Harnessing Shannon entropy-based descriptors in machine learning models to enhance the prediction accuracy of molecular properties

A data science roadmap for open science organizations engaged in early-stage drug discovery

The Structural Genomics Consortium is an international open science research organization with a focus on accelerating early-stage drug discovery, namely hit discovery and optimization. We, as many others, believe that artificial intelligence (AI) is poised to be a main accelerator in the field. The question is then how to best benefit from recent advances in AI and how to generate, format and disseminate data to enable future breakthroughs in AI-guided drug discovery. We present here the recommendations of a working group composed of experts from both the public and private sectors. Robust data management requires precise ontologies and standardized vocabulary while a centralized database architecture across laboratories facilitates data integration into high-value datasets. Lab automation and opening electronic lab notebooks to data mining push the boundaries of data sharing and data modeling. Important considerations for building robust machine-learning models include transparent and reproducible data processing, choosing the most relevant data representation, defining the right training and test sets, and estimating prediction uncertainty. Beyond data-sharing, cloud-based computing can be harnessed to build and disseminate machine-learning models. Important vectors of acceleration for hit and chemical probe discovery will be (1) the real-time integration of experimental data generation and modeling workflows within design-make-test-analyze (DMTA) cycles openly, and at scale and (2) the adoption of a mindset where data scientists and experimentalists work as a unified team, and where data science is incorporated into the experimental design.

Inferring molecular inhibition potency with AlphaFold predicted structures

Even though in silico drug ligand-based methods have been successful in predicting interactions with known target proteins, they struggle with new, unassessed targets. To address this challenge, we propose an approach that integrates structural data from AlphaFold 2 predicted protein structures into machine learning models. Our method extracts 3D structural protein fingerprints and combines them with ligand structural data to train a single machine learning model. This model captures the relationship between ligand properties and the unique structural features of various target proteins, enabling predictions for never before tested molecules and protein targets. To assess our model, we used a dataset of 144 Human G-protein Coupled Receptors (GPCRs) with over 140,000 measured inhibition constants (Ki) values. Results strongly suggest that our approach performs as well as state-of-the-art ligand-based methods. In a second modeling approach that used 129 targets for training and a separate test set of 15 different protein targets, our model correctly predicted interactions for 73% of targets, with explained variances exceeding 0.50 in 22% of cases. Our findings further verified that the usage of experimentally determined protein structures produced models that were statistically indistinct from the Alphafold synthetic structures. This study presents a proteo-chemometric drug screening approach that uses a simple and scalable method for extracting protein structural information for usage in machine learning models capable of predicting protein-molecule interactions even for orphan targets.

Shannon entropy of performance metrics to choose the best novel hybrid algorithm to predict groundwater level (case study: Tabriz plain, Iran)

Predicting groundwater level (GWL) fluctuations, which act as a reserve water reservoir, particularly in arid and semi-arid climates, is vital in water resources management and planning. Within the scope of current research, a novel hybrid algorithm is proposed for estimating GWL values in the Tabriz plain of Iran by combining the artificial neural network (ANN) algorithm with newly developed nature-inspired Coot and Honey Badger metaheuristic optimization algorithms. Various combinations of meteorological data such as temperature, evaporation, and precipitation, previous GWL values, and the month and year values of the data were used to evaluate the algorithm's success. Furthermore, the Shannon entropy of model performance was assessed according to 44 different statistical indicators, classified into two classes: accuracy and error. Hence, based on the high value of Shannon entropy, the best statistical indicator was selected. The results of the best model and the best scenario were analyzed. Results indicated that value of Shannon entropy is higher for the accuracy class than error class. Also, for accuracy and error class, respectively, Akaike information criterion (AIC) and residual sum of squares (RSS) indexes with the highest entropy value which is equal to 12.72 and 7.3 are the best indicators of both classes, and Legate-McCabe efficiency (LME) and normalized root mean square error-mean (NRMSE-Mean) indexes with the lowest entropy value which is equal to 3.7 and - 8.3 are the worst indicators of both classes. According to the evaluation best indicator results in the testing phase, the AIC indicator value for HBA-ANN, COOT-ANN, and the standalone ANN models is equal to - 344, - 332.8, and - 175.8, respectively. Furthermore, it was revealed that the proposed metaheuristic algorithms significantly improve the performance of the standalone ANN model and offer satisfactory GWL prediction results. Finally, it was concluded that the Honey Badger optimization algorithm showed superior results than the Coot optimization algorithm in GWL prediction.