Insights into the mechanisms involved in the fungal degradation of plastics.

Fungi are considered among the most efficient microbial degraders of plastics, as they produce salient enzymes and can survive on recalcitrant compounds with limited nutrients. In recent years, studies have reported numerous species of fungi that can degrade different types of plastics, yet there remain many gaps in our understanding of the processes involved in biodegradation. In addition, many unknowns need to be resolved regarding the fungal enzymes responsible for plastic fragmentation and the regulatory mechanisms which fungi use to hydrolyse, assimilate and mineralize synthetic plastics. This review aims to detail the main methods used in plastic hydrolysis by fungi, key enzymatic and molecular mechanisms, chemical agents that enhance the enzymatic breakdown of plastics, and viable industrial applications. Considering that polymers such as lignin, bioplastics, phenolics, and other petroleum-based compounds exhibit closely related characteristics in terms of hydrophobicity and structure, and are degraded by similar fungal enzymes as plastics, we have reasoned that genes that have been reported to regulate the biodegradation of these compounds or their homologs could equally be involved in the regulation of plastic degrading enzymes in fungi. Thus, this review highlights and provides insight into some of the most likely regulatory mechanisms by which fungi degrade plastics, target enzymes, genes, and transcription factors involved in the process, as well as key limitations to industrial upscaling of plastic biodegradation and biological approaches that can be employed to overcome these challenges.

Method development and validation of LC-MS/MS-based assay for the simultaneous quantitation of trastuzumab and pertuzumab in cynomolgus monkey serum and its application in pharmacokinetic study.

We present a simple and robust LC-MS/MS assay for the simultaneous quantitation of an antibody cocktail of trastuzumab and pertuzumab in monkey serum. The LC-MS/MS method saved costs, decreased the analysis time, and reduced quantitative times relative to the traditional ligand-binding assays. The serum samples were digested with trypsin at 50°C for 60 min after methanol precipitation, ammonium bicarbonate denaturation, dithiothreitol reduction, and iodoacetamide alkylation. The tryptic peptides were chromatographically separated using a C18 column (2.1 × 50 mm, 2.6 µm) with mobile phases of 0.1% formic acid in water and acetonitrile. The other monoclonal antibody, infliximab, was used as internal standards to minimize the variability during sample processing and detection. A unique peptide for each monoclonal antibody was simultaneously quantified using LC-MS/MS in the multiple reaction monitoring mode. Calibration curves were linear from 2.0 to 400 µg/mL. The intra- and inter-assay precision (%CV) was within 8.9 and 7.4% (except 10.4 and 15.1% for lower limit of quantitation), respectively, and the accuracy (%Dev) was within ±13.1%. The other validation parameters were evaluated, and all results met the acceptance criteria of the international guiding principles. Finally, the method was successfully applied to a pharmacokinetics study after a single-dose intravenous drip administration to cynomolgus monkeys.

Simultaneous quantitative determination of liraglutide and insulin degludec in rat plasma by liquid chromatography-tandem mass spectrometry method and its application.

A simple, fast and high-throughput LC-tandem mass spectrometry method was developed and validated to simultaneously measure liraglutide and insulin degludec in rat plasma. After protein precipitation, plasma samples were subjected to gradient elution using an InertSustain Bio C18 column with 1000/20/1 water/acetonitrile/formic acid (v/v/v) and 1000/1 acetonitrile/formic acid (v/v) as the mobile phase. The method was validated from 1.00 to 500 ng/mL of liraglutide and insulin degludec. Further, the extraction recovery from the plasma was 41.8%-49.2% for liraglutide and 56.5%-69.7% for insulin degludec. Intra- and inter-day precision of liraglutide was 3.5%-9.4% and 8.4%-9.8%, respectively, whereas its accuracy was between -12.6% and -1.3%. Intra- and inter-day precision of insulin degludec was 5.2%-13.6% and 11.8%-19.1%, respectively, showing an accuracy between -3.0% and 9.9%. As a result, the method was successfully applied to a pharmacokinetics study of liraglutide and insulin degludec following a single-dose subcutaneous administration to rats.

Magnetic nanoparticles encapsulated laccase nanoflowers: evaluation of enzymatic activity and reusability for degradation of malachite green.

