New algorithms for detecting multi-effect and multi-way epistatic interactions.

MOTIVATION: Epistasis, which is the phenomenon of genetic interactions, plays a central role in many scientific discoveries. However, due to the combinatorial nature of the problem, it is extremely challenging to decipher the exact combinations of genes that trigger the epistatic effects. Many existing methods only focus on two-way interactions. Some of the most effective methods used machine learning techniques, but many were designed for special case-and-control studies or suffer from overfitting. We propose three new algorithms for multi-effect and multi-way epistases detection, with one guaranteeing global optimality and the other two being local optimization oriented heuristics. RESULTS: The computational performance of the proposed heuristic algorithm was compared with several state-of-the-art methods using a yeast dataset. Results suggested that searching for the global optimal solution could be extremely time consuming, but the proposed heuristic algorithm was much more effective and efficient than others at finding a close-to-optimal solution. Moreover, it was able to provide biological insight on the exact configurations of epistases, besides achieving a higher prediction accuracy than the state-of-the-art methods. AVAILABILITY AND IMPLEMENTATION: Data source was publicly available and details are provided in the text.

An interaction regression model for crop yield prediction.

Crop yield prediction is crucial for global food security yet notoriously challenging due to multitudinous factors that jointly determine the yield, including genotype, environment, management, and their complex interactions. Integrating the power of optimization, machine learning, and agronomic insight, we present a new predictive model (referred to as the interaction regression model) for crop yield prediction, which has three salient properties. First, it achieved a relative root mean square error of 8% or less in three Midwest states (Illinois, Indiana, and Iowa) in the US for both corn and soybean yield prediction, outperforming state-of-the-art machine learning algorithms. Second, it identified about a dozen environment by management interactions for corn and soybean yield, some of which are consistent with conventional agronomic knowledge whereas some others interactions require additional analysis or experiment to prove or disprove. Third, it quantitatively dissected crop yield into contributions from weather, soil, management, and their interactions, allowing agronomists to pinpoint the factors that favorably or unfavorably affect the yield of a given location under a given weather and management scenario. The most significant contribution of the new prediction model is its capability to produce accurate prediction and explainable insights simultaneously. This was achieved by training the algorithm to select features and interactions that are spatially and temporally robust to balance prediction accuracy for the training data and generalizability to the test data.

A time-dependent parameter estimation framework for crop modeling.

The performance of crop models in simulating various aspects of the cropping system is sensitive to parameter calibration. Parameter estimation is challenging, especially for time-dependent parameters such as cultivar parameters with 2-3 years of lifespan. Manual calibration of the parameters is time-consuming, requires expertise, and is prone to error. This research develops a new automated framework to estimate time-dependent parameters for crop models using a parallel Bayesian optimization algorithm. This approach integrates the power of optimization and machine learning with prior agronomic knowledge. To test the proposed time-dependent parameter estimation method, we simulated historical yield increase (from 1985 to 2018) in 25 environments in the US Corn Belt with APSIM. Then we compared yield simulation results and nine parameter estimates from our proposed parallel Bayesian framework, with Bayesian optimization and manual calibration. Results indicated that parameters calibrated using the proposed framework achieved an 11.6% reduction in the prediction error over Bayesian optimization and a 52.1% reduction over manual calibration. We also trained nine machine learning models for yield prediction and found that none of them was able to outperform the proposed method in terms of root mean square error and R2. The most significant contribution of the new automated framework for time-dependent parameter estimation is its capability to find close-to-optimal parameters for the crop model. The proposed approach also produced explainable insight into cultivar traits' trends over 34 years (1985-2018).

Performance prediction of crosses in plant breeding through genotype by environment interactions.

Performance prediction of potential crosses plays a significant role in plant breeding, which aims to produce new crop varieties that have higher yields, require fewer resources, and are more adaptable to the changing environments. In the 2020 Syngenta crop challenge, Syngenta challenged participants to predict the yield performance of a list of potential breeding crosses of inbreds and testers based on their historical yield data in different environments. They released a dataset that contained the observed yields for 294,128 corn hybrids through the crossing of 593 unique inbreds and 496 unique testers across multiple environments between 2016 and 2018. To address this challenge, we designed a new predictive approach that integrates random forest and an optimization model for G [Formula: see text] E interaction detection. Our computational experiment found that our approach achieved a relative root-mean-square-error (RMSE) of 0.0869 for the validation data, outperforming other state-of-the-art models such as factorization machine and extreme gradient boosting tree. Our model was also able to detect genotype by environment interactions that are potentially biologically insightful. This model won the first place in the 2020 Syngenta crop challenge in analytics.

Multi-objective integrated planning and scheduling model for operating rooms under uncertainty.

This article formulates the operating rooms considering several constraints of the real world, such as decision-making styles, multiple stages for surgeries, time windows for resources, and specialty and complexity of surgery. Based on planning, surgeries are assigned to the working days. Then, the scheduling part determines the sequence of surgeries per day. Moreover, an integrated fuzzy possibilistic-stochastic mathematical programming approach is applied to consider some sources of uncertainty, simultaneously. Net revenues of operating rooms are maximized through the first objective function. Minimizing a decision-making style inconsistency among human resources and maximizing utilization of operating rooms are considered as the second and third objectives, respectively. Two popular multi-objective meta-heuristic algorithms including Non-dominated Sorting Genetic Algorithm and Multi-Objective Particle Swarm Optimization are utilized for solving the developed model. Moreover, different comparison metrics are applied to compare the two proposed meta-heuristics. Several test problems based on the data obtained from a public hospital located in Iran are used to display the performance of the model. According to the results, Non-dominated Sorting Genetic Algorithm-II outperforms the Multi-Objective Particle Swarm Optimization algorithm in most of the utilized metrics. Moreover, the results indicate that our proposed model is more effective and efficient to schedule and plan surgeries and assign resources than manual scheduling.