Search

Background: Modeling causality through graphs, referred to as causal graph learning, offers an appropriate description of the dynamics of causality. The majority of current machine learning models in clinical decision support systems only predict associations between variables, whereas causal graph learning models causality dynamics through graphs. However, building personalized causal graphs for each individual is challenging due to the limited amount of data available for each patient., Method: In this study, we present a new algorithmic framework using meta-learning for learning personalized causal graphs in biomedicine. Our framework extracts common patterns from multiple patient graphs and applies this information to develop individualized graphs. In multi-task causal graph learning, the proposed optimized initial guess of shared commonality enables the rapid adoption of knowledge to new tasks for efficient causal graph learning., Results: Experiments on one real-world biomedical causal graph learning benchmark data and four synthetic benchmarks show that our algorithm outperformed the baseline methods. Our algorithm can better understand the underlying patterns in the data, leading to more accurate predictions of the causal graph. Specifically, we reduce the structural hamming distance by 50-75%, indicating an improvement in graph prediction accuracy. Additionally, the false discovery rate is decreased by 20-30%, demonstrating that our algorithm made fewer incorrect predictions compared to the baseline algorithms., Conclusion: To the best of our knowledge, this is the first study to demonstrate the effectiveness of meta-learning in personalized causal graph learning and cause inference modeling for biomedicine. In addition, the proposed algorithm can also be generalized to transnational research areas where integrated analysis is necessary for various distributions of datasets, including different clinical institutions., (© 2024. The Author(s).)

Prediction of survival for cancer patients is an open area of research. However, many of these studies focus on datasets with a large number of patients. We present a novel method that is specifically designed to address the challenge of data scarcity, which is often the case for cancer datasets. Our method is able to use unlabeled data to improve classification by adopting a semi-supervised training approach to learn an ensemble classifier. The results of applying our method to three cancer datasets show the promise of semi-supervised learning for prediction of cancer survival.

Automated processing of digital histopathology slides has the potential to streamline patient care and provide new tools for cancer classification and grading. Before automatic analysis is possible, quality control procedures are applied to ensure that each image can be read consistently. One important quality control step is color normalization of the slide image, which adjusts for color variances (batch-effects) caused by differences in stain preparation and image acquisition equipment. Color batch-effects affect color-based features and reduce the performance of supervised color segmentation algorithms on images acquired separately. To identify an optimal normalization technique for histopathological color segmentation applications, five color normalization algorithms were compared in this study using 204 images from four image batches. Among the normalization methods, two global color normalization methods normalized colors from all stain simultaneously and three stain color normalization methods normalized colors from individual stains extracted using color deconvolution. Stain color normalization methods performed significantly better than global color normalization methods in 11 of 12 cross-batch experiments (p<;0.05). Specifically, the stain color normalization method using k-means clustering was found to be the best choice because of high stain segmentation accuracy and low computational complexity.

We have developed omniBiomarker, a web-based application that uses knowledge from the NCI Cancer Gene Index to guide the selection of biologically relevant algorithms for identifying biomarkers. Biomarker identification from high-throughput genomic expression data is difficult because of data properties (i.e., small-sample size compared to large-feature size) as well as the large number of available feature selection algorithms. Thus, it is unclear which algorithm should be used for a particular dataset. These factors lead to instability in biomarker identification and affect the reproducibility of results. We introduce a method for computing the biological relevance of feature selection algorithms using an externally validated knowledge base of manually curated cancer biomarkers. Results suggest that knowledge-driven biomarker identification can improve microarray-based clinical prediction performance. omniBiomarker can be accessed at http://omnibiomarker.bme.gatech.edu/.

