SCSérgio Vale Aguiar Campos

Sérgio Vale Aguiar Campos

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Sérgio Vale Aguiar Campos has a total of 79 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Determination of the lactose content in low-lactose milk using Fourier-transform infrared spectroscopy (FTIR) and convolutional neural network

    by Daniela C.S.Z. Ribeiro, Habib Asseiss Neto, Juliana S. Lima, Débora C.S. de Assis, Kelly M. Keller, Sérgio V.A. Campos, Daniel A. Oliveira, Leorges M. Fonseca


  • BDDBlast—A Memory Efficient Architecture for Pairwise Alignments

    by Demian Bueno de Oliveira, Alessandra Faria-Campos, Sérgio Campos

  • FluxPRT: An Adaptable and Extensible Proteomics LIMS

    by Elizabeth Regina Alfaro-Espinoza, Lucas Ferreira Paiva, Alessandra C. Faria-Campos, Maria Cristina Baracat-Pereira, Sérgio Vale Aguiar Campos

  • Construction and maintenance of P2P overlays for live streaming

    by Eliseu C. Miguel, Cristiano M. Silva, Fernando C. Coelho, Ítalo F. S. Cunha, Sérgio V. A. Campos


  • Open Access

    NASirt: AutoML based learning with instance-level complexity information

    by Habib Asseiss Neto, Ronnie C. O. Alves, Sergio V. A. Campos

    Designing adequate and precise neural architectures is a challenging task, often done by highly specialized personnel. AutoML is a machine learning field that aims to generate good performing models in an automated way. Spectral data such as those obtained from biological analysis have generally a lot of important information, and these data are specifically well suited to Convolutional Neural Networks (CNN) due to their image-like shape. In this work we present NASirt, an AutoML methodology based on Neural Architecture Search (NAS) that finds high accuracy CNN architectures for spectral datasets. The proposed methodology relies on the Item Response Theory (IRT) for obtaining characteristics from an instance level, such as discrimination and difficulty, and it is able to define a rank of top performing submodels. Several experiments are performed in order to demonstrate the methodology's performance with different spectral datasets. Accuracy results are compared to other benchmarks methods, such as a high performing, manually crafted CNN and the Auto-Keras AutoML tool. The results show that our method performs, in most cases, better than the benchmarks, achieving average accuracy as high as 97.40%.

  • In Silico Laboratory Experiments Using Statistical Model Checking: A New Model of the Palytoxin-Induced Pump Channel as Case Study

    by Gabriel Domingo Vilallonga, Daniel Edgardo Riesco, Antonio-Carlos G. de Almeida, Antonio Marcio Rodrigues, Sergio V. A. Campos

    Studying biological systems is a difficult but important task. Traditional methods include laboratory experimentation and computer simulations. However, often researchers need to explore important but potentially rare events that are not easily observed or simulated. We use UPPAAL-SMC, a formal verification tool to support a methodology that allows modelling biological systems, specify events and conditions that we want to analyze, and to explore system executions using controlled simulations. We also describe an efficient way to reproduce laboratory experiments in silico. Unlike traditional simulations, we are able to guide the experiment to explore special events and conditions expressing these conditions in temporal logic formulas. We have applied this methodology to create a more detailed model of Palytoxin-induced Na + /K + pump channels than was previously possible. Moreover, we have reproduced experimental protocols and their associated electrophysiological recordings, which has not been done in previous works. As a consequence, we have been able to propose a new diprotomeric model for the PTX-pump complex and study its behaviour. The use of our methodology enabled us to reduce the effort and time to perform this research. It can be used to model other complex biological systems, potentially increasing the productivity of such studies.


  • Open Access

    Protocol data management in biology laboratories

    by Alessandra Conceição Faria Aguiar Campos, Célia Consolação Dias, Gabriel Teixeira, Alexandre Alphonsos, Germano Leite, Maria Elena Lima, Sergio Campos

    Organizing information objective is to disseminate the information objects effectively to the users. It is a complex but important task that uses elements such as the form and informational content of documents. Organized information is a prerequisite for an efficient organization. The goal of this study is to discuss the proposal of developing a system to organize protocol information from biological laboratories capable of managing protocol data. Research laboratories are examples of organizations that have a diverse and complex set of data that must be well organized. Their flow of information needs to be mapped identifying people, information sources, technology used as well as products and services. In this paper we describe the development of the FluxP system to organize information on protocols from a Biology Research Laboratory — The Animal Venoms and Toxins Laboratory (LVTA) from Federal University of Minas Gerais – Brazil. The following methodological procedures were adopted: technical visits, construction of a tool to manage the protocols (FluxP forms), categorization of the protocols used in the LVTA and experimental tests with 3 LVTA researchers. As a result, we highlight some features like: FluxP is able to manage protocol data making it simple to store and retrieve protocols to aid in the experimental work, increasing the reliability of experiments and helping reduce experimental errors. By establishing a central repository for protocols FluxP prevents protocols from being misplaced or lost and by categorizing them it makes simple to retrieve protocols based on keywords. The system is currently being used by LVTA to manage a collection of 50 protocols, and can be easily adapted for other laboratories.

