Prediction of Optimal Conditions of Hydrogenation Reaction Using the Likelihood Ranking Approach

The selection of experimental conditions leading to a reasonable yield is an important and essential element for the automated development of a synthesis plan and the subsequent synthesis of the target compound. The classical QSPR approach, requiring one-to-one correspondence between chemical structure and a target property, can be used for optimal reaction conditions prediction only on a limited scale when only one condition component (e.g., catalyst or solvent) is considered. However, a particular reaction can proceed under several different conditions. In this paper, we describe the Likelihood Ranking Model representing an artificial neural network that outputs a list of different conditions ranked according to their suitability to a given chemical transformation. Benchmarking calculations demonstrated that our model outperformed some popular approaches to the theoretical assessment of reaction conditions, such as k Nearest Neighbors, and a recurrent artificial neural network performance prediction of condition components (reagents, solvents, catalysts, and temperature). The ability of the Likelihood Ranking model trained on a hydrogenation reactions dataset, (~42,000 reactions) from Reaxys® database, to propose conditions that led to the desired product was validated experimentally on a set of three reactions with rich selectivity issues.

A Hybrid Estimation of Distribution Algorithm for the Quay Crane Scheduling Problem

The aim of the quay crane scheduling problem (QCSP) is to identify the best sequence of discharging and loading operations for a set of quay cranes. This problem is solved with a new hybrid estimation of distribution algorithm (EDA). The approach is proposed to tackle the drawbacks of the EDAs, i.e., the lack of diversity of solutions and poor ability of exploitation. The hybridization approach, used in this investigation, uses a distance based ranking model and the moth-flame algorithm. The distance based ranking model is in charge of modelling the solution space distribution, through an exponential function, by measuring the distance between solutions; meanwhile, the heuristic moth-flame determines who would be the offspring, with a spiral function that identifies the new locations for the new solutions. Based on the results, the proposed scheme, called QCEDA, works to enhance the performance of those other EDAs that use complex probability models. The dispersion results of the QCEDA scheme are less than the other algorithms used in the comparison section. This means that the solutions found by the QCEDA are more concentrated around the best value than other algorithms, i.e., the average of the solutions of the QCEDA converges better than other approaches to the best found value. Finally, as a conclusion, the hybrid EDAs have a better performance, or equal in effectiveness, than the so called pure EDAs.