Due to the growth computational power and easy access to vast amounts of biological data, machine learning (ML) models are being increasingly considered within the field of Rational Drug Design (RDD). In RDD, molecular docking methods are employed to predict the optimal binding mode of a small molecule (ligand) in the binding site of a target receptor (typically a protein). Molecular docking software utilizes Scoring Functions (SFs) to estimate the protein-ligand binding affinity. These SFs can be classified according to their development methodology: Physics-based, Empirical, Knowledge-based, and ML-based. ML-based SFs are trained using features extracted from protein-ligand complexes with known experimental affinities, relying heavily on the attributes used during training. Both the input data and the selected features can significantly impact the accuracy of the SFs. Additionally, different ML algorithms can be applied to select the most appropriate features and propose the SF model. In this study we propose RFL-Score, a novel ML-based SF using Random Forest with Lasso regression. RFL-Score is a ready-to-use SF developed with a straightforward methodology and trained exclusively on open-access biomolecular data. Only open-source software was employed for extracting features from the proteins, ligands, and complexes. The proposed SF was evaluated using the well-established CASF-2016 benchmark achieving outstanding performance compared to other SFs. The RFL-Score scoring function and elements used for training are freely available on GitHub at https://github.com/rflscore.

This complete work on innovative practices presents a proposal for a framework applied in an engineering discipline based on hybrid teaching and active methodologies, carefully planned to allow students to contextualize their essential content added to the social impact of their profession. This proposal seeks to guarantee the possibility of assimilating learning between lines and between years of study, guaranteeing connectivity between the teaching teams of the interdisciplinary faculty, between the lines of the curriculum, and between students, inside and outside their formal studies and the classroom. In this way, we provide not only the development of technical skills but also contemplate one of the significant challenges in engineering education, which is the development of socially relevant engineering curricula, thus strengthening the intrinsic motivation and adaptability of the student. In the face of the ongoing transformations in the engineering field - especially considering the rise of Industry 4.0 - professionals in this area must get an inter and trans disciplinary education, in close touch with society and industry needs. This calls for educational practices that stimulate entrepreneur development, dynamical skills, and traditional technical knowledge. In this work, we propose the 4D CV framework based on hybrid teaching and new trends in teaching and learning based on active methodologies, seeking to train a future professional who acts as an active agent in society, capable of facing the challenges of Engineering in the 21st century. We create learning environments that allow for (i) the development of capacity and motivation for teamwork in a technical, multi, and interdisciplinary way; (ii) a creative environment aiming for a comprehensive education along with entrepreneurial spirit and ability to innovate; (iii) reflection and discussion that favor independent critical thinking; (iv) actions that strengthen the university's relationship with the local community allowing closer relation with society and the productive sector. The proposed framework was the subject of a case study applied in the discipline of Curricular Integration Activities IV, of the undergraduate course in Automation Engineering of a Federal University of Brazil, where the technique of the Discourse of the Collective Subject (DCS) to capture the impression of those involved in the study (students, teachers and partner companies). It was possible that the practices of the proposed curriculum project could provide students with inter and multidisciplinarity in their learning process. In addition, students have been motivated in the face of involvement with the needs of society, achieved through practice in an innovative project in which the challenge was based on the real pains/demands/needs of a real startup company, formed by graduates of the course itself, already established in the market. We can thus conclude not only the tremendous innovative potential of our curricular proposal in the face of the significant challenges in engineering education but also its innovative character in approaches to higher education in Brazil.

This complete work on innovative practices presents a proposal for inserting extension through actions in projects. The current university format in Brazil considers the in-dissociability between teaching, research, and extension. The first two are the most known dimensions, and extension constitutes an interdisciplinary, educational policy, cultural, scientific, and technological process, promoting the transforming interaction between the higher education institutions and society's other sectors, through the knowledge production and application, in permanent joint with research and teaching. In 2014, Brazil's Department of Education instituted the Education National Plan (in Portuguese, “Plano Nacional de Educação” (PNE)), which is still valid until 2023. One of its goals defines that at least 10% of the curricular credits for undergraduate courses must be integrated through extension programs or projects, prioritizing areas of great social relevance. At the same time, since 2019, Education National Conceil has instituted the new National Curricular Guidelines for the Engineering Undergraduate Courses, shifting the focus from the technical content to a new approach considering skills and competencies with the same importance for student education. Within this context, the challenge was to include extension activities, competencies, and skills in the curriculum of three undergraduate courses: Computing Engineering, Automation Engineering, and Information Systems. These courses are in an environment where the project culture is well-established, together with two graduate programs in the field of Computing. Moreover, most of these are research projects, where some activities can be characterized as extension. Also, professors of these courses are involved in specific extension projects. Considering all this context, the innovative practice proposed was to propose a curriculum framework for our undergraduate courses including project activities in the formal curriculum of students, taking place from 10% of traditional classroom training, in a curricular space-time where it is possible to work skills and competencies within real-life problems. In fact, some students experience this project environment but without any curricular formalization. In an empirical analysis of our former students, it is consensual that students who experience projects have a better education than those who only have a traditional classroom environment. The expected result is a curriculum that democratizes all the education spaces in the courses, including components in addition to those already worked in the traditional classroom. Also, it expected the extension as an educational process defined and carried out based on the reality requirements, in a way that university extension be part of the solution to the Brasil social problems.

