Pankaj Aggarwal

Liquid chromatography is a cornerstone analytical technique for separating, quantifying, and purifying components from complex mixtures. To accelerate method screening, we herein introduce an uncertainty-aware graph-based neural network that predicts retention times across multiple column chemistries and buffer pH conditions. Specifically, the multiple condition retention time model, MC-Retention, incorporates explicit column and buffer descriptors and is trained on a newly assembled data set produced by screening 480 analytes under eight chromatography conditions. By being able to accurately model multiple chromatographic methods simultaneously, MC-Retention can substantially reduce the time and resources required for LC method screening and development. With an aggregate R² of 0.86 and a mean absolute error (MAE) of 15.5 s during cross-validation, MC-Retention's respectable performance is greatly enhanced for analytes made present during training for one of the four column chemistries, when those analytes are otherwise not associated with the columns being validated. This selective training of analytes for a single column chemistry reduces error by 50%, with an R² of 0.95 and MAE of 8.2 s in aggregate. Additionally, we demonstrate that MC-Retention effectively identifies optimal conditions for separating amide bond-forming reaction components, while also supplying calibrated uncertainty estimates for its retention time predictions.

Liquid chromatography is a cornerstone analytical technique for separating, quantifying, and purifying components from complex mixtures. To accelerate method screening, an uncertainty-aware graph-based neural network that predicts retention times across multiple column chemistries and buffer pH conditions is herein introduced. Specifically, the Multiple Condition Retention time model, MC-Retention, incorporates explicit column and buffer descriptors and is trained on a newly assembled dataset produced by screening 480 analytes under eight chromatography conditions. By being able to accurately model multiple chromatographic methods simultaneously, MC-Retention can substantially reduce the time and resources required for LC method screening and development. With an aggregate R2 of 0.86 and MAE of 15.5 seconds during cross validation, MC-Retention's respectable performance is greatly enhanced for analytes made present during training for one the four column chemistries when those analytes are otherwise not associated the columns being validated. This selective training of analytes for a single column chemistry reduces error by 50%, with an R2 of 0.95 and MAE of 8.2 seconds in aggregate. Additionally, we demonstrate that MC Retention effectively identifies optimal conditions for separating peptide coupling reaction components, while also suppling calibrated uncertainty estimates for its retention time predictions.

The design‐make‐test cycle for drug discovery is highly dependent on the purification of synthesized compounds. Prior to evaluation of suitability, ultrahigh‐performance liquid chromatography is used for an initial standard analysis, where retention times of analytes are measured with a shorter standard gradient method and used to select the appropriate gradients for a final purification method. To circumvent this preliminary screening experiment for small molecule libraries, retention time prediction had been achieved previously by the use of commercial modeling methods. However, these retention time prediction models can have limited applicability when built from smaller datasets and are less effective when constructed from disparate data collected under differing chromatography conditions. Having thousands of measured retention times from high‐throughput physiochemical screening, we sought to leverage these data for the construction of predictive models for a standard preliminary method enabling high‐throughput purification of macrocyclic peptide libraries. Utilizing 4549 analytes and their retention times from high‐throughput physiochemical screening, a structure‐to‐retention‐time model was built using a graph isomorphism network, a form of artificial neural network architecture. Once fitted to high‐throughput screening data, the model was re‐trained with standard gradient method data, a technique known as transfer learning. Through transfer learning, a training set of 80 analytes yielded a neural network model that, when evaluated against a test set of 24 analytes, displays high performance metrics with a coefficient of determination ( R ² ) of 0.82 and mean average error of 0.088 min, or 1.26% of the gradient time. Comparatively, the best commercial quantitative structure‐retention relationship model poorly performed, with an R ² of 0.11 and mean average error of 0.202 min. This model has been deployed internally as a Dash app to help democratize the use of the developed models and is being used for selecting purification methods based on analyte structure.

The design-make-test cycle for drug discovery is highly dependent on the purification of synthesized compounds. Prior to evaluation of suitability, ultrahigh performance liquid chromatography is used for an initial standard analysis, where retention times of analytes are measured with a shorter standard gradient method and used to select the appropriate gradients for a final purification method. To circumvent this preliminary screening experiment for small molecule libraries, retention time prediction had been achieved previously by use of commercial modeling methods. However, these retention time prediction models can have limited applicability when built from smaller datasets and are less effective when constructed from disparate data collected under differing chromatography conditions. Having thousands of measured retention times from high-throughput physiochemical screening, we sought to leverage these data for the construction of predictive models for a standard preliminary method enabling high-throughput purification of macrocyclic peptide libraries. Utilizing 4549 analytes and their retention times from high-throughput physiochemical screening, a structure to retention time model was built using a graph invariant network, a form of artificial neural network architecture. Once fitted to high-throughput screening data, the model was re-trained with standard gradient method data, a technique known as transfer learning. Through transfer learning, a training set of 80 analytes yielded a neural network model, that when evaluated against a test set of 24 analytes, displays high performance metrics with a coefficient of determination (R2) of 0.82 and mean average error of 0.088 minutes, or 1.26% of the gradient time. This model has been deployed internally as a dash-app to help democratize the use of the developed models and is being used for selecting purification methods based on analyte structure.

