FGV EMAp launches unprecedented platform for analyzing rare diseases and conditions

Developed by PaccanaroLab, LanDis is a platform that allows users to explore the “interactome,” the complex network of molecular interactions essential to understanding diseases.
应用数学
02 九月 2024
FGV EMAp launches unprecedented platform for analyzing rare diseases and conditions

PaccanaroLab at Fundação Getulio Vargas’ School of Applied Mathematics (FGV EMAp) recently launched LanDis, an innovative, online and free tool for studying similarities between hereditary diseases at molecular level. The system allows the scientific community to explore the “interactome,” the complex network of molecular interactions essential to understanding diseases. The software will benefit biologists, research centers and pharmaceutical laboratories.

The pioneering platform maps the distances between the disease modules of more than 44 million pairs of hereditary diseases, offering a comprehensive and interactive view of similarities between illnesses. Linked to the OMIM and UniProt databases, LanDis opens up avenues for deeper analysis, potentially revealing new insights into the etiology of diseases.

“LanDis stands out for its ability to transform a complex set of data into an accessible and intuitive graphic interface. This functionality allows doctors, scientists and other health professionals to visually explore the relationships between different diseases, greatly facilitating research and medical practice,” explains Alberto Paccanaro, the creator and coordinator of PaccanaroLab, a health-focused artificial intelligence laboratory that carries out cutting-edge machine learning research to solve problems in the areas of molecular biology, medicine and pharmacology.

According to researcher Mateo Torres, who contributed to the development of the tool at FGV, “LanDis allows researchers to visually navigate non-obvious relationships between diseases and provides relevant publications that make the similarities between diseases clearer. This is extremely valuable when exploring hypotheses about rare conditions.”

Innovative project

The tool is not only a breakthrough for scientific research, but also a valuable resource for medical diagnosis. LanDis is able to identify diseases with similar molecular characteristics, even in cases where genetic information is limited, based on text contained in scientific publications related to the respective diseases.

The system also promotes scientific collaboration by integrating with other important databases. This functionality expands the potential for discoveries, as every disease on the LanDis map is linked to relevant resources in OMIM, UniProt and the United States National Library of Medicine.

As an open source and freely accessible tool, LanDis is an important milestone in network medicine and genomics. Available at no cost and with no registration required, it democratizes access to crucial information in the study of hereditary diseases and encourages innovation and collaborative research on a global scale.

To find out more about LanDis, click here.

PaccanaroLab

PaccanaroLab is developing new artificial intelligence algorithms in the fields of biology, medicine and pharmacology. In addition to the system for predicting the genes that cause hereditary diseases, there are other research projects under way at the lab, such as a model for predicting the frequency of side effects of medicines, the first of its kind ever developed; an algorithm for predicting which types of medicine can be used for certain viruses, based on identifying the target proteins of medicines; and a tool for predicting the function of proteins, which is currently the world’s best-rated algorithm for predicting the function of proteins in bacteria.

Paccanaro says that the lab’s projects invariably begin with a question asked by a biologist. “The starting point is always a question. Often the biologist doesn’t know how to get their answer from the experiment, because you have to detect patterns in large amounts of data that are very ‘noisy’ and composed of various sets of data from different sources. So, my team and I created an algorithm to answer these questions using data. In doing this, we developed new machine learning methods to answer questions in medicine, biology and pharmacology,” explains the researcher at FGV EMAp, which aims to be a Latin American center of reference for data science by 2028.

These projects are financed by Fundação Getulio Vargas, Brazil’s National Council for Scientific and Technological Development (CNPq), the Rio de Janeiro State Research Foundation (FAPERJ), the United Kingdom’s Medical Research Council and the United States’ National Science Foundation.

For more information about PaccanaroLab’s projects, click here.

To read a full paper about the LanDis project, click here.

视频

Esse site usa cookies

Nosso website coleta informações do seu dispositivo e da sua navegação e utiliza tecnologias como cookies para armazená-las e permitir funcionalidades como: melhorar o funcionamento técnico das páginas, mensurar a audiência do website e oferecer produtos e serviços relevantes por meio de anúncios personalizados. Para mais informações, acesse o nosso Aviso de Cookies e o nosso Aviso de Privacidade.