Browsing by Author "Deepak Chhabra"

Now showing 1 - 12 of 12

A multi-objective hybrid machine learning approach-based optimization for enhanced biomass and bioactive phycobiliproteins production in Nostoc sp. CCC-403
(Elsevier Ltd, 2021) Dinesh Kumar Saini; Amit Rai; Alka Devi; Sunil Pabbi; Deepak Chhabra; Jo-Shu Chang; Pratyoosh Shukla
The cyanobacterial phycobiliproteins (PBPs) are an important natural colorant for nutraceutical industries. Here, a multi-objective hybrid machine learning-based optimization approach was used for enhanced cell biomass and PBPs production simultaneously in Nostoc sp. CCC-403. A central composite design (CCD) was employed to design an experimental setup for four input parameters, including three BG-11 medium components and pH. We achieved a 61.76% increase in total PBPs production and an almost 90% increase in cell biomass by our prediction model. We also established a test genome-scale metabolic network (GSMN) for Nostoc sp. and identified potential metabolic fluxes contributing to PBPs enhanced production. This study highlights the advantage of the hybrid machine learning approach and GSMN to achieve optimization for more than one objective and serves as the foundation for future efforts to convert cyanobacteria as an economically viable source for biofuels and natural products. © 2021 Elsevier Ltd
Application of ANN-MOGA for nutrient sequestration for wastewater remediation and production of polyunsaturated fatty acid (PUFA) by Chlorella sorokiniana MSP1
(Elsevier Ltd, 2024) Mohneesh Kalwani; Arti Kumari; Shalini G. Rudra; Deepak Chhabra; Sunil Pabbi; Pratyoosh Shukla
Chlorella bears excellent potential in removing nutrients from industrial wastewater and lipid production enriched with polyunsaturated fatty acids. However, due to the changing nutrient dynamics of wastewater, growth and metabolic activity of Chlorella are affected. In order to sustain microalgal growth in wastewater with concomitant production of PUFA rich lipids, RSM (Response Surface Methodology) followed by heuristic hybrid computation model ANN-MOGA (Artificial Neural Network- Multi-Objective Genetic Algorithm) were implemented. Preliminary experiments conducted taking one factor at a time and design matrix of RSM with process variables viz. Sodium chloride (1 mM–40 mM), Magnesium sulphate (100 mg–800 mg) and incubation time (4th day to 20th day) were validated by ANN-MOGA. The study reported improved biomass and lipid yield by 54.25% and 12.76%, along with total nitrogen and phosphorus removal by 21.92% and 18.72% respectively using ANN-MOGA. It was evident from FAME results that there was a significantly improved concentration of linoleic acid (19.1%) and γ-linolenic acid (21.1%). Improved PUFA content makes it a potential feedstock with application in cosmeceutical, pharmaceutical and nutraceutical industry. The study further proves that C. sorokiniana MSP1 mediated industrial wastewater treatment with PUFA production is an effective way in providing environmental benefits along with value addition. Moreover, ANN-MOGA is a relevant tool that could control microalgal growth in wastewater. © 2023 Elsevier Ltd
Artificial Neural Network - Multi-Objective Genetic Algorithm based optimization for the enhanced pigment accumulation in Synechocystis sp. PCC 6803
(BioMed Central Ltd, 2025) Namrata Bhagat; Guddu Kumar Gupta; Amritpreet K. Minhas; Deepak Chhabra; Pratyoosh Shukla
Background: Natural colorants produced by the cyanobacterium include carotenoids, chlorophyll a and phycocyanin. The current study used the Synechocystis sp. PCC 6803 to examine how abiotic stress conditions, such as low temperature as well as high light intensity, affect the pigment accumulations in comparison to the control conditions. Additionally, using the response surface methodology (RSM) and artificial neural network - multi-objective genetic algorithm (ANN-MOGA), the impact of several nitrogen sources such as urea, ammonium chloride, and sodium nitrate as nutritional stress on the pigment accumulations in the Synechocystis sp. PCC 6803 was examined. Results: The results showed that the pigment accumulation was more pronounced when urea and ammonium chloride was used in combination with nitrate, respectively, as nitrogen source. With the help of our prediction model that used ANN-MOGA, we were able to enhance the synthesis of chlorophyll a, carotenoids, and phycocyanin by 21.93 µg/mL, 9.78 µg/mL, and 0.05 µg/mL, respectively compared to control with 6.37, 3.88 and 0.008 µg/mL. The significant scavenging activity of pigment was showed with 7.66 ± 0.001 values of IC50. Additionally, a very good correlation of coefficient (R2) value 0.99, 0.99 and 0.92 was obtained for APX, CAT and GPX enzyme activity, respectively. Conclusions: The findings lays the groundwork for future attempts to turn cyanobacteria into a commercially viable source of natural pigments by demonstrating the benefits of using the RSM and machine learning techniques like ANN-MOGA to optimise the production of cyanobacterial pigments. The significant scavenging and antioxidant activities like CAT, GPX and APX were also shown by the pigments of the Synechocystis sp. PCC 6803. Furthermore, these machine learning tools can be used as a model to improve and optimize the yields for other metabolites production. © The Author(s) 2025.
