Prediction of pandemic risk for animal-origin coronavirus using a deep learning method

Predicting Future Pandemics and Formulating Prevention Strategies: The Role of ChatGPT

The emergence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in late 2019 and its subsequent worldwide spread has emphasized the urgent need for better approaches for predicting and managing infectious disease outbreaks. One potential instrument in this effort is artificial intelligence (AI), and in specific, language models like ChatGPT (Chat Generative Pre-trained Transformer). In the present study, to explore how ChatGPT could predict future pandemics and give suggestions about the prevention strategy, our research team chatted with ChatGPT with several questions on July 12, 2023. Based on our conversation, we can conclude that AI is not a substitute for human expertise, but an adjunct to support early prediction, prevention, and management of future pandemics.

A depth-first search algorithm for oligonucleotide design in gene assembly

When synthesizing a gene with a long DNA sequence, it is usually necessary to divide it into several fragments. Based on these fragments, a set of oligonucleotides for gene assembly is produced. Each oligonucleotide is synthesized separately by the chemical reaction, and then the obtained oligonucleotides are assembled into the full gene sequence, in a specific environment, by polymerase chain reaction (PCR) or ligase chain reaction (LCR). In this paper, an effective and efficient algorithm to divide long genes into oligonucleotide sets is presented. First, according to the length of the overlapping oligonucleotide region, the long DNA sequence to be synthesized is divided into fragments of approximately equal length. Second, the length of these fragments is iterated to dynamically optimize the length of the overlapping regions to reduce melting temperature fluctuations. Then, the improved depth-first search algorithm is used according to the design principle of pruning optimization to obtain a uniform set of oligonucleotides with very close melting temperatures. This will decrease the errors in gene assembly with PCR or LCR. Lastly, the oligonucleotides that have homologous melting temperatures needed for PCR-based synthesis and two-step assembly of the target gene are deduced and outputted.

Using amino acid features to identify the pathogenicity of influenza B virus

BACKGROUND

Influenza B virus can cause epidemics with high pathogenicity, so it poses a serious threat to public health. A feature representation algorithm is proposed in this paper to identify the pathogenicity phenotype of influenza B virus.

METHODS

The dataset included all 11 influenza virus proteins encoded in eight genome segments of 1724 strains. Two types of features were hierarchically used to build the prediction model. Amino acid features were directly delivered from 67 feature descriptors and input into the random forest classifier to output informative features about the class label and probabilistic prediction. The sequential forward search strategy was used to optimize the informative features. The final features for each strain had low dimensions and included knowledge from different perspectives, which were used to build the machine learning model for pathogenicity identification.

RESULTS

The 40 signature positions were achieved by entropy screening. Mutations at position 135 of the hemagglutinin protein had the highest entropy value (1.06). After the informative features were directly generated from the 67 random forest models, the dimensions for class and probabilistic features were optimized as 4 and 3, respectively. The optimal class features had a maximum accuracy of 94.2% and a maximum Matthews correlation coefficient of 88.4%, while the optimal probabilistic features had a maximum accuracy of 94.1% and a maximum Matthews correlation coefficient of 88.2%. The optimized features outperformed the original informative features and amino acid features from individual descriptors. The sequential forward search strategy had better performance than the classical ensemble method.

CONCLUSIONS

The optimized informative features had the best performance and were used to build a predictive model so as to identify the phenotype of influenza B virus with high pathogenicity and provide early risk warning for disease control.