Category: Statistics

Bioinformatics. 2024 Jun 28;40(Supplement_1):i501-i510. doi: 10.1093/bioinformatics/btae251.

ABSTRACT

MOTIVATION: In many biomedical applications, we are confronted with paired groups of samples, such as treated versus control. The aim is to detect discriminating features, i.e. biomarkers, based on high-dimensional (omics-) data. This problem can be phrased more generally as a two-sample problem requiring statistical significance testing to establish differences, and interpretations to identify distinguishing features. The multivariate maximum mean discrepancy (MMD) test quantifies group-level differences, whereas statistically significantly associated features are usually found by univariate feature selection. Currently, few general-purpose methods simultaneously perform multivariate feature selection and two-sample testing.

RESULTS: We introduce a sparse, interpretable, and optimized MMD test (SpInOpt-MMD) that enables two-sample testing and feature selection in the same experiment. SpInOpt-MMD is a versatile method and we demonstrate its application to a variety of synthetic and real-world data types including images, gene expression measurements, and text data. SpInOpt-MMD is effective in identifying relevant features in small sample sizes and outperforms other feature selection methods such as SHapley Additive exPlanations and univariate association analysis in several experiments.

AVAILABILITY AND IMPLEMENTATION: The code and links to our public data are available at https://github.com/BorgwardtLab/spinoptmmd.

PMID:38940158 | DOI:10.1093/bioinformatics/btae251

Bioinformatics. 2024 Jun 28;40(Supplement_1):i110-i118. doi: 10.1093/bioinformatics/btae239.

ABSTRACT

Artificial intelligence (AI) is increasingly used in genomics research and practice, and generative AI has garnered significant recent attention. In clinical applications of generative AI, aspects of the underlying datasets can impact results, and confounders should be studied and mitigated. One example involves the facial expressions of people with genetic conditions. Stereotypically, Williams (WS) and Angelman (AS) syndromes are associated with a “happy” demeanor, including a smiling expression. Clinical geneticists may be more likely to identify these conditions in images of smiling individuals. To study the impact of facial expression, we analyzed publicly available facial images of approximately 3500 individuals with genetic conditions. Using a deep learning (DL) image classifier, we found that WS and AS images with non-smiling expressions had significantly lower prediction probabilities for the correct syndrome labels than those with smiling expressions. This was not seen for 22q11.2 deletion and Noonan syndromes, which are not associated with a smiling expression. To further explore the effect of facial expressions, we computationally altered the facial expressions for these images. We trained HyperStyle, a GAN-inversion technique compatible with StyleGAN2, to determine the vector representations of our images. Then, following the concept of InterfaceGAN, we edited these vectors to recreate the original images in a phenotypically accurate way but with a different facial expression. Through online surveys and an eye-tracking experiment, we examined how altered facial expressions affect the performance of human experts. We overall found that facial expression is associated with diagnostic accuracy variably in different genetic conditions.

PMID:38940144 | DOI:10.1093/bioinformatics/btae239

Bioinformatics. 2024 Jun 28;40(Supplement_1):i266-i276. doi: 10.1093/bioinformatics/btae230.

ABSTRACT

SUMMARY: Pretrained large language models (LLMs) have significantly improved code generation. As these models scale up, there is an increasing need for the output to handle more intricate tasks and to be appropriately specialized to particular domains. Here, we target bioinformatics due to the amount of domain knowledge, algorithms, and data operations this discipline requires. We present BioCoder, a benchmark developed to evaluate LLMs in generating bioinformatics-specific code. BioCoder spans much of the field, covering cross-file dependencies, class declarations, and global variables. It incorporates 1026 Python functions and 1243 Java methods extracted from GitHub, along with 253 examples from the Rosalind Project, all pertaining to bioinformatics. Using topic modeling, we show that the overall coverage of the included code is representative of the full spectrum of bioinformatics calculations. BioCoder incorporates a fuzz-testing framework for evaluation. We have applied it to evaluate various models including InCoder, CodeGen, CodeGen2, SantaCoder, StarCoder, StarCoder+, InstructCodeT5+, GPT-3.5, and GPT-4. Furthermore, we fine-tuned one model (StarCoder), demonstrating that our training dataset can enhance the performance on our testing benchmark (by >15% in terms of Pass@K under certain prompt configurations and always >3%). The results highlight two key aspects of successful models: (i) Successful models accommodate a long prompt (>2600 tokens) with full context, including functional dependencies. (ii) They contain domain-specific knowledge of bioinformatics, beyond just general coding capability. This is evident from the performance gain of GPT-3.5/4 compared to the smaller models on our benchmark (50% versus up to 25%).

AVAILABILITY AND IMPLEMENTATION: All datasets, benchmark, Docker images, and scripts required for testing are available at: https://github.com/gersteinlab/biocoder and https://biocoder-benchmark.github.io/.

PMID:38940140 | DOI:10.1093/bioinformatics/btae230

Bioinformatics. 2024 Jun 28;40(Supplement_1):i548-i557. doi: 10.1093/bioinformatics/btae242.