The Electric-Arc Welding process is affected by several physical phenomena which have a direct impact on the final product quality. To understand and improve weld deposition is a key challenge to upgrade the overall metallic welding process. However, controlling the welding process of continuously fed melting wire electrode is still an open problem, which has not yet been solved. In order to study the phenomenon involved in the metallic transfer in linear welding, we employ a high-speed camera and laser lighting equipment to record the deposition images using two distinct imaging setups. Combining the image acquisition setup with voltage, current and wire speed data, we are able to obtain a dataset of distinct welding conditions, which allow us to observe critical aspects of the deposition. We present an acquisition methodology for generating a weld image dataset, as well as a software tool that makes possible to analyze, process and visualize each frame from recorded linear welding, providing per sample statistics and a framework to draw annotations of the due video. Through visual information and inferential statistics, we are able to identify how each parameter influences the weld of thick steel plates. Furthermore, we believe the tools provided will enable researchers to evaluate the deposition process and, thus, foster the development of hardware, software, and control techniques related to the field.

BACKGROUND: One of the goals of the Systems Biology community is to have a detailed map of all biological interactions in an organism. One small yet important step in this direction is the creation of biological networks from post-genomic data. Bayesian networks are a very promising model for the inference of regulatory networks in Systems Biology. Usually, Bayesian networks are sampled with a Markov Chain Monte Carlo (MCMC) sampler in the structure space. Unfortunately, conventional MCMC sampling schemes are often slow in mixing and convergence. To improve MCMC convergence, an alternative method is proposed and tested with different sets of data. Moreover, the proposed method is compared with the traditional MCMC sampling scheme. RESULTS: In the proposed method, a simpler and faster method for the inference of regulatory networks, Graphical Gaussian Models (GGMs), is integrated into the Bayesian network inference, trough a Hierarchical Bayesian model. In this manner, information about the structure obtained from the data with GGMs is taken into account in the MCMC scheme, thus improving mixing and convergence. The proposed method is tested with three types of data, two from simulated models and one from real data. The results are compared with the results of the traditional MCMC sampling scheme in terms of network recovery accuracy and convergence. The results show that when compared with a traditional MCMC scheme, the proposed method presents improved convergence leading to better network reconstruction with less MCMC iterations. CONCLUSIONS: The proposed method is a viable alternative to improve mixing and convergence of traditional MCMC schemes. It allows the use of Bayesian networks with an MCMC sampler with less iterations. The proposed method has always converged earlier than the traditional MCMC scheme. We observe an improvement in accuracy of the recovered networks for the Gaussian simulated data, but this improvement is absent for both real data and data simulated from ODE.

MOTIVATION: An important problem in systems biology is the inference of biochemical pathways and regulatory networks from postgenomic data. Various reverse engineering methods have been proposed in the literature, and it is important to understand their relative merits and shortcomings. In the present paper, we compare the accuracy of reconstructing gene regulatory networks with three different modelling and inference paradigms: (1) Relevance networks (RNs): pairwise association scores independent of the remaining network; (2) graphical Gaussian models (GGMs): undirected graphical models with constraint-based inference, and (3) Bayesian networks (BNs): directed graphical models with score-based inference. The evaluation is carried out on the Raf pathway, a cellular signalling network describing the interaction of 11 phosphorylated proteins and phospholipids in human immune system cells. We use both laboratory data from cytometry experiments as well as data simulated from the gold-standard network. We also compare passive observations with active interventions. RESULTS: On Gaussian observational data, BNs and GGMs were found to outperform RNs. The difference in performance was not significant for the non-linear simulated data and the cytoflow data, though. Also, we did not observe a significant difference between BNs and GGMs on observational data in general. However, for interventional data, BNs outperform GGMs and RNs, especially when taking the edge directions rather than just the skeletons of the graphs into account. This suggests that the higher computational costs of inference with BNs over GGMs and RNs are not justified when using only passive observations, but that active interventions in the form of gene knockouts and over-expressions are required to exploit the full potential of BNs. AVAILABILITY: Data, software and supplementary material are available from http://www.bioss.sari.ac.uk/staff/adriano/research.html