Interpretable molecular encodings and representations for machine learning tasks.

Molecular encodings and their usage in machine learning models have demonstrated significant breakthroughs in biomedical applications, particularly in the classification of peptides and proteins. To this end, we propose a new encoding method: Interpretable Carbon-based Array of Neighborhoods (iCAN). Designed to address machine learning models' need for more structured and less flexible input, it captures the neighborhoods of carbon atoms in a counting array and improves the utility of the resulting encodings for machine learning models.

Misuse of Substitution Drugs in the Substitution-Based Therapy.

Background: The reasons for, and the extent of, misuse of prescribed substitution medication as well as parallel consumption of other drugs during substitution-based therapy have still not been adequately researched in Germany.

Methods: This study examines the use of substitution medication in German substitution clinics utilizing a nationwide survey with anonymised questionnaires.

Results: The analysis of the 605 questionnaires showed a 30-day consumption prevalence of 8.