Classification and regression tree and spatial analyses reveal geographic heterogeneity in genome wide linkage study of Indian visceral leishmaniasis

Selecting optimal conditioning parameters for landslide susceptibility: an experimental research on Aqabat Al-Sulbat, Saudi Arabia

Landslides and other disastrous natural catastrophes jeopardise natural resources, assets, and people's lives. As a result, future resource management will necessitate landslide susceptibility mapping (LSM) using the best conditioning factors. In Aqabat Al-Sulbat, Asir province, Saudi Arabia, the goal of this study was to find optimal conditioning parameters dependent hybrid LSM. LSM was created using machine learning methods such as random forest (RF), logistic regression (LR), and artificial neural network (ANN). To build ensemble models, the LR was combined with RF and ANN models. The receiver operating characteristic (ROC) curve was used to validate the LSMs and determine which models were the best. Then, utilising random forest (RF), classification and regression tree (CART), and correlation feature selection, sensitivity analysis was carried out. Through sensitivity analysis, the most relevant conditioning factors were determined, and the best model was applied to the important parameters to build a highly robust LSM with fewer variables. The ROC curve was also used to evaluate the final model. The results show that two hybrid models (LR-ANN and LR-RF) were predicted the very high as 29.67-32.73 km² and high LS regions as 21.84-33.38 km², with LR predicting 22.34km² as very high and 45.15km² as high LS zones. The LR-RF appeared as best model (AUC: 0.941), followed by LR-ANN (AUC: 0.915) and LR (AUC: 0.872). Sensitivity analysis, on the other hand, allows for the exclusion of aspects, hillshade, drainage density, curvature, and TWI from LSM. The LSM was then predicted using the LR-RF model based on the remaining nine conditioning factors. With fewer variables, this model has achieved greater accuracy (AUC: 0.927). This comes very close to being the best hybrid model. As a result, it is strongly advised to choose conditioning parameters with caution, as redundant parameters would result in less resilient LSM. As a consequence, both time and resources would be saved, and precise LSM would indeed be possible.

Detection of SARS-CoV-2 in nasal swabs using MALDI-MS

Detection of SARS-CoV-2 using RT-PCR and other advanced methods can achieve high accuracy. However, their application is limited in countries that lack sufficient resources to handle large-scale testing during the COVID-19 pandemic. Here, we describe a method to detect SARS-CoV-2 in nasal swabs using matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) and machine learning analysis. This approach uses equipment and expertise commonly found in clinical laboratories in developing countries. We obtained mass spectra from a total of 362 samples (211 SARS-CoV-2-positive and 151 negative by RT-PCR) without prior sample preparation from three different laboratories. We tested two feature selection methods and six machine learning approaches to identify the top performing analysis approaches and determine the accuracy of SARS-CoV-2 detection. The support vector machine model provided the highest accuracy (93.9%), with 7% false positives and 5% false negatives. Our results suggest that MALDI-MS and machine learning analysis can be used to reliably detect SARS-CoV-2 in nasal swab samples.

Machine learning highlights the deficiency of conventional dosimetric constraints for prevention of high-grade radiation esophagitis in non-small cell lung cancer treated with chemoradiation

•

A large cohort to predict radiation esophagitis in lung cancer patients was used.

•

Modern machine learning models were implemented to predict radiation esophagitis.

•

Previously published predictors of grade ≥ 3 radiation esophagitis may be unreliable.

Background and Purpose

Radiation esophagitis is a clinically important toxicity seen with treatment for locally-advanced non-small cell lung cancer. There is considerable disagreement among prior studies in identifying predictors of radiation esophagitis. We apply machine learning algorithms to identify factors contributing to the development of radiation esophagitis to uncover previously unidentified criteria and more robust dosimetric factors.

Materials and Methods

We used machine learning approaches to identify predictors of grade ≥ 3 radiation esophagitis in a cohort of 202 consecutive locally-advanced non-small cell lung cancer patients treated with definitive chemoradiation from 2008 to 2016. We evaluated 35 clinical features per patient grouped into risk factors, comorbidities, imaging, stage, histology, radiotherapy, chemotherapy and dosimetry. Univariate and multivariate analyses were performed using a panel of 11 machine learning algorithms combined with predictive power assessments.

