Multiobjective Patient Stratification Using Evolutionary Multiobjective Optimization

Modeling and optimizing in vitro percentage and speed callus induction of carrot via Multilayer Perceptron-Single point discrete GA and radial basis function

Background

Callus induction is the first step in optimizing plant regeneration. Fit embryogenesis and shooting rely on callus induction. In addition, using artificial intelligence models in combination with an algorithm can be helpful in the optimization of in vitro culture. The present study aimed to evaluate the percentage and speed of callus induction optimization in carrot with a Multilayer Perceptron-Single point discrete genetic algorithm (GA).

Materials and methods

In this study, the outputs included callus induction percentage and speed, while inputs were different types and concentrations of plant growth regulator (0. 5, 0.2 mg/l 2,4-D, 0.3, 0.2, 0.5 mg/l BAP, 1, 0.2 mg/l Kin, and 2 mg/l NAA), different explants (shoot, root, leaf, and nodal), a different concentration compound of MS medium (1 × MS, 4× MS, and 8× MS) and time of sampling. The data were obtained in the laboratory, and multilayer perceptron (MLP) and radial basis function (RBF), two well-known ANNs, were employed to model. Then, GA was used for optimization, and sensitivity analysis was performed to indicate the inputs’ importance.

Results

The results showed that MLP had better prediction efficiency than RBF. Based on the results, R2 in training and testing data was 95 and 95% for the percentage of callus induction, while it was 94 and 95% for the speed of callus induction, respectively. In addition, a concentration compound of MS had high sensitivity, while times of sampling had low sensitivity. Based on the MLP-Single point discrete GA, the best results were obtained for shoot explants, 1× MS media, and 0.5 mg/l 2, 4-D + 0.5 mg/l BAP. Further, a non-significant difference was observed between the test result and predicted MLP.

Conclusions

Generally, MLP-Single point discrete GA is considered a potent tool for predicting treatment and fit model results used in plant tissue culture and selecting the best medium for callus induction.

Evolutionary Multiobjective Clustering Algorithms With Ensemble for Patient Stratification

Patient stratification has been studied widely to tackle subtype diagnosis problems for effective treatment. Due to the dimensionality curse and poor interpretability of data, there is always a long-lasting challenge in constructing a stratification model with high diagnostic ability and good generalization. To address these problems, this article proposes two novel evolutionary multiobjective clustering algorithms with ensemble (NSGA-II-ECFE and MOEA/D-ECFE) with four cluster validity indices used as the objective functions. First, an effective ensemble construction method is developed to enrich the ensemble diversity. After that, an ensemble clustering fitness evaluation (ECFE) method is proposed to evaluate the ensembles by measuring the consensus clustering under those four objective functions. To generate the consensus clustering, ECFE exploits the hybrid co-association matrix from the ensembles and then dynamically selects the suitable clustering algorithm on that matrix. Multiple experiments have been conducted to demonstrate the effectiveness of the proposed algorithm in comparison with seven clustering algorithms, twelve ensemble clustering approaches, and two multiobjective clustering algorithms on 55 synthetic datasets and 35 real patient stratification datasets. The experimental results demonstrate the competitive edges of the proposed algorithms over those compared methods. Furthermore, the proposed algorithm is applied to extend its advantages by identifying cancer subtypes from five cancer-related single-cell RNA-seq datasets.

Metabolic and transcriptional analysis of recombinant Saccharomyces?cerevisiae for xylose fermentation: a feasible and efficient approach

Lignocellulose is an abundant xylose-containing biomass found in agricultural wastes, and has arisen as a suitable alternative to fossil fuels for the production of bioethanol. Although Saccharomyces cerevisiae has been thoroughly used for the production of bioethanol, its potential to utilize lignocellulose remains poorly understood. In this work, xylose-metabolic genes of Pichia stipitis and Candida tropicalis, under the control of different promoters, were introduced into S. cerevisiae. RNA-seq analysis was use to examine the response of S. cerevisiae metabolism to the introduction of xylose-metabolic genes. The use of the PGK1 promoter to drive xylitol dehydrogenase (XDH) expression, instead of the TEF1 promoter, improved xylose utilization in ?XR-pXDH? strain by overexpressing xylose reductase (XR) and XDH from C. tropicalis, enhancing the production of xylitol (13.66 ? 0.54 g/L after 6 days fermentation). Overexpression of xylulokinase and XR/XDH from P. stipitis remarkably decreased xylitol accumulation (1.13 ? 0.06 g/L and 0.89 ? 0.04 g/L xylitol, respectively) and increased ethanol production (196.14% and 148.50% increases during the xylose utilization stage, respectively), in comparison with the results of XR-pXDH. This result may be produced due to the enhanced xylose transport, Embden?Meyerhof and pentose phosphate pathways, as well as alleviated oxidative stress. The low xylose consumption rate in these recombinant strains comparing with P. stipitis and C. tropicalis may be explained by the insufficient supplementation of NADPH and NAD+. The results obtained in this work provide new insights on the potential utilization of xylose using bioengineered S. cerevisiae strains.

Modeling and Optimizing in vitro Sterilization of Chrysanthemum via Multilayer Perceptron-Non-dominated Sorting Genetic Algorithm-II (MLP-NSGAII)

In vitro sterilization is a primary step of plant tissue culture which the ultimate results of in vitro culture are directly depended on the efficiency of the sterilization. Artificial intelligence models in a combination of optimization algorithms could be beneficial computational approaches for modeling and optimizing in vitro culture. The aim of this study was modeling and optimizing in vitro sterilization of chrysanthemum, as a case study, through Multilayer Perceptron- Non-dominated Sorting Genetic Algorithm-II (MLP-NSGAII). MLP was used for modeling two outputs including contamination frequency (CF), and explant viability (EV) based on seven variables including HgCl₂, Ca(ClO)₂, Nano-silver, H₂O₂, NaOCl, AgNO₃, and immersion times. Subsequently, models were linked to NSGAII for optimizing the process, and the importance of each input was evaluated by sensitivity analysis. Results showed all of the R² of training and testing data were over 94%. According to MLP-NSGAII, optimal CF (0%), and EV (99.98%) can be obtained from 1.62% NaOCl at 13.96 min immersion time. The results of sensitivity analysis showed that CF and EV were more sensitive to immersion time and less sensitive to AgNO₃. Subsequently, the performance of predicted and optimized sterilants × immersion times combination were tested, and results indicated that the differences between the MLP predicted and validation data were negligible. Generally, MLP-NSGAII as a powerful methodology may pave the way for establishing new computational strategies in plant tissue culture.

Density propagation based adaptive multi-density clustering algorithm

The performance of density based clustering algorithms may be greatly influenced by the chosen parameter values, and achieving optimal or near optimal results very much depends on empirical knowledge obtained from previous experiments. To address this limitation, we propose a novel density based clustering algorithm called the Density Propagation based Adaptive Multi-density clustering (DPAM) algorithm. DPAM can adaptively cluster spatial data. In order to avoid manual intervention when choosing parameters of density clustering and still achieve high performance, DPAM performs clustering in three stages: (1) generate the micro-clusters graph, (2) density propagation with redefinition of between-class margin and intra-class cohesion, and (3) calculate regional density. Experimental results demonstrated that DPAM could achieve better performance than several state-of-the-art density clustering algorithms in most of the tested cases, the ability of no parameters needing to be adjusted enables the proposed algorithm to achieve promising performance.