DeepRank-GNN: A Graph Neural Network Framework to Learn Patterns in Protein-Protein Interfaces

Gaining structural insights into the protein-protein interactome is essential to understand biological phenomena and extract knowledge for rational drug design or protein engineering. We have previously developed DeepRank, a deep-learning framework to facilitate pattern learning from protein-protein interfaces using Convolutional Neural Network (CNN) approaches. However, CNN is not rotation invariant and data augmentation is required to desensitize the network to the input data orientation which dramatically impairs the computation performance. Representing protein-protein complexes as atomic- or residue-scale rotation invariant graphs instead enables using graph neural networks (GNN) approaches, bypassing those limitations. We have developed DeepRank-GNN, a framework that converts protein-protein interfaces from PDB 3D coordinates files into graphs that are further provided to a pre-defined or user-defined GNN architecture to learn problem-specific interaction patterns. DeepRank-GNN is designed to be highly modularizable, easily customized, and is wrapped into a user-friendly python3 package. Here, we showcase DeepRank-GNN's performance for scoring docking models using a dedicated graph interaction neural network (GINet). We show that this graph-based model performs better than DeepRank, DOVE and HADDOCK scores and competes with iScore on the CAPRI score set. We show a significant gain in speed and storage requirement using DeepRank-GNN as compared to DeepRank. DeepRank-GNN is freely available from https://github.com/DeepRank/DeepRank-GNN.

Attitude and Perceived Barriers towards Research among Undergraduate Medical Students of Bangladesh (Preprint)

BACKGROUND Undergraduate research opportunities teach students not only how to conduct research, but they too learn problem-solving aptitudes. Participating in research also increases students' interest in being involved and making special contributions to the academic field. OBJECTIVE The aim of our study was intended to assess the attitude and perceived barriers toward research among the medical undergraduates of Bangladesh. METHODS A cross-sectional questionnaire based survey was conducted among third, fourth, and fifth year students of medical colleges in Bangladesh, during the month of July, 2020 to December, 2020. A Google-linked questionnaire was disseminated to the students via different social platform and the responses were received through Google drive. RESULTS The questionnaire of the survey received responses from 1279 students, with 94% claiming to be familiar with the scientific method. Most of the students (82.7%) mentioned that they could design and execute a research project as well as can write scientific articles. More than half of the respondents (66.4%) expressed an interest in participating in research. Almost all respondents (96.7%) agreed that research is beneficial as it aid in critical thinking and policy implementation. Almost two-third of respondents (79.8%) opined that education on research methodology is required in the medical curriculum. Majority of the respondents reported that inadequate time and priorities (89.1%), insufficient guidance (86.6%), inadequate familiarities with research methodology (87.5%) and statistical analysis (85.2%) were the barriers of research. CONCLUSIONS Findings of this study indicated that Bangladeshi medical students had a positive attitude toward research and they wish that research methodology should be taught in undergraduate medical education. In order to increase participation in research, the challenges identified by students may be addressed.

Big Data Support for Problem Solving Method in Mass Spectrometry Topic in Modern Analytical Chemistry Course

Extremely large and unpredictable user generation of data, all digitized and stored in large data repositories is built up by scientists, especially from modern analytical chemistry. This study aims to build a new approach in chemistry education, by utilizing Big Data sources to support IDEAL (I-Identify problem, D-Define goal, E-Explore possible strategies, A-anticipate outcomes and act, L-Look back and learn) Problem Solving learning model. Modern analytical chemistry studies and uses instruments to analize chemical compounds up to structural analysis. Modern instruments, such as mass spectrometer, generate information of compounds and stored in big data bank. This must be able to be accessed and used in chemistry education. This report would be around the benefits of using Big Data during learning process in this digital era, through IDEAL Problem Solving learning. Some preliminary progress would be presented. The growing number of data and resources would change also teaching and learning methodology in higher education. Some highlights about disruptive learning innovation would be described

Attitude and Perceived Barriers towards Research among Undergraduate Medical Students of Bangladesh

