Quantifying ultrasonic mouse vocalizations using acoustic analysis in a supervised statistical machine learning framework

Differential Encoding of Two-Tone Harmonics in the Male and Female Mouse Auditory Cortex

Harmonics are an integral part of music, speech, and vocalizations of animals. Since the rest of the auditory environment is primarily made up of nonharmonic sounds, the auditory system needs to perceptually separate the above two kinds of sounds. In mice, harmonics, generally with two-tone components (two-tone harmonic complexes, TTHCs), form an important component of vocal communication. Communication by pups during isolation from the mother and by adult males during courtship elicits typical behaviors in female mice-dams and adult courting females, respectively. Our study shows that the processing of TTHC is specialized in mice providing neural basis for perceptual differences between tones and TTHCs and also nonharmonic sounds. Investigation of responses in the primary auditory cortex (Au1) from in vivo extracellular recordings and two-photon Ca2+ imaging of excitatory and inhibitory neurons to TTHCs exhibit enhancement, suppression, or no-effect with respect to tones. Irrespective of neuron type, harmonic enhancement is maximized, and suppression is minimized when the fundamental frequencies (F 0) match the neuron's best fundamental frequency (BF0). Sex-specific processing of TTHC is evident from differences in the distributions of neurons' best frequency (BF) and best fundamental frequency (BF0) in single units, differences in harmonic suppressed cases re-BF0, independent of neuron types, and from pairwise noise correlations among excitatory and parvalbumin inhibitory interneurons. Furthermore, TTHCs elicit a higher response compared with two-tone nonharmonics in females, but not in males. Thus, our study shows specialized neural processing of TTHCs over tones and nonharmonics, highlighting local network specialization among different neuronal types.

Rodent tests of depression and anxiety: Construct validity and translational relevance

Behavioral testing constitutes the primary method to measure the emotional states of nonhuman animals in preclinical research. Emerging as the characteristic tool of the behaviorist school of psychology, behavioral testing of animals, particularly rodents, is employed to understand the complex cognitive and affective symptoms of neuropsychiatric disorders. Following the symptom-based diagnosis model of the DSM, rodent models and tests of depression and anxiety focus on behavioral patterns that resemble the superficial symptoms of these disorders. While these practices provided researchers with a platform to screen novel antidepressant and anxiolytic drug candidates, their construct validity-involving relevant underlying mechanisms-has been questioned. In this review, we present the laboratory procedures used to assess depressive- and anxiety-like behaviors in rats and mice. These include constructs that rely on stress-triggered responses, such as behavioral despair, and those that emerge with nonaversive training, such as cognitive bias. We describe the specific behavioral tests that are used to assess these constructs and discuss the criticisms on their theoretical background. We review specific concerns about the construct validity and translational relevance of individual behavioral tests, outline the limitations of the traditional, symptom-based interpretation, and introduce novel, ethologically relevant frameworks that emphasize simple behavioral patterns. Finally, we explore behavioral monitoring and morphological analysis methods that can be integrated into behavioral testing and discuss how they can enhance the construct validity of these tests.

Paternal immune activation by Poly I:C modulates sperm noncoding RNA profiles and causes transgenerational changes in offspring behavior

