MD-LAIs Software: Computing Whole-Sequence and Amino Acid-Level "Embeddings" for Peptides and Proteins.

J Chem Inf Model

Facultad de Ingeniería, Universidad Panamericana, Augusto Rodin No. 498, Insurgentes Mixcoac, Benito Juárez, Ciudad de México 03920, México.

Published: December 2024

Several computational tools have been developed to calculate sequence-based molecular descriptors (MDs) for peptides and proteins. However, these tools have certain limitations: 1) They generally lack capabilities for curating input data. 2) Their outputs often exhibit significant overlap. 3) There is limited availability of MDs at the amino acid () level. 4) They lack flexibility in computing specific MDs. To address these issues, we developed (olecular escriptors from ocal mino acid nvariant), Java-based software designed to compute both whole-sequence and -level MDs for peptides and proteins. These MDs are generated by applying aggregation operators () to macromolecular vectors containing the chemical-physical and structural properties of . The set of includes both nonclassical (e.g., Minkowski norms) and classical (e.g., Radial Distribution Function). Classical capture neighborhood structural information at different levels, while nonclassical are applied using a sliding window to generalize the -level output. A weighting system based on fuzzy membership functions is also included to account for the contributions of individual . features: 1) a module for data curation tasks, 2) a feature selection module, 3) projects of highly relevant MDs, and 4) low-dimensional lists of informative global and -level MDs. Overall, we expect that will be a valuable tool for encoding protein or peptide sequences. The software is freely available as a stand-alone system on GitHub (https://github.com/Grupo-Medicina-Molecular-y-Traslacional/MD_LAIS).

Download full-text PDF

Source
http://dx.doi.org/10.1021/acs.jcim.3c01189DOI Listing

Publication Analysis

Top Keywords

peptides proteins
12
mds peptides
8
-level mds
8
mds
7
md-lais software
4
software computing
4
computing whole-sequence
4
whole-sequence amino
4
amino acid-level
4
acid-level "embeddings"
4

Similar Publications

Purpose: Inflammatory processes have been involved in diabetic retinopathy (DR). Interleukin (IL)-17A, a pro-inflammatory cytokine, is associated with DR occurrence and development. However, mechanisms underlying the IL-17A impact on DR need further investigations.

View Article and Find Full Text PDF

Purpose: This study aimed to identify a novel recombinant adeno-associated virus (rAAV) capsid variant that can widely transfect the deep retina through intravitreal injection and to assess their effectiveness and safety in gene delivery.

Methods: By adopting the sequences of various cell-penetrating peptides and inserting them into the capsid modification region of AAV2, we generated several novel variants. The green fluorescent protein (GFP)-carrying variants were screened following intravitreal injection.

View Article and Find Full Text PDF

The HOX and PBX genes encode transcription factors that have key roles in development and cancer, both independently and as a heterodimer within a complex of proteins that recognizes specific sequences in DNA and can both activate and repress transcription of target genes. Due to functional redundancy amongst HOX proteins, knock down or knock out studies of individual genes often do not result in an altered phenotype. An alternative approach is to target the interaction between HOX and PBX proteins, which is dependent on a conserved hexapeptide region within HOX.

View Article and Find Full Text PDF

NADPH-Independent Fluorescent Probe for Live-Cell Imaging of Heme Oxygenase-1.

ACS Sens

January 2025

Hubei Key Laboratory of Genetic Regulation & Integrative Biology, Key Laboratory of Pesticide and Chemical Biology of Ministry of Education, School of Life Sciences, Central China Normal University, Wuhan 430079, China.

Heme oxygenase-1 (HO-1) catalyzes heme degradation on the consumption of NADPH and molecular oxygen. As an inducible enzyme, HO-1 is highly induced in various disease states, including cancer. Currently, two fluorescent probes for HO-1 have been designed based on the catalytic activity of HO-1, in which the probes serve as a substrate, so NADPH is required to enable the detection.

View Article and Find Full Text PDF

is a Gram-negative opportunistic pathogen and is a common cause of nosocomial infections. The increasing development of antibiotic resistance in this organism is a global health concern. The clinical isolate AB307-0294 produces a type VI secretion system (T6SS) that delivers three antibacterial effector proteins that give this strain a competitive advantage against other bacteria in polymicrobial environments.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!