There are over 7000 known rare diseases. Each one afects fewer than 1 in 2000 individuals, but collectively, they afect approximately 10% of the European and American populations. Developing treatment options for rare diseases is essential for those with such conditions, but as drug development is a time-consuming and costly process, developing new treatments is not often economically viable. The result is that fewer than 6% of rare disease have approved treatment options. The rare disease research community are adopting new approaches to this problem, where the focus is not on developing novel treatments, but on identifying approved drugs which could be repurposed to treat other conditions. These computational drug repurposing approaches require data and knowledge integration, to establish links between diseases, their symptoms, associated genes and drugs. Representing these concepts and relationships as a knowledge graph of machine-readable nodes and edges, enables predictions to be made about missing edges that may represent new drug target interactions.
Rare diseases are low-prevalent disorders caused by pathogenic mutations or harmful
environmental factors that can have chronic, debilitating, or life-threatening efects [
Drug repurposing is the process of identifying for an already approved or investigational
drug a new use outside the scope of the original medical indication. For example, a drug could
be repurposed for a diferent disease, based on the knowledge that drugs target particular
pathways and disease mechanisms that may be shared by multiple diseases [
The landscape of biomedical information resources is heterogeneous and broad, yet most
current methods for predicting DTIs are limited to homogeneous networks or bipartite models,
failing to account for the intricate relationships among diverse data sources [
The drug repurposing workflow generalises to any rare disease, but as a proof-of-concept,
we focus on Huntington’s disease (HD). HD is a rare neurodegenerative disorder of the central
nervous system characterized by dementia, involuntary movements due to the movement
disorder chorea and behavioural and psychiatric disturbances [
We present the automated data mining workflow as a web application, using Flask, which makes the workflow accessible for researchers with no technical expertise. The Python code for running this app is accessible as a Docker container, available at https://github.com/carmenreep/ DrugRepurposing, which runs on a laptop with minimal specifications (at least CPU 2.80 GHz).
Figure 1 provides an overview of the proposed drug repurposing workflow. The workflow comprises four main steps: (1) creation of the knowledge graph, (2) embedding of the graph, (3) creation of edge representations, and (4) training of a supervised machine learning model. Besides finding missing edges (potential DTIs) in the knowledge graph, the machine learning model also predicts the interaction types of these missing edges. Good embeddings for this link prediction task were achieved through enriched information on the drugs and target sites.
To obtain both human and animal biological data and metadata, the workflow uses the Monarch
Biolink API version 1.1.14 (https://api.monarchinitiative.org/api). The Monarch Initiative, a
collaborative, open science project, seeks to semantically integrate genotype-phenotype information
from numerous sources and species [
The workflow leverages the BioKnowledge reviewer library to extract and integrate data from
online sources into a knowledge graph. Starting with a list of seed nodes, a Monarch network
is created by including the first layer of neighbours and relations from Monarch for each
seed node, along with their ortholog-phenotype nodes. A seed node can take the form of
a disease phenotype MIM number, such as ’143100’ representing Huntington’s disease. The
edges are formatted as triples, where each triple includes additional information such as the
reference Uniform Resource Identifier (URI), the date when the information was obtained, and
more information about the semantics of the relation. Nodes in the graph are identified using
diferent biomedical ontologies in the OBO Foundry [https://doi.org/10.1093/database/baab069]
maintained or used by Monarch and contain other attributes such as semantic group, URI, label,
name, synonyms, and description. The URI serves as a link to a web page that provides a more
detailed description of the ontology term representing the node [
To obtain drug-target information, we use DGIdb and take all genes (targets) in the Monarch
graph as seeds. First, we need to map the Monarch genes to Entrez Gene identifiers (Entrez
ID), which are used as a standard gene identifier system [
To enable the biophysical drug repurposing approach, it is necessary to identify structurally
similar drugs. In our workflow, we use the Tanimoto coeficient [
The final graph is transformed into a Resource Description Framework (RDF) graph [
A gene is part of a nucleic acid that contains all the necessary elements to encode a functional transcript.
A disease is the outward manifestation of one or more disorders.
A genotype is a functional specification of a biological entity in terms of its genetic composition (or lack thereof).
