Search

Mohammad Hassan Khalid,1 Pezhman Kazemi,1 Lucia Perez-Gandarillas,2 Abderrahim Michrafy,2 Jakub Szlęk,1 Renata Jachowicz,1 Aleksander Mendyk1 1Department of Pharmaceutical Technology and Biopharmaceutics, Faculty of Pharmacy, Jagiellonian University Medical College, Krakow, Poland; 2Centre National de la Recherche Scientifique, Centre RAPSODEE, Mines Albi, Université de Toulouse, Albi, France Abstract: The effects of different formulations and manufacturing process conditions on the physical properties of a solid dosage form are of importance to the pharmaceutical industry. It is vital to have in-depth understanding of the material properties and governing parameters of its processes in response to different formulations. Understanding the mentioned aspects will allow tighter control of the process, leading to implementation of quality-by-design (QbD) practices. Computational intelligence (CI) offers an opportunity to create empirical models that can be used to describe the system and predict future outcomes in silico. CI models can help explore the behavior of input parameters, unlocking deeper understanding of the system. This research endeavor presents CI models to predict the porosity of tablets created by roll-compacted binary mixtures, which were milled and compacted under systematically varying conditions. CI models were created using tree-based methods, artificial neural networks (ANNs), and symbolic regression trained on an experimental data set and screened using root-mean-square error (RMSE) scores. The experimental data were composed of proportion of microcrystalline cellulose (MCC) (in percentage), granule size fraction (in micrometers), and die compaction force (in kilonewtons) as inputs and porosity as an output. The resulting models show impressive generalization ability, with ANNs (normalized root-mean-square error [NRMSE] =1%) and symbolic regression (NRMSE =4%) as the best-performing methods, also exhibiting reliable predictive behavior when presented with a challenging external validation data set (best achieved symbolic regression: NRMSE =3%). Symbolic regression demonstrates the transition from the black box modeling paradigm to more transparent predictive models. Predictive performance and feature selection behavior of CI models hints at the most important variables within this factor space. Keywords: computational intelligence, artificial neural network, symbolic regression, feature selection, die compaction, porosity

Pezhman Kazemi,1 Mohammad Hassan Khalid,1 Ana Pérez Gago,2 Peter Kleinebudde,2 Renata Jachowicz,1 Jakub Szlęk,1 Aleksander Mendyk1 1Department of Pharmaceutical Technology and Biopharmaceutics, Faculty of Pharmacy, Jagiellonian University Medical College, Krakow, Poland; 2Institute of Pharmaceutics and Biopharmaceutics, Heinrich-Heine-University, Düsseldorf, Germany Abstract: Dry granulation using roll compaction is a typical unit operation for producing solid dosage forms in the pharmaceutical industry. Dry granulation is commonly used if the powder mixture is sensitive to heat and moisture and has poor flow properties. The output of roll compaction is compacted ribbons that exhibit different properties based on the adjusted process parameters. These ribbons are then milled into granules and finally compressed into tablets. The properties of the ribbons directly affect the granule size distribution (GSD) and the quality of final products; thus, it is imperative to study the effect of roll compaction process parameters on GSD. The understanding of how the roll compactor process parameters and material properties interact with each other will allow accurate control of the process, leading to the implementation of quality by design practices. Computational intelligence (CI) methods have a great potential for being used within the scope of quality by design approach. The main objective of this study was to show how the computational intelligence techniques can be useful to predict the GSD by using different process conditions of roll compaction and material properties. Different techniques such as multiple linear regression, artificial neural networks, random forest, Cubist and k-nearest neighbors algorithm assisted by sevenfold cross-validation were used to present generalized models for the prediction of GSD based on roll compaction process setting and material properties. The normalized root-mean-squared error and the coefficient of determination (R2) were used for model assessment. The best fit was obtained by Cubist model (normalized root-mean-squared error =3.22%, R2=0.95). Based on the results, it was confirmed that the material properties (true density) followed by compaction force have the most significant effect on GSD. Keywords: computational intelligence, milling, roll compaction, dry granulation, neural network, Cubist

