Search

Affinity fingerprints report the activity of small molecules across a set of assays, and thus permit to gather information about the bioactivities of structurally dissimilar compounds, where models based on chemical structure alone are often limited, and model complex biological endpoints, such as human toxicity and in vitro cancer cell line sensitivity. Here, we propose to model in vitro compound activity using computationally predicted bioactivity profiles as compound descriptors. To this aim, we apply and validate a framework for the calculation of QSAR-derived affinity fingerprints (QAFFP) using a set of 1360 QSAR models generated using Ki, Kd, IC50 and EC50 data from ChEMBL database. QAFFP thus represent a method to encode and relate compounds on the basis of their similarity in bioactivity space. To benchmark the predictive power of QAFFP we assembled IC50 data from ChEMBL database for 18 diverse cancer cell lines widely used in preclinical drug discovery, and 25 diverse protein target data sets. This study complements part 1 where the performance of QAFFP in similarity searching, scaffold hopping, and bioactivity classification is evaluated. Despite being inherently noisy, we show that using QAFFP as descriptors leads to errors in prediction on the test set in the ~ 0.65–0.95 pIC50 units range, which are comparable to the estimated uncertainty of bioactivity data in ChEMBL (0.76–1.00 pIC50 units). We find that the predictive power of QAFFP is slightly worse than that of Morgan2 fingerprints and 1D and 2D physicochemical descriptors, with an effect size in the 0.02–0.08 pIC50 units range. Including QSAR models with low predictive power in the generation of QAFFP does not lead to improved predictive power. Given that the QSAR models we used to compute the QAFFP were selected on the basis of data availability alone, we anticipate better modeling results for QAFFP generated using more diverse and biologically meaningful targets. Data sets and Python code are publicly available at https://github.com/isidroc/QAFFP_regression.

Funder: FP7 People: Marie-Curie Actions; doi: http://dx.doi.org/10.13039/100011264; Grant(s): 238701, 238701, An affinity fingerprint is the vector consisting of compound’s affinity or potency against the reference panel of protein targets. Here, we present the QAFFP fingerprint, 440 elements long in silico QSAR-based affinity fingerprint, components of which are predicted by Random Forest regression models trained on bioactivity data from the ChEMBL database. Both real-valued (rv-QAFFP) and binary (b-QAFFP) versions of the QAFFP fingerprint were implemented and their performance in similarity searching, biological activity classification and scaffold hopping was assessed and compared to that of the 1024 bits long Morgan2 fingerprint (the RDKit implementation of the ECFP4 fingerprint). In both similarity searching and biological activity classification, the QAFFP fingerprint yields retrieval rates, measured by AUC (~ 0.65 and ~ 0.70 for similarity searching depending on data sets, and ~ 0.85 for classification) and EF5 (~ 4.67 and ~ 5.82 for similarity searching depending on data sets, and ~ 2.10 for classification), comparable to that of the Morgan2 fingerprint (similarity searching AUC of ~ 0.57 and ~ 0.66, and EF5 of ~ 4.09 and ~ 6.41, depending on data sets, classification AUC of ~ 0.87, and EF5 of ~ 2.16). However, the QAFFP fingerprint outperforms the Morgan2 fingerprint in scaffold hopping as it is able to retrieve 1146 out of existing 1749 scaffolds, while the Morgan2 fingerprint reveals only 864 scaffolds.