A genomic sequence variant is part of a nucleic acid which is compositionally diferent than another reference genomic part.
A phenotype is an observable characteristic of an individual.
A pathway is an efective specification that outlines a
set of actions that forms a way to achieve an objective.
count
1352
284
194
127
106
71
49
where each entity, relationship, and entity class (gene, drug, etc.) is represented as an ontology
term by its URI. As Monarch did not provide identifiers for the entity classes, we manually
mapped the entity class labels to terms in ontologies and used their URIs. To achieve this,
we utilized the Semanticscience Integrated Ontology (SIO) [
To prepare the knowledge graph for embedding, we first remove all known drug-gene interactions from the graph. This is important to prevent bias in the prediction task, as keeping these edges would make the embedding vectors of the drugs very similar to the embedding vectors of the genes they interact with. We therefore split the graph into two separate graphs, one for drugs and one for genes. Each graph is then embedded separately using a graph embedding algorithm. After the embedding, the drug vectors are fused with the gene vectors to obtain drug-gene edges, which are used for training the machine learning model, as explained in more detail in the XGBoost prediction model section below.
Celebi et al. [26] compared diferent knowledge graph embedding methods for drug-drug interaction prediction, and found that RDF2Vec with Skip-Gram generally outperforms other methods. Therefore, this workflow employs RDF2Vec for graph embedding. RDF2Vec adapts the language modelling approach of Word2Vec to RDF graph embeddings [26]. First, random walks are performed over the graph to generate sequences of entities and relations. Then, the Skip-Gram model is used to learn one embedding for each entity/relationship in the graph. After training, semantically and syntactically similar entities/relationships have similar embeddings [26]. For the prediction task in this study, only the drug and gene vectors are of interest, and therefore, only these vectors were selected for further computation.
For RDF2Vec, the Python function RDF2VecTransformer from the rdf2vec module of the package pyrdf2vec version 0.2.3 is used [27]. The maximum depth of one walk is set to 4 and for each entity in the graph, the maximum number of walks is set to 10.
To train a supervised machine learning model, it is essential to have both positive and negative samples of data [26]. The positive samples are all known interactions (regulates, inhibits, or activates). The negative samples can be obtained from unknown interactions between drugs and genes. Edge embeddings for positive and negative samples are generated by adopting a node embedding fusion approach. For every possible drug-gene combination, we obtain one embedding by fusing the drug embedding and the gene embedding with the Hadamard operator, which is a strong operator for learning edge features in link prediction tasks [28]. We then add the class of the interaction (inhibits, activates, or regulates) to the resulting embedding. For edges that do not exist in the graph, we assign the label ”unknown” to represent the unknown interaction class.
The prediction data for our machine learning model includes all unknown drug-gene interactions involving genes that contribute to the disease phenotype of interest. The negative samples of the training data are all unknown interactions that are not the prediction data. However, the number of negative samples significantly outweighs the number of positive samples. Including all of these negative samples could result in data imbalance and afect the performance of our model [26]. To address this issue, we decided to downsample the negative cases by randomly selecting negative samples with a sample size equal to the class in the positive set with the largest number of interactions (regulates, inhibits, or activates).
For our machine learning model, we utilized the XGBoost classifier proposed by Thafar et al.
in 2021 [
To address minor class imbalance in our positive sample, we computed sample weights using the compute_sample_weight() function from sklearn [30] version 1.1.1. These weights are then used for training the model, which provides some bias towards the minority classes during training.
To optimize the hyperparameters of our model, we conducted a randomized search on the search space presented in Table 3 using the RandomizedSearchCV() function from the model_selection module of the sklearn Python package (version 1.1.1) [30]. We set the number of parameter setting combinations to be tested (n_iter) to 20.
Given the challenge of identifying negative examples of drug-target pairs, as unlinked drugs and targets may simply represent drug-target pairs that have not been identified yet, we opted against conducting an error analysis. Instead, the model performance is assessed using the repeated stratified k-fold cross-validation technique alongside the F1-score metric.. The number of subsets for the k-fold cross validation is set to 10 and the number of repeats is set to 5. During each iteration of the process, the F1-score is calculated and averaged for each class X. Finally, the average F1-score over all k iterations and number of repeats is computed to obtain the final evaluation metric.
