Identifi cation of paralytic shellfi sh toxin-producing microalgae using machine learning and deep learning methods

Paralytic shellfi sh poisoning(PSP)microalgae,as one of the harmful algal blooms,causes great damage to the of fshore fi shery,marine culture,and marine ecological environment.At present,there is no technique for real-time accurate identifi cation of toxic microalgae,by combining three-dimensional fluorescence with machine learning(ML)and deep learning(DL),we developed methods to classify the PSP and non-PSP microalgae.The average classifi cation accuracies of these two methods for microalgae are above 90%,and the accuracies for discriminating 12 microalgae species in PSP and non-PSP microalgae are above 94%.When the emission wavelength is 650-690 nm,the fl uorescence characteristics bands(excitation wavelength)occur dif ferently at 410-480 nm and 500-560 nm for PSP and non-PSP microalgae,respectively.The identification accuracies of ML models(support vector machine(SVM),and k-nearest neighbor rule(k-NN)),and DL model(convolutional neural network(CNN))to PSP microalgae are 96.25%,96.36%,and 95.88%respectively,indicating that ML and DL are suitable for the classifi cation of toxic microalgae.

Stress regulation of photosynthetic system of Phaeocystis globosa and their hemolytic activity

Blooms of Phaeocystis globosa have been reported accountable for massive fi sh mortality worldwide.The toxigenic mechanisms of P.globosa,however,remain largely unclear due to the multiple structures and/or synergistic or antagonistic ef fects of hemolytic compounds.External stressors could lead to the regulation of photoprotective or antioxidative defense system,as well as the potential hemolytic activity.Therefore,the light-induced photosynthetic system,including the accessory photosynthetic growth,the relative electron transfer rate(ETR),photosynthetic e ffi ciency(F_(v)/F_(m)),quantum yield of photosystem II(Yield),together with the hemolytic activity of P.globosa were investigated under variable environmental conditions in the present study.Results confirmed that hemolytic activity of P.globosa was initiated by the light,but inhibited by low temperature(16℃),high light intensity(>100μmol/(m^(2)·s)),and iron-limited conditions.Interestingly,the hemolytic activity was not impacted by photosynthetic electron inhibitors(Diuron,atrazine,paraquat,and dibromothymoquinone),which signifi cantly inhibited the photosynthetic activity of P.globosa.The correlated response of hemolytic and photosynthetic activity of P.globosa under those environmental factors suggested that the hemolytic compounds of P.globosa would be involved in the photosynthetic process but not in the electron transfer chain of P.globosa.

Efficient harvesting of green microalgae cells by magnetic flocculated Fe_(3)O_(4)nanoparticles combined with chitosan

Microalgae harvesting remains a challenging step in microalgae industrialization,thereby provoking the necessity to explore sustainable and economically feasible approaches.This research investigated the use of magnetic flocculated nanoparticles in the harvesting of the common microalgae Chlorella pyrenoidosa and Scenedesmus obliquus.The results showed that magnetic flocculated nanoparticles efficiently adsorbed negatively charged microalgae cells,and a magnetic field could adsorb the magnetic flocculated nanoparticles,thereby harvesting the microalgae cells.Harvesting efficiency was remarkably increased at the optimum magnetic field strength of 0.5 T with the magnetic flocculated nanoparticles at 0.738 g/L,and microalgae broth at pH 9.0,whereas the recovery rates of both C.pyrenoidosa and S.obliquus were around 97%and the sedimentation speed of both was above 2.63 cm/min.This study exemplified the magnetic flocculated nanoparticles-based approach to effectively harvest the microalgae cells.