Quantitative model for genome-wide cyclic AMP receptor protein binding site identification and characteristic analysis.

Cyclic AMP receptor proteins (CRPs) are important transcription regulators in many species. The prediction of CRP-binding sites was mainly based on position-weighted matrixes (PWMs). Traditional prediction methods only considered known binding motifs, and their ability to discover inflexible binding patterns was limited. Thus, a novel CRP-binding site prediction model called CRPBSFinder was developed in this research, which combined the hidden Markov model, knowledge-based PWMs and structure-based binding affinity matrixes. We trained this model using validated CRP-binding data from Escherichia coli and evaluated it with computational and experimental methods. The result shows that the model not only can provide higher prediction performance than a classic method but also quantitatively indicates the binding affinity of transcription factor binding sites by prediction scores. The prediction result included not only the most knowns regulated genes but also 1089 novel CRP-regulated genes. The major regulatory roles of CRPs were divided into four classes: carbohydrate metabolism, organic acid metabolism, nitrogen compound metabolism and cellular transport. Several novel functions were also discovered, including heterocycle metabolic and response to stimulus. Based on the functional similarity of homologous CRPs, we applied the model to 35 other species. The prediction tool and the prediction results are online and are available at: https://awi.cuhk.edu.cn/∼CRPBSFinder.

A novel starch-active lytic polysaccharide monooxygenase discovered with bioinformatics screening and its application in textile desizing.

BACKGROUND: Lytic polysaccharide monooxygenases (LPMOs) catalyzing the oxidative cleavage of different types of polysaccharides have potential to be used in various industries. However, AA13 family LPMOs which specifically catalyze starch substrates have relatively less members than AA9 and AA10 families to limit their application range. Amylase has been used in enzymatic desizing treatment of cotton fabric for semicentury which urgently need for new assistant enzymes to improve reaction efficiency and reduce cost so as to promote their application in the textile industry. RESULTS: A total of 380 unannotated new genes which probably encode AA13 family LPMOs were discovered by the Hidden Markov model scanning in this study. Ten of them have been successfully heterologous overexpressed. AlLPMO13 with the highest activity has been purified and determined its optimum pH and temperature as pH 5.0 and 50 °C. It also showed various oxidative activities on different substrates (modified corn starch > amylose > amylopectin > corn starch). The results of enzymatic textile desizing application showed that the best combination of amylase (5 g/L), AlLPMO13 (5 mg/L), and H2O2 (3 g/L) made the desizing level and the capillary effects increased by 3 grades and more than 20%, respectively, compared with the results treated by only amylase. CONCLUSION: The Hidden Markov model constructed basing on 34 AA13 family LPMOs was proved to be a valid bioinformatics tool for discovering novel starch-active LPMOs. The novel enzyme AlLPMO13 has strong development potential in the enzymatic textile industry both concerning on economy and on application effect.

PHR-search: a search framework for protein remote homology detection based on the predicted protein hierarchical relationships.

Protein remote homology detection is one of the most fundamental research tool for protein structure and function prediction. Most search methods for protein remote homology detection are evaluated based on the Structural Classification of Proteins-extended (SCOPe) benchmark, but the diverse hierarchical structure relationships between the query protein and candidate proteins are ignored by these methods. In order to further improve the predictive performance for protein remote homology detection, a search framework based on the predicted protein hierarchical relationships (PHR-search) is proposed. In the PHR-search framework, the superfamily level prediction information is obtained by extracting the local and global features of the Hidden Markov Model (HMM) profile through a convolution neural network and it is converted to the fold level and class level prediction information according to the hierarchical relationships of SCOPe. Based on these predicted protein hierarchical relationships, filtering strategy and re-ranking strategy are used to construct the two-level search of PHR-search. Experimental results show that the PHR-search framework achieves the state-of-the-art performance by employing five basic search methods, including HHblits, JackHMMER, PSI-BLAST, DELTA-BLAST and PSI-BLASTexB. Furthermore, the web server of PHR-search is established, which can be accessed at http://bliulab.net/PHR-search.

The expected sample allele frequencies from populations of changing size via orthogonal polynomials.