The best hyperparameters are used to build the final model. The confidence of each prediction is obtained using the predict_proba() function of xgboost version 1.3.3, which returns the probability of an interaction belonging to its predicted class.
For every gene in the graph that is associated with the symptom of interest, an interaction type and score is predicted for every drug in the dataset, provided that this interaction does not exist in the graph. To prioritize the most promising drug candidates for further investigation, we perform a ranking step based on the predicted positive interactions. First, we remove all predictions with a confidence score lower than 0.9 to focus only on the most confident predictions. Next, we rank the drugs based on the number of positive interactions they have with the genes associated with the symptom. This ranking approach is based on the hypothesis that drugs with more positive interactions with genes that cause a symptom are more likely to be efective in alleviating that symptom. In the case of drugs with the same number of interactions, we use the sum of prediction confidence scores as a secondary ranking criterion, with drugs having higher sums being ranked higher.
Our workflow was initially run with the terms ”huntington’s disease” (OMIM number ‘143100’) and ”chorea” (‘HP:0002072’) as seeds representing the disease and symptom fields respectively, for constructing the knowledge graph. The graph was created on 2022-06-27 and has in total 2189 nodes and 17467 edges. Figure 2 provides an overview of all entities and relationships in the graph and Table 4 shows the identifiers and descriptions of each relation between nodes in this graph. The graph includes 1352 drugs and 284 genes, resulting in a total of 383,968 edge representations, of which 1753 are known (1301 regulates, 391 inhibits, and 61 activates). This graph has 200 genes that are associated with the symptom chorea, which are the genes of interest, and there are 1077 known drug-gene edges with these 200 genes, indicating that the prediction data consists of 269,323 unknown interactions of potential interest. To deal with the imbalance between the larger number of negative samples and the comparatively smaller number of positive samples, 1301 negative samples were randomly selected, to balance the number of the largest interactions in the positive class (regulates). The best XGBoost hyperparameters can be found in Table 5, and the F1 score with these hyperparameters is 0.867. The trained XGBoost model was used to predict the classes of the unknown drug-gene interactions of interest.
Table 6 shows the predicted top ten ranked drugs that interact with genes that are associated with the phenotype chorea. We manually explored the top ranked predictions for HD that are associated with chorea. Below we present the top three candidates. Table 7 presents the two highest ranked drugs and the genes that these drugs have a positive predicted interaction with. The top predicted ranked drug is CHEMBL29097. CHEMBL29097 (synonym MK-886) is an inhibitor of 5-lipoxygenase-activating protein activity, currently in preclinical phase. It has been found that 10 microM MK-886 can abolish the biosynthetic production of cysteinyl leukotrienes (CysLTs), which is suggested to be involved in brain inflammation and neurological diseases [33].In addition to its anti-inflammatory activity, MK-886 has been shown to activate the proteasome which is known to have a causative role in HD [34]. Impaired function of the proteasome leads to the formation of intracellular aggregates in the nucleus as the proteasome cannot clear eficiently misfolded huntingtin proteins [ 35].
The second highest ranked drug is baicalein. Baicalein (CHEMBL8260) is a flavonoid isolated from the traditional Chinese medicinal herbal Scutellaria baicalensis Georgi, currently on Phase 2. Baicalein has known anti-inflammatory and neuroprotective eficacy in neurodegenerative disease models [36]. Rui et al. [36] studied the efects of baicalein on inflammasome-induced neuroinflammation in Parkinson’s disease(PD) and found that baicalein can suppresses MPTPinduced nigral dopaminergic neuron death, glial activation, and motor dysfunction in mice by suppressing the NLRP3/caspase-1/GSDMD pathway. In addition, several studies have have demonstrated that baicalein protects neurons in animal models of Alzheimer’s disease (AD) and PD by inhibiting neuroinflammation [ 37].