ABSTRACT

SUMMARY: Spatial omics technologies are increasingly leveraged to characterize how disease disrupts tissue organization and cellular niches. While multiple methods to analyze spatial variation within a sample have been published, statistical and computational approaches to compare cell spatial organization across samples or conditions are mostly lacking. We present GraphCompass, a comprehensive set of omics-adapted graph analysis methods to quantitatively evaluate and compare the spatial arrangement of cells in samples representing diverse biological conditions. GraphCompass builds upon the Squidpy spatial omics toolbox and encompasses various statistical approaches to perform cross-condition analyses at the level of individual cell types, niches, and samples. Additionally, GraphCompass provides custom visualization functions that enable effective communication of results. We demonstrate how GraphCompass can be used to address key biological questions, such as how cellular organization and tissue architecture differ across various disease states and which spatial patterns correlate with a given pathological condition. GraphCompass can be applied to various popular omics techniques, including, but not limited to, spatial proteomics (e.g. MIBI-TOF), spot-based transcriptomics (e.g. 10× Genomics Visium), and single-cell resolved transcriptomics (e.g. Stereo-seq). In this work, we showcase the capabilities of GraphCompass through its application to three different studies that may also serve as benchmark datasets for further method development. With its easy-to-use implementation, extensive documentation, and comprehensive tutorials, GraphCompass is accessible to biologists with varying levels of computational expertise. By facilitating comparative analyses of cell spatial organization, GraphCompass promises to be a valuable asset in advancing our understanding of tissue function in health and disease.

.

PMID:38940138 | DOI:10.1093/bioinformatics/btae242

Behav Ther. 2024 Jul;55(4):680-697. doi: 10.1016/j.beth.2024.01.010. Epub 2024 Feb 13.

ABSTRACT

Adolescents with attention-deficit/hyperactivity disorder (ADHD) experience significant academic, behavioral, and social skill difficulties including underachievement, risk for school dropout, poor peer relations, and emotion dysregulation. Although stimulant medication reduces ADHD symptoms, psychosocial and educational interventions are necessary to address functional impairments. We examined the nature and predictors of academic, behavioral, and social skills trajectories in response to multicomponent organizational and interpersonal skills training in 92 high school students with ADHD. Latent trajectory class analyses revealed positive treatment response ranging from 61.5% (report card grades) to 100% (inattention symptoms, organizational skills, social skills). Organizational skill and academic grade treatment response trajectories were predicted by assigned sex, pretreatment anxiety, and treatment dosage, while improvement in behavioral and social functioning was associated with better emotion regulation and family relations prior to treatment along with stronger working alliance with treatment coach at midtreatment. Multicomponent organizational and interpersonal skills training appears effective for most high school students with ADHD and the degree treatment-induced change is associated with multiple malleable factors can be leveraged to enhance intervention response.

PMID:38937043 | DOI:10.1016/j.beth.2024.01.010

Arch Med Res. 2024 Jun;55(4):103017. doi: 10.1016/j.arcmed.2024.103017.

ABSTRACT

This article has been retracted: please see Elsevier Policy on Article Withdrawal (https://www.elsevier.com/locate/withdrawalpolicy). This article has been retracted at the request of the Editorial Board of the Archives of Medical Research after receiving a complaint reporting that the article was based on an unreliable or non-existent statistical method. After analyzing the complaint and carefully reviewing the article, the Editorial Board contacted the corresponding author following due process and received no response. The Editorial Board no longer has confidence in the article and therefore decided to retract the article. Apologies are offered to readers of the journal that this was not detected during the review process.

PMID:38937005 | DOI:10.1016/j.arcmed.2024.103017

J Nucl Med. 2024 Jun 27:jnumed.124.267626. doi: 10.2967/jnumed.124.267626. Online ahead of print.

