A Machine Learning Model to Predict Drug Transfer Across the Human Placenta Barrier

Filippo, Juan I. Di; Bollini, Mariela; Cavasotto, Claudio N.

doi:10.3389/fchem.2021.714678

Cited by 16 publications

(16 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another interesting work was presented by Di Filippo et al in 2021 where a low-dimensional ML model was developed for classifying compounds according to whether they can cross or not the placental barrier, helping to develop safe therapeutic options for pregnancy. 83 A data set of 248 molecules was constructed, and a genetic algorithm was used to perform feature selection from an initial group of 5,400 descriptors. A linear discriminant analysis (LDA) model trained with only four features achieved the best results, having only one false positive case across all testing folds.…”

Section: General Toxicity Predictionmentioning

confidence: 99%

Machine Learning Toxicity Prediction: Latest Advances by Toxicity End Point

Cavasotto

Scardino

2022

ACS Omega

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) models to predict the toxicity of small molecules have garnered great attention and have become widely used in recent years. Computational toxicity prediction is particularly advantageous in the early stages of drug discovery in order to filter out molecules with high probability of failing in clinical trials. This has been helped by the increase in the number of large toxicology databases available. However, being an area of recent application, a greater understanding of the scope and applicability of ML methods is still necessary. There are various kinds of toxic end points that have been predicted in silico. Acute oral toxicity, hepatotoxicity, cardiotoxicity, mutagenicity, and the 12 Tox21 data end points are among the most commonly investigated. Machine learning methods exhibit different performances on different data sets due to dissimilar complexity, class distributions, or chemical space covered, which makes it hard to compare the performance of algorithms over different toxic end points. The general pipeline to predict toxicity using ML has already been analyzed in various reviews. In this contribution, we focus on the recent progress in the area and the outstanding challenges, making a detailed description of the state-of-the-art models implemented for each toxic end point. The type of molecular representation, the algorithm, and the evaluation metric used in each research work are explained and analyzed. A detailed description of end points that are usually predicted, their clinical relevance, the available databases, and the challenges they bring to the field are also highlighted.

show abstract

Section: General Toxicity Predictionmentioning

confidence: 99%

Machine Learning Toxicity Prediction: Latest Advances by Toxicity End Point

Cavasotto

Scardino

2022

ACS Omega

Self Cite

View full text Add to dashboard Cite

show abstract

“…[16,136,137] While in vitro models and other placenta-on-chip models could provide basic details on this aspect, complete knowledge of the translocation and uptake of existing NPs is still largely unknown. One way to work toward this would be to employ several toxicity applications like the use of machine learning (ML) [138,139] and artificial intelligence (AI) [140,141] to identify the structure-activity relationships. Data from these can be coupled with in vitro, continuous placenta-on-chip models and ex vivo models.…”

Section: Placenta-on-chip and Organoidsmentioning

confidence: 99%

Perspectives on the Technological Aspects and Biomedical Applications of Virus‐Like Particles/Nanoparticles in Reproductive Biology: Insights on the Medicinal and Toxicological Outlook

Chandrasekar

Singh

Maharjan

et al. 2022

Advanced NanoBiomed Research

View full text Add to dashboard Cite

Increasing data on the infection indicate that maternal infections are severe. Under the realms of vaccine development, virus‐like particles (VLP)/nanoparticles (NPs) hold the promise of targeted control of therapeutics transfer across the placental barrier with the potential to trigger innate immune responses. Though the placenta is known to act as a barrier against exogenous materials, viruses exploit the transport systems and overcome the barrier properties. VLPs can be strategically designed to obtain the necessary mechanisms for navigation across the placenta and immune response. However, several knowledge gaps on the chemical, viral transmission strategies and the host defense response exist owing to the highly dynamic etiology of the placental barrier. This further complicates the toxicological analysis of the developed therapeutics. Herein, placental physiology and functions are discussed in significance with chemical toxicology, viral infections, and the host defense. Further, the promising applications of VLPs and perspective on their design to overcome the placental gatekeeper to gain the necessary immune response or therapy are provided. Finally, a holistic approach to various bioengineering models for studying chemical toxicants, viral infections, and effects of VLPs is provided to facilitate better translation of these VLPs to clinical applications.

show abstract

“…For example, we ranked the likelihood of all included compounds and drugs to cross the placental barrier and to cause birth defects using an unsupervised machine learning approach. To achieve this, we first identified a list of 248 drugs that are known to cross the placenta [45], and lists of FDA approved drugs classified in the X (n=60) and D categories (n=112). We then mapped these drugs to all the drugs and small molecules profiled by the LINCS L1000 assay (Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Using unsupervised learning we generated placental crossing scores and D and X category scores for all FDA-approved and preclinical compounds profiled by LINCS that are included in the ReproTox KG. To obtain true positives for placental crossing, we first extracted the list of 248 compounds assembled by Di Filippo et al [45]. Category D and X drugs were obtained from DrugCentral [23] and Drugs.com [46], and drugs were filtered by those which could be mapped to the LINCS compounds.…”

Section: Placental Crossing and D And X Category Predictions For Smal...mentioning

confidence: 99%

See 1 more Smart Citation

ReproTox-KG: Toxicology Knowledge Graph for Structural Birth Defects

Evangelista

Clarke

Xie

et al. 2022

Preprint

View full text Add to dashboard Cite

Birth defects are functional and structural abnormalities that impact 1 in 33 births in the United States. Birth defects have been attributed to genetic as well as other factors, but for most birth defects there are no known causes. Small molecule drugs, cosmetics, foods, and environmental pollutants may cause birth defects when the mother is exposed to them during pregnancy. These molecules may interfere with the process of normal fetal development. To characterize associations between small molecule compounds and their potential to induce specific birth abnormalities, we gathered knowledge from multiple sources to construct a reproductive toxicity Knowledge Graph (ReproTox-KG) with an initial focus on associations between birth defects, drugs, and genes. Specifically, to construct ReproTox-KG we gathered data from drug/birth-defect associations from co-mentions in published abstracts, gene/birth-defect associations from genetic studies, drug- and preclinical-compound-induced gene expression data, known drug targets, genetic burden scores for all human genes, and placental crossing scores for all small molecules in ReproTox-KG. Using the data stored within ReproTox-KG, we scored 30,000 preclinical small molecules for their potential to induce birth defects. Querying the ReproTox-KG, we identified over 500 birth-defect/gene/drug cliques that can be used to explain molecular mechanisms for drug-induced birth defects. The ReproTox-KG is provided as curated tables and via a web-based user interface that can enable users to explore the associations between birth defects, approved and preclinical drugs, and human genes.

show abstract

A Machine Learning Model to Predict Drug Transfer Across the Human Placenta Barrier

Cited by 16 publications

References 26 publications

Machine Learning Toxicity Prediction: Latest Advances by Toxicity End Point

Machine Learning Toxicity Prediction: Latest Advances by Toxicity End Point

Perspectives on the Technological Aspects and Biomedical Applications of Virus‐Like Particles/Nanoparticles in Reproductive Biology: Insights on the Medicinal and Toxicological Outlook

ReproTox-KG: Toxicology Knowledge Graph for Structural Birth Defects

Contact Info

Product

Resources

About