Of Mice and Mates: Automated Classification and Modelling of Mouse Behaviour in Groups Using a Single Model Across Cages

Abstract

Behavioural experiments often happen in specialised arenas, but this may confound the analysis. To address this issue, we provide tools to study mice in the home-cage environment, equipping biologists with the possibility to capture the temporal aspect of the individual's behaviour and model the interaction and interdependence between cage-mates with minimal human intervention. Our main contribution is the novel Global Behaviour Model (GBM) which summarises the joint behaviour of groups of mice across cages, using a permutation matrix to match the mouse identities in each cage to the model. In support of the above, we also (a) developed the Activity Labelling Module (ALM) to automatically classify mouse behaviour from video, and (b) released two datasets, ABODe for training behaviour classifiers and IMADGE for modelling behaviour.

Supplementary information: The online version contains supplementary material available at 10.1007/s11263-024-02118-3.

Keywords: Automated behaviour classification; Home-cage analysis; Joint behaviour model; Mouse behaviour data; Mouse behaviour model.

Fig. 1

An example video frame from our data, showing the raw video (left) and an enhanced visual (right) using CLAHE (Zuiderveld, 1994). In the latter, the hopper is marked in yellow and the water spout in purple, while the (RFID) mouse positions are projected into image space and overlaid as red, green and blue dots

Fig. 2

The ALM for classifying observability and behaviour per mouse. The input signal comes from three modalities: i coarse position (RFID), ii identified BBoxes (using the TIM as implemented in (Camilleri et al., 2023)) and iii video frames. An OC iv determines whether the mouse is observable and its behaviour can be classified. If this is the case, then the BC v is activated to generate a probability distribution over behaviours for the mouse. Further architectural details appear in the text

Fig. 3

Graphical representation of our GBM. ‘$\times$’ refers to standard matrix multiplication. To reduce clutter, the model is not shown unrolled in time

Fig. 4

ROC curves for various architectures of the OC evaluated on the Validation split. Each coloured line shows the TP rate against the FP rate for various operating thresholds: the ‘default’ 0.5 threshold in each case is marked with a cross ‘$\times$’. The baseline (worst-case) model is shown as a dotted line

Fig. 5

Behaviour confusion matrix of the End-to-End model as a Hinton plot. The area of each square represents the numerical value, and each row is normalized to sum to 1

Fig. 6

Normalised log-likelihood ($\widehat{\mathcal{L}}$) of the GBM for various dimensionalities of the latent state over all cages

Fig. 7

Posterior probability of the GBM over Q for all cages ($|Z|=7$, model trained on cage L)

Fig. 8

RDLs from Table 6, printed on the number line: the lowest scoring cages are marked

Fig. 9

Parameters for the GBM with $|Z|=7$ trained on Adult mice. For $\mathrm{\Omega }$ (leftmost panel) we show the transition probabilities: underneath the $Z^{[t+1]}$ labels, we also report the steady-state probabilities (first row) and the expected dwell times (in BTIs, second row). The other three panels show the emission probabilities ${\mathrm{\Psi }}_k$ for each mouse as Hinton plots. We omit zeros before the decimal point and suppress values close to 0 (at the chosen precision)

Fig. 10

Ethogram for the regime (GBM $|Z|=7$) and individual behaviour probabilities for a run from cage B. In all but the light status, darker colours signify higher probability: the hue is purple for Z and matches the assignment of mice to variables $X_k$ otherwise. The light-status is indicated by white for lights-on and black for lights-off. Missing data is indicated by grey bars

Fig. 11

Parameters for the per-cage models ($|Z|=7$) for cages D, F and L. The order of the latent states is permuted to maximise the similarity with the global model (using the Hungarian algorithm) for easier comparison. The plot follows the arrangement in Fig. 9

Fig. 12

$\widehat{\mathcal{L}}$ scores (x-axis) of the GBM on each cage (y-axis, left) in the adult/young age groups, together with the accuracy of a binary threshold on the $\widehat{\mathcal{L}}$ (scale on the right)

Fig. 13

$\widehat{\mathcal{L}}$ as a function of $|Z|\in \{2,3,...,7\}$, with each cage as initialiser. The average (per |Z|) is shown as a blue cross

Fig. 14

GBM parameters on the Young mice data for $|Z|=6$. Arrangement is as in Fig. 9