Background: Early identification of pregnant women at risk for preterm birth (PTB), a major cause of infant mortality and morbidity, has a significant potential to improve prenatal care. However, we lack effective predictive models which can accurately forecast PTB and complement these predictions with appropriate interpretations for clinicians. In this work, we introduce a clinical prediction model (PredictPTB) which combines variables (medical codes) readily accessible through electronic health record (EHR) to accurately predict the risk of preterm birth at 1, 3, 6, and 9 months prior to delivery.
Methods: The architecture of PredictPTB employs recurrent neural networks (RNNs) to model the longitudinal patient's EHR visits and exploits a single code-level attention mechanism to improve the predictive performance, while providing temporal code-level and visit-level explanations for the prediction results. We compare the performance of different combinations of prediction time-points, data modalities, and data windows. We also present a case-study of our model's interpretability illustrating how clinicians can gain some transparency into the predictions.
Results: Leveraging a large cohort of 222,436 deliveries, comprising a total of 27,100 unique clinical concepts, our model was able to predict preterm birth with an ROC-AUC of 0.82, 0.79, 0.78, and PR-AUC of 0.40, 0.31, 0.24, at 1, 3, and 6 months prior to delivery, respectively. Results also confirm that observational data modalities (such as diagnoses) are more predictive for preterm birth than interventional data modalities (e.g., medications and procedures).
Conclusions: Our results demonstrate that PredictPTB can be utilized to achieve accurate and scalable predictions for preterm birth, complemented by explanations that directly highlight evidence in the patient's EHR timeline.
Background: Genomic studies increasingly integrate expression quantitative trait loci (eQTL) information into their analysis pipelines, but few tools exist for the visualization of colocalization between eQTL and GWAS results. Those tools that do exist are limited in their analysis options, and do not integrate eQTL and GWAS information into a single figure panel, making the visualization of colocalization difficult.
Results: To address this issue, we developed the intuitive and user-friendly R package eQTpLot. eQTpLot takes as input standard GWAS and cis-eQTL summary statistics, and optional pairwise LD information, to generate a series of plots visualizing colocalization, correlation, and enrichment between eQTL and GWAS signals for a given gene-trait pair. With eQTpLot, investigators can easily generate a series of customizable plots clearly illustrating, for a given gene-trait pair: 1) colocalization between GWAS and eQTL signals, 2) correlation between GWAS and eQTL p-values, 3) enrichment of eQTLs among trait-significant variants, 4) the LD landscape of the locus in question, and 5) the relationship between the direction of effect of eQTL signals and the direction of effect of colocalizing GWAS peaks. These clear and comprehensive plots provide a unique view of eQTL-GWAS colocalization, allowing for a more complete understanding of the interaction between gene expression and trait associations.
Conclusions: eQTpLot provides a unique, user-friendly, and intuitive means of visualizing eQTL and GWAS signal colocalization, incorporating novel features not found in other eQTL visualization software. We believe eQTpLot will prove a useful tool for investigators seeking a convenient and customizable visualization of eQTL and GWAS data colocalization.
Availability and implementation: the eQTpLot R package and tutorial are available at https://github.com/RitchieLab/eQTpLot.
Introduction: Twin studies indicate that a substantial fraction of ovarian cancers should be predictable from genetic testing. Genetic risk scores can stratify women into different classes of risk. Higher risk women can be treated or screened for ovarian cancer, which should reduce ovarian cancer death rates. However, current ovarian cancer genetic risk scores do not work that well. We developed a genetic risk score based on variations in the length of chromosomes.
Methods: We evaluated this genetic risk score using data collected by The Cancer Genome Atlas. We synthesized a dataset of 414 women who had ovarian serous carcinoma and 4225 women who had no form of ovarian cancer. We characterized each woman by 22 numbers, representing the length of each chromosome in their germ line DNA. We used a gradient boosting machine to build a classifier that can predict whether a woman had been diagnosed with ovarian cancer.
Results: The genetic risk score based on chromosomal-scale length variation could stratify women such that the highest 20% had a 160x risk (95% confidence interval 50x-450x) compared to the lowest 20%. The genetic risk score we developed had an area under the curve of the receiver operating characteristic curve of 0.88 (95% confidence interval 0.86-0.91).
Conclusion: A genetic risk score based on chromosomal-scale length variation of germ line DNA provides an effective means of predicting whether or not a woman will develop ovarian cancer.