Correction: Artificial Neural Network - Multi-Objective Genetic Algorithm based optimization for the enhanced pigment accumulation in Synechocystis sp. PCC 6803 (BMC Biotechnology, (2025), 25, 1, (23), 10.1186/s12896-025-00955-9)
(BioMed Central Ltd, 2025) Namrata Bhagat; Guddu Kumar Gupta; Amritpreet K. Minhas; Deepak Chhabra; Pratyoosh Shukla
Following publication of the original article [1], the authors updated Fig. 8 and changed the caption as follows: From: (a) APX, (b) CAT and (c) GPX radical scavenging activities of various concentrations of carotenoid extracts by Synechocystis sp. PCC 6803 where the R2 ≥ 0. 998, 0.995 and 0.923. Mean ± SD, n = 3 To: Linear regression plot of absorbance of (a) APX, (b) CAT and (c) GPX activity of carotenoid extract by Synechocystis sp. PCC 6803 where the R2 ≥ 0. 998, 0.995 and 0.923. Mean ± SD, n = 3 The original article has been corrected. © The Author(s) 2025.
Enhanced indole-3-acetic acid production by Enterobacter hormaechei APSB3 through heuristic artificial neural network and particle swarm optimisation
(Springer, 2025) Aditya Sharma; Guddu Kumar Gupta; Deepak Chhabra; Piyush Pandey; Pratyoosh Shukla
Indole-3-acetic acid (IAA) is essential in abiotic stress tolerance via signalling molecules between plants and microorganisms, contributing to sustainable agricultural practices. The present study investigates a combinatorial artificial neural network (ANN) modelling and particle swarm optimisation (PSO) algorithm to optimise the process parameters for enhanced IAA production by Enterobacter hormaechei APSB3. Hence, to improve IAA production, single-factor experiments and a design matrix generated by central composite design were employed to explore the significant input variables, including temperature, pH, carbon source, and nitrogen source, which were subsequently validated through the application of ANN-PSO. Thus, under the optimised ANN-PSO conditions, i.e. carbon source (2.11%), nitrogen source (2.37%), pH (9), and temperature (45 ℃), IAA production was improved to 94.76 ± 0.03 µg/mL (2.90-fold) as compared to un-optimised condition (33.04 ± 0.58 µg/mL). The IAA production was further confirmed by TLC and HPLC analyses, exhibiting an Rf value of 0.77 and a retention time of 3.301 min. Thus, the present work could conclude that the hybrid heuristic ANN-PSO, an empirical and decision-making tool, significantly improves efficiency and scalability for IAA production by E. hormaechei APSB3. © The Author(s) under exclusive licence to Society for Environmental Sustainability 2025.
Improved deinking and biobleaching efficiency of enzyme consortium from Thermomyces lanuginosus VAPS25 using genetic Algorithm-Artificial neural network based tools
(Elsevier Ltd, 2022) Mandeep Dixit; Guddu Kumar Gupta; Monika Yadav; Deepak Chhabra; Rajeev Kumar Kapoor; Puneet Pathak; Nishi K. Bhardwaj; Pratyoosh Shukla
The present study reports the combined enzymatic production efficiency of thermophilic fungus Thermomyces lanuginosus VAPS25 using a combinatory artificial intelligence-based tool, resulting in 2.7 IU/ml, 5.2 IU/ml, and 18.85 U/ml activity of endoglucanase, amylase, and lipase, respectively with good thermostability at 90 °C (pH 8–10). Interestingly, the metal ions viz. Cu2+ and Mg2+ increased the endoglucanase activity to 5 folds, i.e.,5.6 IU/ml compared to control. Further, the amylase and lipase activity was also enhanced by Fe2+ and Co2+ to 5.4 IU/ml and 19.57 U/ml, respectively. Additionally, the deinking efficiency was improved by 68.9%, 42.7%, and 52.8% by endoglucanase, amylase, and lipase, respectively, while the consortium increased the deinking efficiency to 72.7%. The bio-bleached paper strength parameters such as burst index, breaking length, tear index, and tensile index of sheets were significantly improved by 1.38%, 13.54%, 7.54%, and 20.88%, respectively. These enzymes at an industrial scale would help develop an economical paper recycling process. © 2022 Elsevier Ltd
Improved GA-ANN based optimized bio-deinking strategy for laccase produced from Trametes versicolor GGRK18, and its gene co-expression network analysis
(Elsevier Ltd, 2025) Guddu Kumar Gupta; Tallon Coxe; Eetika Chot; Rajeev Kumar Kapoor; Deepak Chhabra; Nishi K. Bhardwaj; Rajeev Kumar Azad; Pratyoosh Shukla
