A Bayesian model for predicting monthly fire frequency in Kenya.

This study presents a comprehensive analysis of historical fire and climatic data to estimate the monthly frequency of vegetation fires in Kenya. This work introduces a statistical model that captures the behavior of fire count data, incorporating temporal explanatory factors and emphasizing the predictive significance of maximum temperature and rainfall. By employing Bayesian approaches, the paper integrates literature information, simulation studies, and real-world data to enhance model performance and generate more precise prediction intervals that encompass actual fire counts. To forecast monthly fire occurrences aggregated from the Moderate Resolution Imaging Spectroradiometer (MODIS) data in Kenya (2000-2018), the study utilizes maximum temperature and rainfall values derived from global GeoTiff (.tif) files sourced from the WorldClim database. The evaluation of the widely used Negative Binomial (NB) model and the proposed Bayesian Negative Binomial (BNB) model reveals the superiority of the latter in accounting for seasonal patterns and long-term trends. The simulation results demonstrate that the BNB model outperforms the NB model in terms of Root Mean Square Error (RMSE), and Mean Absolute Scaled Error (MASE) on both training and testing datasets. Furthermore, when applied to real data, the Bayesian Negative Binomial model exhibits better performance on the test dataset, showcasing lower RMSE (163.22 vs. 166.67), lower MASE (1.12 vs. 1.15), and reduced bias (-2.52% vs. -2.62%) compared to the NB model. The Bayesian model also offers prediction intervals that closely align with actual predictions, indicating its flexibility in forecasting the frequency of monthly fires. These findings underscore the importance of leveraging past data to forecast the future behavior of the fire regime, thus providing valuable insights for fire control strategies in Kenya. By integrating climatic factors and employing Bayesian modeling techniques, the study contributes to the understanding and prediction of vegetation fires, ultimately supporting proactive measures in mitigating their impact.

Assessing predictive performance of supervised machine learning algorithms for a diamond pricing model.

This study conducted a comprehensive analysis of multiple supervised machine learning models, regressors and classifiers, to accurately predict diamond prices. Diamond pricing is a complex task due to the non-linear relationships between key features such as carat, cut, clarity, table, and depth. The analysis aimed to develop an accurate predictive model by utilizing both regression and classification approaches. To preprocess the data, the study employed various techniques. The work addressed outliers, standardized the predictors, performed median imputation of missing values, and resolved multicollinearity issues. Equal-width binning on the cut variable was performed to handle class imbalance. Correlation-based feature selection was utilized to eliminate highly correlated variables, ensuring that only relevant features were included in the models. Outliers were handled using the inter-quartile range method, and numerical features were normalized through standardization. Missing values in numerical features were imputed using the median, preserving the integrity of the dataset. Among the models evaluated, the RF regressor exhibited exceptional performance. It achieved the lowest root mean squared error (RMSE) of 523.50, indicating superior accuracy compared to the other models. The RF regressor also obtained a high R-squared ([Formula: see text]) score of 0.985, suggesting it explained a significant portion of the variance in diamond prices. Furthermore, the area under the curve with RF classifier for the test set was 1.00 [Formula: see text], indicating perfect classification performance. These results solidify the RF's position as the best-performing model in terms of accuracy and predictive power, both in regression and classification. The MLP regressor showed promising results with an RMSE of 563.74 and an [Formula: see text] score of 0.980, demonstrating its ability to capture the complex relationships in the data. Although it achieved slightly higher errors than the RF regressor, further analysis is needed to determine its suitability and potential advantages compared to the RF regressor. The XGBoost Regressor achieved an RMSE of 612.88 and an [Formula: see text] score of 0.972, indicating its effectiveness in predicting diamond prices but with slightly higher errors compared to the RF regressor. The Boosted Decision Tree Regressor had an RMSE of 711.31 and an [Formula: see text] score of 0.968, demonstrating its ability to capture some of the underlying patterns but with higher errors than the RF and XGBoost models. In contrast, the KNN regressor yielded a higher RMSE of 1346.65 and a lower [Formula: see text] score of 0.887, indicating its inferior performance in accurately predicting diamond prices compared to the other models. Similarly, the Linear Regression model performed similarly to the KNN regressor, with an RMSE of 1395.41 and an [Formula: see text] score of 0.876. The Support Vector Regression model showed the highest RMSE of 3044.49 and the lowest [Formula: see text] score of 0.421, indicating its limited effectiveness in capturing the complex relationships in the data. Overall, the study demonstrates that the RF outperforms the other models in terms of accuracy and predictive power, as evidenced by its lowest RMSE, highest [Formula: see text] score, and perfect classification performance. This highlights its suitability for accurately predicting diamond prices. The study not only provides an effective tool for the diamond industry but also emphasizes the importance of considering both regression and classification approaches in developing accurate predictive models. The findings contribute valuable insights for pricing strategies, market trends, and decision-making processes in the diamond industry and related fields.