Background: Accurate identification of acute ischemic stroke (AIS) patient cohorts is essential for a wide range of clinical investigations. Automated phenotyping methods that leverage electronic health records (EHRs) represent a fundamentally new approach cohort identification without current laborious and ungeneralizable generation of phenotyping algorithms. We systematically compared and evaluated the ability of machine learning algorithms and case-control combinations to phenotype acute ischemic stroke patients using data from an EHR.
Materials and methods: Using structured patient data from the EHR at a tertiary-care hospital system, we built and evaluated machine learning models to identify patients with AIS based on 75 different case-control and classifier combinations. We then estimated the prevalence of AIS patients across the EHR. Finally, we externally validated the ability of the models to detect AIS patients without AIS diagnosis codes using the UK Biobank.
Results: Across all models, we found that the mean AUROC for detecting AIS was 0.963 ± 0.0520 and average precision score 0.790 ± 0.196 with minimal feature processing. Classifiers trained with cases with AIS diagnosis codes and controls with no cerebrovascular disease codes had the best average F1 score (0.832 ± 0.0383). In the external validation, we found that the top probabilities from a model-predicted AIS cohort were significantly enriched for AIS patients without AIS diagnosis codes (60-150 fold over expected).
Conclusions: Our findings support machine learning algorithms as a generalizable way to accurately identify AIS patients without using process-intensive manual feature curation. When a set of AIS patients is unavailable, diagnosis codes may be used to train classifier models.
Background: Determining binding affinity in protein-protein interactions is important in the discovery and design of novel therapeutics and mutagenesis studies. Determination of binding affinity of proteins in the formation of protein complexes requires sophisticated, expensive and time-consuming experimentation which can be replaced with computational methods. Most computational prediction techniques require protein structures that limit their applicability to protein complexes with known structures. In this work, we explore sequence-based protein binding affinity prediction using machine learning.
Method: We have used protein sequence information instead of protein structures along with machine learning techniques to accurately predict the protein binding affinity.
Results: We present our findings that the true generalization performance of even the state-of-the-art sequence-only predictor is far from satisfactory and that the development of machine learning methods for binding affinity prediction with improved generalization performance is still an open problem. We have also proposed a sequence-based novel protein binding affinity predictor called ISLAND which gives better accuracy than existing methods over the same validation set as well as on external independent test dataset. A cloud-based webserver implementation of ISLAND and its python code are available at https://sites.google.com/view/wajidarshad/software .
Conclusion: This paper highlights the fact that the true generalization performance of even the state-of-the-art sequence-only predictor of binding affinity is far from satisfactory and that the development of effective and practical methods in this domain is still an open problem.
Background: COVID-19 has caused a global pandemic, and there is no wonder drug for epidemic control at present. However, many clinical practices have shown that traditional Chinese medicine has played an important role in treating the outbreak. Among them, ephedra-bitter almond is a common couplet medicine in anti-COVID-19 prescriptions. This study aims to conduct an exploration of key components and mechanisms of ephedra-bitter almond anti-COVID-19 based on network pharmacology.
Material and methods: We collected and screened potential active components of ephedra-bitter almond based on the TCMSP Database, and we predicted targets of the components. Meanwhile, we collected relevant targets of COVID-19 through the GeneCards and CTD databases. Then, the potential targets of ephedra-bitter almond against COVID-19 were screened out. The key components, targets, biological processes, and pathways of ephedra-bitter almond anti-COVID-19 were predicted by constructing the relationship network of herb-component-target (H-C-T), protein-protein interaction (PPI), and functional enrichment. Finally, the key components and targets were docked by AutoDock Vina to explore their binding mode.
Results: Ephedra-bitter almond played an overall regulatory role in anti-COVID-19 via the patterns of multi-component-target-pathway. In addition, some key components of ephedra-bitter almond, such as β-sitosterol, estrone, and stigmasterol, had high binding activity to 3CL and ACE2 by molecular docking simulation, which provided new molecular structures for new drug development of COVID-19.
Conclusion: Ephedra-bitter almonds were used to prevent and treat COVID-19 through directly inhibiting the virus, regulating immune responses, and promoting body repair. However, this work is a prospective study based on data mining, and the findings need to be interpreted with caution.
Data science has emerged as an important discipline in the era of big data and biological and biomedical data mining. As such, we have seen a rapid increase in the number of data science departments, research centers, and schools. We review here ten important leadership roles for a successful academic data science chair, director, or dean. These roles include the visionary, executive, cheerleader, manager, enforcer, subordinate, educator, entrepreneur, mentor, and communicator. Examples specific to leadership in data science are given for each role.