Background: Undergraduate research opportunities teach students not only how to conduct research, but they too learn problem-solving aptitudes. Participating in research also increases students' interest is being involved and making special contributions to the academic field. Therefore, the aim of our study was intended to assess the attitude and perceived barriers toward research among the medical undergraduates of Bangladesh. Methods: A cross-sectional questionnaire survey was conducted among third, fourth, and fifth year students across medical colleges in Bangladesh, during the month of July, 2020 to December, 2020. A Google-linked questionnaire was disseminated to the students via different social platform and the responses were received through Google drive. Result: The questionnaire survey received responses from 1279 students, with 94% claiming to be familiar with the scientific method. 82.7% of students mentioned they could design and execute a research project as well as can write scientific articles. More than half of the respondents (66.4%) expressed an interest in participating in research. Almost all respondents (96.7%) agreed that research is beneficial as it aid critical thinking and policy implementation. 79.8% of respondents opined that education on research methodology should be required in the medical curriculum. Majority of the respondents reported that lack of time and priorities to do research work because of compact academic tasks (89.1%), insufficient guidance (86.6%), lack of familiarities with research methodology (87.5%) and statistical analysis (85.2%) are the barriers of research. Conclusion: Our findings indicated that Bangladeshi medical students have a positive attitude toward research and that research methodology should be taught in undergraduate medical education. In order to increase participation in research, the challenges identified by students should be addressed.

Immersive virtual reality as a tool to learn problem-solving skills

Immersive virtual reality (IVR) technology has demonstrated positive educational outcomes related to its use and is gaining traction in educational and training settings; IVR is expected to have widespread adoption within the classroom in the upcoming years. However, the educational potential of IVR has not been thoroughly investigated, especially as a tool for problem-solving skills. Therefore, this study was designed to answer the following questions: (1) Is IVR a useful tool to learn and practice problem-solving skills? More specifically, do children using IVR solve a game better than those using a tablet application or a board game? (2) Does IVR provide a more engaging experience for children to practice problem-solving skills than on a tablet or a board game? (3) Do problem-solving skills learned with IVR technology transfer to real-life (physical game)? Children (n = 120) aged 7–9.9 years were randomly assigned to a problem-solving game in one of three conditions: board game, tablet, or IVR. The results showed that, overall, the percentage of children who completed the problem-solving game was higher in the IVR condition (77.5%), compared with those in the tablet (32.5%) or board game (30%) conditions. We also found that the interest and enjoyment scores of participants using IVR were significantly higher than participants in the other two conditions, and that the children in the IVR condition were able to learn how to solve the problem and transfer their learning to the physical game. IVR is a technology capable of engaging interest and motivating the user, as well as having the potential to assist in cognitive processing and knowledge transfer.

Pengaruh Motivasi Belajar, Kemampuan Pemecahan Masalah, dan Hasil Belajar Terhadap Kesiapan Kerja Siswa Kelas XII Pemesinan SMK Pemuda 3 Kesamben, Blitar

Education is the quality improvement efforts of students to follow technological developments as well as add a breadth in order to be able to compete in further education or in the world of work. In an attempt to influence students in quality improvement by the motivation to learn, problem-solving ability, and the results of the study. This research aims to know the: (1) influence of Learning Motivation towards Work Readiness of students (2) Influences the ability of problem solving students ' Work against Italy (3) Influence the Learning Outcome against Italy work (4) influence of Learning Motivation, Ability of problem solving, and Learning Outcomes against the Work Readiness. This research is the research of ex post-facto. The subject of this research is the whole grade Machining XII SMK Pemuda 3 Kesamben, Blitar as much as 94 students. Now using the method of data collection and documentation. Test instrument of research carried out in the SMK Pemuda 3 Kesamben, Blitar. Testing analysis of the linearity test and the test covers multicollinearity. Data analysis technique used is a simple regression analysis techniques to hepotesis first, second third hypothesis, hypothesis and regression analysis of the double for the fourth hypothesis. Based on the results of research on the first hypothesis of 75.7% which means the direct effect; the second hypothesis of 83.3% of the direct effect; the third hypothesis of 2.6% which means the effect is not immediate; whereas the fourth hypothesis of 23.3% to 65.7%, learning motivation for problem-solving ability, and 2.7% for the results of a study which means there is a direct and indirect influence against the working class XII student readiness Machining SMK Pemuda 3 Kesamben, Blitar. Keywords: The Motivation To Learn, Problem-Solving Abilities, Learning Outcomes, And Work Readiness

Education and Theory of Psychological and Cognitive Barriers

The author identifies the psychological and cognitive barriers (PCBs) in the students' consciousness in schooling as the very important factor of the contemporary education system crisis. Focusing on the unresolved “how to learn” problem, the author reveals the essence of PCBs, their causes, and models for overcoming them. At the same time, the main attention is paid to the social aspect of insurmountable PCBs at school. It is about the education failure of schoolchildren, which predetermines their life and professional failure. And this, in turn, predetermines their negative value orientation in social exchange. As a result, the society receives a low-quality educational component of human capital, which is less and less in demand on the labor market due to the technological challenges of the future. The PCBs overcoming creates conditions for the success of schoolchildren as future carriers of high-quality human capital, able to ensure stable economic growth thanks to the activities of highly educated and intellectually autonomous professionals.