Genome-wide association testing in malaria studies in the presence of overdominance.

BACKGROUND: In human genetics, heterozygote advantage (heterosis) has been detected in studies that focused on specific genes but not in genome-wide association studies (GWAS). For example, heterosis is believed to confer resistance to certain strains of malaria in patients heterozygous for the sickle-cell gene, haemoglobin S (HbS). Yet the power of allelic tests can be substantially diminished by heterosis. Since GWAS (and haplotype-associations) also utilize allelic tests, it is unclear to what degree GWAS could underachieve because heterosis is ignored. METHODS: In this study, a two-step approach to genetic association testing in malaria studies in a GWAS setting that may enhance the power of the tests was proposed, by identifying the underlying genetic model first before applying the association tests. Generalized linear models for dominant, recessive, additive, and heterotic effects were fitted and model selection was performed. This was achieved via tests of significance using the MAX and allelic tests, noting the minimum p-values across all the models and the proportion of tests that a given genetic model was deemed the best. An example dataset, based on 17 SNPs, from a robust genetic association study and simulated genotype datasets, were used to illustrate the method. Case-control genotype data on malaria from Kenya and Gambia were used for validation. RESULTS AND CONCLUSION: Results showed that the allelic test returned some false negatives under the heterosis model, suggesting reduced power in testing genetic association. Disparities were observed for some chromosomes in the Kenyan and Gambian datasets, including the sex chromosomes. Thus, GWAS and haplotype associations should be treated with caution, unless the underlying genetic model had been determined.

Predictors of colorectal cancer survival using cox regression and random survival forests models based on gene expression data.

Understanding and identifying the markers and clinical information that are associated with colorectal cancer (CRC) patient survival is needed for early detection and diagnosis. In this work, we aimed to build a simple model using Cox proportional hazards (PH) and random survival forest (RSF) and find a robust signature for predicting CRC overall survival. We used stepwise regression to develop Cox PH model to analyse 54 common differentially expressed genes from three mutations. RSF is applied using log-rank and log-rank-score based on 5000 survival trees, and therefore, variables important obtained to find the genes that are most influential for CRC survival. We compared the predictive performance of the Cox PH model and RSF for early CRC detection and diagnosis. The results indicate that SLC9A8, IER5, ARSJ, ANKRD27, and PIPOX genes were significantly associated with the CRC overall survival. In addition, age, sex, and stages are also affecting the CRC overall survival. The RSF model using log-rank is better than log-rank-score, while log-rank-score needed more trees to stabilize. Overall, the imputation of missing values enhanced the model's predictive performance. In addition, Cox PH predictive performance was better than RSF.

A stacking ensemble deep learning approach to cancer type classification based on TCGA data.

