Evaluating the effect of SARS-CoV-2 spike mutations with a linear doubly robust learner.

Driven by various mutations on the viral Spike protein, diverse variants of SARS-CoV-2 have emerged and prevailed repeatedly, significantly prolonging the pandemic. This phenomenon necessitates the identification of key Spike mutations for fitness enhancement. To address the need, this manuscript formulates a well-defined framework of causal inference methods for evaluating and identifying key Spike mutations to the viral fitness of SARS-CoV-2. In the context of large-scale genomes of SARS-CoV-2, it estimates the statistical contribution of mutations to viral fitness across lineages and therefore identifies important mutations. Further, identified key mutations are validated by computational methods to possess functional effects, including Spike stability, receptor-binding affinity, and potential for immune escape. Based on the effect score of each mutation, individual key fitness-enhancing mutations such as D614G and T478K are identified and studied. From individual mutations to protein domains, this paper recognizes key protein regions on the Spike protein, including the receptor-binding domain and the N-terminal domain. This research even makes further efforts to investigate viral fitness via mutational effect scores, allowing us to compute the fitness score of different SARS-CoV-2 strains and predict their transmission capacity based solely on their viral sequence. This prediction of viral fitness has been validated using BA.2.12.1, which is not used for regression training but well fits the prediction. To the best of our knowledge, this is the first research to apply causal inference models to mutational analysis on large-scale genomes of SARS-CoV-2. Our findings produce innovative and systematic insights into SARS-CoV-2 and promotes functional studies of its key mutations, serving as reliable guidance about mutations of interest.

Tailoring Combinational Therapy with Monte Carlo Method-based Regression Modeling

Combinatorial drug therapies are generally more effective than monotherapies in treating viral infections. However, it is critical for dose optimization to maximize the efficacy and minimize side effects. Although various strategies have been deviseenchmark functions is available at Github repositoryd to accelerate the optimization process, their efficiencies were limited by the high noises and suboptimal reproducibility of biological assays. With conventional methods, variances among the replications are used to evaluate the errors of the readouts alone rather than actively participating in the optimization. Herein, we present the Regression Modeling Enabled by Monte Carlo Method (ReMEMC) algorithm for rapid identification of effective combinational therapies. ReMEMC transforms the sample variations into probability distributions of the regression coefficients and predictions. In silico simulations revealed that ReMEMC outperformed conventional regression methods in benchmark problems, and demonstrated its superior robustness against experimental noises. Using COVID-19 as a model disease, ReMEMC successfully identified an optimal 3-drug combination among 10 anti-SARS-CoV-2 drug compounds within two rounds of experiments. The optimal combination showed 2-log and 3-log higher load reduction than non-optimized combinations and monotherapy, respectively. Further workflow refinement allowed identification of personalized drug combinational therapies within 5 days. The strategy may serve as an efficient and universal tool for dose combination optimization.

Project IDentif.AI: Harnessing Artificial Intelligence to Rapidly Optimize Combination Therapy Development for Infectious Disease Intervention.

In 2019/2020, the emergence of coronavirus disease 2019 (COVID-19) resulted in rapid increases in infection rates as well as patient mortality. Treatment options addressing COVID-19 included drug repurposing, investigational therapies such as remdesivir, and vaccine development. Combination therapy based on drug repurposing is among the most widely pursued of these efforts. Multi-drug regimens are traditionally designed by selecting drugs based on their mechanism of action. This is followed by dose-finding to achieve drug synergy. This approach is widely-used for drug development and repurposing. Realizing synergistic combinations, however, is a substantially different outcome compared to globally optimizing combination therapy, which realizes the best possible treatment outcome by a set of candidate therapies and doses toward a disease indication. To address this challenge, the results of Project IDentif.AI (Identifying Infectious Disease Combination Therapy with Artificial Intelligence) are reported. An AI-based platform is used to interrogate a massive 12 drug/dose parameter space, rapidly identifying actionable combination therapies that optimally inhibit A549 lung cell infection by vesicular stomatitis virus within three days of project start. Importantly, a sevenfold difference in efficacy is observed between the top-ranked combination being optimally and sub-optimally dosed, demonstrating the critical importance of ideal drug and dose identification. This platform is disease indication and disease mechanism-agnostic, and potentially applicable to the systematic N-of-1 and population-wide design of highly efficacious and tolerable clinical regimens. This work also discusses key factors ranging from healthcare economics to global health policy that may serve to drive the broader deployment of this platform to address COVID-19 and future pandemics.