Exploring the Knowledge of An Outstanding Protein to Protein Interaction Transformer.

Protein-to-protein interaction (PPI) prediction aims to predict whether two given proteins interact or not. Compared with traditional experimental methods of high cost and low efficiency, the current deep learning based approach makes it possible to discover massive potential PPIs from large-scale databases. However, deep PPI prediction models perform poorly on unseen species, as their proteins are not in the training set. Targetting on this issue, the paper first proposes PPITrans, a Transformer based PPI prediction model that exploits a language model pre-trained on proteins to conduct binary PPI prediction. To validate the effectiveness on unseen species, PPITrans is trained with Human PPIs and tested on PPIs of other species. Experimental results show that PPITrans significantly outperforms the previous state-of-the-art on various metrics, especially on PPIs of unseen species. For example, the AUPR improves 0.339 absolutely on Fly PPIs. Aiming to explore the knowledge learned by PPITrans from PPI data, this paper also designs a series of probes belonging to three categories. Their results reveal several interesting findings, like that although PPITrans cannot capture the spatial structure of proteins, it can obtain knowledge of PPI type and binding affinity, learning more than binary PPI.

[Expressions of NF-κBp65 and IκBα in gestational trophoblastic disease and clinical significance].

AIM: To investigate the roles of nuclear factor κB p65 (NF-κBp65) and inhibitor of nuclear factor κB α (IκBα) in the development and metastasis of gestational trophoblastic neoplasia (GTN) by analyzing the expressions of NF-κBp65 and IκBα in normal early pregnancy villi and gestational trophoblastic diseases, and to reveal the relationship of NF-κBp65 and IκBα with age and clinical stage of GTN patients. METHODS: The expressions of NF-κBp65 and IκBα were detected by immunohistochemistry in normal pregnancy villi (20 cases), hydatidiform moles (HM, 30 cases), invasive hydatidiform moles (IHM, 13 cases) and chorionic carcinomas (CCA, 15 cases). RESULTS: NF-κBp65 expression was statistically different (P<0.05) between normal pregnancy villi and IHM (P=0.013), normal pregnancy villi and CCA(P=0.018), HM and IHM(P=0.026), HM and CCA (P=0.035). Differences in IκBα expression were statistically significant between normal pregnancy villi and IHM, normal pregnancy villi and CCA, HM and IHM, HM and CCA (P<0.01). The expressions of NF-κBp65 and IκBα were correlated to clinical stage (P=0.043, 0.042, P<0.05), but not to patients' ages. Spearman correlation analysis revealed that there was a negative association between the protein expressions of NF-κBp65 and IκBα in GTN (r=-0.403, P=0.034, P<0.05). CONCLUSION: Up-regulated expression of NF-κBp65 and down-regulated expression of IκBα may be related to the development, invasion and metastasis of GTN. The expressions of NF-κBp65 and IκBα are negatively correlated in gestational trophoblastic tumor tissues.