Cancer tumor classification based on morphological characteristics alone has been shown to have serious limitations. Breast, lung, colorectal, thyroid, and ovarian are the most commonly diagnosed cancers among women. Precise classification of cancers into their types is considered a vital problem for cancer diagnosis and therapy. In this paper, we proposed a stacking ensemble deep learning model based on one-dimensional convolutional neural network (1D-CNN) to perform a multi-class classification on the five common cancers among women based on RNASeq data. The RNASeq gene expression data was downloaded from Pan-Cancer Atlas using GDCquery function of the TCGAbiolinks package in the R software. We used least absolute shrinkage and selection operator (LASSO) as feature selection method. We compared the results of the new proposed model with and without LASSO with the results of the single 1D-CNN and machine learning methods which include support vector machines with radial basis function, linear, and polynomial kernels; artificial neural networks; k-nearest neighbors; bagging trees. The results show that the proposed model with and without LASSO has a better performance compared to other classifiers. Also, the results show that the machine learning methods (SVM-R, SVM-L, SVM-P, ANN, KNN, and bagging trees) with under-sampling have better performance than with over-sampling techniques. This is supported by the statistical significance test of accuracy where the p-values for differences between the SVM-R and SVM-P, SVM-R and ANN, SVM-R and KNN are found to be p = 0.003, p = < 0.001, and p = < 0.001, respectively. Also, SVM-L had a significant difference compared to ANN p = 0.009. Moreover, SVM-P and ANN, SVM-P and KNN are found to be significantly different with p-values p = < 0.001 and p = < 0.001, respectively. In addition, ANN and bagging trees, ANN and KNN were found to be significantly different with p-values p = < 0.001 and p = 0.004, respectively. Thus, the proposed model can help in the early detection and diagnosis of cancer in women, and hence aid in designing early treatment strategies to improve survival.

Adaptation of a RAS pathway activation signature from FF to FFPE tissues in colorectal cancer.

BACKGROUND: The KRAS gene is mutated in about 40 % of colorectal cancer (CRC) cases, which has been clinically validated as a predictive mutational marker of intrinsic resistance to anti-EGFR inhibitor (EGFRi) therapy. Since nearly 60 % of patients with a wild type KRAS fail to respond to EGFRi combination therapies, there is a need to develop more reliable molecular signatures to better predict response. Here we address the challenge of adapting a gene expression signature predictive of RAS pathway activation, created using fresh frozen (FF) tissues, for use with more widely available formalin fixed paraffin-embedded (FFPE) tissues. METHODS: In this study, we evaluated the translation of an 18-gene RAS pathway signature score from FF to FFPE in 54 CRC cases, using a head-to-head comparison of five technology platforms. FFPE-based technologies included the Affymetrix GeneChip (Affy), NanoString nCounter™ (NanoS), Illumina whole genome RNASeq (RNA-Acc), Illumina targeted RNASeq (t-RNA), and Illumina stranded Total RNA-rRNA-depletion (rRNA). RESULTS: Using Affy_FF as the "gold" standard, initial analysis of the 18-gene RAS scores on all 54 samples shows varying pairwise Spearman correlations, with (1) Affy_FFPE (r = 0.233, p = 0.090); (2) NanoS_FFPE (r = 0.608, p < 0.0001); (3) RNA-Acc_FFPE (r = 0.175, p = 0.21); (4) t-RNA_FFPE (r = -0.237, p = 0.085); (5) and t-RNA (r = -0.012, p = 0.93). These results suggest that only NanoString has successful FF to FFPE translation. The subsequent removal of identified "problematic" samples (n = 15) and genes (n = 2) further improves the correlations of Affy_FF with three of the five technologies: Affy_FFPE (r = 0.672, p < 0.0001); NanoS_FFPE (r = 0.738, p < 0.0001); and RNA-Acc_FFPE (r = 0.483, p = 0.002). CONCLUSIONS: Of the five technology platforms tested, NanoString technology provides a more faithful translation of the RAS pathway gene expression signature from FF to FFPE than the Affymetrix GeneChip and multiple RNASeq technologies. Moreover, NanoString was the most forgiving technology in the analysis of samples with presumably poor RNA quality. Using this approach, the RAS signature score may now be reasonably applied to FFPE clinical samples.

Mechanisms of chromosomal instability in melanoma.

