Notícias

Banca de QUALIFICAÇÃO: EWERTON CRISTHIAN LIMA DE OLIVEIRA

Uma banca de QUALIFICAÇÃO de DOUTORADO foi cadastrada pelo programa.
DISCENTE: EWERTON CRISTHIAN LIMA DE OLIVEIRA
DATA: 26/10/2022
HORA: 14:00
LOCAL: https://meet.google.com/muw-htfn-yep
TÍTULO:

DEVELOPMENT OF MACHINE LEARNING-BASED FRAMEWORKS TO PREDICT PERMEABILITY OF PEPTIDES THROUGH CELL MEMBRANE AND BLOOD-BRAIN BARRIER


PALAVRAS-CHAVES:

Peptides, Biomembranes, CPPs, 3BPPs, Framework, Machine Learning.


PÁGINAS: 106
GRANDE ÁREA: Engenharias
ÁREA: Engenharia Elétrica
RESUMO:

Peptides comprise a versatile class of biomolecules with diverse physicochemical and structural
properties, in addition to numerous pharmacological and biotechnological applications. Some
groups of peptides can cross biological membranes, such as the cell membrane and the human
blood-brain barrier. Researchers have explored this property over the years as an alternative to
developing more powerful drugs, given that some peptides can also be drug carriers. Although
some machine learning-based tools have been developed to predict cell-penetrating peptides
(CPPs) and blood-brain barrier penetrating peptides (3BPPs), some points have not yet been
explored within this theme. These points encompass the use of dimensionality reduction (DR)
techniques in the preprocessing stage, molecular descriptors related to drug bioavailability, and
data structures that encode peptides with chemical modifications. Therefore, the primary pur-
pose of this thesis is to develop and test two frameworks based on DR, the first one to predict
CPPs and the second to predict 3BPPs, also evaluating the molecular descriptors and data struc-
ture of interest. The preliminary results of this thesis show that for the prediction of penetration
in the cell membrane, the proposed framework reached 92% of accuracy in the best performance
in an independent test, outperforming other tools created for the same purpose, besides evidenc-
ing the contribution between the junction of descriptors based on sequence and those related to
bioavailability. Furthermore, the prediction of 3BPPs by the framework using Mordred reached
average values of 99.3% and 99.5% for accuracy and F1-score in 10-fold cross-validation anal-
ysis, respectively. These preliminary results show that the proposed framework achieved good
results and can be used as an additional tool in predicting the penetration of peptides in these
two biomembranes.


MEMBROS DA BANCA:
Presidente - 1809092 - CLAUDOMIRO DE SOUZA DE SALES JUNIOR
Interno - 2170855 - ADRIANA ROSA GARCEZ CASTRO
Interno - 1176325 - ALDEBARO BARRETO DA ROCHA KLAUTAU JUNIOR
Externo ao Programa - 1316033 - ANDERSON HENRIQUE LIMA E LIMA
Externo ao Programa - 1662562 - JERONIMO LAMEIRA SILVA
Notícia cadastrada em: 21/09/2022 13:08
SIGAA | Centro de Tecnologia da Informação e Comunicação (CTIC) - | Copyright © 2006-2022 - UFPA - bacaba.ufpa.br.bacaba1