  • Open Access

    On the utilization of deep and ensemble learning to detect milk adulteration

    by Habib Asseiss Neto, Wanessa L.F. Tavares, Daniela C.S.Z. Ribeiro, Ronnie C.O. Alves, Leorges M. Fonseca, Sérgio V.A. Campos

    Fraudulent milk adulteration is a dangerous practice in the dairy industry that is harmful to consumers since milk is one of the most consumed food products. Milk quality can be assessed by Fourier Transformed Infrared Spectroscopy (FTIR), a simple and fast method for obtaining its compositional information. The spectral data produced by this technique can be explored using machine learning methods, such as neural networks and decision trees, in order to create models that represent the characteristics of pure and adulterated milk samples. Thousands of milk samples were collected, some of them were manually adulterated with five different substances and subjected to infrared spectroscopy. This technique produced spectral data from the milk samples composition, which were used for training different machine learning algorithms, such as deep and ensemble decision tree learners. The proposed method is used to predict the presence of adulterants in a binary classification problem and also the specific assessment of which of five adulterants was found through multiclass classification. In deep learning, we propose a Convolutional Neural Network architecture that needs no preprocessing on spectral data. Classifiers evaluated show promising results, with classification accuracies up to 98.76%, outperforming commonly used classical learning methods. The proposed methodology uses machine learning techniques on milk spectral data. It is able to predict common adulterations that occur in the dairy industry. Both deep and ensemble tree learners were evaluated considering binary and multiclass classifications and the results were compared. The proposed neural network architecture is able to outperform the composition recognition made by the FTIR equipment and by commonly used methods in the dairy industry.


  • ViMT - Development of a Web-Based Vivarium Management Tool

    by Cristiano Guimarães Pimenta, Alessandra Conceição Faria-Campos, Jerônimo Nunes Rocha, Adriana Abalen Martins Dias, Danielle da Glória de Souza, Carolina Andrade Rezende, Giselle Marina Diniz Medeiros, Sérgio Vale Aguiar Campos

  • Open Access

    Computer aided identification of a Hevein-like antimicrobial peptide of bell pepper leaves for biotechnological use

    by Patrícia Dias Games, Elói Quintas Gonçalves Dasilva, Meire de Oliveira Barbosa, Hebréia Oliveira Almeida-Souza, Patrícia Pereira Fontes, Marcos Jorge Demagalhães-Jr, Paulo Roberto Gomes Pereira, Maura Vianna Prates, Gloria Regina Franco, Alessandra Faria-Campos, et al.

    Antimicrobial peptides from plants present mechanisms of action that are different from those of conventional defense agents. They are under-explored but have a potential as commercial antimicrobials. Bell pepper leaves (‘Magali R’) are discarded after harvesting the fruit and are sources of bioactive peptides. This work reports the isolation by peptidomics tools, and the identification and partially characterization by computational tools of an antimicrobial peptide from bell pepper leaves, and evidences the usefulness of records and the in silico analysis for the study of plant peptides aiming biotechnological uses. Aqueous extracts from leaves were enriched in peptide by salt fractionation and ultrafiltration. An antimicrobial peptide was isolated by tandem chromatographic procedures. Mass spectrometry, automated peptide sequencing and bioinformatics tools were used alternately for identification and partial characterization of the Hevein-like peptide, named HEV-CANN. The computational tools that assisted to the identification of the peptide included BlastP, PSI-Blast, ClustalOmega, PeptideCutter, and ProtParam; conventional protein databases (DB) as Mascot, Protein-DB, GenBank-DB, RefSeq, Swiss-Prot, and UniProtKB; specific for peptides DB as Amper, APD2, CAMP, LAMPs, and PhytAMP; other tools included in ExPASy for Proteomics; The Bioactive Peptide Databases, and The Pepper Genome Database. The HEV-CANN sequence presented 40 amino acid residues, 4258.8 Da, theoretical pI-value of 8.78, and four disulfide bonds. It was stable, and it has inhibited the growth of phytopathogenic bacteria and a fungus. HEV-CANN presented a chitin-binding domain in their sequence. There was a high identity and a positive alignment of HEV-CANN sequence in various databases, but there was not a complete identity, suggesting that HEV-CANN may be produced by ribosomal synthesis, which is in accordance with its constitutive nature. Computational tools for proteomics and databases are not adjusted for short sequences, which hampered HEV-CANN identification. The adjustment of statistical tests in large databases for proteins is an alternative to promote the significant identification of peptides. The development of specific DB for plant antimicrobial peptides, with information about peptide sequences, functional genomic data, structural motifs and domains of molecules, functional domains, and peptide-biomolecule interactions are valuable and necessary.