In this article, discrete and stochastic changes in (effective) population size are incorporated into the spectral representation of a biallelic diffusion process for drift and small mutation rates. A forward algorithm inspired by Hidden-Markov-Model (HMM) literature is used to compute exact sample allele frequency spectra for three demographic scenarios: single changes in (effective) population size, boom-bust dynamics, and stochastic fluctuations in (effective) population size. An approach for fully agnostic demographic inference from these sample allele spectra is explored, and sufficient statistics for stepwise changes in population size are found. Further, convergence behaviours of the polymorphic sample spectra for population size changes on different time scales are examined and discussed within the context of inference of the effective population size. Joint visual assessment of the sample spectra and the temporal coefficients of the spectral decomposition of the forward diffusion process is found to be important in determining departure from equilibrium. Stochastic changes in (effective) population size are shown to shape sample spectra particularly strongly.

Atypical dynamic neural configuration in autism spectrum disorder and its relationship to gene expression profiles.

Although it is well recognized that autism spectrum disorder (ASD) is associated with atypical dynamic functional connectivity patterns, the dynamic changes in brain intrinsic activity over each time point and the potential molecular mechanisms associated with atypical dynamic temporal characteristics in ASD remain unclear. Here, we employed the Hidden Markov Model (HMM) to explore the atypical neural configuration at every scanning time point in ASD, based on resting-state functional magnetic resonance imaging (rs-fMRI) data from the Autism Brain Imaging Data Exchange. Subsequently, partial least squares regression and pathway enrichment analysis were employed to explore the potential molecular mechanism associated with atypical neural dynamics in ASD. 8 HMM states were inferred from rs-fMRI data. Compared to typically developing, individuals on the autism spectrum showed atypical state-specific temporal characteristics, including number of states and occurrences, mean life time and transition probability between states. Moreover, these atypical temporal characteristics could predict communication difficulties of ASD, and states assoicated with negative activation in default mode network and frontoparietal network, and positive activation in somatomotor network, ventral attention network, and limbic network, had higher predictive contribution. Furthermore, a total of 321 genes was revealed to be significantly associated with atypical dynamic brain states of ASD, and these genes are mainly enriched in neurodevelopmental pathways. Our study provides new insights into characterizing the atypical neural dynamics from a moment-to-moment perspective, and indicates a linkage between atypical neural configuration and gene expression in ASD.

Research on Pig Sound Recognition Based on Deep Neural Network and Hidden Markov Models.

In order to solve the problem of low recognition accuracy of traditional pig sound recognition methods, deep neural network (DNN) and Hidden Markov Model (HMM) theory were used as the basis of pig sound signal recognition in this study. In this study, the sounds made by 10 landrace pigs during eating, estrus, howling, humming and panting were collected and preprocessed by Kalman filtering and an improved endpoint detection algorithm based on empirical mode decomposition-Teiger energy operator (EMD-TEO) cepstral distance. The extracted 39-dimensional mel-frequency cepstral coefficients (MFCCs) were then used as a dataset for network learning and recognition to build a DNN- and HMM-based sound recognition model for pig states. The results show that in the pig sound dataset, the recognition accuracy of DNN-HMM reaches 83%, which is 22% and 17% higher than that of the baseline models HMM and GMM-HMM, and possesses a better recognition effect. In a sub-dataset of the publicly available dataset AudioSet, DNN-HMM achieves a recognition accuracy of 79%, which is 8% and 4% higher than the classical models SVM and ResNet18, respectively, with better robustness.

In vivo cone-photoreceptor density comparison between eyes with subretinal drusenoid deposits and healthy eyes using high magnification imaging.

