Early prediction of generalized infection in intensive care units from clinical data: a committee-based machine learning approach

Fonseca, Flávio Secco; Torcate, Arianne Sarmento; Silva, Ana Clara Gomes da; Freire, Victor Hugo Wanderley; Farias, Gilles De Medeiros De Paiva; Oliveira, João Fausto Lorenzato de; Oliveira, Flavio Monteiro De; Silva, Jose Carlos Da; Gomes, Dayane Aparecida; Santos, Wellington Pinheiros Dos

doi:10.1109/la-cci54402.2022.9981849

Cited by 1 publication

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models have demonstrated impressive performance in support diagnosis applications based on biomedical images, signals and clinical parameters, like in breast cancer, Covid-19, mental disorders, and in neurodegenerative diseases like Alzheimer's and Parkinson's (Azevedo et al, 2015;Barbosa et al, 2022;F.R. Cordeiro, Santos, & Silva-Filho, 2016b;de Lima, da Silva-Filho, & dos Santos, 2016;De Oliveira et al, 2020;de Santana, de Freitas Barbosa, de Cássia Fernandes de Lima, & dos Santos, 2022;de Santana et al, 2018; Santos Lucas e Silva, dos Santos, de Lima, & Initiative, 2021;Espinola, Gomes, Pereira, & dos Santos, 2021a, 2021bFonseca et al, 2022;Gomes et al, 2020;Gomes, de Santana, Masood, de Lima, & dos Santos, 2023;Gomes, Rodrigues, & dos Santos, 2022;Santana et al, 2018;Shirahige et al, 2022;Wanderley Espinola, Gomes, Mônica Silva Pereira, & dos Santos, 2022). Such models have been used successfully in accurately predicting protein-protein binding affinities.…”

Section: Introduction 1motivation and Problem Characterizationmentioning

confidence: 99%

Evaluation of molecular docking by deep learning and Random Forests: A hybrid approach based on pseudo-convolutions

Ferreira,

Feitosa,

Gomes

et al. 2023

Preprint

View full text Add to dashboard Cite

Purpose: Molecular docking prediction plays a pivotal role in intelligent drug design, offering significant advantages in the development of antivirus medications and vaccines. By accurately evaluating the interactions between drug molecules and target proteins, researchers can effectively expedite the discovery and development of vital pharmaceutical solutions, aiding in the mitigation of epidemics, pandemics, and the urgent need for improved vaccines. Methods: We propose an intelligent hybrid architecture for estimating molecular docking between two proteins using deep networks based on pseudo-convolutions and Random Forests. As input, we Evaluation of molecular docking by deep learning and Random Forests used the sequences of characters representing the bases of each protein. Through two layers of pseudo-convolutions, these sequences are reorganized and, finally, represented as co-occurrence matrices, concatenated into a feature vector. To validate our proposal, we used a combination of the public datasets Affinity Benchmark 3 and Negatome 2. Results: The experimental results revealed that the hybrid architecture , comprising two layers of pseudo-convolution followed by a decision layer with an ensemble of 25 Random Forests, yielded average accuracy of 94%, AUC of 93%, sensitivity of 94%, and specificity of 78%. This demonstrates the feasibility of achieving robust estimates of molecular docking without relying on 3D molecule modeling. Conclusion: These findings the potential of rapidly estimating protein affinity, providing valuable insights into drug interactions, molecular dynamics, and facilitating the intelligent design of pharmaceuticals, encompassing vaccines and antiviral drugs. These advancements play a critical role in cost reduction related to laboratory analysis and expediting the timely delivery of solutions to both the market and society at large, particularly in the context of epidemic outbreaks, pandemics, and the urgent demand for supplementary vaccines.

show abstract