Paternal pre-conceptual environmental experiences, such as stress and diet, can affect offspring brain and behavioral phenotypes via epigenetic modifications in sperm. Furthermore, maternal immune activation due to infection during gestation can reprogram offspring behavior and brain functioning in adulthood. However, the effects of paternal pre-conceptual exposure to immune activation on the behavior and physiology of offspring (F1) and grand-offspring (F2) are not currently known. We explored effects of paternal pre-conceptual exposure to viral-like immune activation on F1 and F2 behavioral and physiological phenotypes using a C57BL/6J mouse model. Males were treated with a single injection (intraperitoneal) of the viral mimetic polyinosinic:polycytidylic acid (Poly I:C: 12 mg/kg) then bred with naïve female mice four weeks after the Poly I:C (or 0.9% saline control) injection. The F1 offspring of Poly I:C treated fathers displayed increased depression-like behavior in the Porsolt swim test, an altered stress response in the novelty-suppressed feeding test, and significant transcriptomic changes in their hippocampus. Additionally, the F1 male offspring of Poly I:C treated F0 males showed significantly increased immune responsivity after a Poly I:C immune challenge (12 mg/kg). Furthermore, the F2 male grand-offspring took longer to enter and travelled significantly shorter distances in the light zone of the light/dark box. An analysis of the small noncoding RNA profiles in sperm from Poly I:C treated males and their male offspring revealed significant effects of Poly I:C on the sperm microRNA content at the time of conception and on the sperm PIWI-interacting RNA content of the male offspring. Notably, eight miRNAs with an FDR < 0.05 (miR-141-3p, miR-126b-5p, miR-669o-5p, miR-10b-3p, miR-471-5p, miR-463-5p, miR-148b-3p, and miR-181c-5p) were found to be significantly downregulated in the sperm of Poly I:C treated males. Collectively, we demonstrate that paternal pre-conceptual exposure to a viral immune challenge results in both intergenerational and transgenerational effects on brain and behavior that may be mediated by alterations in the sperm small noncoding RNA content.

Stuttering associated with a pathogenic variant in the chaperone protein cyclophilin 40

Stuttering is a common speech disorder that interrupts speech fluency and tends to cluster in families. Typically, stuttering is characterized by speech sounds, words or syllables which may be repeated or prolonged and speech that may be further interrupted by hesitations or 'blocks'. Rare variants in a small number of genes encoding lysosomal pathway proteins have been linked to stuttering. We studied a large four-generation family in which persistent stuttering was inherited in an autosomal dominant manner with disruption of the cortico-basal-ganglia-thalamo-cortical network found on imaging. Exome sequencing of three affected family members revealed the PPID c.808C>T (p.Pro270Ser) variant that segregated with stuttering in the family. We generated a Ppid p.Pro270Ser knock-in mouse model and performed ex vivo imaging to assess for brain changes. Diffusion-weighted MRI in the mouse revealed significant microstructural changes in the left corticospinal tract, as previously implicated in stuttering. Quantitative susceptibility mapping also detected changes in cortico-striatal-thalamo-cortical loop tissue composition, consistent with findings in affected family members. This is the first report to implicate a chaperone protein in the pathogenesis of stuttering. The humanized Ppid murine model recapitulates network findings observed in affected family members.

Early-life stressful social experience (SSE) alters ultrasound vocalizations and impairs novel odor preference: Influence of histone dopaminylation

BACKGROUND AND AIM

Rat pups emit ultrasound vocalizations (USVs) in response to negative/positive stimuli, the acoustic features of USVs are altered during the stressful and threatening situation. We hypothesize that maternal separation (MS) and/or stranger (St) exposure would alter acoustic features of USVs, neurotransmitter transmission, epigenetic status and impaired odor recognition later in life.

METHOD

Rat pups were left undisturbed in the home cage (a) control, (b) pups were separated from mother MS [postnatal day (PND) 5-10], (c) intrusion of stranger (St; social experience: SE) to the pups either in the presence of mother (M + P + St) or (d) absence of mother (MSP + St). USVs was recorded on PND10 in two context i) five minutes after MS, MS and St, mother with their pups and St, ii) five minutes after the pups reunited with their pups and/or removal of stranger. Novel odor preference test was conducted during their mid-adolescence on PND34, 35.

RESULTS

Rat pups produced two complex USVs (frequency step-down: 38-48 kHz; and two syllable: 42-52 kHz) especially when the mother was absent and the stranger was present. Further, pups failed to recognize novel odor, which can be linked to an increased dopamine transmission, decreased transglutaminase (TGM)-2, increased histone trimethylation (H3K4me3) and dopaminylation (H3Q5dop) in the amygdala.

CONCLUSIONS

This result suggest that USVs act as acoustic code of different early-life stressful social experience, which appears to have long-term effect on odor recognition, dopaminergic activity and dopamine dependent epigenetic status.