This thesis concerns the application of the Generative Topographic Mapping (GTM) approach to the analysis, visualization, and modeling of Big Data in chemistry. The main topics covered in this work are multi-target virtual screening in drug design and large chemical libraries visualization, analysis, and comparison. Several methodological developments were suggested: (i) an automatized hierarchical GTM zooming algorithm helping to resolve the map resolution problem; (ii) an automatized Maximum Common Substructure (MCS) extraction protocol improving efficiency of data analysis; (iii) constrained GTM-based screening allowing to detect molecules with a desired pharmacological profile, and (iv) a parallel GTM technique, which significantly increases the speed of GTM training. Developed methodologies were implemented in a software package used in both academic (University of Strasbourg, France) and industrial (Boehringer Ingelheim Pharma company, Germany) projects.; Cette thèse concerne l'utilisation de Cartographie Topographique Générative (Generative Topographie Mapping - GTM) pour l'analyse, la visualisation et la modélisation de grands volumes de données chimiques. Les principaux sujets traités dans ces travaux sont le criblage virtuel multi-cibles dans la conception de médicaments et la visualisation, l'analyse et la comparaison de grandes chimiothèques. Plusieurs développements méthodologiques ont été proposés : (1) un algorithme de zoom hiérarchique automatisé pour la GTM afin d'aider à résoudre le problème de la résolution des cartes ; (i1) un protocole d'extraction automatisé des Sous-structures Maximum Communes (MCS) pour améliorer l'efficacité de l'analyse de données ; (iit) un criblage contraint basé sur la GTM permettant de détecter les molécules avec un profil pharmacologique souhaité, et (iv) une technique de GTM parallèle, qui réduit significativement le temps nécessaire pour construire une carte. Les méthodologies développées ont été implémentées sous forme de logiciel, utilisé à la fois dans des projets académiques (Université de Strasbourg, France) et industriels (Compagnie Boehringer lngelheim Pharma, Allemagne)

This thesis concerns the application of the Generative Topographic Mapping (GTM) approach to the analysis, visualization, and modeling of Big Data in chemistry. The main topics covered in this work are multi-target virtual screening in drug design and large chemical libraries visualization, analysis, and comparison. Several methodological developments were suggested: (i) an automatized hierarchical GTM zooming algorithm helping to resolve the map resolution problem; (ii) an automatized Maximum Common Substructure (MCS) extraction protocol improving efficiency of data analysis; (iii) constrained GTM-based screening allowing to detect molecules with a desired pharmacological profile, and (iv) a parallel GTM technique, which significantly increases the speed of GTM training. Developed methodologies were implemented in a software package used in both academic (University of Strasbourg, France) and industrial (Boehringer Ingelheim Pharma company, Germany) projects., Cette thèse concerne l'utilisation de Cartographie Topographique Générative (Generative Topographie Mapping - GTM) pour l'analyse, la visualisation et la modélisation de grands volumes de données chimiques. Les principaux sujets traités dans ces travaux sont le criblage virtuel multi-cibles dans la conception de médicaments et la visualisation, l'analyse et la comparaison de grandes chimiothèques. Plusieurs développements méthodologiques ont été proposés : (1) un algorithme de zoom hiérarchique automatisé pour la GTM afin d'aider à résoudre le problème de la résolution des cartes ; (i1) un protocole d'extraction automatisé des Sous-structures Maximum Communes (MCS) pour améliorer l'efficacité de l'analyse de données ; (iit) un criblage contraint basé sur la GTM permettant de détecter les molécules avec un profil pharmacologique souhaité, et (iv) une technique de GTM parallèle, qui réduit significativement le temps nécessaire pour construire une carte. Les méthodologies développées ont été implémentées sous forme de logiciel, utilisé à la fois dans des projets académiques (Université de Strasbourg, France) et industriels (Compagnie Boehringer lngelheim Pharma, Allemagne)

The relationship between the structure and a property of a chemical compound is an essential concept in chemistry guiding, for example, drug design. Actually, however, we need economic considerations to fully understand the fate of drugs on the market. We are performing here for the first time the exploration of quantitative structure-economy relationships (QSER) for a large dataset of a commercial building block library of over 2.2 million chemicals. This investigation provided molecular statistics that shows that on average what we are paying for is the quantity of matter. On the other side, the influence of synthetic availability scores is also revealed. Finally, we are buying substances by looking at the molecular graphs or molecular formulas. Thus, those molecules that have a higher number of atoms look more attractive and are, on average, also more expensive. Our study shows how data binning could be used as an informative method when analyzing big data in chemistry.