Recycling of waste paper through chemical deinking process led the generation of toxic agents and caused severe issues. Therefore, an alternative deinking process of recycled waste paper is necessity to sustain the eco-friendly environment. This study reports the production of laccase from Trametes versicolor GGRK18 using a genetic algorithm-artificial neural network (GA-ANN) tool, resulting in increased 21.5-fold i.e., 42.06 ± 1.1–906.17 ± 46.76 U/mL laccase activity. The biochemical studies revealed that laccase showed optimum activity at 60 ℃ and pH 4.0, retaining more than 90 % residual activity . Interestingly, the metal ion K+ influenced the laccase activity by 4830.91 ± 129.3 U/mL, and obtained laccase showed an apparent K m value of 0.5 µM and V max of 1666.67 µmol/mL/min. Furthermore, the deinking efficiency was improved by 48 % and 29.3 % for photocopier and newspaper, while the brightness increased by 34.6 % and 10.4 %, respectively, compared to the control values. The tearing index was significantly improved with 18.2 % and burst factor efficiently decreased by 21.1 % of deinked pulp. Furthermore, our study employs Weighted Correlation Network Analysis (WGCNA)-an R package designed to elucidate gene interactions– using next-generation sequencing data. The resulting network revealed over 70000 interactions among approximately 8917 unique genes, which clustered into 11 distinct modules of co-expressed genes; importantly, laccase genes exhibited co-expression patterns associated with various metabolic processes and oxidative stress pathways. In addition, this study also gives a combinatory strategy for waste paper recycling using laccase-mediated paper deinking and its mechanistic understanding of co-expressed genes in T. versicolor. © 2025 Elsevier Ltd.
Low-cost media engineering for phosphate and IAA production by Kosakonia pseudosacchari TCPS-4 using Multi-objective Genetic Algorithm (MOGA) statistical tool
(Springer Science and Business Media Deutschland GmbH, 2021) Twinkle Chaudhary; Dinesh Yadav; Deepak Chhabra; Rajesh Gera; Pratyoosh Shukla
The plant growth-promoting rhizobacteria (PGPR) can improve the biotic or abiotic stress condition by exploiting the productivity and plant growth of the plants under stressful conditions. This study examines the role of a rhizospheric bacterial isolate Kosakonia pseudosacchari TCPS-4 isolated from cluster bean plant (Cyamopsis tetragonoloba) under dryland condition. The low-cost media engineering was evaluated, and the phosphate-solubilizing and IAA-producing abilities of Kosakonia pseudosacchari TCPS-4 were improved using a hybrid statistical tool viz. Multi-objective Genetic Algorithm (MOGA). Further, the effect of carbon and nitrogen media constituents and their interactions on IAA production and phosphate solubilization were also confirmed by a single-factor experiment assay. This revealed that MOGA-based model depicted 47.5 mg/L inorganic phosphate as the highest phosphate concentration in media containing 45 g/L carbon source, 12 g/L nitrogen source and 0.20 g/L MgSO4. The highest IAA production was 18.74 mg/L in media containing 45 g/L carbon source, 12 g/L nitrogen source and 0.2 g/L MgSO4. These values were also confirmed and measured by the experiments with phosphate solubilization of 45.71 mg/L and IAA production of 18.71 mg/L with 1012 cfu/mL. This concludes that effective media engineering using these statistical tools can enhance the phosphate and IAA production by each model. A good correlation between measured and predicted values of each model confirms the validity of both responses. The present study gives an insight on media engineering for phosphate and IAA production by Kosakonia pseudosacchari TCPS-4. © 2021, King Abdulaziz City for Science and Technology.
Microbial Bioprocess Efficiency Improvement Through Artificial Intelligence and Machine Learning (AI-ML) Tools
(CRC Press, 2025) Mandeep Dixit; Guddu Kumar Gupta; Dharini Pandey; Reeta Kumari; Deepak Chhabra; Naveen Kango; Pratyoosh Shukla
Developing eco-friendly microbial bioprocesses for the sustainable development of industries is a prime need. However, optimizing such bioprocesses is an expensive and time-consuming task. Various factors affecting the output need to be controlled during any bioprocess. Artificial intelligence (AI) and machine learning (ML) tools are efficient alternatives to conventional approaches for optimizing process variables and finding the interaction between different factors. AI-ML tools are used for microbial strain selection and bioprocess optimization, scale-up, monitoring, and control, saving time and increasing the efficiency of the bioprocess. Tools like Artificial Neural Networks (ANN), Adaptive-Network-based Fuzzy Inference System (ANFIS), and Artificial Bee Colony (ABC) have provided superior results for the optimization of microbe-assisted production of various bio-metabolites and enzymes. This review highlights the use of various AI-ML tools for effective microbial bioprocess design and optimization. This will further help select suitable AI-ML tools for different bioprocesses and their overall impact on enhancing microbial efficiency. © 2026 Sunil Kumar Khare, Ram Karan, Rajeshwari Sinha and R. Hemamalini.