Extended performance analysis of deep-learning algorithms for mice vocalization segmentation

Ultrasonic vocalizations (USVs) analysis represents a fundamental tool to study animal communication. It can be used to perform a behavioral investigation of mice for ethological studies and in the field of neuroscience and neuropharmacology. The USVs are usually recorded with a microphone sensitive to ultrasound frequencies and then processed by specific software, which help the operator to identify and characterize different families of calls. Recently, many automated systems have been proposed for automatically performing both the detection and the classification of the USVs. Of course, the USV segmentation represents the crucial step for the general framework, since the quality of the call processing strictly depends on how accurately the call itself has been previously detected. In this paper, we investigate the performance of three supervised deep learning methods for automated USV segmentation: an Auto-Encoder Neural Network (AE), a U-NET Neural Network (UNET) and a Recurrent Neural Network (RNN). The proposed models receive as input the spectrogram associated with the recorded audio track and return as output the regions in which the USV calls have been detected. To evaluate the performance of the models, we have built a dataset by recording several audio tracks and manually segmenting the corresponding USV spectrograms generated with the Avisoft software, producing in this way the ground-truth (GT) used for training. All three proposed architectures demonstrated precision and recall scores exceeding [Formula: see text], with UNET and AE achieving values above [Formula: see text], surpassing other state-of-the-art methods that were considered for comparison in this study. Additionally, the evaluation was extended to an external dataset, where UNET once again exhibited the highest performance. We suggest that our experimental results may represent a valuable benchmark for future works.

Prenatal low-dose methylmercury exposure causes premature neuronal differentiation and autism-like behaviors in a rodent model

Aberrant neurodevelopment is a core deficit of autism spectrum disorder (ASD). Here we ask whether a non-genetic factor, prenatal exposure to the environmental pollutant methylmercury (MeHg), is a contributing factor in ASD onset. We showed that adult mice prenatally exposed to non-apoptotic MeHg exhibited key ASD characteristics, including impaired communication, reduced sociability, and increased restrictive repetitive behaviors, whereas in the embryonic cortex, prenatal MeHg exposure caused premature neuronal differentiation. Further single-cell RNA sequencing (scRNA-seq) analysis disclosed that prenatal exposure to MeHg resulted in cortical radial glial precursors (RGPs) favoring asymmetric differentiation to directly generate cortical neurons, omitting the intermediate progenitor stage. In addition, MeHg exposure in cultured RGPs increased CREB phosphorylation and enhanced the interaction between CREB and CREB binding protein (CBP). Intriguingly, metformin, an FDA-approved drug, can reverse MeHg-induced premature neuronal differentiation via CREB/CBP repulsion. These findings provide insights into ASD etiology, its underlying mechanism, and a potential therapeutic strategy.

BAMBI: A new method for automated assessment of bidirectional early-life interaction between maternal behavior and pup vocalization in mouse dam-pup dyads

Vital early-life dyadic interaction in mice requires a pup to signal its needs adequately, and a dam to recognize and respond to the pup's cues accurately and timely. Previous research might have missed important biological and/or environmental elements of this complex bidirectional interaction, because it often focused on one dyadic member only. In laboratory rodents, the Pup Retrieval Test (PRT) is the leading procedure to assess pup-directed maternal care. The present study describes BAMBI (Bidirectional Automated Mother-pup Behavioral Interaction test), a novel automated PRT methodology based on synchronous video recording of maternal behavior and audio recording of pup vocalizations, which allows to assess bidirectional dam-pup dyadic interaction. We were able to estimate pup retrieval and pup vocalization parameters accurately in 156 pups from 29 dams on postnatal days (PND) 5, 7, 9, 11, and 13. Moreover, we showed an association between number of emitted USVs and retrieval success, indicating dyadic interdependency and bidirectionality. BAMBI is a promising new automated home-cage behavioral method that can be applied to both basic and preclinical studies investigating complex phenotypes related to early-life social development.

