Artificial Intelligence/Machine Learning-Driven Small Molecule Repurposing via Off-Target Prediction and Transcriptomics.

The process of discovering small molecule drugs involves screening numerous compounds and optimizing the most promising ones, both in vitro and in vivo. However, approximately 90% of these optimized candidates fail during trials due to unexpected toxicity or insufficient efficacy. Current concepts with respect to drug-protein interactions suggest that each small molecule interacts with an average of 6-11 targets. This implies that approved drugs and even discontinued compounds could be repurposed by leveraging their interactions with unintended targets. Therefore, we developed a computational repurposing framework for small molecules, which combines artificial intelligence/machine learning (AI/ML)-based and chemical similarity-based target prediction methods with cross-species transcriptomics information. This repurposing methodology incorporates eight distinct target prediction methods, including three machine learning methods. By using multiple orthogonal methods for a "dataset" composed of 2766 FDA-approved drugs targeting multiple therapeutic target classes, we identified 27,371 off-target interactions involving 2013 protein targets (i.e., an average of around 10 interactions per drug). Relative to the drugs in the dataset, we identified 150,620 structurally similar compounds. The highest number of predicted interactions were for drugs targeting G protein-coupled receptors (GPCRs), enzymes, and kinases with 10,648, 4081, and 3678 interactions, respectively. Notably, 17,283 (63%) of the off-target interactions have been confirmed in vitro. Approximately 4000 interactions had an IC50 of <100 nM for 1105 FDA-approved drugs and 1661 interactions had an IC50 of <10 nM for 696 FDA-approved drugs. Together, the confirmation of numerous predicted interactions and the exploration of tissue-specific expression patterns in human and animal tissues offer insights into potential drug repurposing for new therapeutic applications.

Therapeutic targeting of the IL-12/23 pathways: generation and characterization of ustekinumab.

Preclinical and clinical studies conducted in the mid-1990s reported strong association and causality between the T-cell helper (T(H)) 1 inductor cytokine interleukin (IL)-12 and numerous immune-mediated disorders, which spurred the development of therapeutic agents targeting IL-12 function. One of the first to enter the clinic, ustekinumab, is a human monoclonal antibody (mAb) that binds to the p40 subunit of IL-12. Subsequent to the generation of ustekinumab, it was discovered that IL-23 also contains the p40 subunit. Thus, although ustekinumab was designed to target IL-12, it also modulates IL-23, a cytokine important to the development and/or maintenance of T(H)17 cells. Clinical observations established that IL-12/23p40 is integral to the pathologies of psoriasis, psoriatic arthritis and Crohn's disease. The molecular and cellular evaluations conducted in ustekinumab clinical programs have provided numerous insights into the pathologic processes of these disorders, illustrating how a novel molecular entity can contribute to our understanding of disease. The individual contributions of these cytokines to specific pathologies require investigation and clinical evaluation of the role of IL-12- and IL-23-specific inhibitors.

Development in the cynomolgus macaque following administration of ustekinumab, a human anti-IL-12/23p40 monoclonal antibody, during pregnancy and lactation.