PURPOSE: To compare photoreceptor density automated quantification in eyes with subretinal drusenoid deposits (SDD) and healthy controls using Heidelberg Spectralis High Magnification Module (HMM) imaging. METHODS: Twelve eyes of 6 patients with intermediate AMD, presenting with SDD were included, as well as twelve eyes of healthy controls. Individual dot SDD within the central 30° retina were examined with infrared confocal laser ophthalmoscopy, HMM, and spectral-domain optical coherence tomography (SD-OCT). Photoreceptor density analysis was performed on the best-quality image using the ImageJ Foci Picker plugin, after the removal of SDD from the HMM image. Correlations were made between the HMM quantified photoreceptor density, SD-OCT characteristics, stage, and number of SDD. RESULTS: Mean age was 75.17 ± 2.51 years in the SDD group (3 males, 3 females) versus 73.17 ± 3.15 years in the healthy control group (p = 0.2). Defects in the overlying ellipsoid zone were present on SD-OCT in 8/12 (66.66%) eyes. The mean ± standard deviation foci detected (i.e., cone photoreceptors) was 7123.75 ± 3683.32 foci/mm2 in the SDD group versus 13,253 ± 3331.00 foci/mm2 in the healthy control group (p = 0.0003). The number of SDD was associated with a reduction in foci density, p = 0.0055, r = - 0.7622. CONCLUSION: The decreased cone density in eyes with SDD may correlate with a decrease in retinal function in intermediate AMD eyes independent of neovascular complications or outer retinal pigment epithelial atrophy.

LuxHMM: DNA methylation analysis with genome segmentation via hidden Markov model.

BACKGROUND: DNA methylation plays an important role in studying the epigenetics of various biological processes including many diseases. Although differential methylation of individual cytosines can be informative, given that methylation of neighboring CpGs are typically correlated, analysis of differentially methylated regions is often of more interest. RESULTS: We have developed a probabilistic method and software, LuxHMM, that uses hidden Markov model (HMM) to segment the genome into regions and a Bayesian regression model, which allows handling of multiple covariates, to infer differential methylation of regions. Moreover, our model includes experimental parameters that describe the underlying biochemistry in bisulfite sequencing and model inference is done using either variational inference for efficient genome-scale analysis or Hamiltonian Monte Carlo (HMC). CONCLUSIONS: Analyses of real and simulated bisulfite sequencing data demonstrate the competitive performance of LuxHMM compared with other published differential methylation analysis methods.

Lokatt: a hybrid DNA nanopore basecaller with an explicit duration hidden Markov model and a residual LSTM network.

BACKGROUND: Basecalling long DNA sequences is a crucial step in nanopore-based DNA sequencing protocols. In recent years, the CTC-RNN model has become the leading basecalling model, supplanting preceding hidden Markov models (HMMs) that relied on pre-segmenting ion current measurements. However, the CTC-RNN model operates independently of prior biological and physical insights. RESULTS: We present a novel basecaller named Lokatt: explicit duration Markov model and residual-LSTM network. It leverages an explicit duration HMM (EDHMM) designed to model the nanopore sequencing processes. Trained on a newly generated library with methylation-free Ecoli samples and MinION R9.4.1 chemistry, the Lokatt basecaller achieves basecalling performances with a median single read identity score of 0.930, a genome coverage ratio of 99.750%, on par with existing state-of-the-art structure when trained on the same datasets. CONCLUSION: Our research underlines the potential of incorporating prior knowledge into the basecalling processes, particularly through integrating HMMs and recurrent neural networks. The Lokatt basecaller showcases the efficacy of a hybrid approach, emphasizing its capacity to achieve high-quality basecalling performance while accommodating the nuances of nanopore sequencing. These outcomes pave the way for advanced basecalling methodologies, with potential implications for enhancing the accuracy and efficiency of nanopore-based DNA sequencing protocols.

ORFeus: a computational method to detect programmed ribosomal frameshifts and other non-canonical translation events.

BACKGROUND: In canonical protein translation, ribosomes initiate translation at a specific start codon, maintain a single reading frame throughout elongation, and terminate at the first in-frame stop codon. However, ribosomal behavior can deviate at each of these steps, sometimes in a programmed manner. Certain mRNAs contain sequence and structural elements that cause ribosomes to begin translation at alternative start codons, shift reading frame, read through stop codons, or reinitiate on the same mRNA. These processes represent important translational control mechanisms that can allow an mRNA to encode multiple functional protein products or regulate protein expression. The prevalence of these events remains uncertain, due to the difficulty of systematic detection. RESULTS: We have developed a computational model to infer non-canonical translation events from ribosome profiling data. CONCLUSION: ORFeus identifies known examples of alternative open reading frames and recoding events across different organisms and enables transcriptome-wide searches for novel events.