Adam Pacławski,1 Jakub Szlęk,1 Raymond Lau,2 Renata Jachowicz,1 Aleksander Mendyk1 1Department of Pharmaceutical Technology and Biopharmaceutics, Jagiellonian University Medical College, Kraków, Poland; 2School of Chemical and Biomedical Engineering, College of Engineering, Nanyang Technological University, Singapore Abstract: In vitro study of the deposition of drug particles is commonly used during development of formulations for pulmonary delivery. The assay is demanding, complex, and depends on: properties of the drug and carrier particles, including size, surface characteristics, and shape; interactions between the drug and carrier particles and assay conditions, including flow rate, type of inhaler, and impactor. The aerodynamic properties of an aerosol are measured in vitro using impactors and in most cases are presented as the fine particle fraction, which is a mass percentage of drug particles with an aerodynamic diameter below 5 µm. In the present study, a model in the form of a mathematical equation was developed for prediction of the fine particle fraction. The feature selection was performed using the R-environment package “fscaret”. The input vector was reduced from a total of 135 independent variables to 28. During the modeling stage, techniques like artificial neural networks, genetic programming, rule-based systems, and fuzzy logic systems were used. The 10-fold cross-validation technique was used to assess the generalization ability of the models created. The model obtained had good predictive ability, which was confirmed by a root-mean-square error and normalized root-mean-square error of 4.9 and 11%, respectively. Moreover, validation of the model using external experimental data was performed, and resulted in a root-mean-square error and normalized root-mean-square error of 3.8 and 8.6%, respectively. Keywords: fine particle fraction, pulmonary delivery, deposition modeling, genetic programming, feature selection, empirical modeling

Jakub Szlęk,1 Adam Pacławski,1 Raymond Lau,2 Renata Jachowicz,1 Aleksander Mendyk11Department of Pharmaceutical Technology and Biopharmaceutics, Jagiellonian University Medical College, Krakow, Poland; 2School of Chemical and Biomedical Engineering, Nanyang Technological University (NTU), SingaporeAbstract: Dissolution of protein macromolecules from poly(lactic-co-glycolic acid) (PLGA) particles is a complex process and still not fully understood. As such, there are difficulties in obtaining a predictive model that could be of fundamental significance in design, development, and optimization for medical applications and toxicity evaluation of PLGA-based multiparticulate dosage form. In the present study, two models with comparable goodness of fit were proposed for the prediction of the macromolecule dissolution profile from PLGA micro- and nanoparticles. In both cases, heuristic techniques, such as artificial neural networks (ANNs), feature selection, and genetic programming were employed. Feature selection provided by fscaret package and sensitivity analysis performed by ANNs reduced the original input vector from a total of 300 input variables to 21, 17, 16, and eleven; to achieve a better insight into generalization error, two cut-off points for every method was proposed. The best ANNs model results were obtained by monotone multi-layer perceptron neural network (MON-MLP) networks with a root-mean-square error (RMSE) of 15.4, and the input vector consisted of eleven inputs. The complicated classical equation derived from a database consisting of 17 inputs was able to yield a better generalization error (RMSE) of 14.3. The equation was characterized by four parameters, thus feasible (applicable) to standard nonlinear regression techniques. Heuristic modeling led to the ANN model describing macromolecules release profiles from PLGA microspheres with good predictive efficiency. Moreover genetic programming technique resulted in classical equation with comparable predictability to the ANN model.Keywords: poly(lactic-co-glycolic acid) (PLGA) microparticles, genetic programming, feature selection, artificial neural networks, molecular descriptors

The pursuit of targeted therapies for cytokine-dependent diseases has led to the discovery of Janus kinase (JAK) inhibitors, a promising class of drugs. Among them, CPL409116, a selective dual JAK and rho-associated protein kinase inhibitor (ROCK), has demonstrated potential for treating conditions such as pulmonary fibrosis exacerbated by the COVID-19 pandemic. This study investigated the feasibility of delivering CPL409116 via inhalation, with the aim of minimizing the systemic adverse effects associated with oral administration. Two micronization methods, jet milling and spray drying, were assessed for CPL409116, with spray drying chosen for its ability to produce an amorphous form of the compound. Moreover, parameters such as the mixing energy, drug load, and force control agent significantly influenced the fine particle fraction (FPF), a critical parameter for pulmonary drug delivery. This study provides insights into optimizing the formulation parameters to enhance the delivery efficiency of CPL409116 to the lungs, offering potential for improved therapeutic outcomes in cytokine-dependent pulmonary diseases.

