GeneAI 3.0: powerful, novel, generalized hybrid and ensemble deep learning frameworks for miRNA species classification of stationary patterns from nucleotides

Due to the intricate relationship between the small non-coding ribonucleic acid (miRNA) sequences, the classification of miRNA species, namely Human, Gorilla, Rat, and Mouse is challenging. Previous methods are not robust and accurate. In this study, we present AtheroPoint's GeneAI 3.0, a powerful, novel, and generalized method for extracting features from the fixed patterns of purines and pyrimidines in each miRNA sequence in ensemble paradigms in machine learning (EML) and convolutional neural network (CNN)-based deep learning (EDL) frameworks. GeneAI 3.0 utilized five conventional (Entropy, Dissimilarity, Energy, Homogeneity, and Contrast), and three contemporary (Shannon entropy, Hurst exponent, Fractal dimension) features, to generate a composite feature set from given miRNA sequences which were then passed into our ML and DL classification framework. A set of 11 new classifiers was designed consisting of 5 EML and 6 EDL for binary/multiclass classification. It was benchmarked against 9 solo ML (SML), 6 solo DL (SDL), 12 hybrid DL (HDL) models, resulting in a total of 11 + 27 = 38 models were designed. Four hypotheses were formulated and validated using explainable AI (XAI) as well as reliability/statistical tests. The order of the mean performance using accuracy (ACC)/area-under-the-curve (AUC) of the 24 DL classifiers was: EDL > HDL > SDL. The mean performance of EDL models with CNN layers was superior to that without CNN layers by 0.73%/0.92%. Mean performance of EML models was superior to SML models with improvements of ACC/AUC by 6.24%/6.46%. EDL models performed significantly better than EML models, with a mean increase in ACC/AUC of 7.09%/6.96%. The GeneAI 3.0 tool produced expected XAI feature plots, and the statistical tests showed significant p-values. Ensemble models with composite features are highly effective and generalized models for effectively classifying miRNA sequences.

A 10(9) neutrons/pulse transportable pulsed D-D neutron source based on flexible head plasma focus unit

A 17 kJ transportable plasma focus (PF) device with flexible transmission lines is developed and is characterized. Six custom made capacitors are used for the capacitor bank (CB). The common high voltage plate of the CB is fixed to a centrally triggered spark gap switch. The output of the switch is coupled to the PF head through forty-eight 5 m long RG213 cables. The CB has a quarter time-period of 4 μs and an estimated current of 506 kA is delivered to the PF device at 17 kJ (60 μF, 24 kV) energy. The average neutron yield measured using silver activation detector in the radial direction is (7.1 ± 1.4) × 10(8) neutrons/shot over 4π sr at 5 mbar optimum D2 pressure. The average neutron yield is more in the axial direction with an anisotropy factor of 1.33 ± 0.18. The average neutron energies estimated in the axial as well as in the radial directions are (2.90 ± 0.20) MeV and (2.58 ± 0.20) MeV, respectively. The flexibility of the PF head makes it useful for many applications where the source orientation and the location are important factors. The influence of electromagnetic interferences from the CB as well as from the spark gap on applications area can be avoided by putting a suitable barrier between the bank and the PF head.

Palm top plasma focus device as a portable pulsed neutron source

Development of a palm top plasma focus device generating (5.2 ± 0.8) × 10(4) neutrons∕pulse into 4π steradians with a pulse width of 15 ± 3 ns is reported for the first time. The weight of the system is less than 1.5 kg. The system comprises a compact capacitor bank, a triggered open air spark gap switch, and a sealed type miniature plasma focus tube. The setup is around 14 cm in diameter and 12.5 cm in length. The energy driver for the unit is a capacitor bank of four cylindrical commercially available electrolytic capacitors. Each capacitor is of 2 μF capacity, 4.5 cm in diameter, and 9.8 cm in length. The cost of each capacitor is less than US$ 10. The internal diameter and the effective length of the plasma focus unit are 2.9 cm and 5 cm, respectively. A DC to DC converter power supply powered by two rechargeable batteries charges the capacitor bank to the desired voltage and also provides a trigger pulse of -15 kV to the spark gap. The maximum energy of operation of the device is 100 J (8 μF, 5 kV, 59 kA) with deuterium gas filling pressure of 3 mbar. The neutrons have also been produced at energy as low as 36 J (3 kV) of operation. The neutron diagnostics are carried out with a bank of (3)He detectors and with a plastic scintillator detector. The device is portable, reusable, and can be operated for multiple shots with a single gas filling.

Note: A portable pulsed neutron source based on the smallest sealed-type plasma focus device

Development and operation of a portable and compact pulsed neutron source based on sealed-type plasma focus (PF) device are reported. The unit is the smallest sealed-type neutron producing PF device. The effective volume of the PF unit is 33 cm(3) only. A compact size single capacitor (4 μF) is used as the energy driver. A battery based power supply unit is used for charging the capacitor and triggering the spark gap. The PF unit is operated at 10 kV (200 J) and at a deuterium gas filling pressure of 8 mb. The device is operated over a time span of 200 days and the neutron emissions have been observed for 200 shots without changing the gas in between the shots. The maximum yield of this device is 7.8 × 10(4) neutrons/pulse. Beyond 200 shots the yield is below the threshold (1050 neutrons/pulse) of our (3)He detector. The neutron energy is evaluated using time of flight technique and the value is (2.49 ± 0.27) MeV. The measured neutron pulse width is (24 ± 5) ns. Multishot and long duration operations envisage the potentiality of such portable device for repetitive mode of operation.