Source Paper
High-fat diet disrupts a septal control on feeding to promote obesity in male mice
Jiang S, Lai S, Jing H, Wu X, Li F et al.
Nat Commun • 2025
Population decoding analysis of food consumption
Objective: To assess whether trial types (chow vs. HFD consumption) could be predicted from trial-by-trial population activities of LS GABA neurons during consumption epochs using machine learning classification
Gather these items before starting the experiment. Check off items as you prepare.
As an Amazon Associate, we earn from qualifying purchases. Product links help support this free resource.
Protocol Steps
Viral injection and imaging preparation
Inject AAV2/9-hEF1a-DIO-GCaMP6s into LS and implant GRIN lens with baseplate for miniscope
View evidence from paper
“After 4-6 weeks of GCaMP6s injection, a baseplate that matched the miniscope (UCLA Miniscope V4, Open Ephys) was fixed”
Adaptive training
Train mice for imaging sessions
View evidence from paper
“Before imaging sessions, mice received 10-minute adaptive training for at least 3 days”
Calcium imaging during food consumption
Record calcium signals while mice consume food pellets
View evidence from paper
“we randomly placed a food pellet for each freely moving mouse in turn, and simultaneously recorded video of the process whereby the mouse ate the food. There were at least 10 food intake periods”
Data acquisition
Acquire imaging data at specified frame rate
View evidence from paper
“Imaging data were acquired at a 30-Hz frame rate and collected using UCLA Miniscope-DAQ-DT-Software”
Signal processing
Extract motion-corrected fluorescence dynamics from individual neurons
View evidence from paper
“Calcium signal processing was performed using CNMF-E software to extract motion-corrected GCaMP6s fluorescence dynamics from individual neurons”
Data normalization
Z-score normalize neuronal activities across trials
View evidence from paper
“First, neuronal activities were z-scored across trials to normalize the data”
Dimensionality reduction
Apply PCA to reduce data dimensions
View evidence from paper
“Principal component analysis (PCA) was then applied to the matrix of z-scored trial-by-trial activities, and the first two principal components (PCs) were retained”
Data splitting
Split dataset into training and test sets
View evidence from paper
“the dataset was split such that a randomly selected subset comprising 75% of trials from each food type (chow and HFD) served as the training set, while the remaining 25% constituted the test set”
Classifier training
Train linear SVM classifier for two-class decoding
View evidence from paper
“Using the low-dimensional PC data from the training set, a linear-kernel SVM classifier ('linear') was trained for two-class decoding (chow vs. HFD trials)”
Classification testing
Validate classifier on test set
View evidence from paper
“The trained classifier was then validated using the 'predict' function to classify the trial-by-trial activities in the test set”
Control analysis
Generate shuffled datasets with randomly reassigned labels
View evidence from paper
“For control purposes, shuffled datasets were generated by randomly reassigning trial-type labels (chow or HFD) to the neuronal activities”
Statistical validation
Repeat classification process multiple times for robustness
View evidence from paper
“To ensure robustness, the entire classification process—including random train/test splitting, classifier training, testing, and shuffling—was repeated 1000 times”