Rates of ultrasonic vocalizations are more strongly related than acoustic features to non-vocal behaviors in mouse pups

Mouse pups produce. ultrasonic vocalizations (USVs) in response to isolation from the nest (i.e., isolation USVs). Rates and acoustic features of isolation USVs change dramatically over the first two weeks of life, and there is also substantial variability in the rates and acoustic features of isolation USVs at a given postnatal age. The factors that contribute to within age variability in isolation USVs remain largely unknown. Here, we explore the extent to which non-vocal behaviors of mouse pups relate to the within age variability in rates and acoustic features of their USVs. We recorded non-vocal behaviors of isolated C57BL/6J mouse pups at four postnatal ages (postnatal days 5, 10, 15, and 20), measured rates of isolation USV production, and applied a combination of pre-defined acoustic feature measurements and an unsupervised machine learning-based vocal analysis method to examine USV acoustic features. When we considered different categories of non-vocal behavior, our analyses revealed that mice in all postnatal age groups produce higher rates of isolation USVs during active non-vocal behaviors than when lying still. Moreover, rates of isolation USVs are correlated with the intensity (i.e., magnitude) of non-vocal body and limb movements within a given trial. In contrast, USVs produced during different categories of non-vocal behaviors and during different intensities of non-vocal movement do not differ substantially in their acoustic features. Our findings suggest that levels of behavioral arousal contribute to within age variability in rates, but not acoustic features, of mouse isolation USVs.

Automatic segmentation and classification of mice ultrasonic vocalizations

This paper addresses the development of a system for classifying mouse ultrasonic vocalizations (USVs) present in audio recordings. The automatic labeling process for USVs is usually divided into two main steps: USV segmentation followed by the matching classification. Three main contributions can be highlighted: (i) a new segmentation algorithm, (ii) a new set of features, and (iii) the discrimination of a higher number of classes when compared to similar studies. The developed segmentation algorithm is based on spectral entropy analysis. This novel segmentation approach can detect USVs with 94% and 74% recall and precision, respectively. When compared to other methods/software, our segmentation algorithm achieves a higher recall. Regarding the classification phase, besides the traditional features from time, frequency, and time-frequency domains, a new set of contour-based features were extracted and used as inputs of shallow machine learning classification models. The contour-based features were obtained from the time-frequency ridge representation of USVs. The classification methods can differentiate among ten different syllable types with 81.1% accuracy and 80.5% weighted F1-score. The algorithms were developed and evaluated based on a large dataset, acquired on diverse social interaction conditions between the animals, to stimulate a varied vocal repertoire.

Quantifying Sex Differences in Behavior in the Era of "Big" Data

Sex differences are commonly observed in behaviors that are closely linked to adaptive function, but sex differences can also be observed in behavioral "building blocks" such as locomotor activity and reward processing. Modern neuroscientific inquiry, in pursuit of generalizable principles of functioning across sexes, has often ignored these more subtle sex differences in behavioral building blocks that may result from differences in these behavioral building blocks. A frequent assumption is that there is a default (often male) way to perform a behavior. This approach misses fundamental drivers of individual variability within and between sexes. Incomplete behavioral descriptions of both sexes can lead to an overreliance on reduced "single-variable" readouts of complex behaviors, the design of which may be based on male-biased samples. Here, we advocate that the incorporation of new machine-learning tools for collecting and analyzing multimodal "big behavior" data allows for a more holistic and richer approach to the quantification of behavior in both sexes. These new tools make behavioral description more robust and replicable across laboratories and species, and may open up new lines of neuroscientific inquiry by facilitating the discovery of novel behavioral states. Having more accurate measures of behavioral diversity in males and females could serve as a hypothesis generator for where and when we should look in the brain for meaningful neural differences.

Relevance, redundancy, and complementarity trade-off (RRCT): A principled, generic, robust feature-selection tool

We present a new heuristic feature-selection (FS) algorithm that integrates in a principled algorithmic framework the three key FS components: relevance, redundancy, and complementarity. Thus, we call it relevance, redundancy, and complementarity trade-off (RRCT). The association strength between each feature and the response and between feature pairs is quantified via an information theoretic transformation of rank correlation coefficients, and the feature complementarity is quantified using partial correlation coefficients. We empirically benchmark the performance of RRCT against 19 FS algorithms across four synthetic and eight real-world datasets in indicative challenging settings evaluating the following: (1) matching the true feature set and (2) out-of-sample performance in binary and multi-class classification problems when presenting selected features into a random forest. RRCT is very competitive in both tasks, and we tentatively make suggestions on the generalizability and application of the best-performing FS algorithms across settings where they may operate effectively.