50 Years of the steric-blocking mechanism in vertebrate skeletal muscle: a retrospective.

Fifty years have now passed since Parry and Squire proposed a detailed structural model that explained how tropomyosin, mediated by troponin, played a steric-blocking role in the regulation of vertebrate skeletal muscle. In this Special Issue dedicated to the memory of John Squire it is an opportune time to look back on this research and to appreciate John's key contributions. A review is also presented of a selection of the developments and insights into muscle regulation that have occurred in the years since this proposal was formulated.

Gains and losses of the epiphytic lifestyle in epidendroid orchids: review and new analyses of succulence traits.

BACKGROUND AND AIMS: Epiphytism has evolved repeatedly in plants and has resulted in a considerable number of species with original characteristics. Because water supply is generally erratic compared to that in soils, succulent forms in particular are widespread in epiphytic species. However, succulent organs also exist in terrestrial plants, and the question of the concomitant evolution of epiphytism and succulence has received little attention, not even in the epidendroid orchids, which account for 67.6 % of vascular epiphytes. METHODS: We built a new time-calibrated phylogenetic tree of Epidendroideae with 203 genera treated in genus Orchidacearum, from which we reconstructed the evolution of epiphytism as well as traits related to water scarcity (stem and leaf succulence and the number of velamen layers), while testing for the correlated evolution between the two. Furthermore, we estimated the ancestral geographical ranges to evaluate the palaeoclimatic context in which epiphytism evolved. KEY RESULTS: Epiphytism evolved at least three times: 39.0 million years ago (Mya) in the common ancestor of the Malaxideae and Cymbidieae that probably ranged from the Neotropics to Southeast Asia and Australia, 11.5 Mya in the Arethuseae in Southeast Asia and Australia, and 7.1 Mya in the neotropical Sobralieae, and it was notably lost in the Malaxidiinae, Collabieae, Calypsoeae, Bletiinae and Eulophiinae. Stem succulence is inferred to have evolved once, in a terrestrial ancestor at least 4.1 Mya before the emergence of epiphytic lineages. If lost, stem succulence was almost systematically replaced by leaf succulence in epiphytic lineages. CONCLUSIONS: Epiphytism may have evolved in seasonally dry forests during the Eocene climatic cooling, among stem-succulent terrestrial orchids. Our results suggest that the emergence of stem succulence in early epidendroids was a key innovation in the evolution of epiphytism, facilitating the colonization of epiphytic environments that later led to the greatest diversification of epiphytic orchids.

Finnish parliament ASR corpus: Analysis, benchmarks and statistics.

Public sources like parliament meeting recordings and transcripts provide ever-growing material for the training and evaluation of automatic speech recognition (ASR) systems. In this paper, we publish and analyse the Finnish Parliament ASR Corpus, the most extensive publicly available collection of manually transcribed speech data for Finnish with over 3000 h of speech and 449 speakers for which it provides rich demographic metadata. This corpus builds on earlier initial work, and as a result the corpus has a natural split into two training subsets from two periods of time. Similarly, there are two official, corrected test sets covering different times, setting an ASR task with longitudinal distribution-shift characteristics. An official development set is also provided. We developed a complete Kaldi-based data preparation pipeline and ASR recipes for hidden Markov models (HMM), hybrid deep neural networks (HMM-DNN), and attention-based encoder-decoders (AED). For HMM-DNN systems, we provide results with time-delay neural networks (TDNN) as well as state-of-the-art wav2vec 2.0 pretrained acoustic models. We set benchmarks on the official test sets and multiple other recently used test sets. Both temporal corpus subsets are already large, and we observe that beyond their scale, HMM-TDNN ASR performance on the official test sets has reached a plateau. In contrast, other domains and larger wav2vec 2.0 models benefit from added data. The HMM-DNN and AED approaches are compared in a carefully matched equal data setting, with the HMM-DNN system consistently performing better. Finally, the variation of the ASR accuracy is compared between the speaker categories available in the parliament metadata to detect potential biases based on factors such as gender, age, and education.

