Mendelian randomization (MR) is a method used to infer causality between an exposure and an outcome using genetic variants as instrumental variables (IVs). However, some genetic variants may not be valid IVs due to pleiotropy, where they affect the outcome through pathways other than the exposure. This paper introduces MR-Egger regression, an adaptation of Egger regression used in meta-analysis, to detect and correct for bias caused by pleiotropy in MR studies. MR-Egger regression treats multiple IVs as a meta-analysis, where the causal effect is estimated as a weighted average of individual IV estimates. Pleiotropy-induced bias is analogous to small study bias in meta-analysis, where smaller studies with less precise estimates tend to report larger effects. MR-Egger regression can detect this bias by estimating the slope of a regression line, which provides a consistent causal effect estimate even when all IVs are invalid. The intercept of the regression line indicates the average pleiotropic effect across the genetic variants. The paper illustrates the use of MR-Egger regression by re-analyzing two published MR studies: one on the causal effect of height on lung function and another on the causal effect of blood pressure on coronary artery disease risk. The results show that MR-Egger regression provides a more robust estimate of the causal effect compared to traditional two-stage least squares (TSLS) methods, especially in the presence of pleiotropy. The study also discusses the limitations of MR-Egger regression, including the assumption that the direct pleiotropic effects of genetic variants on the outcome are independent of their associations with the exposure (the InSIDE assumption). Violations of this assumption can lead to biased estimates. Additionally, the paper highlights the importance of using summary data and the potential for weak instrument bias in MR studies. Overall, MR-Egger regression offers a valuable tool for detecting and correcting for pleiotropy in MR studies, providing a sensitivity analysis to assess the robustness of causal inferences. It is particularly useful when the standard IV assumptions are not met, as it allows for more reliable causal effect estimates even in the presence of pleiotropy.Mendelian randomization (MR) is a method used to infer causality between an exposure and an outcome using genetic variants as instrumental variables (IVs). However, some genetic variants may not be valid IVs due to pleiotropy, where they affect the outcome through pathways other than the exposure. This paper introduces MR-Egger regression, an adaptation of Egger regression used in meta-analysis, to detect and correct for bias caused by pleiotropy in MR studies. MR-Egger regression treats multiple IVs as a meta-analysis, where the causal effect is estimated as a weighted average of individual IV estimates. Pleiotropy-induced bias is analogous to small study bias in meta-analysis, where smaller studies with less precise estimates tend to report larger effects. MR-Egger regression can detect this bias by estimating the slope of a regression line, which provides a consistent causal effect estimate even when all IVs are invalid. The intercept of the regression line indicates the average pleiotropic effect across the genetic variants. The paper illustrates the use of MR-Egger regression by re-analyzing two published MR studies: one on the causal effect of height on lung function and another on the causal effect of blood pressure on coronary artery disease risk. The results show that MR-Egger regression provides a more robust estimate of the causal effect compared to traditional two-stage least squares (TSLS) methods, especially in the presence of pleiotropy. The study also discusses the limitations of MR-Egger regression, including the assumption that the direct pleiotropic effects of genetic variants on the outcome are independent of their associations with the exposure (the InSIDE assumption). Violations of this assumption can lead to biased estimates. Additionally, the paper highlights the importance of using summary data and the potential for weak instrument bias in MR studies. Overall, MR-Egger regression offers a valuable tool for detecting and correcting for pleiotropy in MR studies, providing a sensitivity analysis to assess the robustness of causal inferences. It is particularly useful when the standard IV assumptions are not met, as it allows for more reliable causal effect estimates even in the presence of pleiotropy.