Artificial Intelligence-Based Co-Facilitator (AICF) for Detecting and Monitoring Group Cohesion Outcomes in Web-Based Cancer Support Groups: Single-Arm Trial Study.

BACKGROUND: Commonly offered as supportive care, therapist-led online support groups (OSGs) are a cost-effective way to provide support to individuals affected by cancer. One important indicator of a successful OSG session is group cohesion; however, monitoring group cohesion can be challenging due to the lack of nonverbal cues and in-person interactions in text-based OSGs. The Artificial Intelligence-based Co-Facilitator (AICF) was designed to contextually identify therapeutic outcomes from conversations and produce real-time analytics. OBJECTIVE: The aim of this study was to develop a method to train and evaluate AICF's capacity to monitor group cohesion. METHODS: AICF used a text classification approach to extract the mentions of group cohesion within conversations. A sample of data was annotated by human scorers, which was used as the training data to build the classification model. The annotations were further supported by finding contextually similar group cohesion expressions using word embedding models as well. AICF performance was also compared against the natural language processing software Linguistic Inquiry Word Count (LIWC). RESULTS: AICF was trained on 80,000 messages obtained from Cancer Chat Canada. We tested AICF on 34,048 messages. Human experts scored 6797 (20%) of the messages to evaluate the ability of AICF to classify group cohesion. Results showed that machine learning algorithms combined with human input could detect group cohesion, a clinically meaningful indicator of effective OSGs. After retraining with human input, AICF reached an F1-score of 0.82. AICF performed slightly better at identifying group cohesion compared to LIWC. CONCLUSIONS: AICF has the potential to assist therapists by detecting discord in the group amenable to real-time intervention. Overall, AICF presents a unique opportunity to strengthen patient-centered care in web-based settings by attending to individual needs. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/21453.

T cell epitopes of SARS-CoV-2 spike protein and conserved surface protein of Plasmodium malariae share sequence homology.

Since its emergence in late 2019, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been spreading remarkably fast worldwide. Effective countermeasures require the rapid development of data and tools to monitor its spread and better understand immunogenic profile. However, limited information is available about the tools and target of the immune responses to SARS-CoV-2. In this study, we excogitated a new approach for analyzing phylogenetic relationships by using the whole prototype proteome sequences. Phylogenetic analysis on the whole prototype proteome sequences showed that SARS-CoV-2 was a direct descendant of Bat-CoV and was closely related to Pangolin-CoV, Bat-SL-CoV, and SARS-CoV. The pairwise comparison of SARS-CoV-2 with Bat-CoV showed an unusual replacement of the motif consisting of seven amino acids (NNLDSKV) within the spike protein of SARS-CoV-2. The replaced motif in the spike protein of SARS-CoV-2 was found in 12 other species, including a conserved surface protein of a malaria-causing pathogen, Plasmodium malariae. We further identified the T and B cell epitope sequence homology of SARS-CoV-2 spike protein with conserved surface protein of P. malariae using the Immune Epitope Database and Analysis Resource (IEDB). The shared immunodominant epitopes may provide immunity against SARS-CoV-2 infection to those previously infected with P. malariae.

The regional diversity of gut microbiome along the GI tract of male C57BL/6 mice.

BACKGROUND: The proliferation and survival of microbial organisms including intestinal microbes are determined by their surrounding environments. Contrary to popular myth, the nutritional and chemical compositions, water contents, O2 contents, temperatures, and pH in the gastrointestinal (GI) tract of a human are very different in a location-specific manner, implying heterogeneity of the microbial composition in a location-specific manner. RESULTS: We first investigated the environmental conditions at 6 different locations along the GI tract and feces of ten weeks' old male SPF C57BL/6 mice. As previously known, the pH and water contents of the GI contents at the different locations of the GI tract were very different from each other in a location-specific manner, and none of which were not even similar to those of feces. After confirming the heterogeneous nature of the GI contents in specific locations and feces, we thoroughly analyzed the composition of the microbiome of the GI contents and feces. 16S rDNA-based metagenome sequencing on the GI contents and feces showed the presence of 13 different phyla. The abundance of Firmicutes gradually decreased from the stomach to feces while the abundance of Bacteroidetes gradually increased. The taxonomic α-diversities measured by ACE (Abundance-based Coverage Estimator) richness, Shannon diversity, and Fisher's alpha all indicated that the diversities of gut microbiome at colon and cecum were much higher than that of feces. The diversities of microbiome compositions were lowest in jejunum and ileum while highest in cecum and colon. Interestingly, the diversities of the fecal microbiome were lower than those of the cecum and colon. Beta diversity analyses by NMDS plots, PCA, and unsupervised hierarchical clustering all showed that the microbiome compositions were very diverse in a location-specific manner. Direct comparison of the fecal microbiome with the microbiome of the whole GI tracts by α-and ß-diversities showed that the fecal microbiome did not represent the microbiome of the whole GI tract. CONCLUSION: The fecal microbiome is different from the whole microbiome of the GI tract, contrary to a baseline assumption of contemporary microbiome research work.