Results

All patients were treated to a median dose of 66.6 Gy at 1.8 Gy per fraction using photon (89.6%) and proton (10.4%) beam therapy, most often with concurrent chemotherapy (86.6%). 11.4% of patients developed grade ≥ 3 radiation esophagitis. On univariate analysis, no individual feature was found to predict radiation esophagitis (AUC range 0.45–0.55, p ≥ 0.07). In multivariate analysis, all machine learning algorithms exhibited poor predictive performance (AUC range 0.46–0.56, p ≥ 0.07).

Conclusions

Contemporary machine learning algorithms applied to our modern, relatively large institutional cohort could not identify any reliable predictors of grade ≥ 3 radiation esophagitis. Additional patients are needed, and novel patient-specific and treatment characteristics should be investigated to develop clinically meaningful methods to mitigate this survival altering toxicity.

Predicting radiation pneumonitis in locally advanced stage II-III non-small cell lung cancer using machine learning

BACKGROUND AND PURPOSE

Radiation pneumonitis (RP) is a radiotherapy dose-limiting toxicity for locally advanced non-small cell lung cancer (LA-NSCLC). Prior studies have proposed relevant dosimetric constraints to limit this toxicity. Using machine learning algorithms, we performed analyses of contributing factors in the development of RP to uncover previously unidentified criteria and elucidate the relative importance of individual factors.

MATERIALS AND METHODS

We evaluated 32 clinical features per patient in a cohort of 203 stage II-III LA-NSCLC patients treated with definitive chemoradiation to a median dose of 66.6 Gy in 1.8 Gy daily fractions at our institution from 2008 to 2016. Of this cohort, 17.7% of patients developed grade ≥2 RP. Univariate analysis was performed using trained decision stumps to individually analyze statistically significant predictors of RP and perform feature selection. Applying Random Forest, we performed multivariate analysis to assess the combined performance of important predictors of RP.

RESULTS

On univariate analysis, lung V20, lung mean, lung V10 and lung V5 were found to be significant RP predictors with the greatest balance of specificity and sensitivity. On multivariate analysis, Random Forest (AUC = 0.66, p = 0.0005) identified esophagus max (20.5%), lung V20 (16.4%), lung mean (15.7%) and pack-year (14.9%) as the most common primary differentiators of RP.

CONCLUSIONS

We highlight Random Forest as an accurate machine learning method to identify known and new predictors of symptomatic RP. Furthermore, this analysis confirms the importance of lung V20, lung mean and pack-year as predictors of RP while also introducing esophagus max as an important RP predictor.

Variations in macrophage migration inhibitory factor gene are not associated with visceral leishmaniasis in India

BACKGROUND

The host genetic factors play important role in determining the outcome of visceral leishmaniasis (VL). Macrophage migration inhibitory factor (MIF) is an important host cytokine, which is a key regulator of innate immune system. Genetic variants in MIF gene have been found to be associated with several inflammatory and infectious diseases. Role of MIF is well documented in leishmaniasis diseases, including Indian visceral leishmaniasis, where elevated level of serum MIF has been associated with VL phenotypes. However, there was no genetic study to correlate MIF variants in VL, therefore, we aimed to study the possible association of three reported MIF gene variants -794 CATT, -173G > C and non-coding RNA gene LOC284889 in Indian VL phenotype.

METHODS

Study subjects comprised of 214 VL patients along with ethnically and demographically matched 220 controls from VL endemic regions of Bihar state in India.

RESULTS

We found no significant difference between cases and controls in allelic, genotypic and haplotype frequency of the markers analysed [-794 CATT repeats (χ2=0.86; p=0.35; OR=0.85; 95% CI=0.61-1.19); -173 G>C polymorphism (χ2=1.11; p=0.29; OR=0.83; 95% CI=0.59-1.16); and LOC284889 (χ2=0.78; p=0.37; OR=0.86; 95% CI=0.61-1.20)].