Online Monitoring of Sensor Calibration Status to Support Condition-Based Maintenance.

Condition-Based Maintenance (CBM), based on sensors, can only be reliable if the data used to extract information are also reliable. Industrial metrology plays a major role in ensuring the quality of the data collected by the sensors. To guarantee that the values collected by the sensors are reliable, it is necessary to have metrological traceability made by successive calibrations from higher standards to the sensors used in the factories. To ensure the reliability of the data, a calibration strategy must be put in place. Usually, sensors are only calibrated on a periodic basis; so, they often go for calibration without it being necessary or collect data inaccurately. In addition, the sensors are checked often, increasing the need for manpower, and sensor errors are frequently overlooked when the redundant sensor has a drift in the same direction. It is necessary to acquire a calibration strategy based on the sensor condition. Through online monitoring of sensor calibration status (OLM), it is possible to perform calibrations only when it is really necessary. To reach this end, this paper aims to provide a strategy to classify the health status of the production equipment and of the reading equipment that uses the same dataset. A measurement signal from four sensors was simulated, for which Artificial Intelligence and Machine Learning with unsupervised algorithms were used. This paper demonstrates how, through the same dataset, it is possible to obtain distinct information. Because of this, we have a very important feature creation process, followed by Principal Component Analysis (PCA), K-means clustering, and classification based on Hidden Markov Models (HMM). Through three hidden states of the HMM, which represent the health states of the production equipment, we will first detect, through correlations, the features of its status. After that, an HMM filter is used to eliminate those errors from the original signal. Next, an equal methodology is conducted for each sensor individually and using statistical features in the time domain where we can obtain, through HMM, the failures of each sensor.

Genomic selection pressure discovery using site-frequency spectrum and reduced local variability statistics in Pakistani Dera-Din-Panah goat.

BACKGROUND: Population geneticists have long sought to comprehend various selection traces accumulated in the goat genome due to natural or human driven artificial selection through breeding practices, which led the wild animals to domestication, so understanding evolutionary process may helpful to utilize the full genetic potential of goat genome. METHODS AND RESULTS: As a step forward to pinpoint the selection signals in Pakistani Dera-Din-Panah (DDP) goat, whole-genome pooled sequencing (n = 12) was performed, and 618,236,192 clean paired-end reads were mapped against ARS1 reference goat assembly. Five different selection signature statistics were applied using four site-frequency spectrum (SFS) methods (Tajima's D ([Formula: see text]), Fay and Wu's H ([Formula: see text]), Zeng's E ([Formula: see text]), [Formula: see text]) and one reduced local variability approach named pooled heterozygosity ([Formula: see text]). The under-selection regions were annotated with significant threshold values of [Formula: see text]≥4.7, [Formula: see text]≥6, [Formula: see text]≥2.5, Pool-HMM ≥ 12, and [Formula: see text]≥5 that resulted in accumulative 364 candidate gene hits. The highest genomic selection signals were observed on Chr. 4, 6, 10, 12, 15, 16, 18, 20, and 27 and harbor ADAMTS6, CWC27, RELN, MYCBP2, FGF14, STIM1, CFAP74, GNB1, CALML6, TMEM52, FAM149A, NADK, MMP23B, OPN3, FH, MFHAS1, KLKB1, RRM1, KMO, SPEF2, F11, KIT, KMO, ERI1, ATP8B4, and RHOG genes. Next, the validation of our captured genomic hits was also performed by more than one applied statistics which harbor meat production, immunity, and reproduction associated genes to strengthen our hypothesis of under-selection traits in this Pakistani goat breed. Furthermore, common candidate genes captured by more than one statistical method were subjected to gene ontology and KEGG pathway analysis to get insights of particular biological processes associated with this goat breed. CONCLUSION: Current perception of genomic architecture of DDP goat provides a better understanding to improve its genetic potential and other economically important traits of medium to large body size, milk, and fiber production by updating the genomic insight driven breeding strategies to boost the livestock and agriculture-based economy of the country.

Low-cost and clinically applicable copy number profiling using repeat DNA.