ANALYSIS OF THE EXPECTATIONS AND COMPATIBILITY OF THE PARTICIPANTS IN THE EDUCATIONAL PROCESS IN THE REALIZATION OF PROBLEMS IN MATHEMATICS

There is no universal solution for successful math education. Many roads lead to this goal, some of which are radically different from others. Perhaps attention should be paid to more training in problem-solving; less arrogance and more understanding; learning in context; accounting not only the results, but also the necessary strategies and learning processes. Everyone has to solve problems in their life. The ability to cope with them is a necessity to be successful and competitive in today's society.This article examines the essence of problem education, its characteristics and conditions for the application in mathematics education. Different ways and means have been outlined to help solve a problematic situation during the lesson. Different levels of feasibility of the conditions also determine different levels of implementation of the problem approach. In problematic training, the teacher puts the students in a problematic situation and directs them towards solving it. Looking at it from different perspectives, even if they are wrong, this is extremely useful for understanding all logical links between objects. Any false hypothesis is correlated with new facts or arguments that lead to its rejection. The students, alone or with the help of the teacher, seek and discover the truth, the solution, the fact. The teacher, who has pre-prepared problems and facts, "directs" the process of discovering the new knowledge. With learning through discovery, students do not receive knowledge, but learn about the process of reaching it, and achieve creative goals in learning. Drawn to the discovery of the unknown knowledge, they become active participants in the learning process. The new knowledge they find is memorized more durably because the result has not been just announced to them, instead they have been involved in the search for the logical connectivity and validity of mathematics. They learn to look for different solutions to the problem and to not to be afraid if they get the wrong one. The exhaustion of all possible choices and choosing the right, through indisputable arguments, is a skill that will be extremely necessary in their life.For this research it was conducted a study on "Problem Mathematics Training - Expectations and Results". An analysis of the survey results was made by the participants in the educational process in mathematics - teachers and students with whom the problem education was conducted. The positive results by problem solving make a big impression- greater student activity, increased motivation to learn, problem solving skills, better teamwork. Students realize that math is necessary in life, it has become more interesting to them in class, they are challenged to solve problems and are satisfied with the new knowledge they have discovered. A significant part of the teachers are pleased with the use of problematic math education, but they also point out the problems they have encountered - lack of appropriate tasks in textbooks, methodological development and guidance, more time necessary to prepare the lesson itself.

MAKING UNDERGRADUATE RESEARCH EXPERIENCE MORE PRODUCTIVE

Problem analysis is taught in the classroomenvironment by having students solve problems that oftenhave ready solutions. Because classroom problems areoften solvable within an hour, problem analysis, as oneCEAB (Canadian Engineering Accreditation Board)graduate attribute, may be viewed separately from othergraduate attributes. Students participating inundergraduate research, however, learn problem analysisby also developing investigative skills, use of engineeringtools (Matlab, Excel), even communication skills. In thispaper we discuss our undergraduate research experiencefrom perspectives of mentor and mentee. Mentor'smotivation to recruit undergraduate research studentscould include (i) high probability of finding talentedstudents to work on project of relatively short duration(i.e., one year) and (ii) producing solutions to a variety ofproblems that could lead to research problems. Thesemotivations align well with motivations of undergraduateresearch mentees, i.e., experience in solving morerealistic (open-ended) problems and strengthening theirresearch portfolios. Generating "real world" problemscan be achieved by introducing student-proposed designor analysis project component into a third-year course.Projects completed can then be continued into summerresearch projects. Results from the summer projects inturn enrich the third-year course content. To makeundergraduate research experience more productive,mentor encourages mentee to write and present together aconference paper, such as CEEA 2018 Conference.National-level conference experience would strengthenstudent's research portfolio. Projects with highertechnical content could even be presented to engineeringconferences, which is what we are aiming for. We discussways to increase student participation. We provide acourse project template for faculty members who areinterested in adopting our experience into their teachingand research activities.