Background: Automatic cancer diagnostic systems based on histological image classification are important for improving therapeutic decisions. Previous studies propose textural and morphological features for such systems. These features capture patterns in histological images that are useful for both cancer grading and subtyping. However, because many of these features lack a clear biological interpretation, pathologists may be reluctant to adopt these features for clinical diagnosis., Methods: We examine the utility of biologically interpretable shape-based features for classification of histological renal tumor images. Using Fourier shape descriptors, we extract shape-based features that capture the distribution of stain-enhanced cellular and tissue structures in each image and evaluate these features using a multi-class prediction model. We compare the predictive performance of the shape-based diagnostic model to that of traditional models, i.e., using textural, morphological and topological features., Results: The shape-based model, with an average accuracy of 77%, outperforms or complements traditional models. We identify the most informative shapes for each renal tumor subtype from the top-selected features. Results suggest that these shapes are not only accurate diagnostic features, but also correlate with known biological characteristics of renal tumors., Conclusions: Shape-based analysis of histological renal tumor images accurately classifies disease subtypes and reveals biologically insightful discriminatory features. This method for shape-based analysis can be extended to other histological datasets to aid pathologists in diagnostic and therapeutic decisions.

Background: Population inference is an important problem in genetics used to remove population stratification in genome-wide association studies and to detect migration patterns or shared ancestry. An individual's genotype can be modeled as a probabilistic function of ancestral population memberships, Q, and the allele frequencies in those populations, P. The parameters, P and Q, of this binomial likelihood model can be inferred using slow sampling methods such as Markov Chain Monte Carlo methods or faster gradient based approaches such as sequential quadratic programming. This paper proposes a least-squares simplification of the binomial likelihood model motivated by a Euclidean interpretation of the genotype feature space. This results in a faster algorithm that easily incorporates the degree of admixture within the sample of individuals and improves estimates without requiring trial-and-error tuning., Results: We show that the expected value of the least-squares solution across all possible genotype datasets is equal to the true solution when part of the problem has been solved, and that the variance of the solution approaches zero as its size increases. The Least-squares algorithm performs nearly as well as Admixture for these theoretical scenarios. We compare least-squares, Admixture, and FRAPPE for a variety of problem sizes and difficulties. For particularly hard problems with a large number of populations, small number of samples, or greater degree of admixture, least-squares performs better than the other methods. On simulated mixtures of real population allele frequencies from the HapMap project, Admixture estimates sparsely mixed individuals better than Least-squares. The least-squares approach, however, performs within 1.5% of the Admixture error. On individual genotypes from the HapMap project, Admixture and least-squares perform qualitatively similarly and within 1.2% of each other. Significantly, the least-squares approach nearly always converges 1.5- to 6-times faster., Conclusions: The computational advantage of the least-squares approach along with its good estimation performance warrants further research, especially for very large datasets. As problem sizes increase, the difference in estimation performance between all algorithms decreases. In addition, when prior information is known, the least-squares approach easily incorporates the expected degree of admixture to improve the estimate.

Background: Selecting an appropriate classifier for a particular biological application poses a difficult problem for researchers and practitioners alike. In particular, choosing a classifier depends heavily on the features selected. For high-throughput biomedical datasets, feature selection is often a preprocessing step that gives an unfair advantage to the classifiers built with the same modeling assumptions. In this paper, we seek classifiers that are suitable to a particular problem independent of feature selection. We propose a novel measure, called "win percentage", for assessing the suitability of machine classifiers to a particular problem. We define win percentage as the probability a classifier will perform better than its peers on a finite random sample of feature sets, giving each classifier equal opportunity to find suitable features., Results: First, we illustrate the difficulty in evaluating classifiers after feature selection. We show that several classifiers can each perform statistically significantly better than their peers given the right feature set among the top 0.001% of all feature sets. We illustrate the utility of win percentage using synthetic data, and evaluate six classifiers in analyzing eight microarray datasets representing three diseases: breast cancer, multiple myeloma, and neuroblastoma. After initially using all Gaussian gene-pairs, we show that precise estimates of win percentage (within 1%) can be achieved using a smaller random sample of all feature pairs. We show that for these data no single classifier can be considered the best without knowing the feature set. Instead, win percentage captures the non-zero probability that each classifier will outperform its peers based on an empirical estimate of performance., Conclusions: Fundamentally, we illustrate that the selection of the most suitable classifier (i.e., one that is more likely to perform better than its peers) not only depends on the dataset and application but also on the thoroughness of feature selection. In particular, win percentage provides a single measurement that could assist users in eliminating or selecting classifiers for their particular application.

