Ligand-Based Virtual Screening Using Graph Edit Distance as Molecular Similarity Measure

García-Hernández, Carlos Felipe; Fernández, Alberto; Serratosa, Francesc

doi:10.1021/acs.jcim.8b00820

Cited by 51 publications

(42 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In a previous work [ 39 ], we presented a molecular similarity measure that uses graph edit distance to effectively compare the representation of molecules by extended reduced graphs. In that work, edit costs for the different node and edge operations were assigned using expert knowledge.…”

Section: Discussionmentioning

confidence: 99%

“…In a previous work [ 39 ], we used the edit costs proposed by Harper et al [ 38 ] with small changes to fit the ErG features. The node and edge descriptions are shown in Table 2 and the specific costs proposed by Harper et al [ 38 ] are exposed in Tables 3 and 4 .…”

Section: Methodsmentioning

confidence: 99%

“…Three similarity measures have been used to perform reduced graph comparisons. The first one maps the reduced graphs into a 2D fingerprint [ 35 - 37 ], the second one maps them into sets of shortest paths [ 38 ], and the third one makes the comparison directly on the graphs via the graph edit distance method [ 39 ].…”

Section: Introductionmentioning

confidence: 99%

“…In a previous work [ 39 ], we used the edit costs proposed by Harper et al [ 38 ], which were assigned by experts considering the different node and edge types. In this paper, we present a method for optimizing those edit costs, based on minimizing the distance between molecules correctly classified and maximizing the distance between molecules incorrectly classified.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning the Edit Costs of Graph Edit Distance Applied to Ligand-Based Virtual Screening

García-Hernández

Fernández

Serratosa

2020

CTMC

Self Cite

View full text Add to dashboard Cite

Background: Graph edit distance is a methodology used to solve error-tolerant graph matching. This methodology estimates a distance between two graphs by determining the minimum number of modifications required to transform one graph into the other. These modifications, known as edit operations, have an edit cost associated that has to be determined depending on the problem. Objective: This study focuses on the use of optimization techniques in order to learn the edit costs used when comparing graphs by means of the graph edit distance. Method: Graphs represent reduced structural representations of molecules using pharmacophore-type node descriptions to encode the relevant molecular properties. This reduction technique is known as extended reduced graphs. The screening and statistical tools available on the ligand-based virtual screening benchmarking platform and the RDKit were used. Results: In the experiments, the graph edit distance using learned costs performed better or equally good than using predefined costs. This is exemplified with six publicly available datasets: DUD-E, MUV, GLL&GDD, CAPST, NRLiSt BDB, and ULS-UDS. Conclusion: This study shows that the graph edit distance along with learned edit costs is useful to identify bioactivity similarities in a structurally diverse group of molecules. Furthermore, the target-specific edit costs might provide useful structure-activity information for future drug-design efforts.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning the Edit Costs of Graph Edit Distance Applied to Ligand-Based Virtual Screening

García-Hernández

Fernández

Serratosa

2020

CTMC

Self Cite

View full text Add to dashboard Cite

show abstract

“…Los métodos de búsqueda por similitud usualmente requieren la representación de la estructura molecular, en la cual se ponderan determinadas propiedades moleculares relevantes, y un método mediante el cual se pueda cuantificar el nivel de similitud que existe entre la estructura de referencia y la estructura candidato (Garcia-Hernandez et al, 2019). Se consideran dos enfoques principales para medir cuán similares son las estructuras de las moléculas.…”

Section: Similitud Molecularunclassified

Tamizado virtual aplicado a la búsqueda de nuevos fármacos antiepilépticos activos en el modelo de 6 Hz

