Search

Multi-Parameter Optimization (MPO) is a major challenge in New Chemical Entity (NCE) drug discovery projects, and the inability to identify molecules meeting all the criteria of lead optimization (LO) is an important cause of NCE project failure. Several ligand- and structure-based de novo design methods have been published over the past decades, some of which have proved useful multiobjective optimization. However, there is still need for improvement to better address the chemical feasibility of generated compounds as well as increasing the explored chemical space while tackling the MPO challenge. Recently, promising results have been reported for deep learning generative models applied to de novo molecular design, but until now, to our knowledge, no report has been made of the value of this new technology for addressing MPO in an actual drug discovery project. Our objective in this study was to evaluate the potential of a ligand-based de novo design technology using deep learning generative models to accelerate the discovery of an optimized lead compound meeting all in vitro late stage LO criteria.

In this paper, we propose a new simple method for estimating the shape parameter of the inverse Gaussian distribution. This new method makes use of the reciprocal property of the distribution. Also, bias-reduced versions of this proposed estimator are introduced. Furthermore, a new test for the coefficient of variation in an inverse Gaussian distribution is derived. The performance of the estimators are evaluated via Monte Carlo simulations. In general, compared with the maximum likelihood estimator, the proposed method has smaller bias. Two real data sets are used to illustrate the proposed methodology.

National audience; Radiosusceptibility to cancer, known since decades and concerning probably 10 to 20% of the population, is barely considered in breast cancer screening by X-ray mammography. It has really emerged with the issue of screening in women with high family risk of breast cancer. While a link between breast cancer and low dose ionizing radiation was difficult to establish in the general population, epidemiology has shown a link in BRCA1/2 mutated women. On the other hand, radiation biology has identified indicators of radiosusceptibility at low doses at the cellular level and in subgroups of cancer prone people. Several functional assays of signalization and repair pathways of DNA damage are today available and susceptible to demonstrate this individual abnormal response to X-rays.; La radiosusceptibilité au cancer, connue de longue date et qui touche probablement entre 10 et 20 % de la population, est peu prise en compte dans le cadre du dépistage mammographique du cancer du sein. Elle a réellement émergé avec la problématique du dépistage des femmes à haut risque de cancer du sein. En effet, alors qu’un lien entre le cancer du sein et de faibles doses de rayons X était difficile à établir dans la population générale, l’épidémiologie a montré un lien pour les femmes mutées sur le gène BRCA1/2. D’autre part, la radiobiologie a permis de montrer des indicateurs de radiosusceptibilité aux faibles doses à l’échelon cellulaire et dans des sous-catégories de population prédisposées au cancer. Plusieurs tests fonctionnels des voies de signalisation et de réparation des lésions de l’ADN sont aujourd’hui disponibles et sont susceptibles de pouvoir mettre en évidence cette réponse individuelle variable aux rayons X.