Magnetic laccase nanoflowers (MNFs-Lac) were successfully prepared through encapsulating Fe3O4 magnetic nanoparticles into the interior of laccase nanoflowers by grafting N-(phosphonomethyl)iminodiacetic acid (PMIDA) as an interconnecting bridge between the magnetic nanoparticles and copper ions. The characterizations by scanning electron microscopy and transmission electron microscopy showed that MNFs-Lac were spherical, porous and flower-like crystals with diameters of ∼10 µm, and Fe3O4 nanoparticles were encapsulated in the interior of MNFs-Lac evenly. The enzymatic activity and reusability of MNFs-Lac were evaluated based on the degradation efficiency for malachite green (MG). The degradation parameters, concerning initial MG concentration, dosage of MNFs-Lac, reaction temperature, pH value and reaction time, were optimized through single-factor experiments. Under the optimal conditions, 25 mg·L-1 MG can be degraded almost completely by 1.5 g·L-1 MNFs-Lac within 15 min. When the MNFs-Lac were reused for 18 times, the degradation efficiency of MG was still as high as 90%. These results suggested that the modified preparation method improved greatly the reusability of MNFs-Lac, which made them more suitable to degrade MG in a water environment.

Toll-like receptor 5 signaling restrains T-cell/natural killer T-cell activation and protects against concanavalin A-induced hepatic injury.

Toll-like receptor-5 (TLR5) signaling regulates the immune privileged status of the liver and is involved in hepatic immune disorders. However, the role of TLR5 has not yet been investigated in experimental models of concanavalin A (Con A)-mediated liver injury. Here, we show that TLR5 is highly up-regulated in the hepatic mononuclear cells of mice during Con A-induced hepatitis. Increased mortality and liver histopathology of TLR5-deficient mice correlated with excessive production of proinflammatory cytokines, suggesting that TLR5 knockout mice were more susceptible to Con A-induced hepatitis. We also report that administration of CBLB502, an exogenous TLR5 agonist, substantially alleviated Con A-mediated hepatitis in wild-type mice as shown by increased survival rates, reduced aminotransferase and proinflammatory cytokine production, impaired lymphocyte infiltration, and ameliorated hepatocyte necrosis and/or apoptosis. Mechanistic studies revealed that CBLB502 acts as a negative regulator in limiting T-cell/natural killer T-cell activity and cytokine production in the Con A-hepatitis model. Bone marrow transplantation experiments showed that TLR5 in bone marrow-derived cells contributed to the hepatoprotective efficacy of CBLB502 against Con A-induced liver injury. Moreover, interleukin-6 elevation induced by CBLB502 is an important protective factor against Con A-induced liver injury. In addition, we demonstrate that CBLB502 suppresses α-galactosylceramide-induced natural killer T cell-dependent inflammatory liver injury. CONCLUSION: The TLR5 signaling pathway plays an important role in T cell-mediated hepatic injury and may be exploited for therapeutic treatment of inflammatory liver diseases. (Hepatology 2017;65:2059-2073).

Influences of high-order dispersion on temporal and spectral properties of microcavity solitons.

We theoretically and numerically investigate the effects of high-order dispersion (HOD) on microcavity solitons, both in time and frequency domain with an extended normalized Lugiato-Lefever equation (LLE). The observed temporal drift of bright and dark solitons is shown to originate from high-odd-order dispersion, while the sign determines the direction of soliton movement and the amplitude decides the drift speed. HOD can also be introduced to stabilize the breathing bright and dark cavity solitons. In spectral domain, the nonlinear symmetry breaking is mainly introduced by third-order dispersion, whereas both third- and fourth-order dispersion can introduce dispersive wave accompanied by soliton tail oscillation. This work could give insight for exploring detailed intracavity pulse dynamics and spectral characteristics of Kerr combs influenced by HOD, as well as provide a viable route to delicate control of Kerr comb generation through tailoring the dispersion parameters.

Low-threshold optical bistability in field-enhanced nonlinear guided-mode resonance grating nanostructure.

We have numerically studied the optical bistability in guided-mode resonance-assisted nonlinear grating nanostructure. A low-index slot is introduced to significantly improve the confinement of light in nonlinear material. In this way, the proposed novel configuration possesses low-threshold optical switching intensity (∼3 MW/cm2), which is about 58 times lower than that of typical nonlinear grating nanostructure without the low-index slot. This bistability study provides an effective method to reduce the threshold of optical switching intensity and thus can be applied in optical logic, optical computation, and all-optical memory.

Inhibition of proteases activity in intestine needs a sustainable acidic environment rather than a transient.

