No abstract

Background The zone adjacent to a transcription start site (TSS), namely, the promoter, is primarily involved in the process of DNA transcription initiation and regulation. As a result, proper promoter identification is critical for further understanding the mechanism of the networks controlling genomic regulation. A number of methodologies for the identification of promoters have been proposed. Nonetheless, due to the great heterogeneity existing in promoters, the results of these procedures are still unsatisfactory. In order to establish additional discriminative characteristics and properly recognize promoters, we developed the hybrid model for promoter identification (HMPI), a hybrid deep learning model that can characterize both the native sequences of promoters and the morphological outline of promoters at the same time. We developed the HMPI to combine a method called the PSFN (promoter sequence features network), which characterizes native promoter sequences and deduces sequence features, with a technique referred to as the DSPN (deep structural profiles network), which is specially structured to model the promoters in terms of their structural profile and to deduce their structural attributes. Results The HMPI was applied to human, plant and Escherichia coli K-12 strain datasets, and the findings showed that the HMPI was successful at extracting the features of the promoter while greatly enhancing the promoter identification performance. In addition, after the improvements of synthetic sampling, transfer learning and label smoothing regularization, the improved HMPI models achieved good results in identifying subtypes of promoters on prokaryotic promoter datasets. Conclusions The results showed that the HMPI was successful at extracting the features of promoters while greatly enhancing the performance of identifying promoters on both eukaryotic and prokaryotic datasets, and the improved HMPI models are good at identifying subtypes of promoters on prokaryotic promoter datasets. The HMPI is additionally adaptable to different biological functional sequences, allowing for the addition of new features or models.

Vaccination with intact (146S) foot-and-mouth disease virus (FMDV) particles is used to control FMD. However, 146S particles easily dissociate into stable pentameric 12S particles which are less immunogenic. We earlier isolated several single-domain antibody fragments (VHHs) that specifically bind either 146S or 12S particles. These particle-specific VHHs are excellent tools for vaccine quality control. In this study we mapped the antigenic sites recognized by these VHHs by competition ELISAs, virus neutralization, and trypsin sensitivity of epitopes. We included two previously described monoclonal antibodies (mAbs) that are either 12S specific (mAb 13A6) or 146S specific (mAb 9). Although both are 12S specific, the VHH M3F and mAb 13A6 were found to bind independent antigenic sites. M3F recognized a non-neutralizing and trypsin insensitive site whereas mAb 13A6 recognized the trypsin sensitive VP2 N-terminus. The Asia1 146S-specific site was trypsin sensitive, neutralizing and also recognized by the VHH M8F, suggesting it involves the VP1 GH-loop. The type A 146S-specific VHHs recognized two independent antigenic sites that are both also neutralizing but trypsin insensitive. The major site was further mapped by cross-linking mass spectrometry (XL-MS) of two broadly strain reactive 146S-specific VHHs complexed to FMDV. The epitopes were located close to the 2-fold and 3-fold symmetry axes of the icosahedral virus 3D structure, mainly on VP2 and VP3, overlapping the earlier identified mAb 9 site. Since the epitopes were located on a single 12S pentamer, the 146S specificity cannot be explained by the epitope being split due to 12S pentamer dissociation. In an earlier study the cryo-EM structure of the 146S-specific VHH M170 complexed to type O FMDV was resolved. The 146S specificity was reported to be caused by an altered conformation of this epitope in 12S and 146S particles. This mechanism probably also explains the 146S-specific binding by the two type A VHHs mapped by XL-MS since their epitopes overlapped with the epitope recognized by M170. Surprisingly, residues internal in the 146S quaternary structure were also cross-linked to VHH. This probably reflects particle flexibility in solution. Molecular studies of virus-antibody interactions help to further optimize vaccines and improve their quality control.