Machine learning-based prediction of rheumatoid arthritis with development of ACPA autoantibodies in the presence of non-HLA genes polymorphisms.

Machine learning (ML) algorithms can handle complex genomic data and identify predictive patterns that may not be apparent through traditional statistical methods. They become popular tools for medical applications including prediction, diagnosis or treatment of complex diseases like rheumatoid arthritis (RA). RA is an autoimmune disease in which genetic factors play a major role. Among the most important genetic factors predisposing to the development of this disease and serving as genetic markers are HLA-DRB and non-HLA genes single nucleotide polymorphisms (SNPs). Another marker of RA is the presence of anticitrullinated peptide antibodies (ACPA) which is correlated with severity of RA. We use genetic data of SNPs in four non-HLA genes (PTPN22, STAT4, TRAF1, CD40 and PADI4) to predict the occurrence of ACPA positive RA in the Polish population. This work is a comprehensive comparative analysis, wherein we assess and juxtapose various ML classifiers. Our evaluation encompasses a range of models, including logistic regression, k-nearest neighbors, naïve Bayes, decision tree, boosted trees, multilayer perceptron, and support vector machines. The top-performing models demonstrated closely matched levels of accuracy, each distinguished by its particular strengths. Among these, we highly recommend the use of a decision tree as the foremost choice, given its exceptional performance and interpretability. The sensitivity and specificity of the ML models is about 70% that are satisfying. In addition, we introduce a novel feature importance estimation method characterized by its transparent interpretability and global optimality. This method allows us to thoroughly explore all conceivable combinations of polymorphisms, enabling us to pinpoint those possessing the highest predictive power. Taken together, these findings suggest that non-HLA SNPs allow to determine the group of individuals more prone to develop RA rheumatoid arthritis and further implement more precise preventive approach.

The Association between Inefficient Repair of DNA Double-Strand Breaks and Common Polymorphisms of the HRR and NHEJ Repair Genes in Patients with Rheumatoid Arthritis.

Rheumatoid arthritis (RA) is an autoimmune disease characterized by chronic inflammation affecting up to 2.0% of adults around the world. The molecular background of RA has not yet been fully elucidated, but RA is classified as a disease in which the genetic background is one of the most significant risk factors. One hallmark of RA is impaired DNA repair observed in patient-derived peripheral blood mononuclear cells (PBMCs). The aim of this study was to correlate the phenotype defined as the efficiency of DNA double-strand break (DSB) repair with the genotype limited to a single-nucleotide polymorphism (SNP) of DSB repair genes. We also analyzed the expression level of key DSB repair genes. The study population contained 45 RA patients and 45 healthy controls. We used a comet assay to study DSB repair after in vitro exposure to bleomycin in PBMCs from patients with rheumatoid arthritis. TaqMan SNP Genotyping Assays were used to determine the distribution of SNPs and the Taq Man gene expression assay was used to assess the RNA expression of DSB repair-related genes. PBMCs from patients with RA had significantly lower bleomycin-induced DNA lesion repair efficiency and we identified more subjects with inefficient DNA repair in RA compared with the control (84.5% vs. 24.4%; OR 41.4, 95% CI, 4.8-355.01). Furthermore, SNPs located within the RAD50 gene (rs1801321 and rs1801320) increased the OR to 53.5 (95% CI, 4.7-613.21) while rs963917 and rs3784099 (RAD51B) to 73.4 (95% CI, 5.3-1011.05). These results were confirmed by decision tree (DT) analysis (accuracy 0.84; precision 0.87, and specificity 0.86). We also found elevated expression of RAD51B, BRCA1, and BRCA2 in PBMCs isolated from RA patients. The findings indicated that impaired DSB repair in RA may be related to genetic variations in DSB repair genes as well as their expression levels. However, the mechanism of this relation, and whether it is direct or indirect, needs to be elucidated.

SNP in PTPN22, PADI4, and STAT4 but Not TRAF1 and CD40 Increase the Risk of Rheumatoid Arthritis in Polish Population.