Combining multiple microarray datasets increases sample size and leads to improved reproducibility in identification of informative genes and subsequent clinical prediction. Although microarrays have increased the rate of genomic data collection, sample size is still a major issue when identifying informative genetic biomarkers. Because of this, feature selection methods often suffer from false discoveries, resulting in poorly performing predictive models. We develop a simple meta-analysis-based feature selection method that captures the knowledge in each individual dataset and combines the results using a simple rank average. In a comprehensive study that measures robustness in terms of clinical application (i.e., breast, renal, and pancreatic cancer), microarray platform heterogeneity, and classifier (i.e., logistic regression, diagonal LDA, and linear SVM), we compare the rank average meta-analysis method to five other meta-analysis methods. Results indicate that rank average meta-analysis consistently performs well compared to five other meta-analysis methods.

Histopathological images acquired from different experimental set-ups often suffer from batch-effects due to color variations and scale variations. In this paper, we develop a novel scale normalization model for histopathological images based on nuclear area distributions. Results indicate that the normalization model closely fits empirical values for two renal tumor datasets. We study the effect of scale normalization on classification of renal tumor images. Scale normalization improves classification performance in most cases. However, performance decreases in a few cases. In order to understand this, we propose two methods to filter extracted image features that are sensitive to image scaling and features that are uncorrelated with scaling factor. Feature filtering improves the classification performance of cases that were initially negatively affected by scale normalization.

Microtubule (MT) dynamics quantification includes modeling of elongation, rapid shortening, and pauses. It indicates the effect of the cancer treatment drug paclitaxel because the drug causes MTs to bundle, which will in turn inhibit successful mitosis of cancerous cells. Thus, automatic MT dynamics analysis has been researched intensely because it allows for faster evaluation of potential cancer treatments and better understanding of drug effects on a cell. However, most current literatures still use manual initialization. In this work, we propose an automatic initialization algorithm that selects isolated and active tips for tracking. We use a Gaussian match filter to enhance the MT structures, and a novel technique called Pixel Nucleus Analysis (PNA) for isolated MT tip detection. To find dynamic tips, we applied a masked FFT in the temporal domain followed by K-means clustering. To evaluate the selected tips, we used a low level tip linking algorithm, and show the results of applying the algorithm to a model image and five MCF-7 breast cancer cell line images captured using fluorescent confocal microscopy. Finally, we compare tip selection criteria with existing automatic selection algorithms. We conclude that the proposed analysis is an effective technique based on three criteria which include outer region selection, separation, and MT dynamics.

The task of analyzing tissue biopsies performed by a pathologist is challenging and time consuming. It suffers from intra- and inter-user variability. Computer assisted diagnosis (CAD) helps to reduce such variations and speed up the diagnostic process. In this paper, we propose an automatic computer assisted diagnostic system for renal cell carcinoma subtype classification using scale invariant features. We capture the morphological distinctness of various subtypes and we have used them to classify a heterogeneous data set of renal cell carcinoma biopsy images. Our technique does not require color segmentation and minimizes human intervention. We circumvent user subjectivity using automated analysis and cater for intra-class heterogeneities using multiple class templates. We achieve a classification accuracy of 83% using a Bayesian classifier.

Background: This article provides guidelines for selecting optimal numerical solvers for biomolecular system models. Because various parameters of the same system could have drastically different ranges from 10(-15) to 10(10), the ODEs can be stiff and ill-conditioned, resulting in non-unique, non-existing, or non-reproducible modeling solutions. Previous studies have not examined in depth how to best select numerical solvers for biomolecular system models, which makes it difficult to experimentally validate the modeling results. To address this problem, we have chosen one of the well-known stiff initial value problems with limit cycle behavior as a test-bed system model. Solving this model, we have illustrated that different answers may result from different numerical solvers. We use MATLAB numerical solvers because they are optimized and widely used by the modeling community. We have also conducted a systematic study of numerical solver performances by using qualitative and quantitative measures such as convergence, accuracy, and computational cost (i.e. in terms of function evaluation, partial derivative, LU decomposition, and "take-off" points). The results show that the modeling solutions can be drastically different using different numerical solvers. Thus, it is important to intelligently select numerical solvers when solving biomolecular system models., Results: The classic Belousov-Zhabotinskii (BZ) reaction is described by the Oregonator model and is used as a case study. We report two guidelines in selecting optimal numerical solver(s) for stiff, complex oscillatory systems: (i) for problems with unknown parameters, ode45 is the optimal choice regardless of the relative error tolerance; (ii) for known stiff problems, both ode113 and ode15s are good choices under strict relative tolerance conditions., Conclusions: For any given biomolecular model, by building a library of numerical solvers with quantitative performance assessment metric, we show that it is possible to improve reliability of the analytical modeling, which in turn can improve the efficiency and effectiveness of experimental validations of these models. Also, our study can be extended to study a variety of molecular-level system models for human disease diagnosis and therapeutic treatment.