SerotoninAI is an innovative web application for scientific purposes focused on the serotonergic system. By leveraging SerotoninAI, researchers can assess the affinity (pKi value) of a molecule to all main serotonin receptors and serotonin transporters based on molecule structure introduced as SMILES. Additionally, the application provides essential insights into critical attributes of potential drugs such as blood-brain barrier penetration and human intestinal absorption. The complexity of the serotonergic system demands advanced tools for accurate predictions, which is a fundamental requirement in drug development. SerotoninAI addresses this need by providing an intuitive user interface that generates predictions of pKi values for the main serotonergic targets. The application is freely available on the Internet at https://serotoninai.streamlit.app/, implemented in Streamlit with all major web browsers supported. Currently, to the best of our knowledge, there is no tool that allows users to access affinity predictions for serotonergic targets without registration or financial obligations. SerotoninAI significantly increases the scope of drug development activities worldwide. The source code of the application is available at https://github.com/nczub/SerotoninAI_streamlit.

Understanding the features of compounds that determine their high serotonergic activity and selectivity for specific receptor subtypes represents a pivotal challenge in drug discovery, directly impacting the ability to minimize adverse events while maximizing therapeutic efficacy. Up to now, this process has been a puzzle and limited to a few serotonergic targets. One approach represented in the literature focuses on receptor structure whereas in this study, we followed another strategy by creating AI-based models capable of predicting serotonergic activity and selectivity based on ligands' representation by molecular descriptors. Predictive models were developed using Automated Machine Learning provided by Mljar and later analyzed through the SHAP importance analysis, which allowed us to clarify the relationship between descriptors and the effect on activity and what features determine selective affinity for serotonin receptors. Through the experiments, it was possible to highlight the most important features of ligands based on highly efficient models. These features are discussed in this manuscript. The models are available in the additional modules of the SerotoninAI application called "Serotonergic activity" and "Selectivity".

Oral medicines represent the largest pharmaceutical market area. To achieve a therapeutic effect, a drug must penetrate the intestinal walls, the main absorption site for orally delivered active pharmaceutical ingredients (APIs). Indeed, predicting drug absorption can facilitate candidate screening and reduce time to market. Algorithms are available with good prediction accuracy that however focus only on solubility. In this work, we focused on drug permeability looking at human intestinal absorption as a marker for intestinal bioavailability. Being of considerable therapeutic relevance, APIs with serotonergic activity were selected as a dataset. Due to process complexity, experimental data scarcity, and variability, we turned toward an artificial intelligence (AI)-based system, which is a hierarchical combination of classification and regression models. This combination of seemingly two models into a single system widens the space of molecules classified as highly permeable with high accuracy. The specialized and optimized system enables in silico and structure-based prediction with a high degree of certainty. Predictions in external validation allowed correct selection of the 38% of highly permeable molecules without any false positives. The proposed system based on AI represents a promising tool useful for oral drug screening at an early stage of drug discovery and development. Datasets and the obtained models are available on the GitHub platform (https://github.com/nczub/HIA_5-HT).

The drug discovery and development process requires a lot of time, financial, and workforce resources. Any reduction in these burdens might benefit all stakeholders in the healthcare domain, including patients, government, and companies. One of the critical stages in drug discovery is a selection of molecular structures with a strong affinity to a particular molecular target. The possible solution is the development of predictive models and their application in the screening process, but due to the complexity of the problem, simple and statistical models might not be sufficient for practical application. The manuscript presents the best-in-class predictive model for the serotonin 1A receptor affinity and its validation according to the Organization for Economic Co-operation and Development guidelines for regulatory purposes. The model was developed based on a database with close to 9500 molecules by using an automatic machine learning tool (AutoML). The model selection was conducted based on the Akaike information criterion value and 10-fold cross-validation routine, and later good predictive ability was confirmed with an additional external validation dataset with over 700 molecules. Moreover, the multi-start technique was applied to test if an automatic model development procedure results in reliable results.

Tablets are the most common dosage form of pharmaceutical products. While tablets represent the majority of marketed pharmaceutical products, there remain a significant number of patients who find it difficult to swallow conventional tablets. Such difficulties lead to reduced patient compliance. Orally disintegrating tablets (ODT), sometimes called oral dispersible tablets, are the dosage form of choice for patients with swallowing difficulties. ODTs are defined as a solid dosage form for rapid disintegration prior to swallowing. The disintegration time, therefore, is one of the most important and optimizable critical quality attributes (CQAs) for ODTs. Current strategies to optimize ODT disintegration times are based on a conventional trial-and-error method whereby a small number of samples are used as proxies for the compliance of whole batches. We present an alternative machine learning approach to optimize the disintegration time based on a wide variety of machine learning (ML) models through the H2O AutoML platform. ML models are presented with inputs from a database originally presented by Han et al., which was enhanced and curated to include chemical descriptors representing active pharmaceutical ingredient (API) characteristics. A deep learning model with a 10-fold cross-validation NRMSE of 8.1% and an R 2 of 0.84 was obtained. The critical parameters influencing the disintegration of the directly compressed ODTs were ascertained using the SHAP method to explain ML model predictions. A reusable, open-source tool, the ODT calculator, is now available at Heroku platform.