ABSTRACT

This study aimed to evaluate the prognostic value of ¹⁸F-FDG PET/CT qualitative assessment in terms of recurrence-free survival (RFS), colostomy-free survival (CFS), and overall survival (OS) after radiation therapy (RT) of squamous cell carcinoma of the anus (SCCA). Secondary objectives were to evaluate the prognostic value of baseline and posttherapeutic quantitative ¹⁸F-FDG PET/CT parameters in terms of RFS, CFS, and OS. Methods: We included all consecutive patients from the French multicentric cohort FFCD-ANABASE who had undergone ¹⁸F-FDG PET/CT at baseline and 4-6 mo after RT or chemoradiotherapy for a localized SCCA. Qualitative assessments separated patients with complete metabolic response (CMR) and non-CMR. Quantitative parameters were measured on baseline and posttreatment ¹⁸F-FDG PET/CT. RFS, CFS, and OS were analyzed using the Kaplan-Meier method. Associations among qualitative assessments, quantitative parameters, and RFS, CFS, and OS were analyzed using univariate and multivariate Cox regression. Results: Among 1,015 patients treated between January 2015 and April 2020, 388 patients (300 women and 88 men) from 36 centers had undergone ¹⁸F-FDG PET/CT at diagnosis and after treatment. The median age was 65 y (range, 32-90 y); 147 patients (37.9%) had an early-stage tumor and 241 patients (62.1%) had a locally advanced-stage tumor; 59 patients (15.2%) received RT, and 329 (84.8%) received chemoradiotherapy. The median follow-up was 35.5 mo (95% CI, 32.8-36.6 mo). Patients with CMR had better 3-y RFS, CFS, and OS, at 84.2% (95% CI, 77.8%-88.9%), 84.7% (95% CI, 77.2%-89.3%), and 88.6% (95% CI, 82.5%-92.7%), respectively, than did non-CMR patients, at 42.1% (95% CI, 33.4%-50.6%), 47.9% (95% CI, 38.1%-56.8%), and 63.5 (95% CI, 53.2%-72.1%), respectively (P < 0.0001). Quantitative parameters were available for 154 patients from 3 centers. The following parameters were statistically significantly associated with 3-y RFS: baseline SUV_max (primitive tumor [T]) (hazard ratio [HR], 1.05 [95% CI, 1.01-1.1; P = 0.018]), SUV_peak (T) (HR, 1.09 [95% CI, 1.02-1.15; P = 0.007]), MTV 41% (T) (HR, 1.02 [95% CI, 1-1.03; P = 0.023]), MTV 41% (lymph node [N]) (HR, 1.06 [95% CI, 1.03-1.1; P < 0.001]), MTV 41% (T + N) (HR, 1.02 [95% CI, 1-1.03; P = 0.005]), and posttreatment SUV_max (HR, 1.21 [95% CI, 1.09-1.34; P < 0.001]). Conclusion: Treatment response assessed by ¹⁸F-FDG PET/CT after RT for SCCA has a significant prognostic value.¹⁸F-FDG PET/CT could be useful for adapting follow-up, especially for patients with locally advanced-stage tumors. Quantitative parameters could permit identification of patients with a worse prognosis but should be evaluated in further trials.

PMID:38936973 | DOI:10.2967/jnumed.124.267626

BMJ Support Palliat Care. 2024 Jun 27:spcare-2023-004657. doi: 10.1136/spcare-2023-004657. Online ahead of print.

ABSTRACT

OBJECTIVES: Lower rates of goals of care (GOC) conversations have been observed in non-white hospitalised patients, which may contribute to racial disparities in end-of-life care. We aimed to assess how a targeted initiative to increase GOC documentation rates is associated with GOC documentation by race.

METHODS: We retrospectively assessed GOC documentation during a targeted GOC initiative for adult patients with an artificial intelligence predicted elevated risk of mortality. Patients were admitted to an urban academic medical centre in Pittsburgh, Pennsylvania between July 2021 and 31 December 2022.

RESULTS: The 3643 studied patients had a median age of 72 (SD 13.0) and were predominantly white (87%) with 42% admitted to an intensive care unit and 15% dying during admission. GOC documentation was completed for 28% (n=1019/3643). By race, GOC was documented for 30% black (n=105/351), 28% white (n=883/3161) and 24% other (n=31/131) patients (p=0.3933). There was no statistical difference in the rate of documented GOC among races over time (p=0.5142).

CONCLUSIONS: A targeted initiative to increase documented GOC conversations for hospitalised patients with an elevated risk of mortality is associated with similar documentation rates across racial groups. Further research is needed to assess whether this initiative may promote racial equity in GOC documentation in other settings.

PMID:38936969 | DOI:10.1136/spcare-2023-004657

BMJ. 2024 Jun 27;385:q1436. doi: 10.1136/bmj.q1436.

NO ABSTRACT

PMID:38936955 | DOI:10.1136/bmj.q1436

In Vivo. 2024 Jul-Aug;38(4):1829-1833. doi: 10.21873/invivo.13635.

ABSTRACT

BACKGROUND/AIM: Vildagliptin is one of the dipeptidyl peptidase-4 (DPP-4) inhibitors that have been shown to improve hyperglycemia in clinical trials among patients with type 2 diabetes. However, few studies have examined the efficacy of vildagliptin in patients with diabetic kidney disease (DKD).

PATIENTS AND METHODS: Eight patients with DKD received oral vildagliptin 50-100 mg/day. The duration of diabetes was 6.7±5.9 years and observation period was 23.6±9.8 months. Changes in fasting blood glucose, and hemoglobin A1c (HbA1c), estimated glomerular filtration rate (eGFR), and urine protein-to-creatinine ratio (UPCR) were studied before and after the administration of vildagliptin.

RESULTS: Vildagliptin treatment significantly decreased fasting blood glucose and HbA1c, compared to baseline (132±56 mg/dl, p=0.036, 6.0±0.3, p=0.041, respectively). UPCR tended to be decreased, albeit without statistical significance. However, eGFR was decreased after the administration of vildagliptin. No significant adverse effects were observed in all patients during the study.

CONCLUSION: Although the sample size was limited and the observation period was brief, vildagliptin was found to be an effective and reasonably well-tolerated treatment for patients with DKD.

PMID:38936943 | DOI:10.21873/invivo.13635