Max Pereira

Universidade do Porto

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Vı́tor Santos Costa

INESC TEC

Nuno A. Fonseca

Centro de Investigação em Biodiversidade e Recursos Genéticos

Rui Camacho

Universidade do Porto

Carlos J. V. Simões

University of Coimbra

Rui M. M. Brito

University of Coimbra

Carlos Adriano

Universidade do Porto

Willian Maria

Universidade do Sul de Santa Catarina

João Luccas Damiani

Universidade do Sul de Santa Catarina

Cooperative Institutions

Universidade do Porto

University of Coimbra

INESC TEC

Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento

Institute for Systems Engineering and Computers

University of Lisbon

Instituto Pedro Nunes

University of Aveiro

Instituto Português de Oncologia de Coimbra Francisco Gentil

Universidade do Sul de Santa Catarina

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

A relational learning approach to Structure-Activity Relationships in drug design toxicity studies.

PubMed (2011)

Rui Camacho Max Pereira Vı́tor Santos Costa Nuno A. Fonseca Carlos Adriano

It has been recognized that the development of new therapeutic drugs is a complex and expensive process. A large number of factors affect the activity in vivo of putative candidate molecules and the propensity for causing adverse and toxic effects is recognized as one of the major hurdles behind the current "target-rich, lead-poor" scenario. Structure-Activity Relationship (SAR) studies, using relational Machine Learning (ML) algorithms, have already been shown to be very useful in the complex process of rational drug design. Despite the ML successes, human expertise is still of the utmost importance in the drug development process. An iterative process and tight integration between the models developed by ML algorithms and the know-how of medicinal chemistry experts would be a very useful symbiotic approach. In this paper we describe a software tool that achieves that goal--iLogCHEM. The tool allows the use of Relational Learners in the task of identifying molecules or molecular fragments with potential to produce toxic effects, and thus help in stream-lining drug design in silico. It also allows the expert to guide the search for useful molecules without the need to know the details of the algorithms used. The models produced by the algorithms may be visualized using a graphical interface, that is of common use amongst researchers in structural biology and medicinal chemistry. The graphical interface enables the expert to provide feedback to the learning system. The developed tool has also facilities to handle the similarity bias typical of large chemical databases. For that purpose the user can filter out similar compounds when assembling a data set. Additionally, we propose ways of providing background knowledge for Relational Learners using the results of Graph Mining algorithms.

Interface (matter)

Similarity (geometry)

10.2390/biecoll-jib-2011-182

Cite

Citations (2)

Assessing the Effect of 2D Fingerprint Filtering on ILP-Based Structure-Activity Relationships Toxicity Studies in Drug Design

Advances in intelligent and soft computing (2011)

Rui Camacho Max Pereira Vı́tor Santos Costa Nuno A. Fonseca Carlos J. V. Simões

Similarity (geometry)

Drug Design

10.1007/978-3-642-19914-1_46

Cite

Citations (0)

Interactive Discriminative Mining of Chemical Fragments

Lecture notes in computer science (2011)

Nuno A. Fonseca Max Pereira Vı́tor Santos Costa Rui Camacho

Cheminformatics

Discriminative model

10.1007/978-3-642-21295-6_10

Cite

Citations (2)

A Relational Learning Approach to Structure-Activity Relationships in Drug Design Toxicity Studies

Berichte aus der medizinischen Informatik und Bioinformatik/Journal of integrative bioinformatics (2011)

Rui Camacho Max Pereira Vı́tor Santos Costa Nuno A. Fonseca Carlos Adriano

Summary It has been recognized that the development of new therapeutic drugs is a complex and expensive process. A large number of factors affect the activity in vivo of putative candidate molecules and the propensity for causing adverse and toxic effects is recognized as one of the major hurdles behind the current “target-rich, lead-poor” scenario. Structure-Activity Relationship (SAR) studies, using relational Machine Learning (ML) algorithms, have already been shown to be very useful in the complex process of rational drug design. Despite the ML successes, human expertise is still of the utmost importance in the drug development process. An iterative process and tight integration between the models developed by ML algorithms and the know-how of medicinal chemistry experts would be a very useful symbiotic approach. In this paper we describe a software tool that achieves that goal - iLogCHEM. The tool allows the use of Relational Learners in the task of identifying molecules or molecular fragments with potential to produce toxic effects, and thus help in stream-lining drug design in silico. It also allows the expert to guide the search for useful molecules without the need to know the details of the algorithms used. The models produced by the algorithms may be visualized using a graphical interface, that is of common use amongst researchers in structural biology and medicinal chemistry. The graphical interface enables the expert to provide feedback to the learning system. The developed tool has also facilities to handle the similarity bias typical of large chemical databases. For that purpose the user can filter out similar compounds when assembling a data set. Additionally, we propose ways of providing background knowledge for Relational Learners using the results of Graph Mining algorithms.

Interface (matter)

Similarity (geometry)

10.1515/jib-2011-182

Cite

Citations (7)

Visually Guiding and Controlling the Search While Mining Chemical Structures

Lecture notes in computer science (2009)

Max Pereira Vı́tor Santos Costa Rui Camacho Nuno A. Fonseca

Discriminative model

10.1007/978-3-642-02481-8_158

Cite

Citations (0)

Rede Bayesiana para previsão de Evasão Escolar

Anais ... Workshops do Congresso Brasileiro de Informática na Educação (2016)

Willian Maria João Luccas Damiani Max Pereira

Tendo em vista o grande problema que é a evasão escolar, problema este que impacta instituições de ensino do mundo inteiro, este artigo apresenta a aplicação da técnica computacional de Redes Bayesianas, com o intuito de predizer os percentuais de chance de evasão dos alunos, com o objetivo de auxiliar os gestores educacionais na prevenção destes tipos de situações. A predição é realizada com base nas características dos alunos, coletadas do sistema utilizado pela instituição de ensino SENAI de Tubarão/SC, permitindo ainda a manipulação destas características por parte do gestor, a fim de simular cenários com o objetivo de minimizar as chances de o aluno evadir. Através da validação dos resultados foi obtido 85,6% de taxa de acerto, o que indica um bom desempenho da rede bayesiana modelada para o sistema desenvolvido.

10.5753/cbie.wcbie.2016.920

Cite

Citations (1)

Comparative Study of Classification Algorithms Using Molecular Descriptors in Toxicological DataBases

Lecture notes in computer science (2009)

Max Pereira Vı́tor Santos Costa Rui Camacho Nuno A. Fonseca Carlos J. V. Simões

10.1007/978-3-642-03223-3_11

Cite

Citations (12)