Introduction of a new drug to the market is a challenging and resource-consuming process. Predictive models developed with the use of artificial intelligence could be the solution to the growing need for an efficient tool which brings practical and knowledge benefits, but requires a large amount of high-quality data. The aim of our project was to develop quantitative structure-activity relationship (QSAR) model predicting serotonergic activity toward the 5-HT1A receptor on the basis of a created database. The dataset was obtained using ZINC and ChEMBL databases. It contained 9440 unique compounds, yielding the largest available database of 5-HT1A ligands with specified pKi value to date. Furthermore, the predictive model was developed using automated machine learning (AutoML) methods. According to the 10-fold cross-validation (10-CV) testing procedure, the root-mean-squared error (RMSE) was 0.5437, and the coefficient of determination ( R 2 ) was 0.74. Moreover, the Shapley Additive Explanations method (SHAP) was applied to assess a more in-depth understanding of the influence of variables on the model's predictions. According to to the problem definition, the developed model can efficiently predict the affinity value for new molecules toward the 5-HT1A receptor on the basis of their structure encoded in the form of molecular descriptors. Usage of this model in screening processes can significantly improve the process of discovery of new drugs in the field of mental diseases and anticancer therapy.

Background and Objective: Prediction of drug concentration in heart tissue is important in terms of drug safety and efficacy. This work presents the Open-Source CardiacPBPK platform for the prediction of the time-concentration profile of drugs, which could potentially reduce the risk of drug development failure due to cardiotoxicity. The objective of the CardiacPBPK development is to accelerate and simplify the in-silico toxicological assessment of new drugs, and to provide supportive material for the research community to use., Methods: The CardiacPBPK software provides a modular implementation of the PBPK model of heart tissue. It can be easily accessed via the Internet or installed locally. The graphical user interface and tabular design are easy to configure and use., Results: CardiacPBPK is a tool designed to predict and visualize the time-concentration profiles of a parent compound, and one metabolite, in venous plasma and heart tissue after oral or intravenous drug administration. CardiacPBPK is built on the R-environment framework and supports shiny application features such as interactive visualization of the results, and web applications interface by default. A shiny application refers to a computer program created with the use of shiny package in R. The application is freely available at https://github.com/jszlek/CardiacPBPK and https://sourceforge.net/projects/cardiacpbpk/. This open-source application runs on all platforms supporting R-environment (Linux, Windows, Mac OS X, Solaris)., Conclusions: We demonstrate the application of CardiacPBPK by simulating the study of amitriptyline intoxication in the case of CYP2D6 genetic polymorphism., (Copyright © 2019 Elsevier Ltd. All rights reserved.)

The effect of solvent removal techniques on phase transition, physical stability and dissolution of bicalutamide from solid dispersions containing polyvinylpyrrolidone (PVP) as a carrier was investigated. A spray dryer and a rotavapor were applied to obtain binary systems containing either 50% or 66% of the drug. Applied techniques led to the formation of amorphous solid dispersions as confirmed by X-ray powder diffractometry and differential scanning calorimetry. Moreover, solid⁻solid transition from polymorphic form I to form II was observed for bicalutamide spray dried without a carrier. The presence of intermolecular interactions between the drug and polymer molecules, which provides the stabilization of molecularly disordered bicalutamide, was analyzed using infrared spectroscopy. Spectral changes within the region characteristic for amide vibrations suggested that the amide form of crystalline bicalutamide was replaced by a less stable imidic one, characteristic of an amorphous drug. Applied processes also resulted in changes of particle geometry and size as confirmed by scanning electron microscopy and laser diffraction measurements, however they did not affect the dissolution significantly as confirmed by intrinsic dissolution study. The enhancement of apparent solubility and dissolution were assigned mostly to the loss of molecular arrangement by drug molecules. Performed statistical analysis indicated that the presence of PVP reduces the mean dissolution time and improve the dissolution efficiency. Although the dissolution was equally affected by both applied methods of solid dispersion manufacturing, spray drying provides better control of particle size and morphology as well as a lower tendency for recrystallization of amorphous solid dispersions.

