Structure-based learning to predict and model protein-DNA interactions and transcription-factor co-operativity in cis-regulatory elements.

Transcription factor (TF) binding is a key component of genomic regulation. There are numerous high-throughput experimental methods to characterize TF-DNA binding specificities. Their application, however, is both laborious and expensive, which makes profiling all TFs challenging. For instance, the binding preferences of ∼25% human TFs remain unknown; they neither have been determined experimentally nor inferred computationally. We introduce a structure-based learning approach to predict the binding preferences of TFs and the automated modelling of TF regulatory complexes. We show the advantage of using our approach over the classical nearest-neighbor prediction in the limits of remote homology. Starting from a TF sequence or structure, we predict binding preferences in the form of motifs that are then used to scan a DNA sequence for occurrences. The best matches are either profiled with a binding score or collected for their subsequent modeling into a higher-order regulatory complex with DNA. Co-operativity is modelled by: (i) the co-localization of TFs and (ii) the structural modeling of protein-protein interactions between TFs and with co-factors. We have applied our approach to automatically model the interferon-ß enhanceosome and the pioneering complexes of OCT4, SOX2 (or SOX11) and KLF4 with a nucleosome, which are compared with the experimentally known structures.

Acting Emotions: a comprehensive dataset of elicited emotions.

Emotions encompass physiological systems that can be assessed through biosignals like electromyography and electrocardiography. Prior investigations in emotion recognition have primarily focused on general population samples, overlooking the specific context of theatre actors who possess exceptional abilities in conveying emotions to an audience, namely acting emotions. We conducted a study involving 11 professional actors to collect physiological data for acting emotions to investigate the correlation between biosignals and emotion expression. Our contribution is the DECEiVeR (DatasEt aCting Emotions Valence aRousal) dataset, a comprehensive collection of various physiological recordings meticulously curated to facilitate the recognition of a set of five emotions. Moreover, we conduct a preliminary analysis on modeling the recognition of acting emotions from raw, low- and mid-level temporal and spectral data and the reliability of physiological data across time. Our dataset aims to leverage a deeper understanding of the intricate interplay between biosignals and emotional expression. It provides valuable insights into acting emotion recognition and affective computing by exposing the degree to which biosignals capture emotions elicited from inner stimuli.

A real-world dataset of group emotion experiences based on physiological data.

Affective computing has experienced substantial advancements in recognizing emotions through image and facial expression analysis. However, the incorporation of physiological data remains constrained. Emotion recognition with physiological data shows promising results in controlled experiments but lacks generalization to real-world settings. To address this, we present G-REx, a dataset for real-world affective computing. We collected physiological data (photoplethysmography and electrodermal activity) using a wrist-worn device during long-duration movie sessions. Emotion annotations were retrospectively performed on segments with elevated physiological responses. The dataset includes over 31 movie sessions, totaling 380 h+ of data from 190+ subjects. The data were collected in a group setting, which can give further context to emotion recognition systems. Our setup aims to be easily replicable in any real-life scenario, facilitating the collection of large datasets for novel affective computing systems.

Theoretical 3D Modeling of NLRP3 Inflammasome Complex.

The NOD-like receptor pyrin domain containing 3 (NLRP3) is a multidomain protein that plays a key role in innate immune response. Structures of NLRP3 in different conformational states and bound to cognate partners are available. In this chapter we present an approach to model the oligomeric structure of NLRP3 by homology modeling using multiple templates, symmetry, and refinement. The overall process presented here represents advanced exercise in structural modeling that provides unique insights into the biological role and activation of NLRP3 oligomer. Finally, the same approach can be easily adapted to the rest of the members of the NLRP family.

CM2D3: Furnishing the Human Interactome with Structural Models of Protein Complexes Derived by Comparative Modeling and Docking.

The human interactome is composed of around half a million interactions according to recent estimations and it is only for a small fraction of those that three-dimensional structural information is available. Indeed, the structural coverage of the human interactome is very low and given the complexity and time-consuming requirements of solving protein structures this problem will remain for the foreseeable future. Structural models, or predictions, of protein complexes can provide valuable information when the experimentally determined 3D structures are not available. Here we present CM2D3, a relational database containing structural models of the whole human interactome derived both from comparative modeling and data-driven docking. Starting from a consensus interactome derived from integrating several interactomics databases, a strategy was devised to derive structural models by computational means. Currently, CM2D3 includes 33338 structural models of which 5121 derived from comparative modeling and the remaining from docking. Of the latter, the structures of 14554 complexes were derived from monomers modeled by M4T while the rest were modeled with structures as predicted by AlphaFold2. Lastly, CM2D3 complements existing resources by focusing on models derived from both free-docking, as opposed to template-based docking, and hence expanding the available structural information on protein complexes to the scientific community. Database URL:http://www.bioinsilico.org/CM2D3.

