Search

Optimal first-line treatment that enables deeper and longer remission is crucially important for newly diagnosed multiple myeloma (NDMM). In this study, we developed the machine learning (ML) models predicting overall survival (OS) or response of the transplant-ineligible NDMM patients when treated by one of the two regimens—bortezomib plus melphalan plus prednisone (VMP) or lenalidomide plus dexamethasone (RD). Demographic and clinical characteristics obtained during diagnosis were used to train the ML models, which enabled treatment-specific risk stratification. Survival was superior when the patients were treated with the regimen to which they were low risk. The largest difference in OS was observed in the VMP-low risk & RD-high risk group, who recorded a hazard ratio of 0.15 (95% CI: 0.04–0.55) when treated with VMP vs. RD regimen. Retrospective analysis showed that the use of the ML models might have helped to improve the survival and/or response of up to 202 (39%) patients among the entire cohort (N = 514). In this manner, we believe that the ML models trained on clinical data available at diagnosis can assist the individualized selection of optimal first-line treatment for transplant-ineligible NDMM patients. [ABSTRACT FROM AUTHOR]

Improving a functional property of an enzyme via mutagenesis is still a challenging problem due to vast search space and difficulty of predicting the effects of mutation(s). Machine learning has proven to be proficient in solving similar problems with unprecedented speed owing to the latest advances in computing power and analytical algorithms. In this study, we investigate the performance of machine learning methods in predicting the H2 production activity and O2 tolerance of the hydrogenase variants. Experimentally measured activities and tolerance of 377 variants having single or double amino acid replacements are used to train and test seven types of machine learning models. Binary representation of amino acid sequence as well as the series of vectors quantifying physicochemical properties of amino acids, namely VHSE, are employed as features representing each variant. The results show that the VHSE enable higher performance, especially with respect to correlation coefficient and coefficient of determination in addition to the root mean square error. Next, the analysis of model performance with respect to changes in the data size and heterogeneity is conducted to provide insights on designing effective mutagenesis library for applying machine learning. The best performance was obtained when support vector machine or ridge regression was trained using a large, homogeneous data. In this manner, our study reveals the factors affecting the performance of machine learning in identifying the enzyme variants with enhanced function. [ABSTRACT FROM AUTHOR]

Mixed-culture fermentation that does not require an energy-intensive sterilization process is a viable approach for the economically feasible production of lactic acid (LA) due to the potential use of organic waste as feedstock. This study investigated mixed-culture LA fermentation of whey, a high-strength organic wastewater, in continuous mode. Variations in the hydraulic retention time (HRT) from 120 to 8 h under different pH regimes in two thermophilic reactors (55 °C) were compared for their fermentation performance. One reactor was maintained at a low pH (pH 3.0) during operation at HRTs of 120 to 24 h and then adjusted to pH 5.5 in the later phases of fermentation at HRTs of 24 to 8 h (R1), while the second reactor was maintained at pH 5.5 throughout the experiment (R2). Although the LA production in R1 was negligible at low pH, it increased dramatically after the pH was raised to 5.5 and exceeded that in R2 when stabilized at HRTs of 8 and 12 h. The maximum yield (0.62 g LA/g substrate fed as the chemical oxygen demand (COD) equivalent), the production rate (11.5 g/L day), and the selectivity (95 %) of LA were all determined at a 12-h HRT in R1. Additionally, molecular and statistical analyses revealed that changes in the HRT and the pH significantly affected the bacterial community structure and thus the fermentation characteristics of the experimental reactors. Bacillus coagulans was likely the predominant LA producer in both reactors. The overall results suggest that low pH start-up has a positive effect on yield and selectivity in mixed-culture LA fermentation. [ABSTRACT FROM AUTHOR]