Goicoechea¹

View full text Add to dashboard Cite

La Epilepsia es uno de los desórdenes neurológicos más comunes, afectando a alrededor de 50 millones de personas en todo el mundo sin distinguir raza, sexo, edad y/o clase social. Esta enfermedad está caracterizada por crisis recurrentes y espontáneas provocadas por una actividad neuronal excesiva. Pese a los múltiples esfuerzos por encontrar nuevos tratamientos para esta patología existe un 30% de pacientes que no logra controlar las convulsiones con la farmacoterapia disponible, lo cual se conoce como epilepsia refractaria o intratable. Esta proporción de pacientes refractarios no se ha modificado a pesar de la considerable introducción en el mercado farmacéutico de numerosos fármacos antiepilépticos (FAEs) de última generación. Con el propósito de buscar nuevos candidatos a fármacos que demuestren protección frente a distintos tipos de crisis epilépticas, el Instituto Nacional de Salud de los Estados Unidos (National Institute of Health, NIH) ha modificado en los últimos tiempos el Programa de Screening de Fármacos Anticonvulsivos, reincorporando al modelo animal de crisis epiléptica de 6 Hz para ser utilizado en el screening primario de nuevos FAEs. A través de este modelo animal se ha identificado al fármaco de uso clínico levetiracetam, el cual está asociado a un mecanismo de acción novedoso. En el presente trabajo de tesis se propone realizar una búsqueda racional mediante tamizado virtual de nuevos compuestos activos frente al modelo de 6 Hz en ratones. Se ha realizado una campaña de tamizado virtual a partir del desarrollo de modelos computacionales basados en el ligando con capacidad de identificar compuestos candidatos con actividad anticonvulsiva frente el modelo animal en cuestión. Los modelos clasificatorios individuales han sido combinados y aplicados sobre las bases de datos DrugBank y SweetLead, revelando 57 fármacos que podrían poseer la actividad deseada. A partir de ello, se han adquirido 3 compuestos para ser evaluados durante la validación experimental frente al modelo de crisis epiléptica de 6 Hz. Como resultado, uno de los candidatos demostró poseer actividad anticonvulsiva, mientras que un segundo candidato demostró una leve tendencia a proteger frente a las crisis provocadas en el modelo animal. Los resultados obtenidos demuestran que las estrategias computacionales basadas en el ligando y aplicadas durante este trabajo de tesis, como el cribado virtual y el reposicionamiento de fármacos asistido por computadoras, han sido particularmente útiles para abordar de manera sistemática la búsqueda de nuevos usos terapéuticos de fármacos ya existentes. Asimismo, se ha destacado la importancia de aplicar estas metodologías escasamente exploradas y explotadas en el campo de la epilepsia.

show abstract

Unlocking The Mysteries of DNA Adducts with Artificial Intelligence

Arora,

Satija,

Mittal

et al. 2023

ChemBioChem

View full text Add to dashboard Cite

Cellular genome is considered a dynamic blueprint of a cell since it encodes genetic information that gets temporally altered due to various endogenous and exogenous insults. Largely, the extent of genomic dynamicity is controlled by the trade‐off between DNA repair processes and the genotoxic potential of the causative agent (genotoxins or potential carcinogens). A subset of genotoxins form DNA adducts by covalently binding to the cellular DNA, triggering structural or functional changes that lead to significant alterations in cellular processes via genetic (e.g., mutations) or non‐genetic (e.g., epigenome) routes. Identification, quantification, and characterization of DNA adducts are indispensable for their comprehensive understanding and could expedite the ongoing efforts in predicting carcinogenicity and their mode of action. In this review, we elaborate on using Artificial Intelligence (AI)‐based modeling in adducts biology and present multiple computational strategies to gain advancements in decoding DNA adducts. The proposed AI‐based strategies encompass predictive modeling for adduct formation via metabolic activation, novel adducts’ identification, prediction of biochemical routes for adduct formation, adducts’ half‐life predictions within biological ecosystems, and, establishing methods to predict the link between adducts chemistry and its location within the genomic DNA. In summary, we discuss some futuristic AI‐based approaches in DNA adduct biology.

show abstract

Ligand-Based Virtual Screening Using Graph Edit Distance as Molecular Similarity Measure

Cited by 51 publications

References 57 publications

Learning the Edit Costs of Graph Edit Distance Applied to Ligand-Based Virtual Screening

Learning the Edit Costs of Graph Edit Distance Applied to Ligand-Based Virtual Screening

Tamizado virtual aplicado a la búsqueda de nuevos fármacos antiepilépticos activos en el modelo de 6 Hz

Unlocking The Mysteries of DNA Adducts with Artificial Intelligence

Contact Info

Product

Resources

About