Capturing the songs of mice with an improved detection and classification method for ultrasonic vocalizations (BootSnap)

House mice communicate through ultrasonic vocalizations (USVs), which are above the range of human hearing (>20 kHz), and several automated methods have been developed for USV detection and classification. Here we evaluate their advantages and disadvantages in a full, systematic comparison, while also presenting a new approach. This study aims to 1) determine the most efficient USV detection tool among the existing methods, and 2) develop a classification model that is more generalizable than existing methods. In both cases, we aim to minimize the user intervention required for processing new data. We compared the performance of four detection methods in an out-of-the-box approach, pretrained DeepSqueak detector, MUPET, USVSEG, and the Automatic Mouse Ultrasound Detector (A-MUD). We also compared these methods to human visual or ‘manual’ classification (ground truth) after assessing its reliability. A-MUD and USVSEG outperformed the other methods in terms of true positive rates using default and adjusted settings, respectively, and A-MUD outperformed USVSEG when false detection rates were also considered. For automating the classification of USVs, we developed BootSnap for supervised classification, which combines bootstrapping on Gammatone Spectrograms and Convolutional Neural Networks algorithms with Snapshot ensemble learning. It successfully classified calls into 12 types, including a new class of false positives that is useful for detection refinement. BootSnap outperformed the pretrained and retrained state-of-the-art tool, and thus it is more generalizable. BootSnap is freely available for scientific use.

House mice and many other species use ultrasonic vocalizations to communicate in various contexts including social and sexual interactions. These vocalizations are increasingly investigated in research on animal communication and as a phenotype for studying the genetic basis of autism and speech disorders. Because manual methods for analyzing vocalizations are extremely time consuming, automatic tools for detection and classification are needed. We evaluated the performance of the available tools for analyzing ultrasonic vocalizations, and we compared detection tools for the first time to manual methods (“ground truth”) using recordings from wild-derived and laboratory mice. For the first time, class-wise inter-observer reliability of manual labels used for ground truth are analyzed and reported. Moreover, we developed a new classification method based on ensemble deep learning that provides more generalizability than the current state-of-the-art tool (both pretrained and retrained). Our new classification method is free for scientific use.

A feature of maternal sleep apnea during gestation causes autism-relevant neuronal and behavioral phenotypes in offspring

Mounting epidemiologic and scientific evidence indicates that many psychiatric disorders originate from a complex interplay between genetics and early life experiences, particularly in the womb. Despite decades of research, our understanding of the precise prenatal and perinatal experiences that increase susceptibility to neurodevelopmental disorders remains incomplete. Sleep apnea (SA) is increasingly common during pregnancy and is characterized by recurrent partial or complete cessations in breathing during sleep. SA causes pathological drops in blood oxygen levels (intermittent hypoxia, IH), often hundreds of times each night. Although SA is known to cause adverse pregnancy and neonatal outcomes, the long-term consequences of maternal SA during pregnancy on brain-based behavioral outcomes and associated neuronal functioning in the offspring remain unknown. We developed a rat model of maternal SA during pregnancy by exposing dams to IH, a hallmark feature of SA, during gestational days 10 to 21 and investigated the consequences on the offspring's forebrain synaptic structure, synaptic function, and behavioral phenotypes across multiples stages of development. Our findings represent a rare example of prenatal factors causing sexually dimorphic behavioral phenotypes associated with excessive (rather than reduced) synapse numbers and implicate hyperactivity of the mammalian target of rapamycin (mTOR) pathway in contributing to the behavioral aberrations. These findings have implications for neuropsychiatric disorders typified by superfluous synapse maintenance that are believed to result, at least in part, from largely unknown insults to the maternal environment.

