Artificial intelligence-based decision support model for new drug development planning.

New drug development guarantees a very high return on success, but the success rate is extremely low. Pharmaceutical companies have attempted to use various strategies to increase the success rate of drug development, but this goal has been difficult to achieve. In this study, we developed a model that can guide effective decision-making at the planning stage of new drug development by leveraging machine learning. The Drug Development Recommendation (DDR) model, we present here, is a hybrid model for recommending and/or predicting drug groups suitable for development by individual pharmaceutical companies. It combines association rule learning, collaborative filtering, and content-based filtering approaches for enterprise-customized recommendations. In the case of content-based filtering applying a random forest classification algorithm, the accuracy and area under curve were 78% and 0.74, respectively. In particular, the DDR model was applied to predict the success probability of companies developing Coronavirus disease 2019 (COVID-19) vaccines. It was demonstrated that the higher the predicted score from the DDR model, the more progress in the clinical phase of the COVID-19 vaccine development. Although our approach has limitations that should be improved, it makes scientific as well as industrial contributions in that the DDR model can support rational decision-making prior to initiating drug development by considering not only technical aspects but also company-related variables.

Disease burden metrics and the innovations of leading pharmaceutical companies: a global and regional comparative study.

BACKGROUND: The recent innovation activities of global top-tier pharmaceutical companies in accordance with global and regional health concerns were investigated in order to identify their innovations contributing to population health. METHODS: "Innovation activity" was defined as the number of drugs for which R&D activities have been reported within the last three years. Such activities were measured by collecting the data on drug developments and classifying them by developer company, phase of development, therapeutic use, and the country in which the development conducted. Subsequently, we examined and compared the correlations between the global innovation activities of the top 20 pharmaceutical companies and the disease burden measured in disability-adjusted life years (DALYs) by income level and region. In addition, this study analyzed the association between country-specific innovations and DALYs in the corresponding countries. RESULTS: At a global level, the innovation activities were not associated with global DALYs. However, when analyzed by income level, the innovation activities were associated with DALYs in high income and upper middle income countries while it was not associated with DALYs in low middle income and low income countries. In terms of region, correlations were found between the innovation activities and DALYs in the European region, the Americas, and the Western Pacific region whereas such correlations were not found in the African, Eastern Mediterranean, and South-East Asian regions. Similar to the analyses by income level and region, correlations between country-specific innovations and DALYs were only found in high income or high GDP countries. In addition, an empirical analysis of several cases including Canada, Germany, South Korea, and the United Kingdom revealed that pharmaceutical innovation is more closely related to market size than disease burden. CONCLUSIONS: This study identified that discrepancies between pharmaceutical innovation and public health needs, i.e., disease burden values, have persisted until recently. To alleviate this imbalance, both public and private sectors should not only fulfill their respective roles and responsibilities regarding these issues, but also make strategic and collaborative efforts such as Product Development Partnerships (PDPs) directed toward public health improvement.

Isolation and Characterization of Pepper Genes Interacting with the CMV-P1 Helicase Domain.

Cucumber mosaic virus (CMV) is a destructive pathogen affecting Capsicum annuum (pepper) production. The pepper Cmr1 gene confers resistance to most CMV strains, but is overcome by CMV-P1 in a process dependent on the CMV-P1 RNA1 helicase domain (P1 helicase). Here, to identify host factors involved in CMV-P1 infection in pepper, a yeast two-hybrid library derived from a C. annuum 'Bukang' cDNA library was screened, producing a total of 76 potential clones interacting with the P1 helicase. Beta-galactosidase filter lift assay, PCR screening, and sequencing analysis narrowed the candidates to 10 genes putatively involved in virus infection. The candidate host genes were silenced in Nicotiana benthamiana plants that were then inoculated with CMV-P1 tagged with the green fluorescent protein (GFP). Plants silenced for seven of the genes showed development comparable to N. benthamiana wild type, whereas plants silenced for the other three genes showed developmental defects including stunting and severe distortion. Silencing formate dehydrogenase and calreticulin-3 precursor led to reduced virus accumulation. Formate dehydrogenase-silenced plants showed local infection in inoculated leaves, but not in upper (systemic) leaves. In the calreticulin-3 precursor-silenced plants, infection was not observed in either the inoculated or the upper leaves. Our results demonstrate that formate dehydrogenase and calreticulin-3 precursor are required for CMV-P1 infection.

Plant Translation Elongation Factor 1Bß Facilitates Potato Virus X (PVX) Infection and Interacts with PVX Triple Gene Block Protein 1.

The eukaryotic translation elongation factor 1 (eEF1) has two components: the G-protein eEF1A and the nucleotide exchange factor eEF1B. In plants, eEF1B is itself composed of a structural protein (eEF1Bγ) and two nucleotide exchange subunits (eEF1Bα and eEF1Bß). To test the effects of elongation factors on virus infection, we isolated eEF1A and eEF1B genes from pepper (Capsicum annuum) and suppressed their homologs in Nicotiana benthamiana using virus-induced gene silencing (VIGS). The accumulation of a green fluorescent protein (GFP)-tagged Potato virus X (PVX) was significantly reduced in the eEF1Bß- or eEF1BÉ£-silenced plants as well as in eEF1A-silenced plants. Yeast two-hybrid and co-immunoprecipitation analyses revealed that eEF1Bα and eEF1Bß interacted with eEF1A and that eEF1A and eEF1Bß interacted with triple gene block protein 1 (TGBp1) of PVX. These results suggest that both eEF1A and eEF1Bß play essential roles in the multiplication of PVX by physically interacting with TGBp1. Furthermore, using eEF1Bß deletion constructs, we found that both N- (1-64 amino acids) and C-terminal (150-195 amino acids) domains of eEF1Bß are important for the interaction with PVX TGBp1 and that the C-terminal domain of eEF1Bß is involved in the interaction with eEF1A. These results suggest that eEF1Bß could be a potential target for engineering virus-resistant plants.

