Dans cet article, nous développons une méthode (WTRFS) incluant le retour utilisateur dans le but... more Dans cet article, nous développons une méthode (WTRFS) incluant le retour utilisateur dans le but de le guider parmi les résultats d'une fouille de motifs. Ce travail vise à remplacer l'étape de déclaration des descripteurs utilisée dans la fouille interactive de motifs. Pour cela, la méthode s'appuie sur l'existence hypothétique d'un lien entre les différents motifs intéressants un expert. Nous montrons empiriquement que WTRFS renvoie rapidement les résultats les plus pertinents pour l'utilisateur. De plus, même si les retours de l'utilisateur sont imparfaits, le comportement de WTRFS n'en est pas altéré.
This paper presents a novel approach called Pharmacophore Activity Delta for extracting outstandi... more This paper presents a novel approach called Pharmacophore Activity Delta for extracting outstanding pharmacophores from a chemogenomic dataset, with a specific focus on a kinase target known as BCR-ABL. The method involves constructing a Hasse diagram, referred to as the pharmacophore network, by utilizing the subgraph partial order as an initial step, leading to the identification of pharmacophores for further evaluation. A pharmacophore is classified as a 'Pharmacophore Activity Delta' if its capability to effectively discriminate between active vs inactive molecules significantly deviates (by at least δ standard deviations) from the mean capability of its related pharmacophores. Among the 1479 molecules associated to BCR-ABL binding data, 130 Pharmacophore Activity Delta were identified. The pharmacophore network reveals distinct regions associated with active and inactive molecules. The study includes a discussion on representative key areas linked to different pharmacophores, emphasizing structure-activity relationships.
This paper describes an original approach for extracting outstanding pharmacophores, named PADs (... more This paper describes an original approach for extracting outstanding pharmacophores, named PADs (for Pharmacophore Activity Delta), from a chemogenomic dataset (BCR-ABL in our case). This involves building both a partial order graph (POG) and a condensed POG as a first step to finally land on PADs to be assessed. A pharmacophore is a PAD if its quality deviates at least δ standard deviations from the mean of the quality (growth rate value) of its siblings. From 1479 molecules, 377 PADs were extracted. PADs were summarized afterwards by 130 representative PADs with the MMRFS technique. To analyze these PADs, a pharmacophore network was derived, leading to different areas associated with active and inactive molecules. A discussion of some representative key areas is carried out, pointing out some structure–activity relationships (SARs). Cross-validation studies were also carried out with a potential selection of the most stable PADs for SARs.
Dans cet article, nous développons une méthode (WTRFS) incluant le retour utilisateur dans le but... more Dans cet article, nous développons une méthode (WTRFS) incluant le retour utilisateur dans le but de le guider parmi les résultats d'une fouille de motifs. Ce travail vise à remplacer l'étape de déclaration des descripteurs utilisée dans la fouille interactive de motifs. Pour cela, la méthode s'appuie sur l'existence hypothétique d'un lien entre les différents motifs intéressants un expert. Nous montrons empiriquement que WTRFS renvoie rapidement les résultats les plus pertinents pour l'utilisateur. De plus, même si les retours de l'utilisateur sont imparfaits, le comportement de WTRFS n'en est pas altéré.
This paper presents a novel approach called Pharmacophore Activity Delta for extracting outstandi... more This paper presents a novel approach called Pharmacophore Activity Delta for extracting outstanding pharmacophores from a chemogenomic dataset, with a specific focus on a kinase target known as BCR-ABL. The method involves constructing a Hasse diagram, referred to as the pharmacophore network, by utilizing the subgraph partial order as an initial step, leading to the identification of pharmacophores for further evaluation. A pharmacophore is classified as a 'Pharmacophore Activity Delta' if its capability to effectively discriminate between active vs inactive molecules significantly deviates (by at least δ standard deviations) from the mean capability of its related pharmacophores. Among the 1479 molecules associated to BCR-ABL binding data, 130 Pharmacophore Activity Delta were identified. The pharmacophore network reveals distinct regions associated with active and inactive molecules. The study includes a discussion on representative key areas linked to different pharmacophores, emphasizing structure-activity relationships.
This paper describes an original approach for extracting outstanding pharmacophores, named PADs (... more This paper describes an original approach for extracting outstanding pharmacophores, named PADs (for Pharmacophore Activity Delta), from a chemogenomic dataset (BCR-ABL in our case). This involves building both a partial order graph (POG) and a condensed POG as a first step to finally land on PADs to be assessed. A pharmacophore is a PAD if its quality deviates at least δ standard deviations from the mean of the quality (growth rate value) of its siblings. From 1479 molecules, 377 PADs were extracted. PADs were summarized afterwards by 130 representative PADs with the MMRFS technique. To analyze these PADs, a pharmacophore network was derived, leading to different areas associated with active and inactive molecules. A discussion of some representative key areas is carried out, pointing out some structure–activity relationships (SARs). Cross-validation studies were also carried out with a potential selection of the most stable PADs for SARs.
Uploads
Papers by Etienne LEHEMBRE