α-Chymotrypsin (α-CT) and trypsin are important components of the enzymatic barrier. They could degrade the therapeutic proteins and peptides, inhibit their activity consequently, and thereby reduce their oral bioavailability. Acidic agents, as one type of indirect protease inhibitors, have shown proof of concept in clinical trials. We report here the inactivated proteases due to acid influence can be reactivated immediately by environmental pH recovery regardless of how long the inactivation last. To keep the inactivation time of proteases for 4-5 h, we designed and prepared a sustained-release tablet containing citric acid (CA) which can effectively reduce the pH below 5.0 and maintain it for 5 h in the dissolution-reaction medium. The activity of α-CT and trypsin was quantified by analyzing the residual amount of their respective substrates BTEE and TAME. More than 80% of the substrates were survived in 5.0 h of incubation, whereas the common tablet inhibited the proteases activity for only two hours in the same experimental medium. It indicates that the sustained-release tablet loaded with CA can efficiently inhibit the α-CT and trypsin activity longer than the common tablet. The results will be beneficial for designing and formulating the peroral administration of peptide and protein drugs.

Synthesis and biological evaluation of novel 3-substituted amino-4-hydroxylcoumarin derivatives as chitin synthase inhibitors and antifungal agents.

A series of novel 3-substituted amino-4-hydroxycoumarin derivatives have been designed and synthesized as chitin synthase (CHS) inhibitors. All the synthesized compounds have been screened for their CHS inhibition activity and antimicrobial activity in vitro. The enzymatic assay indicated that most of the compounds have good inhibitory activity against CHS, in which compound 6o with IC50 of 0.10 mmol/L had stronger activity than that of polyoxins B, which acts as control drug with IC50 of 0.18 mmol/L. As far as the antifungal activity is concerned, most of the compounds possessed moderate to excellent activity against some representative pathogenic fungi. Especially, compound 6b was found to be the most potent agent against Cryptococcus neoformans with minimal inhibitory concentration (MIC) of 4 µg/mL. Moreover, the results of antibacterial screening showed that these compounds have negligible actions to some tested bacteria. Therefore, these compounds would be promising to develop selective antifungal agents.

Hepassocin is required for hepatic outgrowth during zebrafish hepatogenesis.

BACKGROUND & AIMS: Hepassocin (HPS) is a hepatotrophic growth factor that specifically stimulates hepatocyte proliferation and promotes liver regeneration after liver damage. In this paper, zebrafish were used to investigate the role of HPS in liver development. METHODS AND RESULTS: During zebrafish development, HPS expression is enriched in liver throughout hepatogenesis. Knockdown of HPS using its specific morpholino leads to a smaller liver phenotype. Further results showed that the HPS knockdown has no effect on the expression of the early endoderm marker gata6 and early hepatic marker hhex. In addition, results showed that the smaller-liver phenotype in HPS morphants was caused by suppression of cell proliferation, not induction of cell apoptosis. CONCLUSIONS: Current findings indicated that HPS is essential to the later stages of development in vertebrate liver organogenesis.

Design, synthesis and evaluation of novel quinazoline-2,4-dione derivatives as chitin synthase inhibitors and antifungal agents.

A series of novel 1-methyl-3-substituted quinazoline-2,4-dione derivatives were designed, synthesized, and characterized by (1)H NMR, (13)C NMR and MS spectral data. Their inhibition against chitin synthase (CHS) and antifungal activities were evaluated in vitro. Results showed compounds 5b, 5c, 5e, 5f, 5j, 5k, 5l, and 5o had strong inhibitory potency against CHS. Compound 5c, which has the highest potency among these compounds, had a half-inhibition concentration (IC50) of 0.08mmol/L, while polyoxin B as positive drug had IC50 of 0.18mmol/L. These IC50 values of compounds 5i, 5m, 5n, and 5s were greater than 0.75mmol/L, which revealed that those compounds had weak inhibition activity against CHS. Moreover, most of these compounds exhibited moderate to excellent antifungal activities. In detail, to Candida albicans, the activities of compound 5g and 5k were 8-fold stronger than that of fluconazole and 4-fold stronger than that of polyoxin B; to Aspergillus flavus, the activities of 5g, 5l and 5o were16-fold stronger than that of fluconazole and 8-fold stronger than that of polyoxin B; to Cryptococcus neoformans, the minimum-inhibition-concentration (MIC) values of compounds 5c, 5d, 5e and 5l were comparable to those of fluconazole and polyoxin B. The antifungal activities of these compounds were positively correlated to their IC50 values against CHS. Furthermore, these compounds had negligible actions to bacteria. Therefore, these compounds were promising selective antifungal agents.