Amphotericin b (CHEMBL267345) was another drug on our list that ranked very high. Ampotericin b is an approved antifungal drug used to treat serious fungal infections. Experimental evidence shows that some antibiotics and antifungal medication have neuroprotective action through anti-aggregating activity on disease-associated proteins [38]. Although this drug has been shown to cause a delay in the formation of amyloid- , it was also found to induce toxicity [39]. However, Soler et al., [40] developed a derivative of amphotericin that has anti-aggregating action but lacks toxicity and antimicrobial activity [38].
To demonstrate the reusability of our approach, we also applied our methodology to another rare disease that currently lacks treatment; Spinocerebellar ataxia type 1 (SCA1). We used as seeds the terms ”SCA1” (OMIM number ’164400’) and the symptom ”hyporeflexia” (HP:0001265) to run our drug repurposing workflow and below we describe few of the top hits.
The first prioritized drug by our workflow was Dovitinib (CHEMBL522892) currently in phase 3. Dovitinib is a pan receptor tyrosine kinase (RTK) inhibitor that has anti-tumor activity in pre clinical models of several cancers [41]. It has been recently suggested as a candidate treatment for AD because it normalizes amyloid mediated transcriptional responses by targeting the CREB3L2-ATF4 heterodimerization which is responsible for the majority of the transcriptional changes occuring in AD neurons [42]. Its well tolerated safety profile and the ability to cross the blood brain barrier [42] makes it an interesting candidate for AD but also potentially for other neurodegenerative disorders that exhibit similar disease mediated changes like AD.
The second predicted drug on the list was broquinaldol (CHEMBL1394319), a small molecule that has antifungal and antibacterial activity. This is an investigational drug that was found to have activity against thyroid cancer in a high throughput screening experiment [43]. However, there is currently no evidence for being associated with neurodegenerative diseases.
Number three on the candidate drug list for SCA1 was an interesting compound, astemizole (CHEMBL296419). Astemizole is an approved second generation antihistamine drug [44] that has been found to rescue motor phenotype in a Drosophila model of PD [45].
This work presents a novel disease-drug profiling approach to identifying potential candidate
compounds that could alleviate the symptoms of a rare disease. It combines two established, and
widely accepted approaches, of mining rare disease-specific data from multiple public databases
into a knowledge graph [
The advance that this work provides to the field is the use of rare disease specific knowledge
graphs. Using BioKnowlegde reviewer in a drug repurposing automated workflow enables
to learn from a comprehensive view of the underlying druggable rare disease biology and
pathogenesis of interest. This is advantageous over current integration methods used in rare
disease research, which use information about thousands of complex disorders [
Through sophisticated graph-based algorithms, we can traverse the knowledge graph to
identify patterns in the data and predict potential new relationships between drugs and diseases.
We demonstrated that knowledge graphs and graph machine learning used streamlined in an
automated workflow gives testable DTI hypotheses for drug repurposing in the rare disease
area. This can support researchers to systematically generate compound prioritization coupled
with well-designed validation experiments to discover treatments for rare diseases in a timely
and cost-efective manner. One limitation is that we did not integrate domain expert knowledge
on disease pathobiology with patient data, which can be the basis for highly innovative drugs.
While [
Our results provide some interesting candidates that could potentially be of great value for the rare disease community. Some of our prioritized drugs are already associated with other neurodegenerative disorders (AD and PD) targetting neuroinflammation, which is a hallmark of the HD pathology. Other candidates (Broquinaldol and Amphotericin b) belong to the class of antifungal and antibacterial medication. These types of drugs have drawn a lot of attention and although they are mainly used to treat infections new applications are being discovered. It has been reported that antibiotics, for example Doxycycline and minocycline, have neuroprotective efects due to their anti-inflammatory properties [ 46].
The workflow is presented as a web application and yields promising results in a reusable and reproducible way for the rare diseases community. In the future, it could be extended and improved by the addition of experimentally validated negative interactions from reliable databases. Our current approach uses unknown drug-gene pairs as negative samples for classification. It is therefore possible that this set includes currently unknown positive interactions, which may adversely afect model training [ 47]. Additionally, the knowledge graph could be extended to include further information about each drug, such as side-efects and drug interactions, and additional input seeds could be obtained from the Monarch database, such as genes and metabolites associated with the particular disease, or related diseases. Moreover, integrating the predicted embeddings into the knowledge graph would enable the evaluation of performance across diverse prediction methods, ofering valuable insights into model eficacy and versatility. Lastly, it is important to note that the RDF graphs are stored in turtle format at the location where the code is executed, to enable further use in code execution and analysis. The RDF graph is currently not served as a live RDF/SPARQL endpoint, which presents an opportunity for improvement in our approach. This aligns with broader eforts in the field to enhance the transparency and accessibility of machine learning outcomes.