BACKGROUND: Somatic copy number alterations (SCNAs) are an important class of genomic alteration in cancer. They are frequently observed in cancer samples, with studies showing that, on average, SCNAs affect 34% of a cancer cell's genome. Furthermore, SCNAs have been shown to be major drivers of tumour development and have been associated with response to therapy and prognosis. Large-scale cancer genome studies suggest that tumours are driven by somatic copy number alterations (SCNAs) or single-nucleotide variants (SNVs). Despite the frequency of SCNAs and their clinical relevance, the use of genomics assays in the clinic is biased towards targeted gene panels, which identify SNVs but provide limited scope to detect SCNAs throughout the genome. There is a need for a comparably low-cost and simple method for high-resolution SCNA profiling. RESULTS: We present conliga, a fully probabilistic method that infers SCNA profiles from a low-cost, simple, and clinically-relevant assay (FAST-SeqS). When applied to 11 high-purity oesophageal adenocarcinoma samples, we obtain good agreement (Spearman's rank correlation coefficient, rs=0.94) between conliga's inferred SCNA profiles using FAST-SeqS data (approximately £14 per sample) and those inferred by ASCAT using high-coverage WGS (gold-standard). We find that conliga outperforms CNVkit (rs=0.89), also applied to FAST-SeqS data, and is comparable to QDNAseq (rs=0.96) applied to low-coverage WGS, which is approximately four-fold more expensive, more laborious and less clinically-relevant. By performing an in silico dilution series experiment, we find that conliga is particularly suited to detecting SCNAs in low tumour purity samples. At two million reads per sample, conliga is able to detect SCNAs in all nine samples at 3% tumour purity and as low as 0.5% purity in one sample. Crucially, we show that conliga's hidden state information can be used to decide when a sample is abnormal or normal, whereas CNVkit and QDNAseq cannot provide this critical information. CONCLUSIONS: We show that conliga provides high-resolution SCNA profiles using a convenient, low-cost assay. We believe conliga makes FAST-SeqS a more clinically valuable assay as well as a useful research tool, enabling inexpensive and fast copy number profiling of pre-malignant and cancer samples.

Data and model considerations for estimating time-varying functional connectivity in fMRI.

Functional connectivity (FC) in the brain has been shown to exhibit subtle but reliable modulations within a session. One way of estimating time-varying FC is by using state-based models that describe fMRI time series as temporal sequences of states, each with an associated, characteristic pattern of FC. However, the estimation of these models from data sometimes fails to capture changes in a meaningful way, such that the model estimation assigns entire sessions (or the largest part of them) to a single state, therefore failing to capture within-session state modulations effectively; we refer to this phenomenon as the model becoming static, or model stasis. Here, we aim to quantify how the nature of the data and the choice of model parameters affect the model's ability to detect temporal changes in FC using both simulated fMRI time courses and resting state fMRI data. We show that large between-subject FC differences can overwhelm subtler within-session modulations, causing the model to become static. Further, the choice of parcellation can also affect the model's ability to detect temporal changes. We finally show that the model often becomes static when the number of free parameters per state that need to be estimated is high and the number of observations available for this estimation is low in comparison. Based on these findings, we derive a set of practical recommendations for time-varying FC studies, in terms of preprocessing, parcellation and complexity of the model.

Inferring Adaptive Introgression Using Hidden Markov Models.

Adaptive introgression-the flow of adaptive genetic variation between species or populations-has attracted significant interest in recent years and it has been implicated in a number of cases of adaptation, from pesticide resistance and immunity, to local adaptation. Despite this, methods for identification of adaptive introgression from population genomic data are lacking. Here, we present Ancestry_HMM-S, a hidden Markov model-based method for identifying genes undergoing adaptive introgression and quantifying the strength of selection acting on them. Through extensive validation, we show that this method performs well on moderately sized data sets for realistic population and selection parameters. We apply Ancestry_HMM-S to a data set of an admixed Drosophila melanogaster population from South Africa and we identify 17 loci which show signatures of adaptive introgression, four of which have previously been shown to confer resistance to insecticides. Ancestry_HMM-S provides a powerful method for inferring adaptive introgression in data sets that are typically collected when studying admixed populations. This method will enable powerful insights into the genetic consequences of admixture across diverse populations. Ancestry_HMM-S can be downloaded from https://github.com/jesvedberg/Ancestry_HMM-S/.

pamlr: A toolbox for analysing animal behaviour using pressure, acceleration, temperature, magnetic or light data in R.