Multi-Objective Optimization Through Machine Learning Modeling for Production of Xylooligosaccharides from Alkali-Pretreated Corn-Cob Xylan Via Enzymatic Hydrolysis
(Springer, 2021) Ishu Khangwal; Deepak Chhabra; Pratyoosh Shukla
The hemicellulose content present in corn cobs can help in producing a high amount of xylooligosaccharides (XOS) in an eco-friendly manner. In this work, the XOS was produced from alkali pre-treated corn-cobs having a true yield of 38 ± 1.4% via enzymatic hydrolysis with the help of xylanase from T. lanuginosus VAPS-24. The production process was optimized to achieve a high concentration of XOS using innovative multi-objective optimization through machine learning modeling and finding out the most suitable parameters where xylobiose production is higher than xylose. The Multi-objective connected neural networks (MOCNN) model with tangent sigmoid activation function yielded a correlation coefficient of 96.51%; there were six optimal sets where xylobiose concentration was higher than xylose. The best-optimized conditions yielded 3.03 mg/ml of xylobiose and 1.31 mg/ml of xylose. Therefore, this novel approach of machine learning can target the increasing demand for xylooligosaccharides in the growing industrial market of prebiotics. © 2021, Association of Microbiologists of India.
Optimization of endoglucanase-lipase-amylase enzyme consortium from Thermomyces lanuginosus VAPS25 using Multi-Objective genetic algorithm and their bio-deinking applications
(Elsevier Ltd, 2023) Mandeep Dixit; Deepak Chhabra; Pratyoosh Shukla
In this study, the enzyme consortium of endoglucanase, lipase, and amylase was obtained and optimized using artificial intelligence-based tools. After optimization using a multi-objective genetic algorithm and artificial neural network, the enzyme activity was 8.8 IU/g, 153.68 U/g, and 19.2 IU/g for endoglucanase, lipase, and amylase, respectively, using Thermomyces lanuginosus VAPS25. The highest enzyme activity was obtained at parameters 77.69% moisture content, 52.7 °C temperature, 98 h, and 3.1 eucalyptus leaves: wheat bran ratio. The endoglucanase-lipase-amylase (END-LIP-AMY) enzyme consortium showed reliable characteristics in terms of catalytic activity at 50–80 °C and pH 6.0–9.0. The increase in deinking efficiency of 27.8% and 11.1% were obtained compared to control for mixed office waste and old newspaper, respectively, using the enzyme consortium. The surface chemical composition and fiber morphology of deinked pulp was investigated using Attenuated total reflectance-Fourier transform infrared spectroscopy (ATR-FTIR) and Scanning electron microscopy (SEM). © 2022 Elsevier Ltd
Synergistic effect of cellulo-xylanolytic and laccase enzyme consortia for improved deinking of waste papers
(Elsevier Ltd, 2024) Guddu Kumar Gupta; Rajeev Kumar Kapoor; Deepak Chhabra; Nishi Kant Bhardwaj; Pratyoosh Shukla
This study reports the cellulo-xylanolytic cocktail production from Hypocrea lixii GGRK4 using multi-objective genetic algorithm-artificial neural network tool, resulting in 8.32 ± 1.07 IU/mL, 51.53 ± 3.78 IU/mL activity of CMCase and xylanase, respectively with more than 85 % residual activity at 60 °C and pH 6.0. Interestingly, metal ions viz. K+ and Ca2+ stimulated the enzyme activity, whereas Fe2+ and Cu2+ reduced the activity. Significant amounts of hydrophobic compounds, chromophores, and phenolics were released after wastepapers deinking. The deinking efficiency of 73.60 ± 2.45 % and 38.60 ± 1.34 % was obtained for photocopier paper and newspaper, respectively, whereas brightness of 89.90 ± 2.10 % ISO and 44.90 ± 1.63 % ISO was reported for both types of waste papers. The physical strength of deinked photocopier paper and newspapers, i.e., tensile index (3.10 and 0.50 %), tearing index (7.10 and 4.83 %), and burst factor (8.61) were enhanced whereas double fold property was decreased proving wastepaper reusability. This consortium showed effective and significant enzymatic deinking efficiency for recycled wastepapers. © 2024 Elsevier Ltd