BACKGROUND: Ustekinumab is a human monoclonal antibody that binds to the p40 subunit of interleukin (IL) 12 and IL-23 and inhibits their pharmacological activity. To evaluate potential effects of ustekinumab treatment during pregnancy, developmental studies were conducted in cynomolgus macaques. METHODS: Ustekinumab was tested in two embryo/fetal development (EFD) studies and in a combined EFD/pre and postnatal development (PPND) study. In the EFD studies, pregnant macaques (12/group) were dosed with saline or ustekinumab (9 mg/kg IV, 22.5 mg/kg SC, or 45 mg/kg IV or SC during the period of major organogenesis, gestation day [GD] 20-50). Fetuses were harvested on GD100-102 and examined for any effects on development. In the EFD/PPND study, pregnant macaques were injected with saline or ustekinumab (22.5 or 45 mg/kg SC) from GD20 through lactation day 33. Infants were examined from birth through 6 months of age for morphological and functional development. Potential effects on the immune system were evaluated by immunophenotyping of peripheral blood lymphocytes and immunohistopathology of lymphoid tissues in fetuses and infants and by T-dependent antibody response (TDAR) to KLH and TTX and by DTH response in infants. Ustekinumab concentrations were measured in serum from dams, fetus, and infants and in breast milk. RESULTS: Ustekinumab treatment produced no maternal toxicity and no toxicity in the fetuses or infants, including no effects on the TDAR or DTH responses. Ustekinumab was present in serum from GD100 fetuses and was present in infant serum through day 120 post-birth. Low levels of ustekinumab were present in breast milk. CONCLUSIONS: Exposure of macaque fetuses and infants to ustekinumab had no adverse effects on pre- and postnatal development.

Carcinogenicity assessments of biotechnology-derived pharmaceuticals: a review of approved molecules and best practice recommendations.

An important safety consideration for developing new therapeutics is assessing the potential that the therapy will increase the risk of cancer. For biotherapeutics, traditional two-year rodent bioassays are often not scientifically applicable or feasible. This paper is a collaborative effort of industry toxicologists to review past and current practice regarding carcinogenicity assessments of biotherapeutics and to provide recommendations. Publicly available information on eighty marketed protein biotherapeutics was reviewed. In this review, no assessments related to carcinogenicity or tumor growth promotion were identified for fifty-one of the eighty molecules. For the twenty-nine biotherapeutics in which assessments related to carcinogenicity were identified, various experimental approaches were employed. This review also discusses several key principles to aid in the assessment of carcinogenic potential, including (1) careful consideration of mechanism of action to identify theoretical risks, (2) careful investigation of existing data for indications of proliferative or immunosuppressive potential, and (3) characterization of any proliferative or immunosuppressive signals detected. Traditional two-year carcinogenicity assays should not be considered as the default method for assessing the carcinogenicity potential of biotherapeutics. If experimentation is considered warranted, it should be hypothesis driven and may include a variety of experimental models. Ultimately, it is important that preclinical data provide useful guidance in product labeling.

Effects of CNTO 530, an erythropoietin mimetic-IgG4 fusion protein, on embryofetal development in rats and rabbits.

BACKGROUND: CNTO 530is a biopharmaceutical consisting of a novel peptide that mimics the actions of erythropoietin, fused to the Fc fragment of human IgG4. Pharmacokinetic and pharmacodynamic studies showed that CNTO 530 produced sustained increases in red blood cell parameters in rats and rabbits and that the serum half life of CNTO 530 was 2 days in rabbits and 3 days in rats. METHODS: For the evaluation of embryofetal development, CNTO 530 was injected at loading doses of 0, 0.9/1, 6, or 60 mg/kg subcutaneously (SC) on gestation day (GD)7 followed by maintenance doses of 0, 0.3, 2, or 20 mg/kg SC every 3 days through GD16 in rats and every 2 days through GD19 in rabbits (GD0 was the day of mating). Rats were Caesarean sectioned on GD21, rabbits on GD29. RESULTS: Administration of CNTO 530 was associated with an increase in hematocrit at all dose levels and a decrease in maternal body weight gains. Fetuses exhibited reduced body weight and delayed ossification. Soft tissue changes were limited to cardiovascular alterations in the high-dose rabbits only. Rat and rabbit fetuses were exposed to CNTO 530 in all dose groups. CONCLUSIONS: These studies show that the embryo/fetal development effects observed following CNTO 530 treatment during organogenesis are qualitatively similar to those seen with other erythropoietin agonists and are likely a secondary consequence of increased hematocrit in the dams. Unlike other erythropoietin receptor agonists, CNTO 530 was able to cross the placental barrier, which was considered likely the result of FcRn-mediated transcytosis.