CONCLUSION

Since we did not find any significant differences between case and control groups, we conclude that sequencing of complete MIF gene and extensive study on innate and adaptive immunity genes may help in identifying genetic variations that are associated with VL susceptibility/resistance among Indians.

River suspended sediment modelling using the CART model: A comparative study of machine learning techniques

Suspended sediment load (SSL) modelling is an important issue in integrated environmental and water resources management, as sediment affects water quality and aquatic habitats. Although classification and regression tree (CART) algorithms have been applied successfully to ecological and geomorphological modelling, their applicability to SSL estimation in rivers has not yet been investigated. In this study, we evaluated use of a CART model to estimate SSL based on hydro-meteorological data. We also compared the accuracy of the CART model with that of the four most commonly used models for time series modelling of SSL, i.e. adaptive neuro-fuzzy inference system (ANFIS), multi-layer perceptron (MLP) neural network and two kernels of support vector machines (RBF-SVM and P-SVM). The models were calibrated using river discharge, stage, rainfall and monthly SSL data for the Kareh-Sang River gauging station in the Haraz watershed in northern Iran, where sediment transport is a considerable issue. In addition, different combinations of input data with various time lags were explored to estimate SSL. The best input combination was identified through trial and error, percent bias (PBIAS), Taylor diagrams and violin plots for each model. For evaluating the capability of the models, different statistics such as Nash-Sutcliffe efficiency (NSE), Kling-Gupta efficiency (KGE) and percent bias (PBIAS) were used. The results showed that the CART model performed best in predicting SSL (NSE=0.77, KGE=0.8, PBIAS<±15), followed by RBF-SVM (NSE=0.68, KGE=0.72, PBIAS<±15). Thus the CART model can be a helpful tool in basins where hydro-meteorological data are readily available.

Mannose-binding Lectin (MBL) as a susceptible host factor influencing Indian Visceral Leishmaniasis

Visceral Leishmaniasis (VL), caused by Leishmania donovani is endemic in the Indian sub-continent. Mannose-binding Lectin (MBL) is a complement lectin protein that binds to the surface of Leishmania promastigotes and results in activation of the complement lectin cascade. We utilized samples of 218 VL patients and 215 healthy controls from an Indian population. MBL2 functional variants were genotyped and the circulating MBL serum levels were measured. MBL serum levels were elevated in patients compared to the healthy controls (adjusted P=0.007). The MBL2 promoter variants -78C/T and +4P/Q were significantly associated with relative protection to VL (-78C/T, OR=0.7, 95% CI=0.5-0.96, adjusted P=0.026 and +4P/Q, OR=0.66, 95% CI=0.48-0.9, adjusted P=0.012). MBL2*LYQA haplotypes occurred frequently among controls (OR=0.69, 95% CI=0.5-0.97, adjusted P=0.034). MBL recognizes Leishmania and plays a relative role in establishing L. donovani infection and subsequent disease progression. In conclusion, MBL2 functional variants were associated with VL.

Decision Trees Predicting Tumor Shrinkage for Head and Neck Cancer: Implications for Adaptive Radiotherapy

OBJECTIVE

To develop decision trees predicting for tumor volume reduction in patients with head and neck (H&N) cancer using pretreatment clinical and pathological parameters.

METHODS

Forty-eight patients treated with definitive concurrent chemoradiotherapy for squamous cell carcinoma of the nasopharynx, oropharynx, oral cavity, or hypopharynx were retrospectively analyzed. These patients were rescanned at a median dose of 37.8 Gy and replanned to account for anatomical changes. The percentages of gross tumor volume (GTV) change from initial to rescan computed tomography (CT; %GTVΔ) were calculated. Two decision trees were generated to correlate %GTVΔ in primary and nodal volumes with 14 characteristics including age, gender, Karnofsky performance status (KPS), site, human papilloma virus (HPV) status, tumor grade, primary tumor growth pattern (endophytic/exophytic), tumor/nodal/group stages, chemotherapy regimen, and primary, nodal, and total GTV volumes in the initial CT scan. The C4.5 Decision Tree induction algorithm was implemented.

