Comp2Bio Logo

Prof. Dr. Anderson Rodrigues dos Santos

Head of Computational Biology and Bioinformatics Laboratory
Federal University of Uberlândia (UFU)

Welcome to the Computational Biology and Bioinformatics laboratory (Comp2Bio). Comp2Bio strives to complete undergraduate and graduate studies, providing students with concepts and methodology to work in the vast area of Genetics and Biochemistry.

"This is a small and almost inexistent laboratory surviving due to the stubbornness of its head. Where you read 'practically inexistent,' I'm not overreacting: if you hang out at the Federal University of Uberlândia, in the state of Minas Gerais, Brazil, and ask someone how to get at the Comp2Bio, I suppose that not a single person will give a useful answer, except if you bump on me."

"I cannot blame them because, in Brazil, people are trained to be employees. They don't have skills to think about that as an opportunity for an inexistent area in Brazil. One shall remember Brazil as a country without significative manufacturing nor technology. For instance, I never received a grant from the government to my research despite always had indicated as conducting a prominent investigation."

Despite these challenges, our research focuses on three complementary branches: Genomic Annotation, Target Discovery for Vaccines, and Protein Interaction Networks.

RIS Project

Bypassing the O(N2) memory wall of Transformer auto-attention to democratize long-context LLM inference on commodity, unaccelerated CPU hardware.

RIS Press Pitch Satire

"Throwing RIS messages into the ocean of mainstream media."

Research Highlight

Reduced Interaction Sampling (RIS)

The expansion of Large Language Model (LLM) context windows is hindered by the quadratic scaling O(N2) of self-attention memory allocations. The RIS-Kernel resolves this bottleneck. Without retraining model weights, it leverages sparse stochastic geometry to reduce attention complexity to O(N log N), enabling 65k context inference on commodity CPU servers.

This 100% national technology was officially submitted to the Brazilian Ministry of Science, Technology and Innovation (MCTI) within the scope of the Brazilian AI Plan (PBIA) to support data sovereignty and local inference in public bodies.

Interestingly, the algorithm was not born in traditional NLP, but in the field of Bioinformatics. It was originally designed in our lab to handle network saturation while mapping bacterial protein-protein interactions in the GenPPi software, and later transposed to LLMs due to shared topological properties.

Video Presentations

Divulgação Científica: IA sem Supercomputadores

Science communication explaining the project's background and purpose.

Watch directly on YouTube

RIS-Kernel Technical Presentation

Technical talk recorded for the IKE'26 Conference.

Watch directly on YouTube

Developed Software

MEDpipe

Target selection based on immunoinformatics and exported prokaryotic proteins.


medpipe.facom.ufu.br

GENPPI

Standalone software for creating protein interaction networks from genomes.


genppi.facom.ufu.br

Selected Publications

Highlighting recent work as Senior/Last Author (2021-2026)

2026

Towards million-token context windows: a topology-preserving framework for adaptive transformer sparsification

Scientific Reports (Nature Portfolio)

Santos, Anderson R.

2026

In silico interactome analysis reveals distinct and complementary metabolic roles of bacteria in stingless bee larval food

Computational and Structural Biotechnology Journal

Avila, N.B. et al., Santos, A.R.

2025

Improving protein interaction prediction in GenPPi: a novel interaction sampling approach preserving network topology

BMC Bioinformatics

Silva, A., Marquez, C., Godoy, I., Silva, L., Prado, M., Beppler, M., Avila, N., Travençolo, B., Santos, Anderson R.

2025

Beyond Methane Oxidation: The Protein Landscape of -2a Reveals an Integrated System for Diazotrophy and Membrane Fortification

Environmental Microbiology Reports

Silva, S.S., Avila, N.B., Silva, A.W., Silva, L.R.F., Prado, M.R., Beppler, M.A., Santos, Anderson R.

2025

A Deep Metagenomic Snapshot as a Proof-of-Concept for Resource Generation: Simultaneous Assembly of Host, Food, and Microbiome Genomes From Stingless Bee Larval Food

Ecology and Evolution

Ueira-Vieira, C., Santos, A.C.C., Araújo, T.N., Augusto, S.C., Avila, N.B., Bonetti, A.M., Santos, Anderson R.

2024

Unveiling the Brazilian kefir microbiome: discovery of a novel Lactobacillus kefiranofaciens genome

BMC Genomics

Silva, M.H. et al., Santos, Anderson R.

2024

Enhancing omics analyses of bacterial protein secretion via non-classical pathways

Neural Computing and Applications

Oliveira, L.G.S., Lanes, G.C., Santos, A.R.

2024

Pannotator integrated with Medpipe provides immunological and subcellular location features using a microservice

Biomedical Informatics

Gonçalves, R., Santos, Anderson

2023

Implementation of a Noise Filter for Grouping in Bibliographic Databases using Latent Semantic Indexing

Int. Journal of Bioinformatics and Intelligent Computing

Gomes, M.M.A. et al., Santos, A.

2021

GENPPI: standalone software for creating protein interaction networks from genomes

BMC Bioinformatics

Anjos, W.F. et al., Santos, A.R.

Google Scholar

Patents & Innovation

BR10202401581

Formulações para Controle de Fitobactérias

2024 (Depósito)

BR10202001099

Perfil Espectral para Diagnóstico de COVID-19

2020 (Depósito)

BR10202001560

Plataforma de Amostra Reutilizável (Infravermelho)

2020 (Depósito)

BR10201601689

Fosfatase Ácida Recombinante (Vacina Linfadenite)

2016 (Concessão 2023)

BR102016016754

Esterase Recombinante (Vacina)

2016

BR512022003514-6

SamplesDB - Sistema Web

2022 (Software)

BR512018052200-9

EasyQuizzer

2018 (Software)

The Lab

Current Research Projects & Students

Research Lines

Recent Projects

  • RIS-Kernel: Sparsification of Transformer Self-Attention 2025 - Current. Developing algorithms and systems to execute long-context LLMs on unaccelerated CPU hardware.
  • GenPPi: Comparative Analysis via Machine Learning 2025 - Current. Investigation of PPI networks in Kosakonia cowanii strains.
  • Rare Diseases & Genomic Interpretation 2023 - 2024. Training professionals in bioinformatics for rare disease diagnosis.
  • Anaerobic Methane Oxidation 2020 - 2023. Synergistic relationship between archaea and bacteria.

Current Students (IC)

  • Davi Mota Campos Undergrad (2025) - GenPPi Kosakonia Analysis
  • Gustavo Henrique Leal da Fonseca Undergrad (2025) - GenPPi Kosakonia Analysis

Alumni (Egressos)

  • Allisson William da Silva MSc (2025) - GenPPi Random Forest Improvements
  • Murilo Alves Beppler Undergrad (2025) - Rare Diseases / Methane Oxidation
  • Iury Gregório Godoy / Matheus Ribeiro Prado Undergrad (2024) - GenPPI / Methane Oxidation
  • Luiz Gustavo de Sousa Oliveira MSc (2020) - Non-classical Secretion