Spiking neural P systems, shortly named SN P systems, are bio-inspired neural-like computing models, which are obtained by abstracting the way of biological neurons’ spiking and communication by means of spikes in central nervous systems. SN P systems performed well in describing and modeling behaviors that occur simultaneously, yet weak at modeling complex systems with the limits of using a single spike. In this work, drawing on the idea from colored petri nets, SN P systems with colored spikes are proposed, where a finite set of colors is introduced to mark the spikes such that each spike is associated with a unique color. The updated spiking rule is applied by consuming and emitting a number of colored spikes (with the same or different colors). The computation power of the systems is investigated. Specifically, it is shown that SN P systems with colored spikes having 3 neurons are sufficient to compute Turing computable sets of numbers, and such system having 2 neurons is able to compute the family of recursive functions. These results improved the corresponding ones on the number of neurons needed to construct universal SN P systems recently appeared in [Neurocomputing, 2016, 193(12): 193–200]. To our best knowledge, this is the smallest number of neurons used to construct Turing universal SN P systems as number generator and function computing device by far.

Neural-like computing models are versatile computing mechanisms in the field of artificial intelligence. Spiking neural P systems (SN P systems for short) are one of the recently developed spiking neural network models inspired by the way neurons communicate. The communications among neurons are essentially achieved by spikes, i. e. short electrical pulses. In terms of motivation, SN P systems fall into the third generation of neural network models. In this study, a novel variant of SN P systems, namely SN P systems with self-organization, is introduced and the computational power of the system is investigated and evaluated. It is proved that SN P systems with self-organization are capable of computing and accept the family of sets of Turing computable natural numbers. Moreover, with 87 neurons the system can compute any Turing computable recursive function, thus achieves Turing universality. These results demonstrate promising initiatives to solve an open problem arisen by Gh Păun.

Spiking neural P systems, otherwise known as named SN P systems, are bio-inspired parallel and distributed neural-like computing models. Due to the spiking behavior, SN P systems fall into the category of spiking neural networks, and are considered to be an auspicious candidate of the 3G of neural networks. It has been reported that SN P systems with colored spikes are computationally capable, and perform well in describing behaviors of complex systems. Nonetheless, some practical issue is open to be investigate, such as workflow and traffic flow modeling. In this paper, a parallel workflow pattern modeling using SN P systems with colored spikes is proposed. As results, 20 designs are constructed using SN P systems for 20 classical workflow patterns. The functioning processes that operate both sequentially and simultaneously in the workflow pattern are able to be modeled and simulated. SN P systems with colored spikes have some similarity with Petri nets, hence can be used to model workflow patterns. This will provide a novel neural-like modeling method for modeling traffic flow.

Recent years have seen tremendous success in the design of novel drug molecules through deep generative models. Nevertheless, existing methods only generate drug-like molecules, which require additional structural optimization to be developed into actual drugs. In this study, a deep learning method for generating target-specific ligands was proposed. This method is useful when the dataset for target-specific ligands is limited. Deep learning methods can extract and learn features (representations) in a data-driven way with little or no human participation. Generative pretraining (GPT) was used to extract the contextual features of the molecule. Three different protein-encoding methods were used to extract the physicochemical properties and amino acid information of the target protein. Protein-encoding and molecular sequence information are combined to guide molecule generation. Transfer learning was used to fine-tune the pretrained model to generate molecules with better binding ability to the target protein. The model was validated using three different targets. The docking results show that our model is capable of generating new molecules with higher docking scores for the target proteins.