Dose-Dependent Teratology in Humans: Clinical Implications for Prevention

Machine Learning to Predict Teratogenicity: Theory and Practice

Machine learning (ML) is a subfield of artificial intelligence (AI) that consists of developing algorithms that can automatically learn patterns and relationships from data, without being explicitly programmed. It continues to advance with the development of more sophisticated algorithms, increased computational power, and larger datasets, leading to significant advancements in AI technology. With the significant progress made in ML, the need to apply these systems in the area of teratogenicity is growing. It is sought as robust boosting methods to overcome many limitations and restrictions facing the experimental studies. By performing tasks such as classification, regression, clustering, anomaly detection, and decision systems, ML can be used to assess whether an agent is teratogen or not or to determine its teratogenic potential. It may also be used for the purpose of deciding on the use of medicinal products. In this chapter, we describe how ML can be used to investigate teratogenicity.

Kinetic modeling of stem cell transcriptome dynamics to identify regulatory modules of normal and disturbed neuroectodermal differentiation

Thousands of transcriptome data sets are available, but approaches for their use in dynamic cell response modelling are few, especially for processes affected simultaneously by two orthogonal influencing variables. We approached this problem for neuroepithelial development of human pluripotent stem cells (differentiation variable), in the presence or absence of valproic acid (signaling variable). Using few basic assumptions (sequential differentiation states of cells; discrete on/off states for individual genes in these states), and time-resolved transcriptome data, a comprehensive model of spontaneous and perturbed gene expression dynamics was developed. The model made reliable predictions (average correlation of 0.85 between predicted and subsequently tested expression values). Even regulations predicted to be non-monotonic were successfully validated by PCR in new sets of experiments. Transient patterns of gene regulation were identified from model predictions. They pointed towards activation of Wnt signaling as a candidate pathway leading to a redirection of differentiation away from neuroepithelial cells towards neural crest. Intervention experiments, using a Wnt/beta-catenin antagonist, led to a phenotypic rescue of this disturbed differentiation. Thus, our broadly applicable model allows the analysis of transcriptome changes in complex time/perturbation matrices.

Relation of in-utero exposure to antiepileptic drugs to pregnancy duration and size at birth

BACKGROUND

The associations of individual antiepileptic drugs (AEDs) with pregnancy duration and size at birth, and potential dose relations, are not well characterized.

METHODS

This cohort study used nationwide Swedish register data (1996-2013). Adjusting for smoking, epilepsy and other AED indications, we used linear and quantile regression to explore associations with pregnancy duration, and birth weight, length, and head circumference (the last three operationalized as z-scores). We used logistic regression for preterm delivery, small for gestational age, and microcephaly. Lamotrigine was the reference drug.

RESULTS

6,720 infants were exposed to AEDs in utero; AED exposure increased over the study period. Relative to lamotrigine-exposed infants, carbamazepine-exposed infants were born, on average, 1.3 days earlier (mean [95% confidence interval]: -1.3 [-2.3 to -0.3]); were 0.1 standard deviations (SDs) lighter (-0.1 [-0.2 to 0.0]); and had a head circumference that was 0.2 SDs smaller (-0.2 [-0.3 to -0.1]). Pregabalin-exposed infants were born, on average, 1.1 days earlier (-1.1 [-3.0 to 0.8]); were 0.1 SDs lighter (-0.1 [-0.3 to 0.0]); and had the same head circumference as lamotrigine-exposed infants. Levetiracetam-exposed infants were born, on average, 0.5 days earlier (-0.5 [-2.6 to 1.6]); were 0.1 SDs lighter (-0.1 [-0.3 to 0.0]); and had a head circumference 0.1 SDs smaller (-0.1 [-0.3 to 0.1]). Valproic acid-exposed infants had, on average, the same duration of gestation and birth weight z-score as lamotrigine-exposed infants, but had a head circumference 0.2 SDs smaller (-0.2 [-0.2 to -0.1]). Associations between carbamazepine exposure and pregnancy duration and between valproic acid exposure and pregnancy duration and birth weight z-score were more negative at the left than at the right tails of the outcome distributions. Effect-measure modification and dose-response relations were noted for some of the associations.

CONCLUSIONS

Relative to lamotrigine, valproic acid and carbamazepine were associated with smaller head circumference.