Sensing the Sounds of Silence: A Pilot Study on the Detection of Model Mice of Autism Spectrum Disorder from Ultrasonic Vocalisations

Studying the animal models of human neuropsychiatric disorders can facilitate the understanding of mechanisms of symptoms both physiologically and genetically. Previous studies have shown that ultrasonic vocalisations (USVs) of mice might be efficient markers to distinguish the wild type group and the model of autism spectrum disorder (mASD). Nevertheless, in-depth analysis of these 'silence' sounds by leveraging the power of advanced computer audition technologies (e. g., deep learning) is limited. To this end, we propose a pilot study on using a large-scale pre-trained audio neural network to extract high-level representations from the USVs of mice for the task on detection of mASD. Experiments have shown a best result reaching an unweighted average recall of 79.2 % for the binary classification task in a rigorous subject-independent scenario. To the best of our knowledge, this is the first time to analyse the sounds that cannot be heard by human beings for the detection of mASD mice. The novel findings can be significant to motivate future works with according means on studying animal models of human patients.

Ultrasonic vocalizations in mice: relevance for ethologic and neurodevelopmental disorders studies

Mice use ultrasonic vocalizations (USVs) to communicate each other and to convey their emotional state. USVs have been greatly characterized in specific life phases and contexts, such as mother isolation-induced USVs for pups or female-induced USVs for male mice during courtship. USVs can be acquired by means of specific tools and later analyzed on the base of both quantitative and qualitative parameters. Indeed, different ultrasonic call categories exist and have already been defined. The understanding of different calls meaning is still missing, and it will represent an essential step forward in the field of USVs. They have long been studied in the ethological context, but recently they emerged as a precious instrument to study pathologies characterized by deficits in communication, in particular neurodevelopmental disorders (NDDs), such as autism spectrum disorders. This review covers the topics of USVs characteristics in mice, contexts for USVs emission and factors that modulate their expression. A particular focus will be devoted to mouse USVs in the context of NDDs. Indeed, several NDDs murine models exist and an intense study of USVs is currently in progress, with the aim of both performing an early diagnosis and to find a pharmacological/behavioral intervention to improve patients' quality of life.

Newborn mice form lasting CA2-dependent memories of their mothers

Some of the most enduring social connections begin when infants first recognize their caregivers, memories that form the basis of many family relationships. It remains unknown whether these early social memories persist into adulthood in mice and, if so, which brain regions support them. Here we show that mice form memories of their mother within days after birth and that these memories persist into adulthood. Pups display greater interest in the mother than in an unfamiliar dam before weaning, after which this preference reverses. Inhibition of CA2 neurons in the pup temporarily blocks the ability to discriminate between the mother and an unfamiliar dam, whereas doing so in adulthood prevents the formation of short-term memories about conspecifics, as well as social discrimination related to long-term memories of the mother. These results suggest that the CA2 supports memories of the mother during infancy and adulthood with a developmental switch in social preference.

Automatic classification of mice vocalizations using Machine Learning techniques and Convolutional Neural Networks

Ultrasonic vocalizations (USVs) analysis is a well-recognized tool to investigate animal communication. It can be used for behavioral phenotyping of murine models of different disorders. The USVs are usually recorded with a microphone sensitive to ultrasound frequencies and they are analyzed by specific software. Different calls typologies exist, and each ultrasonic call can be manually classified, but the qualitative analysis is highly time-consuming. Considering this framework, in this work we proposed and evaluated a set of supervised learning methods for automatic USVs classification. This could represent a sustainable procedure to deeply analyze the ultrasonic communication, other than a standardized analysis. We used manually built datasets obtained by segmenting the USVs audio tracks analyzed with the Avisoft software, and then by labelling each of them into 10 representative classes. For the automatic classification task, we designed a Convolutional Neural Network that was trained receiving as input the spectrogram images associated to the segmented audio files. In addition, we also tested some other supervised learning algorithms, such as Support Vector Machine, Random Forest and Multilayer Perceptrons, exploiting informative numerical features extracted from the spectrograms. The performance showed how considering the whole time/frequency information of the spectrogram leads to significantly higher performance than considering a subset of numerical features. In the authors’ opinion, the experimental results may represent a valuable benchmark for future work in this research field.