Integrating data into knowledge graphs with state-of-the-art graph-based machine learning methods results in a novel automated drug repurposing workflow, specifically suited for rare diseases, where data tends to be sparse and distributed. The workflow produces a ranked list of candidate compounds, which serve as new hypotheses for drug treatments. The drug repurposing workflow generalises to any rare disease, but as a proof-of-concept, we focused on Huntington’s disease, and a related condition, SCA1. We identified several promising candidate drugs for Huntington’s Disease for the symptom chorea, demonstrating the potential of our approach. With further testing and validation, these candidates could be explored as potential treatments for the disease. The workflow is provided as a web application, in a publicly available Docker container. It is therefore accessible for researchers with no technical expertise and is a reusable and reproducible application for the rare disease community. [24] I. Aucamp, Rdflib, 2021. URL: https://github.com/RDFLib/rdflib. [25] RDF 1.1 turtle, 2014. URL: https://www.w3.org/TR/turtle/. [26] R. Celebi, H. Uyar, E. Yasar, O. Gumus, O. Dikenelli, M. Dumontier, Evaluation of knowledge graph embedding approaches for drug-drug interaction prediction in realistic settings, BMC Bioinformatics 20 (2019). doi:10.1186/s12859-019-3284-5. [27] G. Vandewiele, B. Steenwinckel, T. Agozzino, M. Weyns, P. Bonte, F. Ongenae, F. D.
Turck, pyRDF2Vec: Python Implementation and Extension of RDF2Vec, IDLab, 2020. URL: https://github.com/IBCNServices/pyRDF2Vec. [28] A. Grover, J. Leskovec, node2vec: Scalable feature learning for networks, 2016. doi:10.
48550/ARXIV.1607.00653. [29] T. Chen, C. Guestrin, XGBoost: A scalable tree boosting system, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, ACM, New York, NY, USA, 2016, pp. 785–794. doi:10.1145/2939672.2939785. [30] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, Édouard Duchesnay, Scikit-learn: Machine learning in python, Journal of Machine Learning Research 12 (2011) 2825–2830. URL: http://jmlr.org/papers/v12/pedregosa11a. html. [31] C. Mungall, J. A. Overton, D. Osumi-Sutherland, M. Haendel, Mbrush, Obo-relations: 2015-10-29 release, 2015. doi:10.5281/ZENODO.32899. [32] M. Brush, N. Matentzoglu, M. Haendel, Geno-ontology, 2022. URL: https://github.com/ monarch-initiative/GENO-ontology. [33] P. Ballerini, P. D. Iorio, R. Ciccarelli, F. Caciagli, A. Polp, A. Beraudi, S. Buccella, I. D'Alimonte, M. D'Auro, E. Nargi, P. Patricelli, D. Visini, U. Traversa, P2y<sub>1</sub> and cysteinyl leukotriene receptors mediate purine and cysteinyl leukotriene co-release in primary cultures of rat microglia, International Journal of Immunopathology and Pharmacology 18 (2005) 255–268. doi:10.1177/039463200501800208. [34] E. E. Liao, M. Yang, N. Nathan Kochen, N. Vunnam, A. R. Braun, D. M. Ferguson, J. N. Sachs, Proteasomal stimulation by mk886 and its derivatives can rescue tauinduced neurite pathology, Molecular neurobiology 60 (2023) 6133–6144. doi:10.1007/ s12035-023-03417-5. [35] T. R. Soares, S. D. Reis, B. R. Pinho, M. R. Duchen, J. M. Oliveira, Targeting the proteostasis network in huntington’s disease, Ageing Research Reviews 49 (2019) 92–103. doi:10.1016/ j.arr.2018.11.006. [36] W. Rui, S. Li, H. Xiao, M. Xiao, J. Shi, Baicalein attenuates neuroinflammation by inhibiting NLRP3/caspase-1/GSDMD pathway in MPTP induced mice model of parkinson’s disease, Int. J. Neuropsychopharmacol. 