Benchmarking of Sensor Configurations and Measurement Sites for Out-of-the-Lab Photoplethysmography.

Photoplethysmography (PPG) is used for heart-rate monitoring in a variety of contexts and applications due to its versatility and simplicity. These applications, namely studies involving PPG data acquisition during day-to-day activities, require reliable and continuous measurements, which are often performed at the index finger or wrist. However, some PPG sensors are susceptible to saturation, motion artifacts, and discomfort upon their use. In this paper, an off-the-shelf PPG sensor was benchmarked and modified to improve signal saturation. Moreover, this paper explores the feasibility of using an optimized sensor in the lower limb as an alternative measurement site. Data were collected from 28 subjects with ages ranging from 18 to 59 years. To validate the sensors' performance, signal saturation and quality, wave morphology, performance of automatic systolic peak detection, and heart-rate estimation, were compared. For the upper and lower limb locations, the index finger and the first toe were used as reference locations, respectively. Lowering the amplification stage of the PPG sensor resulted in a significant reduction in signal saturation, from 18% to 0.5%. Systolic peak detection at rest using an automatic algorithm showed a sensitivity and precision of 0.99 each. The posterior wrist and upper arm showed pulse wave morphology correlations of 0.93 and 0.92, respectively. For these locations, peak detection sensitivity and precision were 0.95, 0.94 and 0.89, 0.89, respectively. Overall, the adjusted PPG sensors are a good alternative for obtaining high-quality signals at the fingertips, and for new measurement sites, the posterior pulse and the upper arm allow for high-quality signal extraction.

Prediction of Protein-Protein Binding Affinities from Unbound Protein Structures.

Proteins are the workhorses of cells to carry out sophisticated and complex cellular processes. Such processes require a coordinated and regulated interactions between proteins that are both time and location specific. The strength, or binding affinity, of protein-protein interactions ranges between the micro- and the nanomolar association constant, often dictating the molecular mechanisms underlying the interaction and the longevity of the complex, i.e., transient or permanent. In consequence, there is a need to quantify the strength of protein-protein interactions for biological, biomedical, and biotechnological applications. While experimental methods are labor intensive and costly, computational ones are useful tools to predict the affinity of protein-protein interactions. In this chapter, we review the methods developed by us to address this question. We briefly present two methods to comprehend the structure of the protein complex derived by either comparative modeling or docking. Then we introduce BADOCK, a method to predict the binding energy without requiring the structure of the protein complex, thus overcoming one of the major limitations of structure-based methods for the prediction of binding affinity. BADOCK utilizes the structure of unbound proteins and the protein docking sampling space to predict protein-protein binding affinities. We present step-by-step protocols to utilize these methods, describing the inputs and potential pitfalls as well as their respective strengths and limitations.

Mining drug-target and drug-adverse drug reaction databases to identify target-adverse drug reaction relationships.

The level of attrition on drug discovery, particularly at advanced stages, is very high due to unexpected adverse drug reactions (ADRs) caused by drug candidates, and thus, being able to predict undesirable responses when modulating certain protein targets would contribute to the development of safer drugs and have important economic implications. On the one hand, there are a number of databases that compile information of drug-target interactions. On the other hand, there are a number of public resources that compile information on drugs and ADR. It is therefore possible to link target and ADRs using drug entities as connecting elements. Here, we present T-ARDIS (Target-Adverse Reaction Database Integrated Search) database, a resource that provides comprehensive information on proteins and associated ADRs. By combining the information from drug-protein and drug-ADR databases, we statistically identify significant associations between proteins and ADRs. Besides describing the relationship between proteins and ADRs, T-ARDIS provides detailed description about proteins along with the drug and adverse reaction information. Currently T-ARDIS contains over 3000 ADR and 248 targets for a total of more 17 000 pairwise interactions. Each entry can be retrieved through multiple search terms including target Uniprot ID, gene name, adverse effect and drug name. Ultimately, the T-ARDIS database has been created in response to the increasing interest in identifying early in the drug development pipeline potentially problematic protein targets whose modulation could result in ADRs. Database URL: http://www.bioinsilico.org/T-ARDIS.

Galaxy InteractoMIX: An Integrated Computational Platform for the Study of Protein-Protein Interaction Data.