A systems biology approach was applied to investigate the mechanisms of chromosomal instability in melanoma cell lines. Chromosomal instability was quantified using array comparative genomic hybridization to identify somatic copy number alterations (deletions and duplications). Primary human melanocytes displayed an average of 8.5 alterations per cell primarily representing known polymorphisms. Melanoma cell lines displayed 25 to 131 alterations per cell, with an average of 68, indicative of chromosomal instability. Copy number alterations included approximately equal numbers of deletions and duplications with greater numbers of hemizygous (-1,+1) alterations than homozygous (-2,+2). Melanoma oncogenes, such as BRAF and MITF, and tumor suppressor genes, such as CDKN2A/B and PTEN, were included in these alterations. Duplications and deletions were functional as there were significant correlations between DNA copy number and mRNA expression for these genes. Spectral karyotype analysis of three lines confirmed extensive chromosomal instability with polyploidy, aneuploidy, deletions, duplications, and chromosome rearrangements. Bioinformatic analysis identified a signature of gene expression that was correlated with chromosomal instability but this signature provided no clues to the mechanisms of instability. The signature failed to generate a significant (P = 0.105) prediction of melanoma progression in a separate dataset. Chromosomal instability was not correlated with elements of DNA damage response (DDR) such as radiosensitivity, nucleotide excision repair, expression of the DDR biomarkers γH2AX and P-CHEK2, nor G1 or G2 checkpoint function. Chromosomal instability in melanoma cell lines appears to influence gene function but it is not simply explained by alterations in the system of DDR.

Development of DNA damage response signaling biomarkers using automated, quantitative image analysis.

The DNA damage response (DDR) coordinates DNA repair with cell cycle checkpoints to ameliorate or mitigate the pathological effects of DNA damage. Automated quantitative analysis (AQUA) and Tissue Studio are commercial technologies that use digitized immunofluorescence microscopy images to quantify antigen expression in defined tissue compartments. Because DDR is commonly activated in cancer and may reflect genetic instability within the lesion, a method to quantify DDR in cancer offers potential diagnostic and/or prognostic value. In this study, both AQUA and Tissue Studio algorithms were used to quantify the DDR in radiation-damaged skin fibroblasts, melanoma cell lines, moles, and primary and metastatic melanomas. Digital image analysis results for three markers of DDR (γH2AX, P-ATM, P-Chk2) correlated with immunoblot data for irradiated fibroblasts, whereas only γH2AX and P-Chk2 correlated with immunoblot data in melanoma cell lines. Melanoma cell lines displayed substantial variation in γH2AX and P-Chk2 expression, and P-Chk2 expression was significantly correlated with radioresistance. Moles, primary melanomas, and melanoma metastases in brain, lung and liver displayed substantial variation in γH2AX expression, similar to that observed in melanoma cell lines. Automated digital analysis of immunofluorescent images stained for DDR biomarkers may be useful for predicting tumor response to radiation and chemotherapy.

Pathologic and gene expression features of metastatic melanomas to the brain.

BACKGROUND: The prognosis of metastatic melanomas to the brain (MBM) is variable with prolonged survival in a subset. It is unclear whether MBM differ from extracranial metastases (EcM) and primary melanomas (PrM). METHODS: To study the biology of MBM, histopathologic analysis of tumor blocks from patients' craniotomy samples and whole-genome expression profiling (WGEP) with confirmatory immunohistochemistry were performed. RESULTS: High mononuclear infiltrate and low intratumoral hemorrhage were associated with prolonged overall survival (OS). Pathway analysis of WGEP data from 29 such craniotomy tumor blocks demonstrated that several immune-related BioCarta gene sets were associated with prolonged OS. WGEP analysis of MBM in comparison with same-patient EcM and PrM showed that MBM and EcM were similar, but both differ significantly from PrM. Immunohistochemical analysis revealed that peritumoral CD3⁺ and CD8⁺ cells were associated with prolonged OS. CONCLUSIONS: MBMs are more similar to EcM compared with PrM. Immune infiltrate is a favorable prognostic factor for MBM.

A prognostic signature of G(2) checkpoint function in melanoma cell lines.

