Zanoni Dias
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
Research Subjects
Zanoni Dias has a total of 79 co-authors. Here are the top co-authors by number of shared publications:
- Andre Rodrigues Oliveira
Faculdade de Computação e Informática, Universidade Presbiteriana Mackenzie, São Paulo, Brazil
37 shared publications - Alexsandro Oliveira Alexandrino
Instituto de Computação, Universidade Estadual de Campinas (UNICAMP), Campinas, Brazil
35 shared publications - Ulisses Dias
Faculdade de Tecnologia, Universidade Estadual de Campinas (UNICAMP), Limeira, Brazil
34 shared publications - Klairton Lima Brito
Instituto de Computação, Universidade Estadual de Campinas (UNICAMP), Campinas, Brazil
22 shared publications - Gabriel Siqueira
Instituto de Computação, Universidade Estadual de Campinas (UNICAMP), Campinas, Brazil
18 shared publications - Helio Pedrini
University of Campinas
16 shared publications
Latest Publications
- 3 October 2026
- Published by Springer Nature
- p. 304-318
Analyzing Language Models for Hate Speech Detection in Brazilian Political Content
- 3 October 2026
- Published by Springer Nature
- p. 304-318
Analyzing Language Models for Hate Speech Detection in Brazilian Political Content
- 1 October 2026
- Published by Springer Nature
- p. 325-339
Beyond Sequence: Propagating Inter-protein Structural Context for Protein Language Models
- 1 October 2026
- Published by Springer Nature
- p. 325-339
Beyond Sequence: Propagating Inter-protein Structural Context for Protein Language Models
- 30 September 2026
- Published by Springer Nature
- p. 184-199
What Matters in RAG for Small Language Models? A Large-Scale Sensitivity Study
- 30 September 2026
- Published by Springer Nature
- p. 184-199
What Matters in RAG for Small Language Models? A Large-Scale Sensitivity Study
- 30 September 2026
- Published by Springer Nature
- p. 309-324
Enem-VL: A Multimodal Benchmark of Brazilian Exams for Evaluating Vision-Language Models
- 30 September 2026
- Published by Springer Nature
- p. 309-324
Enem-VL: A Multimodal Benchmark of Brazilian Exams for Evaluating Vision-Language Models
- 30 September 2026
- Published by Springer Nature
- p. 584-598
LLM-Lobotomy: A Representation Engineering Framework for LLM Behavioral Steering
- 30 September 2026
- Published by Springer Nature
- p. 584-598
LLM-Lobotomy: A Representation Engineering Framework for LLM Behavioral Steering
- 30 September 2026
- Published by Springer Nature
- p. 277-292
How Large Language Models Profile Brazilians: Socioeconomic Attribution and Stereotypes
- 30 September 2026
- Published by Springer Nature
- p. 277-292
How Large Language Models Profile Brazilians: Socioeconomic Attribution and Stereotypes
- Open Access
- 19 July 2026
- Published by Sociedade Brasileira de Computação
- p. 11-20
Anotações de Funções de Proteínas Utilizando Aprendizado de Máquina e Alinhamento Local
Com o avanço das tecnologias de sequenciamento, milhões de proteínas tiveram suas sequências determinadas, enquanto a anotação experimental de suas funções permanece limitada. A predição computacional de funções proteicas tornou-se, portanto, um problema central em bioinformática, caracterizado como uma tarefa de classificação multirrótulo hierárquica de larga escala. Nesta tese, propomos dois métodos baseados em aprendizado de máquina utilizando embeddings de modelos Transformers, bem como duas abordagens de ensemble que integram essas predições com alinhamento local de sequências. Avaliados na base derivada do CAFA5, principal conjunto de dados da área, os métodos propostos superaram consistentemente as principais abordagens da literatura, estabelecendo-se como os novos estado da arte para o problema de predição de funções proteicas a partir exclusivamente da sequência de aminoácidos. Além disso, apresentamos versões otimizadas em memória e um servidor Web público para uso da comunidade científica.
- 19 July 2026
- Published by Sociedade Brasileira de Computação
- p. 11-20
Open AccessAnotações de Funções de Proteínas Utilizando Aprendizado de Máquina e Alinhamento Local
Com o avanço das tecnologias de sequenciamento, milhões de proteínas tiveram suas sequências determinadas, enquanto a anotação experimental de suas funções permanece limitada. A predição computacional de funções proteicas tornou-se, portanto, um problema central em bioinformática, caracterizado como uma tarefa de classificação multirrótulo hierárquica de larga escala. Nesta tese, propomos dois métodos baseados em aprendizado de máquina utilizando embeddings de modelos Transformers, bem como duas abordagens de ensemble que integram essas predições com alinhamento local de sequências. Avaliados na base derivada do CAFA5, principal conjunto de dados da área, os métodos propostos superaram consistentemente as principais abordagens da literatura, estabelecendo-se como os novos estado da arte para o problema de predição de funções proteicas a partir exclusivamente da sequência de aminoácidos. Além disso, apresentamos versões otimizadas em memória e um servidor Web público para uso da comunidade científica.