23 (2020) 762–773. doi:10.1093/ijnp/pyaa060. [37] Y. Li, J. Zhao, C. Hölscher, Therapeutic potential of baicalein in alzheimer’s disease and parkinson’s disease, CNS drugs 31 (2017) 639–652. doi:10.1007/s40263-017-0451-y. [38] S. B. Socias, F. González-Lizárraga, C. L. Avila, C. Vera, L. Acuña, J. E. Sepulveda-Diaz, E. DelBel, R. Raisman-Vozari, R. N. Chehin, Exploiting the therapeutic potential of ready-to-use drugs: Repurposing antibiotics against amyloid aggregation in neurodegenerative diseases, Progress in Neurobiology 162 (2018) 17–36. doi:10.1016/j.pneurobio.2017.12.002. [39] F. Durães, M. Pinto, E. Sousa, Old drugs as new treatments for neurodegenerative diseases,
Pharmaceuticals 11 (2018). doi:10.3390/ph11020044. [40] L. Soler, P. Cafrey, H. E. McMahon, Efects of new amphotericin analogues on the scrapie isoform of the prion protein, Biochimica et Biophysica Acta (BBA) - General Subjects 1780 (2008) 1162–1167. doi:https://doi.org/10.1016/j.bbagen.2008.07.005. [41] S. S. Yadav, J. Li, J. A. Stockert, B. Herzog, J. O’Connor, L. Garzon-Manco, R. Parsons, A. K.
Tewari, K. K. Yadav, Induction of neuroendocrine diferentiation in prostate cancer cells by dovitinib (tki-258) and its therapeutic implications, Translational Oncology 10 (2017) 357–366. doi:https://doi.org/10.1016/j.tranon.2017.01.011. [42] C. G. Roque, K. M. Chung, E. P. McCurdy, R. Jagannathan, L. K. Randolph, K. HerlineKillian, J. Baleriola, U. Hengst, Creb3l2-atf4 heterodimerization defines a transcriptional hub of alzheimer’s disease gene expression linked to neuropathology, Science Advances 9 (2023) eadd2671. doi:10.1126/sciadv.add2671. [43] L. Zhang, M. He, Y. Zhang, N. Nilubol, M. Shen, E. Kebebew, Quantitative High-Throughput Drug Screening Identifies Novel Classes of Drugs with Anticancer Activity in Thyroid Cancer Cells: Opportunities for Repurposing, The Journal of Clinical Endocrinology Metabolism 97 (2012) E319–E328. doi:10.1210/jc.2011-2671. arXiv:https://academic.oup.com/jcem/articlepdf/97/3/E319/10416587/jcemE319.pdf. [44] P. M. Krstenansky, J. Robert J. Cluxton, Astemizole: A long-acting, nonsedating antihistamine, Drug Intelligence & Clinical Pharmacy 21 (1987) 947–953. doi:10.1177/ 106002808702101202. [45] K. Styczyńska-Soczka, L. Zechini, L. Zografos, Validating the predicted efect of astemizole and ketoconazole using a drosophila model of parkinson’s disease, Assay and drug development technologies 15 (2017) 106–112. [46] A. Dominguez-Meijide, V. Parrales, E. Vasili, F. González-Lizárraga, A. König, D. F. Lázaro, A. Lannuzel, S. Haik, E. Del Bel, R. Chehín, R. Raisman-Vozari, P. P. Michel, N. Bizat, T. F. Outeiro, Doxycycline inhibits α-synuclein-associated pathologies in vitro and in vivo, Neurobiology of Disease 151 (2021) 105256. doi:https://doi.org/10.1016/j.nbd.2021. 105256. [47] L. Xu, X. Ru, R. Song, Application of machine learning for drug–target interaction prediction, Frontiers in Genetics 12 (2021). URL: https://doi.org/10.3389/fgene.2021.680117. doi:10.3389/fgene.2021.680117.
