Monte Carlo Thompson sampling-guided design for antibody engineering.

Antibodies are one of the predominant treatment modalities for various diseases. To improve the characteristics of a lead antibody, such as antigen-binding affinity and stability, we conducted comprehensive substitutions and exhaustively explored their sequence space. However, it is practically unfeasible to evaluate all possible combinations of mutations owing to combinatorial explosion when multiple amino acid residues are incorporated. It was recently reported that a machine-learning guided protein engineering approach such as Thompson sampling (TS) has been used to efficiently explore sequence space in the framework of Bayesian optimization. For TS, over-exploration occurs when the initial data are biasedly distributed in the vicinity of the lead antibody. We handle a large-scale virtual library that includes numerous mutations. When the number of experiments is limited, this over-exploration causes a serious issue. Thus, we conducted Monte Carlo Thompson sampling (MTS) to balance the exploration-exploitation trade-off by defining the posterior distribution via the Monte Carlo method and compared its performance with TS in antibody engineering. Our results demonstrated that MTS largely outperforms TS in discovering desirable candidates at an earlier round when over-exploration occurs on TS. Thus, the MTS method is a powerful technique for efficiently discovering antibodies with desired characteristics when the number of rounds is limited.

Digital workflows for pathological assessment of rat estrous cycle stage using images of uterine horn and vaginal tissue.

Assessment of the estrous cycle of mature female mammals is an important component of verifying the efficacy and safety of drug candidates. The common pathological approach of relying on expert observation has several drawbacks, including laborious work and inter-viewer variability. The recent advent of image recognition technologies using deep learning is expected to bring substantial benefits to such pathological assessments. We herein propose 2 distinct deep learning-based workflows to classify the estrous cycle stage from tissue images of the uterine horn and vagina, respectively. These constructed models were able to classify the estrous cycle stages with accuracy comparable with that of expert pathologists. Our digital workflows allow efficient pathological assessments of the estrous cycle stage in rats and are thus expected to accelerate drug research and development.

A novel therapeutic approach for thrombocytopenia by minibody agonist of the thrombopoietin receptor.

Antibodies have brought valuable therapeutics in the clinical treatment of various diseases without serious adverse effects through their intrinsic features such as specific binding to the target antigen with high affinity, clinical safety as serum proteins, and long half-life. Agonist antibodies, furthermore, could be expected to maximize the value of therapeutic antibodies. Indeed, several IgG/IgM antibodies have been reported to induce cellular growth/differentiation and apoptosis. These agonist antibodies, however, should be further improved to exert more potent biologic activities and appropriate serum half-life depending upon the disease indications. Here, we report that IgG antibodies against the thrombopoietin receptor (Mpl), which have an absence or very weak agonist activity, can be engineered to be agonist minibodies, which include diabody or sc(Fv)2 as potent as natural ligand. Through this technological development, minibodies have been successfully constructed to bind and activate 2 types of dysfunctional mutant Mpls that cause congenital amegakaryocytic thrombocytopenia (CAMT). This drastic conversion of biologic activities by designing minibodies can be widely applicable to generate agonist minibodies for clinical application, which will constitute a new paradigm in antibody-based therapeutics.