Protein interactions play a crucial role among the different functions of a cell and are central to our understanding of cellular processes both in health and disease. Here we present Galaxy InteractoMIX (http://galaxy.interactomix.com), a platform composed of 13 different computational tools each addressing specific aspects of the study of protein-protein interactions, ranging from large-scale cross-species protein-wide interactomes to atomic resolution level of protein complexes. Galaxy InteractoMIX provides an intuitive interface where users can retrieve consolidated interactomics data distributed across several databases or uncover links between diseases and genes by analyzing the interactomes underlying these diseases. The platform makes possible large-scale prediction and curation protein interactions using the conservation of motifs, interology, or presence or absence of key sequence signatures. The range of structure-based tools includes modeling and analysis of protein complexes, delineation of interfaces and the modeling of peptides acting as inhibitors of protein-protein interactions. Galaxy InteractoMIX includes a range of ready-to-use workflows to run complex analyses requiring minimal intervention by users. The potential range of applications of the platform covers different aspects of life science, biomedicine, biotechnology and drug discovery where protein associations are studied.

Emotion Assessment Using Feature Fusion and Decision Fusion Classification Based on Physiological Data: Are We There Yet?

Emotion recognition based on physiological data classification has been a topic of increasingly growing interest for more than a decade. However, there is a lack of systematic analysis in literature regarding the selection of classifiers to use, sensor modalities, features and range of expected accuracy, just to name a few limitations. In this work, we evaluate emotion in terms of low/high arousal and valence classification through Supervised Learning (SL), Decision Fusion (DF) and Feature Fusion (FF) techniques using multimodal physiological data, namely, Electrocardiography (ECG), Electrodermal Activity (EDA), Respiration (RESP), or Blood Volume Pulse (BVP). The main contribution of our work is a systematic study across five public datasets commonly used in the Emotion Recognition (ER) state-of-the-art, namely: (1) Classification performance analysis of ER benchmarking datasets in the arousal/valence space; (2) Summarising the ranges of the classification accuracy reported across the existing literature; (3) Characterising the results for diverse classifiers, sensor modalities and feature set combinations for ER using accuracy and F1-score; (4) Exploration of an extended feature set for each modality; (5) Systematic analysis of multimodal classification in DF and FF approaches. The experimental results showed that FF is the most competitive technique in terms of classification accuracy and computational complexity. We obtain superior or comparable results to those reported in the state-of-the-art for the selected datasets.

Using collections of structural models to predict changes of binding affinity caused by mutations in protein-protein interactions.

Protein-protein interactions (PPIs) in all the molecular aspects that take place both inside and outside cells. However, determining experimentally the structure and affinity of PPIs is expensive and time consuming. Therefore, the development of computational tools, as a complement to experimental methods, is fundamental. Here, we present a computational suite: MODPIN, to model and predict the changes of binding affinity of PPIs. In this approach we use homology modeling to derive the structures of PPIs and score them using state-of-the-art scoring functions. We explore the conformational space of PPIs by generating not a single structural model but a collection of structural models with different conformations based on several templates. We apply the approach to predict the changes in free energy upon mutations and splicing variants of large datasets of PPIs to statistically quantify the quality and accuracy of the predictions. As an example, we use MODPIN to study the effect of mutations in the interaction between colicin endonuclease 9 and colicin endonuclease 2 immune protein from Escherichia coli. Finally, we have compared our results with other state-of-art methods.

A Semi-Automatic Annotation Approach for Human Activity Recognition.

Modern smartphones and wearables often contain multiple embedded sensors which generate significant amounts of data. This information can be used for body monitoring-based areas such as healthcare, indoor location, user-adaptive recommendations and transportation. The development of Human Activity Recognition (HAR) algorithms involves the collection of a large amount of labelled data which should be annotated by an expert. However, the data annotation process on large datasets is expensive, time consuming and difficult to obtain. The development of a HAR approach which requires low annotation effort and still maintains adequate performance is a relevant challenge. We introduce a Semi-Supervised Active Learning (SSAL) based on Self-Training (ST) approach for Human Activity Recognition to partially automate the annotation process, reducing the annotation effort and the required volume of annotated data to obtain a high performance classifier. Our approach uses a criterion to select the most relevant samples for annotation by the expert and propagate their label to the most confident samples. We present a comprehensive study comparing supervised and unsupervised methods with our approach on two datasets composed of daily living activities. The results showed that it is possible to reduce the required annotated data by more than 89% while still maintaining an accurate model performance.