Machine Learning and Pharmacometrics for Prediction of Pharmacokinetic Data: Differences, Similarities and Challenges Illustrated with Rifampicin.

Pharmacometrics (PM) and machine learning (ML) are both valuable for drug development to characterize pharmacokinetics (PK) and pharmacodynamics (PD). Pharmacokinetic/pharmacodynamic (PKPD) analysis using PM provides mechanistic insight into biological processes but is time- and labor-intensive. In contrast, ML models are much quicker trained, but offer less mechanistic insights. The opportunity of using ML predictions of drug PK as input for a PKPD model could strongly accelerate analysis efforts. Here exemplified by rifampicin, a widely used antibiotic, we explore the ability of different ML algorithms to predict drug PK. Based on simulated data, we trained linear regressions (LASSO), Gradient Boosting Machines, XGBoost and Random Forest to predict the plasma concentration-time series and rifampicin area under the concentration-versus-time curve from 0-24 h (AUC0-24h) after repeated dosing. XGBoost performed best for prediction of the entire PK series (R2: 0.84, root mean square error (RMSE): 6.9 mg/L, mean absolute error (MAE): 4.0 mg/L) for the scenario with the largest data size. For AUC0-24h prediction, LASSO showed the highest performance (R2: 0.97, RMSE: 29.1 h·mg/L, MAE: 18.8 h·mg/L). Increasing the number of plasma concentrations per patient (0, 2 or 6 concentrations per occasion) improved model performance. For example, for AUC0-24h prediction using LASSO, the R2 was 0.41, 0.69 and 0.97 when using predictors only (no plasma concentrations), 2 or 6 plasma concentrations per occasion as input, respectively. Run times for the ML models ranged from 1.0 s to 8 min, while the run time for the PM model was more than 3 h. Furthermore, building a PM model is more time- and labor-intensive compared with ML. ML predictions of drug PK could thus be used as input into a PKPD model, enabling time-efficient analysis.

Molecular optimization by capturing chemist's intuition using deep neural networks.

A main challenge in drug discovery is finding molecules with a desirable balance of multiple properties. Here, we focus on the task of molecular optimization, where the goal is to optimize a given starting molecule towards desirable properties. This task can be framed as a machine translation problem in natural language processing, where in our case, a molecule is translated into a molecule with optimized properties based on the SMILES representation. Typically, chemists would use their intuition to suggest chemical transformations for the starting molecule being optimized. A widely used strategy is the concept of matched molecular pairs where two molecules differ by a single transformation. We seek to capture the chemist's intuition from matched molecular pairs using machine translation models. Specifically, the sequence-to-sequence model with attention mechanism, and the Transformer model are employed to generate molecules with desirable properties. As a proof of concept, three ADMET properties are optimized simultaneously: logD, solubility, and clearance, which are important properties of a drug. Since desirable properties often vary from project to project, the user-specified desirable property changes are incorporated into the input as an additional condition together with the starting molecules being optimized. Thus, the models can be guided to generate molecules satisfying the desirable properties. Additionally, we compare the two machine translation models based on the SMILES representation, with a graph-to-graph translation model HierG2G, which has shown the state-of-the-art performance in molecular optimization. Our results show that the Transformer can generate more molecules with desirable properties by making small modifications to the given starting molecules, which can be intuitive to chemists. A further enrichment of diverse molecules can be achieved by using an ensemble of models.

PTEN Expression in Human Granulosa Cells Is Associated with Ovarian Responses and Clinical Outcomes in IVF.

The ovarian reserve determines the success of in vitro fertilization (IVF) and embryo transfer treatment. It predicts the ovarian response in controlled ovarian hyperstimulation cycles. Apoptosis in granulosa cells surrounding oocytes is important for ovarian function and has been closely associated with follicular atresia. PTEN (encoding phosphatase and tensin homolog) is a well-known tumor suppressor gene that functions as a mediator of apoptosis and is crucial for mammal reproduction. In the present study, we analyzed the expression level of PTEN in human granulosa cells and aimed to investigate its association with the ovarian response and clinical outcomes in IVF. Apoptosis in granulosa cells were analyzed using Annexin V-Allophycocyanin staining after PTEN short hairpin RNA lentivirus transfection. Real-time fluorescent quantitative PCR analysis showed that the PTEN transcript level was significantly higher in poor responders and significantly lower in high responders, compared with that in normal responders. However, PTEN expression in the pregnancy group decreased slightly, but not significantly, compared with that in the non-pregnancy group. The apoptosis rate of granulosa cells declined significantly after 24-h transfection of the PTEN-shRNA lentivirus. These results suggest a fundamental role of PTEN in the regulation of follicular development, and that it might be involved in the pathogenesis of follicular dysplasia and ovarian dysfunction.