Prediction of novel mouse TLR9 agonists using a random forest approach

Abstract

BackgroundToll-like receptor 9 is a key innate immune receptor involved in detecting infectious diseases and cancer. TLR9 activates the innate immune system following the recognition of single-stranded DNA oligonucleotides (ODN) containing unmethylated cytosine-guanine (CpG) motifs. Due to the considerable number of rotatable bonds in ODNs, high-throughput in silico screening for potential TLR9 activity via traditional structure-based virtual screening approaches of CpG ODNs is challenging. In the current study, we present a machine learning based method for predicting novel mouse TLR9 (mTLR9) agonists based on features including count and position of motifs, the distance between the motifs and graphically derived features such as the radius of gyration and moment of Inertia. We employed an in-house experimentally validated dataset of 396 single-stranded synthetic ODNs, to compare the results of five machine learning algorithms. Since the dataset was highly imbalanced, we used an ensemble learning approach based on repeated random down-sampling.ResultsUsing in-house experimental TLR9 activity data we found that random forest algorithm outperformed other algorithms for our dataset for TLR9 activity prediction. Therefore, we developed a cross-validated ensemble classifier of 20 random forest models. The average Matthews correlation coefficient and balanced accuracy of our ensemble classifier in test samples was 0.61 and 80.0%, respectively, with the maximum balanced accuracy and Matthews correlation coefficient of 87.0% and 0.75, respectively. We confirmed common sequence motifs including ‘CC’, ‘GG’,‘AG’, ‘CCCG’ and ‘CGGC’ were overrepresented in mTLR9 agonists. Predictions on 6000 randomly generated ODNs were ranked and the top 100 ODNs were synthesized and experimentally tested for activity in a mTLR9 reporter cell assay, with 91 of the 100 selected ODNs showing high activity, confirming the accuracy of the model in predicting mTLR9 activity.ConclusionWe combined repeated random down-sampling with random forest to overcome the class imbalance problem and achieved promising results. Overall, we showed that the random forest algorithm outperformed other machine learning algorithms including support vector machines, shrinkage discriminant analysis, gradient boosting machine and neural networks. Due to its predictive performance and simplicity, the random forest technique is a useful method for prediction of mTLR9 ODN agonists.

An Advax-CpG55.2™ adjuvanted recombinant spike protein vaccine protects cynomolgus macaques from a homologous SARS-CoV-2 virus challenge

“…Advax-CpG55.2™ is a new polysaccharide adjuvant formulation where the CpG55.2 component was developed through artificial intelligence, with machine learning being used to screen large numbers of oligonucleotides for human TLR9 agonist activity [30] . This NHP protection data further supports the efficacy and safety of this Advax-CpG55.2™ adjuvanted recombinant spike protein ECD vaccine as also demonstrated in ferret [11] and hamster [22] models.…”

Multiple Factors Determine the Oncolytic or Carcinogenic Effects of TLRs Activation in Cancer

“…These were then synthesized and tested in the laboratory. Ninety-one of the 100 ODNs displayed high activity with TLR9 [189]. The algorithm used is shown in Figure 6.…”

Review: Current trends, challenges, and success stories in adjuvant research

“…A remarkable success story of in silico adjuvant screening, albeit not of a small molecule adjuvant, is the discovery of novel CpG ODN sequences. In the absence of a full crystal structure of the receptor, a hypothetical structure of TLR9 was used for the in silico high-throughput screening campaign (17). This approach yielded CpG55.2, a multi-species active TLR9 adjuvant that acts synergistically with the carbohydrate Advax 7 in Advax/CpG55.2 8 , that is used in the COVID vaccine Spikogen/ Covax-19 (18).…”