- 29 May 2026
- Published by Springer Nature
- p. 129-139
DCJ and Indel Distance Considering Intergenic Region Information
- 29 May 2026
- Published by Springer Nature
- p. 129-139
DCJ and Indel Distance Considering Intergenic Region Information
- Open Access
- 7 March 2026
- Published by Springer Nature in Journal of Combinatorial Optimization
- Vol. 51 (2) , 26
Maximum alternating clean balanced cycle decomposition and applications in rearrangement distance problems
In genome rearrangement, graph-based representations are widely used to analyze and solve rearrangement problems. In particular, when each gene occurs at most once, the breakpoint graph is a useful tool. A maximum cycle decomposition of this graph yields immediate lower bounds for several genome rearrangement distances. This paper introduces a generalization of the Maximum Alternating Cycle Decomposition problem ( MAX-ACD ), called the Maximum Alternating Clean Balanced Cycle Decomposition problem ( MAX-ACBCD ). The MAX-ACD problem is closely related to some rearrangement problems, where the orientation of the genes is unknown, and all genes are common to both genomes. The MAX-ACBCD problem has applications to related rearrangement problems, which allow genes present in only one of the genomes and consider both gene order and intergenic-region information. We present a constant-factor approximation and a heuristic for the MAX-ACBCD problem, and we performed tests with the heuristic applied to artificially generated genomes. Considering intergenic regions and a scenario where the orientation of the genes is known, we design an improved algorithm for the Sorting by Reversals and Intergenic Indels problem that guarantees an approximation factor of $$\frac{3}{2}$$ . For the scenario where the orientation of the genes is unknown, and using the MAX-ACBCD problem, we develop approximation algorithms for the Sorting by Reversals, the Sorting by Reversals and Intergenic Indels, the Reversal, Transposition and Indel Distance, the Sorting by DCJ, and the Sorting by DCJ and Intergenic Indels problems with approximation factors of 2 k , $$\frac{3k}{2}$$ , 4 k , 2 k , and k , respectively, where $$k=\frac{31}{21}+\epsilon $$ .- 7 March 2026
- Published by Springer Nature in Journal of Combinatorial Optimization
- Vol. 51 (2) , 26
Open AccessMaximum alternating clean balanced cycle decomposition and applications in rearrangement distance problems
In genome rearrangement, graph-based representations are widely used to analyze and solve rearrangement problems. In particular, when each gene occurs at most once, the breakpoint graph is a useful tool. A maximum cycle decomposition of this graph yields immediate lower bounds for several genome rearrangement distances. This paper introduces a generalization of the Maximum Alternating Cycle Decomposition problem ( MAX-ACD ), called the Maximum Alternating Clean Balanced Cycle Decomposition problem ( MAX-ACBCD ). The MAX-ACD problem is closely related to some rearrangement problems, where the orientation of the genes is unknown, and all genes are common to both genomes. The MAX-ACBCD problem has applications to related rearrangement problems, which allow genes present in only one of the genomes and consider both gene order and intergenic-region information. We present a constant-factor approximation and a heuristic for the MAX-ACBCD problem, and we performed tests with the heuristic applied to artificially generated genomes. Considering intergenic regions and a scenario where the orientation of the genes is known, we design an improved algorithm for the Sorting by Reversals and Intergenic Indels problem that guarantees an approximation factor of $$\frac{3}{2}$$ . For the scenario where the orientation of the genes is unknown, and using the MAX-ACBCD problem, we develop approximation algorithms for the Sorting by Reversals, the Sorting by Reversals and Intergenic Indels, the Reversal, Transposition and Indel Distance, the Sorting by DCJ, and the Sorting by DCJ and Intergenic Indels problems with approximation factors of 2 k , $$\frac{3k}{2}$$ , 4 k , 2 k , and k , respectively, where $$k=\frac{31}{21}+\epsilon $$ . - Open Access
Approximations for the Weighted Reversal, Transposition, and Indel Distance Problem with Intergenic Region Information
Genome rearrangement distances are an established method in genome comparison. Works in this area may include various rearrangement operations representing large-scale mutations, gene orientation information, the number of nucleotides in intergenic regions, and weights reflecting the expected frequency of each operation. In this article, we model genomes containing at most one copy of each gene by considering gene sequences, with orientations, and representing intergenic regions according to their nucleotide lengths. We looked at a problem called Weighted Reversal, Transposition, and Indel Distance, which seeks the minimal cost sequence composed by the rearrangement operations of reversals, transposition, and indels, capable of transforming one genome into another. We leverage a structure called Labeled Intergenic Breakpoint Graph to show an algorithm for that problem with guaranteed approximations considering some sets of weights for the operations.
Open AccessApproximations for the Weighted Reversal, Transposition, and Indel Distance Problem with Intergenic Region Information
Genome rearrangement distances are an established method in genome comparison. Works in this area may include various rearrangement operations representing large-scale mutations, gene orientation information, the number of nucleotides in intergenic regions, and weights reflecting the expected frequency of each operation. In this article, we model genomes containing at most one copy of each gene by considering gene sequences, with orientations, and representing intergenic regions according to their nucleotide lengths. We looked at a problem called Weighted Reversal, Transposition, and Indel Distance, which seeks the minimal cost sequence composed by the rearrangement operations of reversals, transposition, and indels, capable of transforming one genome into another. We leverage a structure called Labeled Intergenic Breakpoint Graph to show an algorithm for that problem with guaranteed approximations considering some sets of weights for the operations.