The Recurrent Hopfield Mass Model (RHoMM) is a novel generative model developed for the estimation of large-scale effective connectivity from magnetoencephalography (MEG) Band Limited Power signals. This binary mass model, compared to the other popular generative models, has the advantages of being data-driven and in principle scalable to encode large-scale systems interactions. The aim of this work is to evaluate the scalability of the RHoMM and to optimize it at different network sizes (20-200 nodes). Specifically, using simulated objective networks with different architectures, we analysed the effects of L1 rows' normalization and of the addition of a bias in the training. We obtained that in RHoMM without normalization wider intervals of larger learning rates and convergence speeds, associated with lower errors in the inference of the effective connectivity matrix, can be obtained compared to the implementation with normalization, independently from the objective network architecture. Thus, the selection of the learning rate in this case is less critical than with normalization. To also validate the model on experimental data, we employed a dataset of MEG recordings from 10 subjects and a network size of 155 nodes. The obtained results suggest that the model could be effectively scaled to estimate standard-size MEG connectomes.

The architecture of communication within the brain, represented by the human connectome, has gained a paramount role in the neuroscience community. Several features of this communication, e.g., the frequency content, spatial topology, and temporal dynamics are currently well established. However, identifying generative models providing the underlying patterns of inhibition/excitation is very challenging. To address this issue, we present a novel generative model to estimate large-scale effective connectivity from MEG. The dynamic evolution of this model is determined by a recurrent Hopfield neural network with asymmetric connections, and thus denoted Recurrent Hopfield Mass Model (RHoMM). Since RHoMM must be applied to binary neurons, it is suitable for analyzing Band Limited Power (BLP) dynamics following a binarization process. We trained RHoMM to predict the MEG dynamics through a gradient descent minimization and we validated it in two steps. First, we showed a significant agreement between the similarity of the effective connectivity patterns and that of the interregional BLP correlation, demonstrating RHoMM's ability to capture individual variability of BLP dynamics. Second, we showed that the simulated BLP correlation connectomes, obtained from RHoMM evolutions of BLP, preserved some important topological features, e.g, the centrality of the real data, assuring the reliability of RHoMM. Compared to other biophysical models, RHoMM is based on recurrent Hopfield neural networks, thus, it has the advantage of being data-driven, less demanding in terms of hyperparameters and scalable to encompass large-scale system interactions. These features are promising for investigating the dynamics of inhibition/excitation at different spatial scales.

MOTIVATION: Thermal properties of proteins are of great importance for a number of theoretical and practical implications. Predicting the thermal stability of a protein is a difficult and still scarcely addressed task. RESULTS: Here, we introduce Thermometer, a webserver to assess the thermal stability of a protein using structural information. Thermometer is implemented as a publicly available, user-friendly interface. AVAILABILITY AND IMPLEMENTATION: Our server can be found at the following link (all major browser supported): http://service.tartaglialab.com/new_submission/thermometer_file. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Monoclonal antibodies are essential tools in the contemporary therapeutic armory. Understanding how these recognize their antigen is a fundamental step in their rational design and engineering. The rising amount of publicly available data is catalyzing the development of computational approaches able to offer valuable, faster and cheaper alternatives to classical experimental methodologies used for the study of antibody-antigen complexes. RESULTS: Here, we present proABC-2, an update of the original random-forest antibody paratope predictor, based on a convolutional neural network algorithm. We also demonstrate how the predictions can be fruitfully used to drive the docking in HADDOCK. AVAILABILITY AND IMPLEMENTATION: The proABC-2 server is freely available at: https://wenmr.science.uu.nl/proabc2/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Understanding the molecular mechanisms of thermal stability is a challenge in protein biology. Indeed, knowing the temperature at which proteins are stable has important theoretical implications, which are intimately linked with properties of the native fold, and a wide range of potential applications from drug design to the optimization of enzyme activity. RESULTS: Here, we present a novel graph-theoretical framework to assess thermal stability based on the structure without any a priori information. In this approach we describe proteins as energy-weighted graphs and compare them using ensembles of interaction networks. Investigating the position of specific interactions within the 3D native structure, we developed a parameter-free network descriptor that permits to distinguish thermostable and mesostable proteins with an accuracy of 76% and area under the receiver operating characteristic curve of 78%. AVAILABILITY AND IMPLEMENTATION: Code is available upon request to [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Determination of drug absorption is an important component of the drug discovery and development process in that it plays a key role in the decision to promote drug candidates to clinical trials. We have developed a method that, on the basis of an analysis of the dynamic distribution of water molecules around a compound obtained by molecular dynamics simulations, can compute a parameter-free value that correlates very well with the compound permeability measured using the human colon adenocarcinoma (Caco-2) cell line assay. RESULTS: The method has been tested on twenty-three neutral drugs for which a consistent set of experimental data is available. We show here that our method reproduces the experimental data better than other existing tools. Furthermore it provides a detailed view of the relationship between the hydration and the permeability properties of molecules. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.