Single nucleotide polymorphisms in non-HLA genes are involved in the development of rheumatoid arthritis (RA). SNPS in genes: PADI4 (rs2240340), STAT4 (rs7574865), CD40 (rs4810485), PTPN22 (rs2476601), and TRAF1 (rs3761847) have been described as risk factors for the development of autoimmune diseases, including RA. This study aimed to assess the prevalence of polymorphisms of these genes in the Polish population of patients with rheumatoid arthritis as compared to healthy controls. 324 subjects were included in the study: 153 healthy subjects and 181 patients from the Department of Rheumatology, Medical University of Lodz who fulfilled the criteria of rheumatoid arthritis diagnosis. Genotypes were determined by Taqman SNP Genotyping Assay. rs2476601 (G/A, OR = 2.16, CI = 1.27-3.66; A/A, OR = 10.35, CI = 1.27-84.21), rs2240340 (C/T, OR = 4.35, CI = 2.55-7.42; T/T, OR = 2.80, CI = 1.43-4.10) and rs7574865 (G/T, OR = 1.97, CI = 1.21-3.21; T/T, OR = 3.33, CI = 1.01-11.02) were associated with RA in the Polish population. Rs4810485 was also associated with RA, however after Bonferroni's correction was statistically insignificant. We also found an association between minor alleles of rs2476601, rs2240340, and rs7574865 and RA (OR = 2.32, CI = 1.47-3.66; OR = 2.335, CI = 1.64-3.31; OR = 1.88, CI = 1.27-2.79, respectively). Multilocus analysis revealed an association between CGGGT and rare (below 0.02 frequency) haplotypes (OR = 12.28, CI = 2.65-56.91; OR = 3.23, CI = 1.63-6.39). In the Polish population, polymorphisms of the PADI4, PTPN22, and STAT4 genes have been detected, which are also known risk factors for RA in various other populations.

Polymorphisms in DNA Repair Genes and Association with Rheumatoid Arthritis in a Pilot Study on a Central European Population.

Rheumatoid arthritis (RA) is a chronic, multifactorial autoimmune disease characterized by chronic arthritis, a tendency to develop joint deformities, and involvement of extra-articular tissues. The risk of malignant neoplasms among patients with RA is the subject of ongoing research due to the autoimmune pathogenesis that underlies RA, the common etiology of rheumatic disease and malignancies, and the use of immunomodulatory therapy, which can alter immune system function and thus increase the risk of malignant neoplasms. This risk can also be increased by impaired DNA repair efficiency in individuals with RA, as reported in our recent study. Impaired DNA repair may reflect the variability in the genes that encode DNA repair proteins. The aim of our study was to evaluate the genetic variation in RA within the genes of the DNA damage repair system through base excision repair (BER), nucleotide excision repair (NER), and the double strand break repair system by homologous recombination (HR) and non-homologous end joining (NHEJ). We genotyped a total of 28 polymorphisms in 19 genes encoding DNA repair-related proteins in 100 age- and sex-matched RA patients and healthy subjects from Central Europe (Poland). Polymorphism genotypes were determined using the Taq-man SNP Genotyping Assay. We found an association between the RA occurrence and rs25487/XRCC1, rs7180135/RAD51, rs1801321/RAD51, rs963917/RAD51B, rs963918/RAD51B, rs2735383/NBS1, rs132774/XRCC6, rs207906/XRCC5, and rs861539/XRCC3 polymorphisms. Our results suggest that polymorphisms of DNA damage repair genes may play a role in RA pathogenesis and may be considered as potential markers of RA.

Increased Circulating H3 Histone in Response to Repeated Bouts of Exercise Does Not Associate with Parallel Alterations of Cell-Free DNA.

Numerous studies have shown that cf nDNA significantly rises in stress caused by exercise. However, during nuclear decondensation, released DNA is followed by histones. Histones are also a common disease marker. After PAD4 mediated hypercitrullination extracellular H3Cit exhibits high toxicity contributing to tissue damage which, in cases of systemic inflammation, may lead to multiorgan failure and finally to death. We tested whether circulating histones rise in response to strenuous exercise. Eleven average-trained men performed three treadmill exercise tests to exhaustion at speed corresponding to 70% VO2max separated by 72 h of resting. Blood was collected before and just after each bout of exercise and plasma proteins were measured using enzyme-linked immunosorbent assay, whereas platelet activity was estimated with Light Transmission Aggregometry. Both, circulating histones and PAD4 raised in response to exercise. Plasma citrullinated histones increased from 3.1 ng/mL to 5.96 ng/mL (p = 0.0059), from 3.65 ng/mL to 6.37 ng/mL (p = 0.02), and from 3.86 ng/mL to 4.75 ng/mL (p = 0.033) after the first, second, and third treadmill run, respectively. However despite the parallel increase, no significant correlation between citrullinated histone and aggregation or cell-free nDNA was found. Furthermore, positive correlations of cf nDNA with aggregation and PAD4, lactate with aggregation, and lactate with citrullinated histone have been observed.

Circulating cell free DNA response to exhaustive exercise in average trained men with type I diabetes mellitus.