Microarray technology has enabled us to simultaneously measure the expression of thousands of genes. Using this high-throughput data collection, we can examine subtle genetic changes between biological samples and build predictive models for clinical applications. Although microarrays have dramatically increased the rate of data collection, sample size is still a major issue in feature selection. Previous methods show that microarray data combination is successful in improving selection when using z-scores and fold change. We propose a wrapper based gene selection technique that combines bootstrap estimated classification errors for individual genes across multiple datasets. The bootstrap is an unbiased estimator of classification error and has been shown to be effective for small sample data. Coupled with data combination across multiple data sets, we show that this meta-analytic approach improves gene selection.

Quality assurance of high throughput "-omics" data is a major concern for biomedical discovery and translational medicine, and is considered a top priority in bioinformatics and systems biology. Here, we report a web-based bioinformatics tool called caCORRECT for chip artifact detection, analysis, and CORRECTion, which removes systematic artifactual noises that are commonly observed in microarray gene expression data. Despite the development of major databases such as GEO arrayExpress, caArray, and the SMD to manage and distribute microarray data to the public, reproducibility has been questioned in many cases, including high-profile papers and datasets. Based on both archived and synthetic data, we have designed the caCORRECT to have several advanced features: (1) to uncover significant, correctable artifacts that affect reproducibility of experiments; (2) to improve the integrity and quality of public archives by removing artifacts; (3) to provide a universal quality score to aid users in their selection of suitable microarray data; and (4) to improve the true-positive rate of biomarker selection verified by test data. These features are expected to improve the reproducibility of Microarray study. caCORRECT is freely available at: http://caCORRECT.bme.gatech.edu.

A Modified Genetic Algorithm has been developed for the task of optimal parameter selection for compartmental models. As a case study, a predictive model of the emerging health threat of obesity in America was developed which incorporated varying levels of three treatment strategies in an attempt to decrease the amount of overweight Americans over a ten-year period. The Genetic Algorithm was then applied to the task of minimizing the number of overweight persons while minimizing the costs associated with implementing the chosen treatment plans. Throughout repeated trials, the GA was able to converge to consistent, high-scoring treatment strategies after only a few minutes of computation on a desktop PC. This result demonstrates the ability of the modified Genetic Algorithm to effectively perform multivariate, nonlinear, simulation-based optimization routines in a short time.

Studies have implicated ceramide as a key molecular agent in regulating programmed cell death, or apoptosis. Consequently, there is significant potential in targeting intracellular ceramide as a cancer therapeutic agent. The cell's major ceramide source is the ceramide de novo synthesis pathway, which consists of a complex network of interdependent enzyme-catalyzed biochemical reactions. To understand how ceramide works, we have initiated the study of the ceramide de novo synthesis pathway using computational modeling based on fundamental principles of biochemical kinetics. Specifically, we designed and developed the model in MATLAB SIMULINK for the behavior of dihydroceramide desaturase. Dihydroceramide desaturase is one of three key enzymes in the ceramide de novo synthesis pathway, and it converts a relatively inert precursor molecule, dihydroceramide into biochemically reactive ceramide. A major issue in modeling is parameter estimation. We solved this problem by adopting a heuristic strategy based on a priori knowledge from literature and experimental data. We evaluated model accuracy by comparing the model prediction results with interpolated experimental data. Our future work includes more experimental validation of the model, dynamic rate constants assessment, and expansion of the model to include additional enzymes in the ceramide de novo synthesis pathway.