Skip to main content
Fig. 4 | BMC Medical Genomics

Fig. 4

From: A novel proteomic-based model for predicting colorectal cancer with Schistosoma japonicum co‐infection by integrated bioinformatics analysis and machine learning

Fig. 4

Screening genes that are correlated with the outcome variable from DEPs through LASSO regression analysis, providing a foundation for subsequent modeling. (A) Protein coefficient distribution plot. The different color lines represent the coefficient distribution curves of 13 proteins. The horizontal axis represents the Lambda value, the two dashed lines in the Fig indicate the variable and Lambda corresponding to the minimum fitting error on the left, and one standard deviation of the minimum fitting error of Lambda on the right. The y-axis represents the coefficients of the different variables. (B) Error Curve. The red line represents deviation curve of 13 proteins. The abscissa represents Lambda value. The ordinate represents the fitting error (C-O). LASSO regression evaluation results. The horizontal axis represents group information, and the vertical axis represents predicted values. The red box plot represents the group of CRC, while the blue box plot represents the group CRC combined with S. japonicum infection. The parameters that minimize the error were selected as the LASSO regression results for this analysis

Back to article page