It is believed that neutrophils extracellular traps (NETs) formation is responsible for the increase in cf DNA after exercise. Since T1DM is accompanied by enhanced NETs generation, we compared exercise-induced increase in cf DNA in 14 men with T1DM and 11 healthy controls and analyzed its association with exercise load. Subjects performed a treadmill run to exhaustion at speed corresponding to 70% of their personal VO2max. Blood was collected before and just after exercise for determination of plasma cf nuclear and mitochondrial DNA (cf n-DNA, cf mt-DNA) by real-time PCR, blood cell count and metabolic markers. Exercise resulted in the increase in median cf n-DNA from 3.9 ng/mL to 21.0 ng/mL in T1DM group and from 3.3 ng/mL to 28.9 ng/mL in controls. Median exercise-induced increment (∆) in cf n-DNA did not differ significantly in both groups (17.8 ng/mL vs. 22.1 ng/mL, p = 0.23), but this variable correlated with run distance (r = 0.66), Δ neutrophils (r = 0.86), Δ creatinine (r = 0.65) and Δ creatine kinase (r = 0.77) only in controls. Pre- and post-exercise cf mt-DNA were not significantly different within and between groups. These suggest low usefulness of Δ cf n-DNA as a marker of exercise intensity in T1DM men.

Author Correction: Decreased integrity of exercise-induced plasma cell free nuclear DNA - negative association with the increased oxidants production by circulating phagocytes.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Decreased integrity of exercise-induced plasma cell free nuclear DNA - negative association with the increased oxidants production by circulating phagocytes.

Strenuous exercise increases circulating cell free DNA (cfDNA) and stimulates blood phagocytes to generate reactive oxygen species (ROS) which may induce DNA strand breaks. We tested whether: (A) elevated cfDNA in response to three repeated bouts of exhaustive exercise has decreased integrity; (B) each bout of exercise increases luminol enhanced whole blood chemiluminescence (LBCL) as a measure of ROS production by polymorphonuclear leukocytes. Eleven men performed three treadmill exercise tests to exhaustion separated by 72 hours of resting. Pre- and post-exercise concentrations and integrity of cf nuclear and mitochondrial DNA (cf n-DNA, cf mt-DNA) and resting (r) and fMLP (n-formyl-methionyl-leucyl-phenylalanine)-stimulated LBCL were determined. Each bout increased concentrations of cf n-DNA by more than 10-times which was accompanied by about 2-times elevated post-exercise rLBCL and fMLP-LBCL. Post-exercise cf n-DNA integrity (integrity index, I229/97) decreased after the first (0.59 ± 0.19 vs. 0.48 ± 0.18) and second (0.53 ± 0.14 vs. 0.44 ± 0.17) bout of exercise. There were negative correlations between I229/97 and rLBCL (ƍ = -0.37), and I229/97 and fMLP-LBCL (ƍ = -0.40) - analysis of pooled pre- and post-exercise data (n = 66). cf mt- DNA integrity (I218/78) did not alter in response to exercise. This suggests an involvement of phagocyte ROS in cf n-DNA strand breaks in response to exhaustive exercise.

Repeated bouts of exhaustive exercise increase circulating cell free nuclear and mitochondrial DNA without development of tolerance in healthy men.

OBJECTIVE: Acute single strenuous exercise increases circulating cell free DNA (cf DNA). We tested whether three repeated bouts of exhaustive exercise induced the cf DNA response without development of tolerance in healthy men. METHODS: Eleven average-trained men (age 34.0±5.2 years, body mass index 26.2±3.1 kg/m2, maximal oxygen consumption-VO2max 49.6±4.5 ml/kg*min) performed three treadmill exercise tests to exhaustion at speed corresponding to 70% VO2max separated by 72 hours of resting. Blood was collected before and after each bout of exercise for determination of cell free nuclear and mitochondrial DNA (cf n-DNA, cf mt-DNA) by real-time PCR, selected markers of muscle damage, and blood cell count. RESULTS: Each bout induced the increase (p<0.05) in plasma cf n-DNA: from 3.4±1.4 to 38.5±27.5, from 4.1±3.3 to 48.5±26.2, and 3.1±1.6 to 53.8±39.9 ng/mL after the first, second, and third exercise, respectively. In a congruent way, cf mt-DNA rose significantly after the second (from 229±216 to 450±228*103 GE/mL) and third bout of exercise (from 173±120 to 462±314*103 GE/mL). Pre-exercise cf mt-DNA decreased (p<0.05) by 2-times (from 355±219 before the first bout to 173±120*103 GE/mL before the third bout) over the study period and were accompanied by significant increase in white blood cells, platelets, creatine kinase, creatinine and lactate after each bout. However, the exercise induced percentage increment of cf n-DNA was always many times higher than corresponding increments of the afore-mentioned markers at any occasion. CONCLUSIONS: Repeated bouts of exhaustive exercise induced remarkable increase in circulating cf n-DNA without signs of tolerance development. Baseline cf mt-DNA decreased in response to series of strenuous exercise. Since percentage increments of cf n-DNA in response to exercise were many times higher than those observed for other markers, measurement of circulating cf n-DNA could be a sensitive tool for monitoring acute exercise effects in human body.