Light-level geolocators have revolutionised the study of animal behaviour. However, lacking spatial precision, their usage has been primary targeted towards the analysis of large-scale movements. Recent technological developments have allowed the integration of magnetometers and accelerometers into geolocator tags in addition to barometers and thermometers, offering new behavioural insights. Here, we introduce an R toolbox for identifying behavioural patterns from multisensor geolocator tags, with functions specifically designed for data visualisation, calibration, classification and error estimation. More specifically, the package allows for the flexible analysis of any combination of sensor data using k-means clustering, expectation maximisation binary clustering, hidden Markov models and changepoint analyses. Furthermore, the package integrates tailored algorithms for identifying periods of prolonged high activity (most commonly used for identifying migratory flapping flight), and pressure changes (most commonly used for identifying dive or flight events). Finally, we highlight some of the limitations, implications and opportunities of using these methods.

Les géolocalisateurs lumineux ont révolutionné l'étude du comportement animal. Toutefois, en raison de leur manque de précision spatiale, leur utilisation a été principalement dirigée vers l'analyse de mouvements à grandes échelles. Les développements technologiques récents ont permis l'intégration de magnétomètres et d'accéléromètres dans les balises de géolocalisation, en plus de baromètres et de thermomètres, permettant de nouvelles analyses du comportement animalier. Nous présentons ici notre R package pour l'identification de modèles comportementaux à partir de balises géolocalisatrices multisensoriels. Le package intègre des fonctions conçues spécifiquement pour la visualisation de données, la calibration des balises, la classification du comportement et l'estimation des erreurs d'analyses. Plus précisément, le package permet l'analyse flexible de n'importe quelle combinaison de capteurs de données en utilisant le k-means clustering, le expectation maximisation binary clustering, les hidden Markov models et les analyses changepoint. En outre, le package intègre des algorithmes adaptés pour identifier les périodes de haute activité prolongée (le plus souvent utilisé pour identifier le vol migratoire d'oiseaux), et les changements de pression (le plus souvent utilisé pour identifier des periodes où l'animal est en plongée ou au vol). Enfin, nous soulignons les limites, les implications et les opportunités d'utilisation de ces méthodes.

Learning Dynamics and Control of a Stochastic System under Limited Sensing Capabilities.

The operation of a variety of natural or man-made systems subject to uncertainty is maintained within a range of safe behavior through run-time sensing of the system state and control actions selected according to some strategy. When the system is observed from an external perspective, the control strategy may not be known and it should rather be reconstructed by joint observation of the applied control actions and the corresponding evolution of the system state. This is largely hurdled by limitations in the sensing of the system state and different levels of noise. We address the problem of optimal selection of control actions for a stochastic system with unknown dynamics operating under a controller with unknown strategy, for which we can observe trajectories made of the sequence of control actions and noisy observations of the system state which are labeled by the exact value of some reward functions. To this end, we present an approach to train an Input-Output Hidden Markov Model (IO-HMM) as the generative stochastic model that describes the state dynamics of a POMDP by the application of a novel optimization objective adopted from the literate. The learning task is hurdled by two restrictions: the only available sensed data are the limited number of trajectories of applied actions, noisy observations of the system state, and system state; and, the high failure costs prevent interaction with the online environment, preventing exploratory testing. Traditionally, stochastic generative models have been used to learn the underlying system dynamics and select appropriate actions in the defined task. However, current state of the art techniques, in which the state dynamics of the POMDP is first learned and then strategies are optimized over it, frequently fail because the model that best fits the data may not be well suited for controlling. By using the aforementioned optimization objective, we try to to tackle the problems related to model mis-specification. The proposed methodology is illustrated in a scenario of failure avoidance for a multi component system. The quality of the decision making is evaluated by using the collected reward on the test data and compared against the previous literature usual approach.