Human heart electrophysiology is complex biological phenomenon, which is indirectly assessed by the measured ECG signal. ECG trace is further analyzed to derive interpretable surrogates including QT interval, QRS complex, PR interval, and T wave morphology. QT interval and its modification are the most commonly used surrogates of the drug triggered arrhythmia, but it is known that the QT interval itself is determined by other nondrug related parameters, physiological and pathological. In the current study, we used the computational intelligence algorithms to analyze correlations between various simulated physiological parameters and QT interval. Terfenadine given concomitantly with 8 enzymatic inhibitors was used as an example. The equation developed with the use of genetic programming technique leads to general reasoning about the changes in the prolonged QT. For small changes of the QT interval, the drug-related IKr and ICa currents inhibition potentials have major impact. The physiological parameters such as body surface area, potassium, sodium, and calcium ions concentrations are negligible. The influence of the physiological variables increases gradually with the more pronounced changes in QT. As the significant QT prolongation is associated with the drugs triggered arrhythmia risk, analysis of the role of physiological parameters influencing ECG seems to be advisable.

The study provides the physicochemical characteristic of bosentan (BOS) in comparison to tadalafil (TA) and sildenafil citrate (SIL). Despite some reports dealing with thermal characteristic of SIL and TA, physicochemical properties of BOS have not been investigated so far. Recent clinical reports have indicated that the combination of bosentan and PDE-5 inhibitor can improve the effectiveness of pharmacotherapy of pulmonary arterial hypertension (PAH). However, in order to design personalized medicines for therapy of chronic rare diseases, detailed information on the thermal behaviour and solubility of each drug is indispensable. Thus, XRD, DSC and TGA-QMS analyses were applied to compare the properties of the drugs, their thermal stability as well as to identify the products of thermal degradation. The dehydration of BOS started at 70°C and was followed by the chemical degradation with the onset at 290°C. The highest thermal stability was stated for TA, which decomposed at ca. 320°C, whereas the lowest onset of the thermal decomposition process was stated for SIL, i.e. 190°C. The products of the drug decomposition were identified. FT-FIR was applied to study intra- and intermolecular interactions between the drug molecules. FT-MIR and Raman spectroscopy were used to examine the chemical structure of the drugs. Chemoinformatic tools were used to predict the polar surface area, pKa, or logP of the drugs. Their results were in line with solubility and dissolution studies.

Background and Objectives: Poly(lactic-co-glycolic acid) (PLGA) has become one of the most promising in design, development, and optimization for medical applications polymers. PLGA-based multiparticulate dosage forms are usually prepared as microspheres where the size is from 5 to 100 µm, depending on the route of administration. The main objectives of the study were to develop a predictive model of mean volumetric particle size and on its basis extract knowledge of PLGA containing proteins forming behaviour., Methods: In the present study, a model for the prediction of mean volumetric particle size developed by an rgp package of R environment is presented. Other tools like fscaret, monmlp, fugeR, MARS, SVM, kNNreg, Cubist, randomForest and piecewise linear regression are also applied during the data mining procedure., Results: The feature selection provided by the fscaret package reduced the original input vector from a total of 295 input variables to 10, 16 and 19. The developed models had good predictive ability, which was confirmed by a normalized root-mean-square error (NRMSE) of 6.8 to 11.1% in 10-fold cross validation training procedure. Moreover, the best models were validated using external experimental data. The superior predictiveness had a model obtained by rgp in the form of a classical equation with a normalized root-mean-squared error (NRMSE) of 6.1%., Conclusions: A new approach is proposed for computational modelling of the mean particle size of PLGA microspheres and rules extraction from tree-based models. The feature selection leads to revealing chemical descriptor variables which are important in predicting the size of PLGA microspheres. In order to achieve better understanding in the relationships between particle size and formulation characteristics, the surface analysis method and rules extraction procedures were applied., (Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.)