RESULTS

The median %GTVΔ for primary, nodal, and total GTVs was 26.8%, 43.0%, and 31.2%, respectively. Type of chemotherapy, age, primary tumor growth pattern, site, KPS, and HPV status were the most predictive parameters for primary %GTVΔ decision tree, whereas for nodal %GTVΔ, KPS, site, age, primary tumor growth pattern, initial primary GTV, and total GTV volumes were predictive. Both decision trees had an accuracy of 88%.

CONCLUSIONS

There can be significant changes in primary and nodal tumor volumes during the course of H&N chemoradiotherapy. Considering the proposed decision trees, radiation oncologists can select patients predicted to have high %GTVΔ, who would theoretically gain the most benefit from adaptive radiotherapy, in order to better use limited clinical resources.

Common variants in the HLA-DRB1-HLA-DQA1 HLA class II region are associated with susceptibility to visceral leishmaniasis

To identify susceptibility loci for visceral leishmaniasis, we undertook genome-wide association studies in two populations: 989 cases and 1,089 controls from India and 357 cases in 308 Brazilian families (1,970 individuals). The HLA-DRB1-HLA-DQA1 locus was the only region to show strong evidence of association in both populations. Replication at this region was undertaken in a second Indian population comprising 941 cases and 990 controls, and combined analysis across the three cohorts for rs9271858 at this locus showed P(combined) = 2.76 × 10(-17) and odds ratio (OR) = 1.41, 95% confidence interval (CI) = 1.30-1.52. A conditional analysis provided evidence for multiple associations within the HLA-DRB1-HLA-DQA1 region, and a model in which risk differed between three groups of haplotypes better explained the signal and was significant in the Indian discovery and replication cohorts. In conclusion, the HLA-DRB1-HLA-DQA1 HLA class II region contributes to visceral leishmaniasis susceptibility in India and Brazil, suggesting shared genetic risk factors for visceral leishmaniasis that cross the epidemiological divides of geography and parasite species.

Genetic and functional evaluation of the role of DLL1 in susceptibility to visceral leishmaniasis in India

Chromosome 6q26-27 is linked to susceptibility to visceral leishmaniasis (VL) in Brazil and Sudan. DLL1 encoding the Delta-like 1 ligand for Notch 3 was implicated as the etiological gene. DLL1 belongs to the family of Notch ligands known to selectively drive antigen-specific CD4 T helper 1 cell responses, which are important in protective immune response in leishmaniasis. Here we provide further genetic and functional evidence that supports a role for DLL1 in a well-powered population-based study centred in the largest global focus of VL in India. Twenty-one single nucleotide polymorphisms (SNPs) at PHF10/C6orf70/DLL1/FAM120B/PSMB1/TBP were genotyped in 941 cases and 992 controls. Logistic regression analysis under an additive model showed association between VL and variants at DLL1 and FAM120B, with top associations (rs9460106, OR=1.17, 95%CI 1.01-1.35, P=0.033; rs2103816, OR=1.16, 95%CI 1.01-1.34, P=0.039) robust to analysis using caste as a covariate to take account of population substructure. Haplotype analysis taking population substructure into account identified a common 2-SNP risk haplotype (frequency 0.43; P=0.028) at FAM120B, while the most significant protective haplotype (frequency 0.18; P=0.007) was a 5-SNP haplotype across the interval 5' of both DLL1 (negative strand) and FAM120B (positive strand) and extending to intron 4 of DLL1. Quantitative RT/PCR was used to compare expression of 6q27 genes in paired pre- and post-treatment splenic aspirates from VL patients (N=19). DLL1 was the only gene to show differential expression that was higher (P<0.0001) in pre- compared to post-treatment samples, suggesting that regulation of gene expression was important in disease pathogenesis. This well-powered genetic and functional study in an Indian population provides evidence supporting DLL1 as the etiological gene contributing to susceptibility to VL at Chromosome 6q27, confirming the potential for polymorphism at DLL1 to act as a genetic risk factor across the epidemiological divides of geography and parasite species.