Similarities between the Effects of Prenatal Chlorpyrifos and Valproic Acid on Ultrasonic Vocalization in Infant Wistar Rats

Background: In recent years, ultrasonic vocalizations (USV) in pups has become established as a good tool for evaluating behaviors related to communication deficits and emotional states observed in autism spectrum disorder (ASD). Prenatal valproic acid (VPA) exposure leads to impairments and social behavior deficits associated with autism, with the effects of VPA being considered as a reliable animal model of ASD. Some studies also suggest that prenatal exposure to chlorpyrifos (CPF) could enhance autistic-like behaviors. Methods: In order to explore these similarities, in the present study we tested whether prenatal exposure to CPF at GD12.5–14.5 produces effects that are comparable to those produced by prenatal VPA exposure at GD12.5 in infant Wistar rats. Using Deep Squeek software, we evaluated total number of USVs, latency to the first call, mean call duration, principal frequency peak, high frequency peak, and type of calls. Results: Consistent with our hypothesis, we found that exposure to both CPF and VPA leads to a significantly smaller number of calls along with a longer latency to produce the first call. No significant effects were found for the remaining dependent variables. Conclusions: These results suggest that prenatal exposure to CPF could produce certain behaviors that are reminiscent of those observed in ASD patients.

Classifying sex and strain from mouse ultrasonic vocalizations using deep learning

Vocalizations are widely used for communication between animals. Mice use a large repertoire of ultrasonic vocalizations (USVs) in different social contexts. During social interaction recognizing the partner's sex is important, however, previous research remained inconclusive whether individual USVs contain this information. Using deep neural networks (DNNs) to classify the sex of the emitting mouse from the spectrogram we obtain unprecedented performance (77%, vs. SVM: 56%, Regression: 51%). Performance was even higher (85%) if the DNN could also use each mouse's individual properties during training, which may, however, be of limited practical value. Splitting estimation into two DNNs and using 24 extracted features per USV, spectrogram-to-features and features-to-sex (60%) failed to reach single-step performance. Extending the features by each USVs spectral line, frequency and time marginal in a semi-convolutional DNN resulted in a performance mid-way (64%). Analyzing the network structure suggests an increase in sparsity of activation and correlation with sex, specifically in the fully-connected layers. A detailed analysis of the USV structure, reveals a subset of male vocalizations characterized by a few acoustic features, while the majority of sex differences appear to rely on a complex combination of many features. The same network architecture was also able to achieve above-chance classification for cortexless mice, which were considered indistinguishable before. In summary, spectrotemporal differences between male and female USVs allow at least their partial classification, which enables sexual recognition between mice and automated attribution of USVs during analysis of social interactions.

High-throughput analysis of vocalizations reveals sex-specific changes in Fmr1 mutant pups

There have been several reports that individuals with Fragile X syndrome (FXS) and animal models of FXS have communication deficits. The present study utilized two different call classification taxonomies to examine the sex-specificity of ultrasonic vocalization (USV) production on postnatal day (PD8) in the FVB strain of Fmr1 knockout (KO) mice. One classification protocol requires the investigator to score each call by hand, while the other protocol uses an automated algorithm. Results using the hand-scoring protocol indicated that male Fmr1 KO mice exhibited longer calls (P = .03) than wild types on PD8. Male KOs also produced fewer complex, composite, downward, short and two-syllable call-types, as well as more frequency steps and chevron call-types. Female heterozygotes exhibited no significant changes in acoustic or temporal aspects of calls, yet showed significant changes in call-type production proportions across two different classification taxonomies (P < .001). They exhibited increased production of harmonic and frequency steps calls, as well as fewer chevron, downward and short calls. According to the second high-throughput analysis, female heterozygotes produced significantly fewer single-type and more multiple-type syllables, unlike male KOs that showed no changes in these aspects of syllable production. Finally, we correlated both scoring methods and found a high level of correlation between the two methods. These results contribute further knowledge of sex differences in USV calling behavior for Fmr1 heterozygote and KO mice and provide a foundation for the use of high-throughput analysis of neonatal USVs.