Deep Probabilistic Principal Component Analysis for Process Monitoring.

Probabilistic latent variable models (PLVMs), such as probabilistic principal component analysis (PPCA), are widely employed in process monitoring and fault detection of industrial processes. This article proposes a novel deep PPCA (DePPCA) model, which has the advantages of both probabilistic modeling and deep learning. The construction of DePPCA includes a greedy layer-wise pretraining phase and a unified end-to-end fine-tuning phase. The former establishes a hierarchical deep structure based on cascading multiple layers of the PPCA module to extract high-level features. The latter builds an end-to-end connection between the raw inputs and the final outputs to further improve the representation of the model to high-level features. After constructing the model structure of DePPCA, we first present the detailed training processes of the pretraining and fine-tuning stages, then clarify the theoretical merits of the proposed model from the perspective of variational inference. For process monitoring purposes, we develop two statistics based on the established DePPCA. The monitoring performance of these two statistics can remain superior even if the features extracted by DePPCA are significantly compressed to univariate. This makes the feature extraction process and online monitoring procedure of DePPCA quite fast. In other words, the proposed DePPCA can achieve accurate and efficient process monitoring by only extracting one feature for each sample. Finally, the effectiveness of DePPCA is evaluated on the Tennessee Eastman (TE) process and the multiphase flow (MPF) facility.

Integration of protein L-immobilized epoxy magnetic bead capture with LC-MS/MS for therapeutic monoclonal antibody quantification in serum.

In recent years, there has been a growing interest in the thriving monoclonal antibody (mAb) industry due to the wide utilization of mAbs in clinical therapies. Robust and accurate bioanalytical methods are required to enable fast quantification of mAbs in biological matrices, especially in the context of pharmacokinetics (PKs)/pharmacodynamics (PDs) and therapeutic drug monitoring (TDM) studies. In this investigation, we presented a novel immuno-magnetic capture coupled with a liquid chromatography-tandem mass spectrometry (LC-MS/MS) method designed for the quantification of immunoglobulin G-kappa-based mAbs in biological fluids. The immunoaffinity absorbent for mAb drug purification was meticulously crafted by immobilizing protein L onto monosize, magnetic poly(glycidyl methacrylate) (m-pGMA) beads, synthesized through dispersion polymerization. The microspheres were acquired with an average size of 1.6 µm, and the optimal binding of mAbs from the aqueous mAb solution was determined to be 45.82 mg g-1. The quantification of mAbs in 10 µL serum samples was achieved through affinity purification using m-pGMA@protein L beads (employing rituximab as an internal standard (IS)), on-bead reduction, and rapid tryptic digestion. Remarkably, the entire process, taking less than 2.5 hours, held significant potential for simplifying pretreatment procedures and minimizing analytical time. Furthermore, the developed method underwent validation in accordance with the European Medicines Agency (EMA) guidelines. The assay demonstrated commendable linearity within the 2-400 µg mL-1 range for both daratumumab and pembrolizumab. Intra- and inter-assay coefficients of variation fell within the range of 0.7% to 13.4%, meeting established acceptance criteria. Other validation parameters also conformed to regulatory standards. Ultimately, the efficacy of the method was substantiated in a pharmacokinetic study following a single-dose intravenous administration to mice, underscoring its applicability and reliability in real-world scenarios.

Deep PLS: A Lightweight Deep Learning Model for Interpretable and Efficient Data Analytics.

The salient progress of deep learning is accompanied by nonnegligible deficiencies, such as: 1) interpretability problem; 2) requirement for large data amounts; 3) hard to design and tune parameters; and 4) heavy computation complexity. Despite the remarkable achievements of neural networks-based deep models in many fields, the practical applications of deep learning are still limited by these shortcomings. This article proposes a new concept called the lightweight deep model (LDM). LDM absorbs the useful ideas of deep learning and overcomes their shortcomings to a certain extent. We explore the idea of LDM from the perspective of partial least squares (PLS) by constructing a deep PLS (DPLS) model. The feasibility and merits of DPLS are proved theoretically, after that, DPLS is further generalized to a more common form (GDPLS) by adding a nonlinear mapping layer between two cascaded PLS layers in the model structure. The superiority of DPLS and GDPLS is demonstrated through four practical cases involving two regression problems and two classification tasks, in which our model not only achieves competitive performance compared with existing neural networks-based deep models but also is proven to be a more interpretable and efficient method, and we know exactly how it improves performance, how it gives correct results. Note that our proposed model can only be regarded as an alternative to fully connected neural networks at present and cannot completely replace the mature deep vision or language models.