Genetic and functional evaluation of the role of CXCR1 and CXCR2 in susceptibility to visceral leishmaniasis in north-east India

Background

IL8RA and IL8RB, encoded by CXCR1 and CXCR2, are receptors for interleukin (IL)-8 and other CXC chemokines involved in chemotaxis and activation of polymorphonuclear neutrophils (PMN). Variants at CXCR1 and CXCR2 have been associated with susceptibility to cutaneous and mucocutaneous leishmaniasis in Brazil. Here we investigate the role of CXCR1/CXCR2 in visceral leishmaniasis (VL) in India.

Methods

Three single nucleotide polymorphisms (SNPs) (rs4674259, rs2234671, rs3138060) that tag linkage disequilibrium blocks across CXCR1/CXCR2 were genotyped in primary family-based (313 cases; 176 nuclear families; 836 individuals) and replication (941 cases; 992 controls) samples. Family- and population-based analyses were performed to look for association between CXCR1/CXCR2 variants and VL. Quantitative RT/PCR was used to compare CXCR1/CXCR2 expression in mRNA from paired splenic aspirates taken before and after treatment from 19 VL patients.

Results

Family-based analysis using FBAT showed association between VL and SNPs CXCR1_rs2234671 (Z-score = 2.935, P = 0.003) and CXCR1_rs3138060 (Z-score = 2.22, P = 0.026), but not with CXCR2_rs4674259. Logistic regression analysis of the case-control data under an additive model of inheritance showed association between VL and SNPs CXCR2_rs4674259 (OR = 1.15, 95%CI = 1.01-1.31, P = 0.027) and CXCR1_rs3138060 (OR = 1.25, 95%CI = 1.02-1.53, P = 0.028), but not with CXCR1_rs2234671. The 3-locus haplotype T_G_C across these SNPs was shown to be the risk haplotype in both family- (TRANSMIT; P = 0.014) and population- (OR = 1.16, P = 0.028) samples (combined P = 0.002). CXCR2, but not CXCR1, expression was down regulated in pre-treatment compared to post-treatment splenic aspirates (P = 0.021).

Conclusions

This well-powered primary and replication genetic study, together with functional analysis of gene expression, implicate CXCR2 in determining outcome of VL in India.

No evidence for association between SLC11A1 and visceral leishmaniasis in India

Background

SLC11A1 has pleiotropic effects on macrophage function and remains a strong candidate for infectious disease susceptibility. 5' and/or 3' polymorphisms have been associated with tuberculosis, leprosy, and visceral leishmaniasis (VL). Most studies undertaken to date were under-powered, and none has been replicated within a population. Association with tuberculosis has replicated variably across populations. Here we investigate SLC11A1 and VL in India.

Methods

Nine polymorphisms (rs34448891, rs7573065, rs2276631, rs3731865, rs17221959, rs2279015, rs17235409, rs17235416, rs17229009) that tag linkage disequilibrium blocks across SLC11A1 were genotyped in primary family-based (313 cases; 176 families) and replication (941 cases; 992 controls) samples. Family- and population-based analyses were performed to look for association between SLC11A1 variants and VL. Quantitative RT/PCR was used to compare SLC11A1 expression in mRNA from paired splenic aspirates taken before and after treatment from 24 VL patients carrying different genotypes at the functional promoter GT_n polymorphism (rs34448891).

Results

No associations were observed between VL and polymorphisms at SLC11A1 that were either robust to correction for multiple testing or replicated across primary and replication samples. No differences in expression of SLC11A1 were observed when comparing pre- and post-treatment samples, or between individuals carrying different genotypes at the GT_n repeat.

Conclusions

This is the first well-powered study of SLC11A1 as a candidate for VL, which we conclude does not have a major role in regulating VL susceptibility in India.