The screening of chemical libraries is an essential starting point in the drug discovery process. While some researchers desire a more thorough screening of drug targets against a narrower scope of molecules, it is not uncommon for diverse screening sets to be favored during early stages of drug discovery. However, a cost burden is associated with the screening of molecules, with potential drawbacks if particular areas of chemical space are needlessly over represented. To facilitate triaged sampling of chemical libraries and other collections of molecules, we have developed Dedenser, a tool for the downsampling of chemical clusters. Dedenser functions by reducing the membership of clusters within chemical point clouds while maintaining the initial topology, or distribution, in chemical space. Dedenser is a Python package that utilizes Hierarchical Density-Based Spatial Clustering of Applications with Noise to first identify clusters present in 3D chemical point clouds, and then downsamples by applying Poisson disk sampling to clusters based on either their volume or density in chemical space. A command line interface tool is available with Dedenser, which allows for generation of chemical point clouds, using Mordred for QSAR descriptor calculations and uniform manifold approximation and projection for 3D embedding, as well as visualization. We hope that Dedenser will serve the community by enabling quick access to reduced collections of molecules that are representative of larger sets, selecting even distributions of molecules within clusters rather than single representative molecules.

The growing use of adjuvants in the fast-paced formulation of new vaccines has created an unprecedented need for meaningful analytical assays that deliver reliable quantitative data from complex adjuvant and adjuvant-antigen mixtures. Due to their complex chemical and physical properties, method development for the separation of vaccine adjuvants is considered a highly challenging and laborious task. Reversed-phase liquid chromatography (RPLC) is among the most important tests in the (bio)pharmaceutical industry for release and stability indicating measurements including adjuvant content, identity, and purity profile. However, the time constraints of developing “on-demand” robust quantitative methods prior to each change in formulation can easily lead to sample analysis becoming a bottleneck in vaccine development. Herein a simple and efficient generic analytical framework capable of chromatographically resolving the most commonly used non-aluminum based adjuvants across academic and industrial sectors is introduced. This was designed to seek a more proactive approach for fast-paced assay development endeavors that evolved from extensive stationary phase screening in conjunction with multifactorial in silico simulations of adjuvant retention time (RT) as a function of gradient time, temperature, organic modifier blending, and buffer concentration. The multifactorial retention models yield 3D resolution maps with excellent baseline separation of all adjuvants in a single run, which was found to be very accurate, with differences between experimental and simulated retention times of less than 1%. The analytical framework described here also includes the introduction of a more versatile approach to method development by introducing a dynamic RT database for adjuvants covering the entire library of adjuvants with broad mechanisms of action across numerous vaccine formulations with excellent linearity, accuracy, precision, and specificity. The power of this framework was also demonstrated with numerous analytical assays that can be generated rapidly from simulations guiding vaccine processes in the development of new adjuvant formulations. Analytical assay in this work covers content, purity profile by RPLC-UV-CAD, and component identification (RPLC-MS) across complex vaccine formulations, including the use of surfactants (e.g., polysorbates), as well as their separation from adjuvant targets.

Purpose Significant resources are spent on developing robust liquid chromatography (LC) methods with optimum conditions for all project in the pipeline. Although, data-driven computer assisted modelling has been implemented to shorten the method development timelines, these modelling approaches require project-specific screening data to model retention time (RT) as function of method parameters. Sometimes method re-development is required, leading to additional investments and redundant laboratory work. Cheminformatics techniques have been successfully used to predict the RT of metabolites & other component mixtures for similar use cases. Here we will show that these techniques can be used to model structurally diverse molecules and predictions of these models trained on multiple LC conditions can be used for downstream data-driven modelling. Methods The Molecular Operating Environment (MOE) was used to calculate over 800 descriptors using the strucutres of the analytes. These descriptors were used to model the RT of the analytes under four chromatographic conditions. These models were then used to create data-driven models using LC-SIM. Results A structural-based Random Forest (RF) model outperformed other techniques in cross-validation studies and predicted the RTs of a randomized test set with a median percentage error less than 4% for all LC conditions. RTs predicted by this structure-based model were used to fit a data-driven model that identifies optimum LC conditions without any additional experimental work. Conclusions These results show that small training sets yield pharmaceutically relevant models when used in a combination of structure-based and data-driven model.