Predictive Modeling With Multiresolution Pyramid VAE and Industrial Soft Sensor Applications.

In industrial processes, the sampling rates of process variables are discrepant because of the nature of instruments and measuring demands, which forms the challenging issue, that is, the multirate modeling in the data-driven soft sensor development. In this work, a multiresolution pyramid variational autoencoder (MR-PVAE) predictive model is proposed to solve this problem based on the deep feature extraction and feature pyramid augmentation. First, a multirate data filter is designed through a resolution searching strategy to turn the original process data into a multiresolution dataset. Then, the pyramid variational autoencoder (PVAE) is proposed to extract deep nonlinear features from the data with different resolutions. In PVAE, the augmented feature pyramid is constructed layer by layer to fuse extracted features from low resolution to the high. As a consequence, the extracted features with various resolutions are gathered to form the regression model, where the process information contained in data with discrepant sampling rates can be fully utilized. Due to the layer-by-layer enhanced features, the prediction accuracy of the soft sensing model are gradually improved. Meanwhile, an optimized training strategy is established to select the optimal feature pyramid for prediction. A numerical experiment and an industrial soft sensing case are given to validate the effectiveness and superiority of the proposed MR-PVAE model.

Security Versus Accuracy: Trade-Off Data Modeling to Safe Fault Classification Systems.

While the data-driven fault classification systems have achieved great success and been widely deployed, machine-learning-based models have recently been shown to be unsafe and vulnerable to tiny perturbations, i.e., adversarial attack. For the safety-critical industrial scenarios, the adversarial security (i.e., adversarial robustness) of the fault system should be taken into serious consideration. However, security and accuracy are intrinsically conflicting, which is a trade-off issue. In this article, we first study this new trade-off issue in the design of fault classification models and solve it from a brand new view, hyperparameter optimization (HPO). Meanwhile, to reduce the computational expense of HPO, we propose a new multiobjective (MO), multifidelity (MF) Bayesian optimization (BO) algorithm, MMTPE. The proposed algorithm is evaluated on safety-critical industrial datasets with the mainstream machine learning (ML) models. The results show that the following hold: 1) MMTPE is superior to other advanced optimization algorithms in both efficiency and performance and 2) fault classification models with optimized hyperparameters are competitive with advanced adversarially defensive methods. Moreover, insights into the model security are given, including the model intrinsic security properties and the correlations between hyperparameters and security.

BRISC is required for optimal activation of NF-κB in Kupffer cells induced by LPS and contributes to acute liver injury.

BRISC (BRCC3 isopeptidase complex) is a deubiquitinating enzyme that has been linked with inflammatory processes, but its role in liver diseases and the underlying mechanism are unknown. Here, we investigated the pathophysiological role of BRISC in acute liver failure using a mice model induced by D-galactosamine (D-GalN) plus lipopolysaccharide (LPS). We found that the expression of BRISC components was dramatically increased in kupffer cells (KCs) upon LPS treatment in vitro or by the injection of LPS in D-GalN-sensitized mice. D-GalN plus LPS-induced liver damage and mortality in global BRISC-null mice were markedly attenuated, which was accompanied by impaired hepatocyte death and hepatic inflammation response. Constantly, treatment with thiolutin, a potent BRISC inhibitor, remarkably alleviated D-GalN/LPS-induced liver injury in mice. By using bone marrow-reconstituted chimeric mice and cell-specific BRISC-deficient mice, we demonstrated that KCs are the key effector cells responsible for protection against D-GalN/LPS-induced liver injury in BRISC-deficient mice. Mechanistically, we found that hepatic and circulating levels of TNF-α, IL-6, MCP-1, and IL-1ß, as well as TNF-α- and MCP-1-producing KCs, in BRISC-deleted mice were dramatically decreased as early as 1 h after D-GalN/LPS challenge, which occurred prior to the elevation of the liver injury markers. Moreover, LPS-induced proinflammatory cytokines production in KCs was significantly diminished by BRISC deficiency in vitro, which was accompanied by potently attenuated NF-κB activation. Restoration of NF-κB activation by two small molecular activators of NF-κB p65 effectively reversed the suppression of cytokines production in ABRO1-deficient KCs by LPS. In conclusion, BRISC is required for optimal activation of NF-κB-mediated proinflammatory cytokines production in LPS-treated KCs and contributes to acute liver injury. This study opens the possibility to develop new strategies for the inhibition of KCs-driven inflammation in liver diseases.