As DNA damage checkpoints are barriers to carcinogenesis, G(2) checkpoint function was quantified to test for override of this checkpoint during melanomagenesis. Primary melanocytes displayed an effective G(2) checkpoint response to ionizing radiation (IR)-induced DNA damage. Thirty-seven percent of melanoma cell lines displayed a significant defect in G(2) checkpoint function. Checkpoint function was melanoma subtype-specific with "epithelial-like" melanoma lines, with wild type NRAS and BRAF displaying an effective checkpoint, while lines with mutant NRAS and BRAF displayed defective checkpoint function. Expression of oncogenic B-Raf in a checkpoint-effective melanoma attenuated G(2) checkpoint function significantly but modestly. Other alterations must be needed to produce the severe attenuation of G(2) checkpoint function seen in some BRAF-mutant melanoma lines. Quantitative trait analysis tools identified mRNA species whose expression was correlated with G(2) checkpoint function in the melanoma lines. A 165 gene signature was identified with a high correlation with checkpoint function (p < 0.004) and low false discovery rate (≤ 0.077). The G(2) checkpoint gene signature predicted G(2) checkpoint function with 77-94% accuracy. The signature was enriched in lysosomal genes and contained numerous genes that are associated with regulation of chromatin structure and cell cycle progression. The core machinery of the cell cycle was not altered in checkpoint-defective lines but rather numerous mediators of core machinery function were. When applied to an independent series of primary melanomas, the predictive G(2) checkpoint signature was prognostic of distant metastasis-free survival. These results emphasize the value of expression profiling of primary melanomas for understanding melanoma biology and disease prognosis.

A prognostic signature of defective p53-dependent G1 checkpoint function in melanoma cell lines.

Melanoma cell lines and normal human melanocytes (NHM) were assayed for p53-dependent G1 checkpoint response to ionizing radiation (IR)-induced DNA damage. Sixty-six percent of melanoma cell lines displayed a defective G1 checkpoint. Checkpoint function was correlated with sensitivity to IR with checkpoint-defective lines being radio-resistant. Microarray analysis identified 316 probes whose expression was correlated with G1 checkpoint function in melanoma lines (P≤0.007) including p53 transactivation targets CDKN1A, DDB2, and RRM2B. The 316 probe list predicted G1 checkpoint function of the melanoma lines with 86% accuracy using a binary analysis and 91% accuracy using a continuous analysis. When applied to microarray data from primary melanomas, the 316 probe list was prognostic of 4-yr distant metastasis-free survival. Thus, p53 function, radio-sensitivity, and metastatic spread may be estimated in melanomas from a signature of gene expression.

Reliability of three methods of computer-aided thermal pattern analysis.

BACKGROUND: The objective of this study was to assess three methods of computer-aided thermal pattern analysis for a) examiner reliability, b) inter-method differences, and c) determine which method yields the highest percent-similarity between paired test-retest scans. METHODS: Three examiners compared two sets of thermal scans from the same 30 subjects using three different methods of scan alignment. The results were evaluated by the Intraclass Correlation Coefficient and the Wilcoxon signed-rank test, at the 5% level of significance. RESULTS: Intra and inter-examiner ICC scores for all methods were acceptable (> 0.75). There were no statistically significant differences (at the Bonferroni-corrected level of significance of 0.0004%) in percent similarity of the scans between the three methods CONCLUSIONS: The results contribute evidence to the reliability of TPC program software. Manually aligning the readings plays an important role in obtaining precise TPC percent-similarities.

Thermal patterns and health perceptions.

INTRODUCTION: Thermal pattern analysis is thought to be an indicator of health. However, the validity of this concept has not been established. To further investigate the relationship between thermal pattern analysis and health perceptions, thermal scans were assessed in conjunction with results from the SF-12 health survey. METHODS: Sixty-eight chiropractic students were recruited to receive two paraspinal thermal scans, 5 minutes apart, on three visits that were 1 week apart. Each scan produces three graphs or channels; one for each of left and right sides of the spine and a delta or difference between left and right. The scans were imported into a thermal pattern calculator (TPC) providing a percent similarity between the two. The TPC percent were compared with to their corresponding SF-12 scores. RESULTS: There were no significant findings in the left or delta channel. For the right channel, there was a decrease in mental health perception in participants having a TPC percent of 70.8 or higher (32.3% of all visits). CONCLUSION: Participants in this study who had right channel TPC percent of 70.8 or higher were associated with lower mental health perception scores. The study is considered a preliminary inquiry only due to the small sample size.