIF1α fused to GFP, indicating promotion of the state of pseudohypoxia. Molecular modeling predicted the succinyl group anchored into the proximal CII ubiquinone (UbQ)-binding site and successively reduced interaction energies for serially shorter phytyl chain homologs of MitoVES correlated with their lower effects on apoptosis induction, ROS generation, and SDH activity. Mutation of the UbQ-binding Ser(68) within the proximal site of the CII SDHC subunit (S68A or S68L) suppressed both ROS generation and apoptosis induction by MitoVES. In vivo studies indicated that MitoVES also acts by causing pseudohypoxia in the context of tumor suppression. We propose that mitochondrial targeting of VES with an 11-carbon chain localizes the agent into an ideal position across the interface of the mitochondrial inner membrane and matrix, optimizing its biological effects as an anti-cancer drug.

Mapping progress in intravascular catheter quality surveillance: An Australian case study of electronic medical record data linkage.

Background and significance: Intravascular (IV) catheters are the most invasive medical device in healthcare. Localized priority-setting related to IV catheter quality surveillance is a key objective of recent healthcare reform in Australia. We sought to determine the plausibility of using electronic health record (EHR) data for catheter surveillance by mapping currently available data across state-wide platforms. This work has identified barriers and facilitators to a state-wide EHR surveillance initiative. Materials and methods: Data variables were generated and mapped from routinely used EHR sources across Queensland, Australia through a systematic search of gray literature and expert consultation with clinical information specialists. EHR systems were eligible for inclusion if they collected data related to IV catheter insertion, care, or outcomes of hospitalized patients. Generated variables were mapped against international recommendations for IV catheter surveillance, with data linkage and data export capacity narratively summarized. Results: We identified five EHR systems, namely, iEMR, MetaVision ICU®, Multiprac, RiskMan, and the Nephrology Registry. Systems were used across jurisdictions and hospital wards. Data linkage was not evident across systems. Extraction processes for catheter data were not standardized, lacking clear and reliable extraction techniques. In combination, EHR systems collected 43/50 international variables recommended for catheter surveillance, however, individual systems collected a median of 24/50 (IQR 22, 30) variables. We did not identify integrated clinical analytic systems (incorporating machine learning) to support clinical decision making or for risk stratification (e.g., catheter-related infection). Conclusion: Current data linkage across EHR systems limits the development of an IV catheter quality surveillance system to provide timely data related to catheter complications and harm. To facilitate reliable and timely surveillance of catheter outcomes using clinical informatics, substantial work is needed to overcome existing barriers and transform health surveillance.

Towards an implicit treatment of periodically-repeated medical data.

Temporal information plays a crucial role in medicine, so that in Medical Informatics there is an increasing awareness that suitable database approaches are needed to store and support it. Specifically, a great amount of clinical data (e.g., therapeutic data) are periodically repeated. Although an explicit treatment is possible in most cases, it causes severe storage and disk I/O problems. In this paper, we propose an innovative approach to cope with periodic medical data in an implicit way. We propose a new data model, representing periodic data in a compact (implicit) way, which is a consistent extension of TSQL2 consensus approach. Then, we identify some important types of temporal queries, and present query answering algorithms to answer them. We also sketch a temporal relational algebra for our approach. Finally, we show experimentally that our approach outperforms current explicit approaches.

Efficacy of deep learning methods for predicting under-five mortality in 34 low-income and middle-income countries.

OBJECTIVES: To explore the efficacy of machine learning (ML) techniques in predicting under-five mortality (U5M) in low-income and middle-income countries (LMICs) and to identify significant predictors of U5M. DESIGN: This is a cross-sectional, proof-of-concept study. SETTINGS AND PARTICIPANTS: We analysed data from the Demographic and Health Survey. The data were drawn from 34 LMICs, comprising a total of n=1 520 018 children drawn from 956 995 unique households. PRIMARY AND SECONDARY OUTCOME MEASURES: The primary outcome measure was U5M; secondary outcome was comparing the efficacy of deep learning algorithms: deep neural network (DNN); convolution neural network (CNN); hybrid CNN-DNN with logistic regression (LR) for the prediction of child's survival. RESULTS: We found that duration of breast feeding, number of antenatal visits, household wealth index, postnatal care and the level of maternal education are some of the most important predictors of U5M. We found that deep learning techniques are superior to LR for the classification of child survival: LR sensitivity=0.47, specificity=0.53; DNN sensitivity=0.69, specificity=0.83; CNN sensitivity=0.68, specificity=0.83; CNN-DNN sensitivity=0.71, specificity=0.83. CONCLUSION: Our findings provide an understanding of determinants of U5M in LMICs. It also demonstrates that deep learning models are more efficacious than traditional analytical approach.

Systematic review and meta-analysis of the association between dimensions of inequality and a selection of indicators of Reproductive, Maternal, Newborn and Child Health (RMNCH).

