Tailored treatments for metastatic colorectal cancer (mCRC) have not yet completely evolved due to the variety in response to drugs. Therefore, artificial intelligence has been recently used to develop prognostic and predictive models of treatment response (either activity/efficacy or toxicity) to aid in clinical decision making. In this systematic review, we have examined the ability of learning methods to predict response to chemotherapy alone or combined with targeted therapy in mCRC patients by targeting specific narrative publications in Medline up to April 2022 to identify appropriate original scientific articles. After the literature search, 26 original articles met inclusion and exclusion criteria and were included in the study. Our results show that all investigations conducted on this field have provided generally promising results in predicting the response to therapy or toxic side-effects. By a meta-analytic approach we found that the overall weighted means of the area under the receiver operating characteristic (ROC) curve (AUC) were 0.90, 95% C.I. 0.80–0.95 and 0.83, 95% C.I. 0.74–0.89 in training and validation sets, respectively, indicating a good classification performance in discriminating response vs. non-response. The calculation of overall HR indicates that learning models have strong ability to predict improved survival. Lastly, the delta-radiomics and the 74 gene signatures were able to discriminate response vs. non-response by correctly identifying up to 99% of mCRC patients who were responders and up to 100% of patients who were non-responders. Specifically, when we evaluated the predictive models with tests reaching 80% sensitivity (SE) and 90% specificity (SP), the delta radiomics showed an SE of 99% and an SP of 94% in the training set and an SE of 85% and SP of 92 in the test set, whereas for the 74 gene signatures the SE was 97.6% and the SP 100% in the training set.

Studies have indicated that air pollution, including surface-level ozone (O₃), can significantly influence the risk of chronic diseases. To better understand the carcinogenic mechanisms of air pollutants and identify predictive disease biomarkers, we examined the association between traffic-related pollutants with DNA methylation alterations and bulky DNA adducts, two biomarkers of carcinogen exposure and cancer risk, in the peripheral blood of 140 volunteers—95 traffic police officers, and 45 unexposed subjects. The DNA methylation and adduct measurements were performed by bisulfite-PCR and pyrosequencing and ³²P-postlabeling assay. Airborne levels of benzo(a)pyrene [B(a)P], carbon monoxide, and tropospheric O₃ were determined by personal exposure biomonitoring or by fixed monitoring stations. Overall, air pollution exposure was associated with a significant reduction (1.41 units) in global DNA methylation (95% C.I. −2.65–0.04, p = 0.026). The decrement in ALU repetitive elements was greatest in the policemen working downtown (95% C.I. −3.23–−0.49, p = 0.008). The DNA adducts were found to be significantly increased (0.45 units) in the municipal officers with respect to unexposed subjects (95% C.I. 0.02–0.88, p = 0.039), mainly in those who were controlling traffic in downtown areas (95% C.I. 0.39–1.29, p < 0.001). Regression models indicated an increment of ALU methylation at higher B(a)P concentrations (95% C.I. 0.03–0.60, p = 0.032). Moreover, statistical models showed a decrement in ALU methylation and an increment of DNA damage only above the cut-off value of 30 µg/m³ O₃. A significant increment of 0.73 units of IL-6 gene methylation was also found in smokers with respect to non-smokers. Our results highlighted the role of air pollution on epigenetic alterations and genotoxic effects, especially above the target value of 30 µg/m³ surface-level O₃, supporting the necessity for developing public health strategies aimed to reduce traffic-related air pollution molecular alterations.

Molecular mechanisms underlying Hepatitis C virus (HCV)-associated hepatocellular carcinoma (HCC) pathogenesis are still unclear. Therefore, we analyzed the levels of 8-oxo-7,8-dihydro-2′-deoxyguanosine (8-oxodG) and other oxidative lesions at codon 176 of the p53 gene, as well as the generation of 3-(2-deoxy-β-d-erythro-pentafuranosyl)pyrimido[1,2-α]purin-10(3H)-one deoxyguanosine (M₁dG), in a cohort of HCV-related HCC patients from Italy. Detection of 8-oxodG and 5-hydroxycytosine (5-OHC) was performed by ligation mediated-polymerase chain reaction assay, whereas the levels of M₁dG were measured by chromatography and mass-spectrometry. Results indicated a significant 130% excess of 8-oxodG at –TGC– position of p53 codon 176 in HCV-HCC cases as compared to controls, after correction for age and gender, whereas a not significant increment of 5-OHC at –TGC– position was found. Then, regression models showed an 87% significant excess of M₁dG in HCV-HCC cases relative to controls. Our study provides evidence that increased adduct binding does not occur randomly on the sequence of the p53 gene but at specific sequence context in HCV-HCC patients. By-products of lipid peroxidation could also yield a role in HCV-HCC development. Results emphasize the importance of active oxygen species in inducing nucleotide lesions at a p53 mutational hotspot in HCV-HCC patients living in geographical areas without dietary exposure to aflatoxin B₁.

Epidemiologic studies have indicated that cruciferous vegetables can influence the cancer risk; therefore, we examined with a cross-sectional approach the correlation between the frequent consumption of the total cruciferous vegetables and the formation of bulky DNA damage, a biomarker of carcinogen exposure and cancer risk, in the Gen-Air study within the European Prospective Investigation into Cancer and Nutrition (EPIC) cohort. DNA damage measurements were performed in the peripheral blood of 696 of those apparently healthy without cancer controls, including 379 never-smokers and 317 former smokers from seven European countries by the ³²P-postlabeling assay. In the Gen-Air controls, the median intake of cruciferous vegetables was 6.16 (IQR 1.16–13.66) g/day, ranging from 0.37 (IQR 0–6.00) g/day in Spain to 11.34 (IQR 6.02–16.07) g/day in the UK. Based on this information, participants were grouped into: (a) high consumers (>20 g/day), (b) medium consumers (3–20 g/day) and (c) low consumers (<3.0 g/day). Overall, low cruciferous vegetable intake was correlated with a greater frequency of bulky DNA lesions, including benzo(a)pyrene, lactone and quinone-adducts and bulky oxidative lesions, in the adjusted models. Conversely, a high versus low intake of cruciferous vegetables was associated with a reduction in DNA damage (up to a 23% change, p = 0.032); this was particularly evident in former smokers (up to a 40% change, p = 0.008). The Generalized Linear Regression models indicated an overall Mean Ratio between the high and the low consumers of 0.78 (95% confidence interval, 0.64–0.97). The current study suggests that a higher intake of cruciferous vegetables is associated with a lower level of bulky DNA adducts and supports the potential for cancer prevention strategies through dietary habit changes aimed at increasing the consumption of cruciferous vegetables.