description similar to CHEM- Connects a molecular entity that is deemed similar to another accord- 13023
INF:000481 ing to some algorithm. regulates RO:0011002 The entity has an activity that regulates an activity of the entity . 1301 has pheno- RO:0002200 A relationship that holds between a biological entity and a phenotype. 1016 type Here a phenotype is construed broadly as any kind of quality of an organism part, a collection of these qualities, or a change in quality or qualities. The subject of this relationship can be an organism, a genomic entity such as a gene or genotype, or a condition such as a disease. interacts with RO:0002434 A relationship that holds between two entities in which the processes 900 executed by the two entities are causally connected. inhibits RO:0002408 Directly negatively regulates. 391 causes condi- RO:0003303 A relationship between an entity (e.g. a genotype, genetic variation, 212 tion chemical, or environmental exposure) and a condition (a phenotype or disease), where the entity has some causal role for the condition. contributes to RO:0003304 A relationship between an entity (e.g. a genotype, genetic variation, 107 condition chemical, or environmental exposure) and a condition (a phenotype or disease), where the entity has some contributing role that influences the condition. has genotype GENO:0000222 A relationship that holds between a biological entity and some level of 106 genetic variation present in its genome. has role in RO:0003301 A relation between a biological, experimental, or computational arte- 103 modelling fact and an entity it is used to study, in virtue of its replicating or approximating features of the studied entity. correlated RO:0002610 A relationship that holds between two entities, where the entities 72 with exhibit a statistical dependence relationship. The entities may be statistical variables, or they may be other kinds of entities such as diseases, chemical entities or processes. activates RO:0002406 Directly positively regulates. 61 involved in RO:0002331 is involved in if and only if enables some process ′, and ′ is part of . enables RO:0002327 catalyses. 49 colocalises RO:0002325 colocalises with if and only if is transiently or peripherally associ- 38 with ated with . is allele of GENO:0000408 A relation linking an instance of a variable feature (aka an allele) to a 39 genomic location/locus it occupies. This is typically a gene locus, but a feature may be an allele of other types of named loci such as QTLs, or alleles of some unnamed locus of arbitrary size. has afected GENO:0000418 A relation that holds between an instance of a genetic variation and a 22 feature genomic feature (typically a gene class) that is afected in its sequence or expression. is causal loss RO:0004012 Relates a gene to a condition, such that a mutation in this gene in a 15 of function germ cell impairs the function of the corresponding product and that germline is suficient to produce the condition and that can be passed on to mutation of ofspring. in 1 to 1 or- RO:HOM0000020Orthology that involves two genes that did not experience any dupli- 10 thology rela- cation after the speciation event that created them. tionship with is marker for RO:0002607 1 is causal gain of function germline mutation of
RO:0004011 is marker for if the presence or occurrence of is correlated with the presence or occurrence of , and the observation of is used to infer the presence or occurrence of . Note that this does not imply that and are in a direct causal relationship, as it may be the case that there is a third entity that stands in a direct causal relationship with and .
Relates a gene to a condition, such that a mutation in this gene in a germ cell provides a new function of the corresponding product and that is suficient to produce the condition and that can be passed on to ofspring.
parameter min_child_weight gamma reg_alpha reg_lambda colsample_bytree max_depth n_estimators learning_rate best https://identifiers.org/chembl:CHEMBL29097 https://identifiers.org/chembl:CHEMBL8260 https://identifiers.org/chembl:CHEMBL221137 https://identifiers.org/chembl:CHEMBL267345 https://identifiers.org/chembl:CHEMBL308688 https://identifiers.org/chembl:CHEMBL2110660 https://identifiers.org/chembl:CHEMBL275809 https://identifiers.org/chembl:CHEMBL161343 https://identifiers.org/chembl:CHEMBL585 https://identifiers.org/chembl:CHEMBL1269845 name CHEMBL29097 BAICALEIN EMBELIN AMPHOTERICIN B 5,7-DIMETHOXYISOFLAVONE IGMESINE FR-122047 ARACHIDONOYL GLYCINE TRIAMTERENE
CHEMBL1269845 drug ID
drug label chembl:CHEMBL29097
CHEMBL29097 chembl:CHEMBL8260
BAICALEIN