Transgenic Brassica rapa plants over-expressing eIF(iso)4E variants show broad-spectrum Turnip mosaic virus (TuMV) resistance.

The protein-protein interaction between VPg (viral protein genome-linked) of potyviruses and eIF4E (eukaryotic initiation factor 4E) or eIF(iso)4E of their host plants is a critical step in determining viral virulence. In this study, we evaluated the approach of engineering broad-spectrum resistance in Chinese cabbage (Brassica rapa) to Turnip mosaic virus (TuMV), which is one of the most important potyviruses, by a systematic knowledge-based approach to interrupt the interaction between TuMV VPg and B. rapa eIF(iso)4E. The seven amino acids in the cap-binding pocket of eIF(iso)4E were selected on the basis of other previous results and comparison of protein models of cap-binding pockets, and mutated. Yeast two-hybrid assay and co-immunoprecipitation analysis demonstrated that W95L, K150L and W95L/K150E amino acid mutations of B. rapa eIF(iso)4E interrupted its interaction with TuMV VPg. All eIF(iso)4E mutants were able to complement an eIF4E-knockout yeast strain, indicating that the mutated eIF(iso)4E proteins retained their function as a translational initiation factor. To determine whether these mutations could confer resistance, eIF(iso)4E W95L, W95L/K150E and eIF(iso)4E wild-type were over-expressed in a susceptible Chinese cabbage cultivar. Evaluation of the TuMV resistance of T1 and T2 transformants demonstrated that the over-expression of the eIF(iso)4E mutant forms can confer resistance to multiple TuMV strains. These data demonstrate the utility of knowledge-based approaches for the engineering of broad-spectrum resistance in Chinese cabbage.

Two leucines in the N-terminal MAPK-docking site of tomato SlMKK2 are critical for interaction with a downstream MAPK to elicit programmed cell death associated with plant immunity.

Tomato MAPK kinase SlMKK2 is a key protein regulating immunity-associated programmed cell death (PCD) in plants. We examined the role of the N-terminal MAPK-docking site (or D-site) of SlMKK2 in PCD elicitation. In vivo assays revealed that SlMKK2 interacted with the downstream MAPK SlMPK3 independent of PCD elicitation and two conserved leucines in the D-site were required for both interaction with SlMPK3 and PCD elicitation. These results demonstrate that two leucines in the D-site of SlMKK2 play a critical role in regulation of signal transfer to the downstream MAPK by regulating their physical interaction.

Translation elongation factor 1B (eEF1B) is an essential host factor for Tobacco mosaic virus infection in plants.

Identifying host factors provides an important clue to understand virus infection. We selected 10 host factor candidate genes and each gene was silenced in Nicotiana benthamiana (N. benthamiana) to investigate their roles in virus infection. The resulting plants were infected with Tobacco mosaic virus (TMV). The accumulation of viral coat protein and the spread of virus were greatly reduced in the plants that eukaryotic translation elongation factor 1A (eEF1A) or 1B (eEF1B) was silenced. These results suggest both eEF1A and eEF1B are required for TMV infection. We also tested for interactions between the eEFs and viral proteins of TMV. Both eEF1A and eEF1B proteins interacted directly with the methyltransferase (MT) domain of the TMV RNA-dependent RNA polymerase (RdRp). eEF1A and eEF1B also interacted with each other in vivo. Our data suggest that eEF1B may be a component of the TMV replication complex which interacts with MT domain of TMV RdRp and eEF1A.

Double mutations in eIF4E and eIFiso4E confer recessive resistance to Chilli veinal mottle virus in pepper.

To evaluate the involvement of translation initiation factors eIF4E and eIFiso4E in Chilli veinai mottle virus (ChiVMV) infection in pepper, we conducted a genetic analysis using a segregating population derived from a cross between Capsicum annuum 'Dempsey' containing an eIF4E mutation (pvr1(2)) and C. annuum 'Perennial' containing an eIFiso4E mutation (pvr6). C. annuum 'Dempsey' was susceptible and C. annuum 'Perennial' was resistant to ChiVMV. All F(1) plants showed resistance, and F(2) individuals segregated in a resistant-susceptible ratio of 166:21, indicating that many resistance loci were involved. Seventy-five F(2) and 329 F(3) plants of 17 families were genotyped with pvr1(2) and pvr6 allele-specific markers, and the genotype data were compared with observed resistance to viral infection. All plants containing homozygous genotypes of both pvr1(2) and pvr6 were resistant to ChiVMV, demonstrating that simultaneous mutations in eIF4E and eIFiso4E confer resistance to ChiVMV in pepper. Genotype analysis of F2 plants revealed that all plants containing homozygous genotypes of both pvr1(2) and pvr6 showed resistance to ChiVMV. In protein-protein interaction experiments, ChiVMV viral genome-linked protein (VPg) interacted with both eIF4E and eIFiso4E. Silencing of eIF4E and eIFiso4E in the VIGS experiment showed reduction in ChiVMV accumulation. These results demonstrated that ChiVMV can use both eIF4E and eIFiso4E for replication, making simultaneous mutations in eIF4E and eIFiso4E necessary to prevent ChiVMV infection in pepper.