On the relation of gene essentiality to intron structure: a computational and deep learning approach
LIFE SCIENCE ALLIANCE
2021; 4 (6)
Essential genes have been studied by copy number variants and deletions, both associated with introns. The premise of our work is that introns of essential genes have distinct characteristic properties. We provide support for this by training a deep learning model and demonstrating that introns alone can be used to classify essentiality. The model, limited to first introns, performs at an increased level, implicating first introns in essentiality. We identify unique properties of introns of essential genes, finding that their structure protects against deletion and intron-loss events, especially centered on the first intron. We show that GC density is increased in the first introns of essential genes, allowing for increased enhancer activity, protection against deletions, and improved splice site recognition. We find that first introns of essential genes are of remarkably smaller size than their nonessential counterparts, and to protect against common 3' end deletion events, essential genes carry an increased number of (smaller) introns. To demonstrate the importance of the seven features we identified, we train a feature-based model using only these features and achieve high performance.
View details for DOI 10.26508/lsa.202000951
View details for Web of Science ID 000654748200008
View details for PubMedID 33906938
View details for PubMedCentralID PMC8127325
Rib Fracture Frailty Index: A Risk-Stratification Tool for Geriatric Patients with Multiple Rib Fractures.
The journal of trauma and acute care surgery
Rib fractures are consequential injuries for geriatric patients (age ≥ 65 years). Although age and injury patterns drive many rib fracture management decisions, the impact of frailty-which baseline conditions affect rib fracture-specific outcomes-remains unclear for geriatric patients. We aimed to develop and validate the Rib Fracture Frailty (RFF) Index, a practical risk-stratification tool specific for geriatric patients with rib fractures. We hypothesized that a compact list of frailty markers can accurately risk stratify clinical outcomes after rib fractures.We queried nationwide US admission encounters of geriatric patients admitted with multiple rib fractures from 2016-2017. Partitioning-around-medoids clustering identified a development subcohort with previously-validated frailty characteristics. Ridge regression with penalty for multicollinearity aggregated baseline conditions most prevalent in this frail subcohort into RFF scores. Regression models with adjustment for injury severity, sex, and age assessed associations between frailty risk categories (low, medium, and high) and inpatient outcomes among validation cohorts (OR [95%CI]). We report results according to Transparent Reporting of Multivariable Prediction Model for Individual Prognosis guidelines.Development cohort (N = 55,540) cluster analysis delineated thirteen baseline conditions constituting the RFF Index. Among external validation cohort (N = 77,710), increasing frailty risk (low [reference group], moderate, high) was associated with stepwise worsening adjusted odds of mortality (1.5[1.2-1.7], 3.5 [3.0-4.0]), intubation (2.4[1.5-3.9], 4.7[3.1-7.5]), hospitalization ≥5 days (1.4[1.3-1.5], 1.8[1.7-2.0]), and disposition to home (0.6[0.5-0.6], 0.4[0.3-0.4]). Locally weighted scatterplot smoothing showed correlations between increasing RFF scores and worse outcomes.RFF Index is a practical frailty risk-stratification tool for geriatric patients with multiple rib fractures. The mobile app we developed may facilitate rapid implementation and further validation of RFF Index at the bedside.level III, prognostic study.
View details for DOI 10.1097/TA.0000000000003390
View details for PubMedID 34446653
Practical Computer Vision Application to Compute Total Body Surface Area Burn: Reappraising a Fundamental Burn Injury Formula in the Modern Era.
Critical burn management decisions rely on accurate percent total body surface area (%TBSA) burn estimation. Existing %TBSA burn estimation models (eg, Lund-Browder chart and rule of nines) were derived from a linear formula and a limited number of individuals a century ago and do not reflect the range of body habitus of the modern population.To develop a practical %TBSA burn estimation tool that accounts for exact burn injury pattern, sex, and body habitus.This population-based cohort study evaluated the efficacy of a computer vision algorithm application in processing an adult laser body scan data set. High-resolution surface anthropometry laser body scans of 3047 North American and European adults aged 18 to 65 years from the Civilian American and European Surface Anthropometry Resource data set (1998-2001) were included. Of these, 1517 participants (49.8%) were male. Race and ethnicity data were not available for analysis. Analyses were conducted in 2020.The contributory %TBSA for 18 body regions in each individual. Mobile application for real-time %TBSA burn computation based on sex, habitus, and exact burn injury pattern.Of the 3047 individuals aged 18 to 65 years for whom body scans were available, 1517 (49.8%) were male. Wide individual variability was found in the extent to which major body regions contributed to %TBSA, especially in the torso and legs. Anterior torso %TBSA increased with increasing body habitus (mean [SD], 15.1 [0.9] to 19.1 [2.0] for male individuals; 15.1 [0.8] to 18.0 [1.7] for female individuals). This increase was attributable to increase in abdomen %TBSA (mean [SD], 5.3 [0.7] to 8.7 [1.8]) among male individuals and increase in abdomen (mean [SD], 4.6 [0.6] to 6.8 [1.7]) and pelvis (mean [SD], 1.5 [0.2] to 2.9 [0.9]) %TBSAs among female individuals. For most body regions, Lund-Browder chart and rule of nines estimates fell outside the population's measured interquartile ranges. The mobile application tested in this study, Burn Area, facilitated accurate %TBSA burn computation based on exact burn injury pattern for 10 sex and body habitus-specific models.Computer vision algorithm application to a large laser body scan data set may provide a practical tool that facilitates accurate %TBSA burn computation in the modern era.
View details for DOI 10.1001/jamasurg.2021.5848
View details for PubMedID 34817552