The currently changing cardiac safety testing paradigm suggests, among other things, a shift towards using in silico models of cellular electrophysiology and assessment of a concomitant block of multiple ion channels. In this study, a set of four enhanced QSAR models have been developed: for the rapid delayed rectifying potassium current (IKr), slow delayed rectifying potassium current (IKs), peak sodium current (INa) and late calcium current (ICaL), predicting ion currents changes for the specific in vitro experiment from the 2D structure of the compounds. The models are a combination of both in vitro study parameters and physico-chemical descriptors, which is a novel approach in drug-ion channels interactions modeling. Their predictive power assessed in the enhanced, more demanding than standard procedure, 10-fold cross validation was reasonably high. Rough comparison with published pure in silico hERG interaction models shows that the quality of the model predictions does not differ from other models available in the public domain, however, it takes its advantage in accounting for inter-experimental settings variability. Developed models are implemented in the Cardiac Safety Simulator, a commercially available platform enabling the in vitro-in vivo extrapolation of the drugs proarrhythmic effect and ECG simulation. A more comprehensive assessment of the effects of the compounds on ion channels allows for making more informed decisions regarding the risk - and thus avoidance - of exclusion of potentially safe and effective drugs., (Copyright © 2015 John Wiley & Sons, Ltd.)

The influence of alkaline and the neutral grade of magnesium aluminometasilicate as a porous solid carrier for the liquid self-emulsifying formulation with ibuprofen is investigated. Ibuprofen is dissolved in Labrasol, then this solution is adsorbed on the silicates. The drug to the silicate ratio is 1:2, 1:4, and 1:6, respectively. The properties of formulations obtained are analyzed, using morphological, porosity, crystallinity, and dissolution studies. Three solid self-emulsifying (S-SE) formulations containing Neusilin SG2 and six consisting of Neusilin US2 are in the form of powder without agglomerates. The nitrogen adsorption method shows that the solid carriers are mesoporous but they differ in a specific surface area, pore area, and the volume of pores. The adsorption of liquid SE formulation on solid silicate particles results in a decrease in their porosity. If the neutral grade of magnesium aluminometasilicate is used, the smallest pores, below 10 nm, are completely filled with liquid formulation, but there is still a certain number of pores of 40-100 nm. Dissolution studies of liquid SEDDS carried out in pH = 1.2 show that Labrasol improves the dissolution of ibuprofen as compared to the pure drug. Ibuprofen dissolution from liquid SE formulations examined in pH of 7.2 is immediate. The adsorption of the liquid onto the particles of the silicate causes a decrease in the amount of the drug released. Finally, more ibuprofen is dissolved from S-SE that consist of the neutral grade of magnesium aluminometasilicate than from the formulations containing the alkaline silicate.

The purpose of this work was to develop a mathematical model of the drug dissolution (Q) from the solid lipid extrudates based on the empirical approach. Artificial neural networks (ANNs) and genetic programming (GP) tools were used. Sensitivity analysis of ANNs provided reduction of the original input vector. GP allowed creation of the mathematical equation in two major approaches: (1) direct modeling of Q versus extrudate diameter (d) and the time variable (t) and (2) indirect modeling through Weibull equation. ANNs provided also information about minimum achievable generalization error and the way to enhance the original dataset used for adjustment of the equations' parameters. Two inputs were found important for the drug dissolution: d and t. The extrudates length (L) was found not important. Both GP modeling approaches allowed creation of relatively simple equations with their predictive performance comparable to the ANNs (root mean squared error (RMSE) from 2.19 to 2.33). The direct mode of GP modeling of Q versus d and t resulted in the most robust model. The idea of how to combine ANNs and GP in order to escape ANNs' black-box drawback without losing their superior predictive performance was demonstrated. Open Source software was used to deliver the state-of-the-art models and modeling strategies.

The objective was to prepare neural models identifying relationships between formulation characteristics and pellet properties based on algorithmic approach of crucial variables selection and neuro-fuzzy systems application. The database consisted of information about 227 pellet formulations prepared by extrusion/spheronization method, with various model drugs and excipients. Cheminformatic description of excipients and model drugs was employed for numerical description of pellet formulations. Initial numbers of neural model inputs were up to around 3000. The inputs reduction procedure based on sensitivity analysis allowed to obtain less than 40 inputs for each model. The reduced models were subjects of fuzzy logic implementation resulting in logical rules tables providing human-readable rule sets applicable in future development of pellet formulations. Neural modeling enhanced knowledge about pelletization process and provided means for future computer-guided search for the optimal formulation., (Copyright © 2010 Elsevier B.V. All rights reserved.)