BACKGROUND: Globally, progress in Maternal and Child Health (MCH) has been inconsistent, with several evidence showing both between and within country disparities in several RMNCH outcome measures. In this study, we aim to meta-analyse existing literature on association between three major equity stratifiers and a selection of RMNCH indicators. METHODS: We searched PubMed, Embase, Scopus databases and grey literatures from the WHO, UNICEF and World Bank publications. Using the PRISMA guidelines, we identified and reviewed studies from low and middle-income countries, that explored the effects of inequalities on RMNCH, with focus on studies that utilised data from a nationally representative survey. The review protocol was registered at the PROSPERO international prospective register of systematic reviews. RESULTS: A total of 28 studies were included in the meta-analysis. Results revealed the existence of marked inequality based on income levels, education and place of residence. The most significant level of disparity was with regards to unmet need for contraception and antenatal coverage. For both respective indicators, those with secondary or higher education were 6 times more likely to have better coverage, than those with lesser level of education; (odds ratio (OR) = 6.25 (95% confidence interval (CI) = 1.68-23.23; I2 = 98%, P = 0.006) and (OR = 6.17 (95% CI = 3.03-12.56; I2 = 97%, P < 0.00001) respectively. In contrast, the lowest inequality was in the completion of 3 doses of diphtheria, pertussis and tetanus vaccines (DPT3), those with primary or no education, were equally as likely as those with secondary or higher education to have received DPT3; (OR = 1.21, 95% CI = 0.34-4.27; I2 = 96%, P = 0.77). CONCLUSIONS: In developing countries, maternal and child health coverage remains highly inequitable and assess to maternal and child health services are governed by factors such as income, level of education, and place of residence.

Representing and querying now-relative relational medical data.

Temporal information plays a crucial role in medicine. Patients' clinical records are intrinsically temporal. Thus, in Medical Informatics there is an increasing need to store, support and query temporal data (particularly in relational databases), in order, for instance, to supplement decision-support systems. In this paper, we show that current approaches to relational data have remarkable limitations in the treatment of "now-relative" data (i.e., data holding true at the current time). This can severely compromise their applicability in general, and specifically in the medical context, where "now-relative" data are essential to assess the current status of the patients. We propose a theoretically grounded and application-independent relational approach to cope with now-relative data (which can be paired, e.g., with different decision support systems) overcoming such limitations. We propose a new temporal relational representation, which is the first relational model coping with the temporal indeterminacy intrinsic in now-relative data. We also propose new temporal algebraic operators to query them, supporting the distinction between possible and necessary time, and Allen's temporal relations between data. We exemplify the impact of our approach, and study the theoretical and computational properties of the new representation and algebra.

EASE-MM: Sequence-Based Prediction of Mutation-Induced Stability Changes with Feature-Based Multiple Models.

Protein engineering and characterisation of non-synonymous single nucleotide variants (SNVs) require accurate prediction of protein stability changes (ΔΔGu) induced by single amino acid substitutions. Here, we have developed a new prediction method called Evolutionary, Amino acid, and Structural Encodings with Multiple Models (EASE-MM), which comprises five specialised support vector machine (SVM) models and makes the final prediction from a consensus of two models selected based on the predicted secondary structure and accessible surface area of the mutated residue. The new method is applicable to single-domain monomeric proteins and can predict ΔΔGu with a protein sequence and mutation as the only inputs. EASE-MM yielded a Pearson correlation coefficient of 0.53-0.59 in 10-fold cross-validation and independent testing and was able to outperform other sequence-based methods. When compared to structure-based energy functions, EASE-MM achieved a comparable or better performance. The application to a large dataset of human germline non-synonymous SNVs showed that the disease-causing variants tend to be associated with larger magnitudes of ΔΔGu predicted with EASE-MM. The EASE-MM web-server is available at http://sparks-lab.org/server/ease.

An implicit approach to deal with periodically repeated medical data.

CONTEXT: Temporal information plays a crucial role in medicine, so that in medical informatics there is an increasing awareness that suitable database approaches are needed to store and support it. Specifically, a great amount of clinical data (e.g., therapeutic data) are periodically repeated. Although an explicit treatment is possible in most cases, it causes severe storage and disk I/O problems. OBJECTIVE: In this paper, we propose an innovative approach to cope with periodic relational medical data in an implicit way. METHODS: We propose a new data model, representing periodic data in a compact (implicit) way, which is a consistent extension of TSQL2 consensus approach. Then, we identify some important types of temporal queries, and present query answering algorithms to answer them. Finally, we also run experiments to evaluate our approach. RESULTS: The experiments show that our approach outperforms current explicit approaches, especially as regard disk I/O. CONCLUSION: We have provided an implicit approach to periodic data with is a consistent extension of TSQL2 (and which is thus grant interoperable with it), and we have experimentally proven that it outperforms current explicit approaches.

Coping efficiently with now-relative medical data.

In Medical Informatics, there is an increasing awareness that temporal information plays a crucial role, so that suitable database approaches are needed to store and support it. Specifically, most clinical data are intrinsically temporal, and a relevant part of them are now-relative (i.e., they are valid at the current time). Even if previous studies indicate that the treatment of now-relative data has a crucial impact on efficiency, current approaches have several limitations. In this paper we propose a novel approach, which is based on a new representation of now, and on query transformations. We also experimentally demonstrate that our approach outperforms its best competitors in the literature to the extent of a factor of more than ten, both in number of disk accesses and of CPU usage.