Orthologue chemical space and its influence on target prediction

Mervin, Lewis; Bulusu, Krishna C.; Kalash, Leen; Afzal, Avid M.; Svensson, Fredrik; Firth, Mike; Barrett, Ian P.; Engkvist, Ola

doi:10.1093/bioinformatics/btx525

Cited by 35 publications

(29 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A possible reason behind the low performance of the TFP descriptor models is that the protein targets from PIDGIN are of human origin, and are unlikely to provide a useful representation of target interactions in P. falciparum . However, it is the case that orthologous proteins exist between Homo sapiens and P. falciparum , and it has previously been shown that the number of conflicting bioactivities between human and ortholog targets in public databases is comparatively low (Mervin et al, 2018 ), which supports the use of human targets as bioactivity spectra in this indirect manner. It has also been shown that bioactivity spectra can be used more generally as a descriptor that captures biologically relevant information, and can outperform chemical descriptors in the identification of compounds with similar bioactivities [see Petrone et al (Petrone et al, 2012 ) Bender et al (Bender et al, 2006 ), Kauvar et al (Kauvar et al, 1995 ), Riniker et al (Riniker et al, 2014 ), and Paricharak et al (Paricharak et al, 2016 )].…”

Section: Resultsmentioning

confidence: 99%

Using Machine Learning to Predict Synergistic Antimalarial Compound Combinations With Novel Structures

et al. 2018

Self Cite

View full text Add to dashboard Cite

The parasite Plasmodium falciparum is the most lethal species of Plasmodium to cause serious malaria infection in humans, and with resistance developing rapidly novel treatment modalities are currently being sought, one of which being combinations of existing compounds. The discovery of combinations of antimalarial drugs that act synergistically with one another is hence of great importance; however an exhaustive experimental screen of large drug space in a pairwise manner is not an option. In this study we apply our machine learning approach, Combination Synergy Estimation (CoSynE), which can predict novel synergistic drug interactions using only prior experimental combination screening data and knowledge of compound molecular structures, to a dataset of 1,540 antimalarial drug combinations in which 22.2% were synergistic. Cross validation of our model showed that synergistic CoSynE predictions are enriched 2.74 × compared to random selection when both compounds in a predicted combination are known from other combinations among the training data, 2.36 × when only one compound is known from the training data, and 1.5 × for entirely novel combinations. We prospectively validated our model by making predictions for 185 combinations of 23 entirely novel compounds. CoSynE predicted 20 combinations to be synergistic, which was experimentally validated for nine of them (45%), corresponding to an enrichment of 1.70 × compared to random selection from this prospective data set. Such enrichment corresponds to a 41% reduction in experimental effort. Interestingly, we found that pairwise screening of the compounds CoSynE individually predicted to be synergistic would result in an enrichment of 1.36 × compared to random selection, indicating that synergy among compound combinations is not a random event. The nine novel and correctly predicted synergistic compound combinations mainly (where sufficient bioactivity information is available) consist of efflux or transporter inhibitors (such as hydroxyzine), combined with compounds exhibiting antimalarial activity alone (such as sorafenib, apicidin, or dihydroergotamine). However, not all compound synergies could be rationalized easily in this way. Overall, this study highlights the potential for predictive modeling to expedite the discovery of novel drug combinations in fight against antimalarial resistance, while the underlying approach is also generally applicable.

show abstract

Section: Resultsmentioning

confidence: 99%

Using Machine Learning to Predict Synergistic Antimalarial Compound Combinations With Novel Structures

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…To annotate the drugs in the database with their respective protein targets, we used the rat models available in PIDGIN version 2 50 on a per-compound bases. Previous benchmarking results have shown such in silico protocols perform with an average precision and recall of ~82% and ~83%, respectively, during fivefold cross validation 20 , hence giving a reasonable likelihood that compounds predicted to bind a particular target will indeed bind to this protein, or set of proteins.…”

Section: Methodsmentioning

confidence: 99%

Systemic neurotransmitter responses to clinically approved and experimental neuropsychiatric drugs

et al. 2018

Self Cite

View full text Add to dashboard Cite

Neuropsychiatric disorders are the third leading cause of global disease burden. Current pharmacological treatment for these disorders is inadequate, with often insufficient efficacy and undesirable side effects. One reason for this is that the links between molecular drug action and neurobehavioral drug effects are elusive. We use a big data approach from the neurotransmitter response patterns of 258 different neuropsychiatric drugs in rats to address this question. Data from experiments comprising 110,674 rats are presented in the Syphad database [www.syphad.org]. Chemoinformatics analyses of the neurotransmitter responses suggest a mismatch between the current classification of neuropsychiatric drugs and spatiotemporal neurostransmitter response patterns at the systems level. In contrast, predicted drug–target interactions reflect more appropriately brain region related neurotransmitter response. In conclusion the neurobiological mechanism of neuropsychiatric drugs are not well reflected by their current classification or their chemical similarity, but can be better captured by molecular drug–target interactions.

show abstract

“…This resulted in data for 327 protein targets, which we divided into five sub-classes: nuclear receptors, GPCRs, kinases, other enzymes, and ion channels. Inactive ligands were acquired from two sources: inactive ligands labeled on PubChem indexed by UniProt Protein ID (57,58) and for targets with a DUD-E decoy set, some inactives from the DUD-E set were included (59). To ensure a reasonable balance of actives to inactives, we also added a randomly selected set of 500 decoys per run; these decoy ligands were selected to not be in any previous set of ligands, either active or inactive.…”

Section: Methods and Data Availabilitymentioning

confidence: 99%

Using Single Protein/Ligand Binding Models to Predict Active Ligands for Unseen Proteins

Sundar

Colwell

2020

Preprint

View full text Add to dashboard Cite

Machine learning models that predict which small molecule ligands bind a single protein target report high levels of accuracy for held-out test data. An important challenge is to extrapolate and make accurate predictions for new protein targets. Improvements in drug-target interaction (DTI) models that address this challenge would have significant impact on drug discovery by eliminating the need for high-throughput screening experiments against new protein targets. Here we propose a data augmentation strategy that addresses this challenge to enable accurate prediction in cases where no experimental data is available. To proceed, we first build single protein-ligand binding models and use these models to predict whether additional ligands bind to each protein. We then use these predictions to augment the experimental data, train standard DTI models, and predict interactions between unseen test proteins and ligands. This approach achieves Area Under the Receiver Operator Characteristic (AUC) > 0.9 consistently on test sets consisting exclusively of proteins and ligands for which the model is given no experimental data. We verify that performance improvements extend to held-out test proteins distant from the training set. Our data augmentation framework can be applied to any DTI model, and enhances performance on a range of simple models.

show abstract

Orthologue chemical space and its influence on target prediction

Cited by 35 publications

References 25 publications

Using Machine Learning to Predict Synergistic Antimalarial Compound Combinations With Novel Structures

Using Machine Learning to Predict Synergistic Antimalarial Compound Combinations With Novel Structures

Systemic neurotransmitter responses to clinically approved and experimental neuropsychiatric drugs

Using Single Protein/Ligand Binding Models to Predict Active Ligands for Unseen Proteins

Contact Info

Product

Resources

About