RESUMEN
Understanding the interaction of T-cell receptor (TCR) with major histocompatibility-peptide (MHC-peptide) complex is extremely important in human immunotherapy and vaccine development. However, due to the limited available data, the performance of existing models for predicting the interaction of T-cell receptors (TCR) with major histocompatibility-peptide complexes is still unsatisfactory. Deep learning models have been applied to prediction tasks in various fields and have achieved better results compared with other traditional models. In this study, we leverage the gMLP model combined with attention mechanism to predict the interaction of MHC-peptide and TCR. Experiments show that our model can predict TCR-peptide interactions accurately and can handle the problems caused by different TCR lengths. Moreover, we demonstrate that the models trained with paired CDR3ß-chain and CDR3α-chain data are better than those trained with only CDR3ß-chain or with CDR3α-chain data. We also demonstrate that the hybrid model has greater potential than the traditional convolutional neural network.
RESUMEN
A wide variety of computational models covering statistical, mechanistic, and machine learning (locked and adaptive) methods are explored for use in biopharmaceutical manufacturing. Limited discussion exists on how to establish the credibility of a computational model for application in biopharmaceutical manufacturing. In this work, we tried to use the American Society of Mechanical Engineers (ASME) Verification and Validation 40 (V&V 40) standard and FDA proposed AI/ML model life cycle management framework for Software as a Medical Device (SaMD) in biopharmaceutical manufacturing use cases, by applying to a set of curated hypothetical examples. We discussed the need for standardized frameworks to facilitate consistent decision making to enable efficient adoption of computational models in biopharmaceutical manufacturing and alignment of existing good practices with existing frameworks. In the study of our examples, we anticipate existing frameworks like V&V 40 can be adopted.
Asunto(s)
Productos Biológicos , Animales , Simulación por Computador , Estadios del Ciclo de Vida , Aprendizaje Automático , Estados UnidosRESUMEN
This study aimed to assess the effect of encapsulating humic acid inside yeast cell walls (YCW) to detoxify AFB1 in in vitro gastrointestinal models. Glucan Mannan Lipid Particles (GMLPs) from Saccharomyces cerevisiae cell walls showed the highest AFB1 adsorption in simulated gastric fluid (SGF) after 10 min, and in simulated intestinal fluid (SIF) after 1 h. GMLPs are hollow 3-4 micron porous microspheres that provide an efficient system for the synthesis and encapsulation of AFB1-absorbing nanoparticles (NPs). Humic acid nanoparticles (HA-NPs) were synthesized within the GMLP cavity by complexation with ferric chloride. Encapsulating HA-NPs in GMLPs increased HA-NP stability in SIF. The hybrid GMLP HA-NP formulation synergistically enhanced AFB1 binding compared to individual GMLP and HA components in SGF and in SIF. Cytotoxicity on a murine macrophage cell line demonstrated that GMLP HA-NP-AFB1 complexes were stable in both SGF and SIF, detoxified AFB1 and are suitable for in vivo testing.