Volcano plot (statistics)
Imagine you're drawing a picture of a mountain with an active volcano on top. But instead of using colors, you're using numbers to show how important different things are.
On the bottom of your paper, you have a list of all the things you're measuring. Maybe these are genes or proteins or chemicals. Each one has a number that tells you how different it is in two different groups. For example, you might have a group of healthy people and a group of sick people, and you want to see which genes are more active in one group than the other.
To draw your volcano plot, you'll need to do two things with each item on your list. First, you'll need to figure out how different it is between the two groups. This is called the "fold change." If something has a fold change of 1, it's the same in both groups. If it has a fold change of 2, it's twice as much in one group as the other.
Second, you'll need to figure out how certain you are that the difference is real. This is called the "p-value." If the p-value is very small, it means you're pretty sure there's a real difference. If it's bigger, it means there's a chance it could just be random chance.
Now you're ready to draw your volcano plot. First, draw a line at a fold change of 1, which is the same in both groups. Then, draw a line at a p-value of 0.05, which is a common threshold for saying something is statistically significant (meaning you're pretty sure it's real).
Now, for each item on your list, put a dot on the graph. The x-axis is the fold change (whether it's higher or lower in one group), and the y-axis is the negative log of the p-value (how certain you are there's a real difference). So if something has a really small p-value, it will be high up on the y-axis, and if it has a big fold change it will be far to the left or right on the x-axis.
Now you can see which items are "hot spots" on your volcano plot - these are the things with both a big fold change and a small p-value. They're like the top of the volcano where all the action is happening!
On the bottom of your paper, you have a list of all the things you're measuring. Maybe these are genes or proteins or chemicals. Each one has a number that tells you how different it is in two different groups. For example, you might have a group of healthy people and a group of sick people, and you want to see which genes are more active in one group than the other.
To draw your volcano plot, you'll need to do two things with each item on your list. First, you'll need to figure out how different it is between the two groups. This is called the "fold change." If something has a fold change of 1, it's the same in both groups. If it has a fold change of 2, it's twice as much in one group as the other.
Second, you'll need to figure out how certain you are that the difference is real. This is called the "p-value." If the p-value is very small, it means you're pretty sure there's a real difference. If it's bigger, it means there's a chance it could just be random chance.
Now you're ready to draw your volcano plot. First, draw a line at a fold change of 1, which is the same in both groups. Then, draw a line at a p-value of 0.05, which is a common threshold for saying something is statistically significant (meaning you're pretty sure it's real).
Now, for each item on your list, put a dot on the graph. The x-axis is the fold change (whether it's higher or lower in one group), and the y-axis is the negative log of the p-value (how certain you are there's a real difference). So if something has a really small p-value, it will be high up on the y-axis, and if it has a big fold change it will be far to the left or right on the x-axis.
Now you can see which items are "hot spots" on your volcano plot - these are the things with both a big fold change and a small p-value. They're like the top of the volcano where all the action is happening!