ACS Spring 2021
Apr 5 – 30, 2021 · Virtual
ACS Meetings & Expositions bring together chemistry professionals, educators, and students worldwide to discover and share research, network, and advance careers. These meetings are an excellent opportunity for professionals and students to showcase their work and connect with colleagues in all areas of chemistry. Participate in up to 4,000 hours of live interactive technical sessions, poster presentations, and more. Gain access to cutting-edge research at your pace over the course of four weeks.
Visit our poster in CHED division
Organic chemistry students’ self-determined motivation to practice
Erika Biró1, Judit Beagle2 , Ágnes Peragovics1, Daniel Taskó1
1ChemAxon Ltd, Záhony utca 7, Budapest, 1031, Hungary
2University of Dayton, Chemistry Department, 300 College Park, Dayton, OH, 45469, USA
In online learning, motivation is crucial for a better outcome. As learning is more facilitated through online technology during the COVID pandemic, we had the opportunity to do qualitative research on motivation and learning habits in an online organic chemistry class at the University of Dayton. The students enrolled in the class received optional chemistry practice quizzes on a regular basis in an online educational tool, Zosimos, and their engagement with the extra learning material was monitored throughout the semester. An online follow-up survey was also completed by the students to share insights about their practice habits. Our findings indicate that self-motivation to complete non-mandatory practice exercises is high. The majority of students used the non-mandatory resources beyond the mandatory homework to improve their understanding of organic chemistry and to prepare for exams. Student’s motivational dispositions were very similar and we were able to identify some patterns in how they chose non-mandatory practice material. First of all, they consider how closely the extra exercises relate to the core material but their personal interest in specific topics also appears to be an important aspect of their observed behavior. Furthermore, nomenclature, structure drawing, understanding reaction mechanisms, and organic syntheses seemed to be complicated topics for many students. Thus, the majority of the students preferred the quizzes addressing these problems in the online tool to improve their learning outcome.
Join our talk on 15 April 5:05 PM PDT
Automation of building reliable models
ChemAxon Ltd, Záhony utca 7, Budapest, 1031, Hungary
Volume and velocity of bioactivity data available in public or in-house sources represent an immense opportunity to be exploited in novel compound design. Wider and wider array of targets with labelled data necessitates efficient solutions to build a large number of individual models. Velocity of data growth provides the possibility to yield higher accuracy through continuous re-training of the existing models. Automatic re-training maximizes the applicability domain and minimizes the risk of accuracy drop while a project expands into novel chemical series. Based on the recognition of these requirements we launched a project to develop an automated solution for model building relying on ChemAxon chemical toolkits and Smile Java library. Validation of the prediction power and reliability is a key factor in case of machine learning. In order to give an estimation of the prediction error we implemented and tested the conformal prediction framework. Applicability domain calculation based on chemical and descriptor space similarity were introduced to provide a tool that supports the assessment of the predicted values. Summary of descriptor selection, machine learning algorithms (RF, SVR) and hyperparameter optimization for a bioactivity data set including >150 ChEMBL targets will be presented. This pool varies in size (from hundreds to thousands) and covers a large spectrum of pharmaceutically relevant targets. Our results showed 0.8< median Pearson correlation value for these targets measured on the test sets. hERG ion channel inhibition is one of the most important safety related off-target. Related liabilities are to be recognized and filtered out early on during drug design. As a case study we present detailed results on hERG model development.
Visit conference website.