Influence of electrolyte and poloxamer 188 on the aggregation kinetics of solid lipid nanoparticles (SLNs).

Solid lipid nanoparticles (SLNs) have attracted increasing attention as colloidal drug carriers due to theirs advantages including low toxicity, drug targeting and modified release. However, undesired particle aggregation in aqueous dispersions would limit the applicability of SLNs for drug delivery. The purpose of the present article is to investigate the aggregation behavior of the SLNs and quantitatively evaluate how the concentration of NaCl and F68 affect the stability of the SLNs. The early stage aggregation kinetics of the SLNs was investigated over a wide range of NaCl concentrations by employing dynamic light scattering (DLS). In the presence of the NaCl, aggregation kinetics of the SLNs exhibited reaction-limited (slow) and diffusion-limited (fast) regimes. These results indicated that the aggregation behavior of these new nanoparticles can be well explained by the classical Derjaguin-Landau-Verwey-Overbeek (DLVO) theory. The critical coagulation concentration (CCC) of SLNs containing 0.0%, 0.1%, 0.5%, 2.0%, and 4.0% of Poloxamer 188 (F68) was 416, 328, 519, 607, and 602 mM, respectively, suggesting that the F68 influences the aggregation behavior of the SLNs. F68 made the SLNs more sensitive to the electrolyte when its concentration is low (0.1%), the bush of the polymer F68 has a bridging effect that accelerated the aggregation process of the SLNs. However, at the high concentration, F68 can provide the steric repulsion to the nanoparticles, which effectively stabilized the SLNs dispersions.

Nanostructured lipid carriers improve skin permeation and chemical stability of idebenone.

Idebenone (IDB) is a synthetic antioxidant and analog of coenzyme Q10. The percutaneous permeation of IDB was investigated in guinea pig skin after application of different formulations. The enhancing effects of various formulations [nanostructured lipid carriers (NLCs), nanoemulsion (NE), or oil solution] on the permeation of IDB were evaluated using ex vivo guinea pig skins. Furthermore, stability of different formulations and in which chemical stability of IDB was determined during storage. Permeation experiments revealed that formulations varied in their ability to enhance the skin permeation of IDB. For NLC formulation, the cumulative amount of IDB in the epidermis, dermis, and acceptor medium of diffusion cells was approximately threefold more than NE or oil solution at the end of 24-h experiment. No significant difference between NE and oil solution was observed in the enhancement of penetration efficacy of IDB. Different formulations resulted in stability with different properties. NLC formulation revealed preferentially more stable than NE. The residual percentage of IDB loaded in NLCs, NE, and oil solution was 90.1%, 65.4%, and 51.3%, respectively, when stored at 40°C under 75% RH and 3,000 lx light conditions for 180 days. The results obtained here demonstrated that the abilities of NLCs to improve the chemical stability of IDB and enhance the skin permeation are much better than NE and oil solution. These suggest that NLCs containing IDB have significant potential use for skin care as an alternative topical formulation.

Gated Stacked Target-Related Autoencoder: A Novel Deep Feature Extraction and Layerwise Ensemble Method for Industrial Soft Sensor Application.

These days, data-driven soft sensors have been widely applied to estimate the difficult-to-measure quality variables in the industrial process. How to extract effective feature representations from complex process data is still the difficult and hot spot in the soft sensing application field. Deep learning (DL), which has made great progresses in many fields recently, has been used for process monitoring and quality prediction purposes for its outstanding nonlinear modeling and feature extraction abilities. In this work, deep stacked autoencoder (SAE) is introduced to construct a soft sensor model. Nevertheless, conventional SAE-based methods do not take information related to target values in the pretraining stage and just use the feature representations in the last hidden layer for final prediction. To this end, a novel gated stacked target-related autoencoder (GSTAE) is proposed for improving modeling performance in view of the above two issues. By adding prediction errors of target values into the loss function when executing a layerwise pretraining procedure, the target-related information is used to guide the feature learning process. Besides, gated neurons are utilized to control the information flow from different layers to the final output neuron that take full advantage of different levels of abstraction representations and quantify their contributions. Finally, the effectiveness and feasibility of the proposed approach are verified in two real industrial cases.