CoChat
Sign Up
Cited by 139Computational Drug Discovery MethodsTelomeres, Telomerase, and SenescenceMachine Learning in Materials Science

The DOI matches its Crossref record; 85 of the 86 references it cites were found in a registry or an index; 38 of the 60 sources its claims cite were checked for support.

Discovery of senolytics using machine learning

Open access
Smer-Barreto, Vanessa, Quintanilla, Andrea, Elliott, Richard J. R., Dawson, John C., Sun, Jiugeng, Campa, Víctor M., Lorente-Macías, Álvaro, Unciti-Broceta, Asier, Carragher, Neil O., Acosta, Juan Carlos, Oyarzún, Diego A.·2023·Nature Communications
DOI 10.1038/s41467-023-39120-1PMC PMC10257182
Open this paper in CoChat — free accountOpen PDF

Abstract

Cellular senescence is a stress response involved in ageing and diverse disease processes including cancer, type-2 diabetes, osteoarthritis and viral infection. Despite growing interest in targeted elimination of senescent cells, only few senolytics are known due to the lack of well-characterised molecular targets. Here, we report the discovery of three senolytics using cost-effective machine learning algorithms trained solely on published data. We computationally screened various chemical libraries and validated the senolytic action of ginkgetin, periplocin and oleandrin in human cell lines under various modalities of senescence. The compounds have potency comparable to known senolytics, and we show that oleandrin has improved potency over its target as compared to best-in-class alternatives. Our approach led to several hundred-fold reduction in drug screening costs and demonstrates that artificial intelligence can take maximum advantage of small and heterogeneous drug screening data, paving the way for new open science approaches to early-stage drug discovery.

Overview

AI snapshot

Written from the paper’s full text.

TL;DR

A machine-learning pipeline trained solely on published senolytic data screened 4,340 compounds and identified three senolytics—ginkgetin, periplocin, and oleandrin—validated in human cell models of oncogene- and therapy-induced senescence. Oleandrin showed improved potency over benchmark cardiac glycosides, while the approach reduced experimental screening by more than 200-fold.

Key findings

  • The training set contained 2,523 compounds, including 58 positives (2.3%), featurized with 200 RDKit physicochemical descriptors reduced to 165 features; XGBoost gave the best performance, with average precision 0.7 ± 0.16 in 5-fold cross-validation and an average false discovery rate of 30%.
  • Screening 4,340 compounds from the L2100 TargetMol Anticancer and L3800 Selleck FDA-approved & Passed Phase libraries yielded 21 compounds with P > 44% (0.4% of the library); experimental validation confirmed three senolytics—ginkgetin, oleandrin, and periplocin—for a hit confirmation rate of 14.28%.
  • In oncogene-induced senescence (IMR90 ER:RAS), IC50 values were 85 nM control vs 14 nM senescent for oleandrin, 300 nM vs 24 nM for periplocin, and 26 μM vs 2.6 μM for ginkgetin; in therapy-induced senescence (A549), IC50 values were 19.5 nM vs 5.4 nM, 267 nM vs 72.2 nM, and 10.4 μM vs 5.7 μM, respectively.
  • At 10 nM, oleandrin significantly reduced senescent cell content, inhibited the Na+/K+ ATPase target, and induced NOXA mRNA, showing improved senolytic performance over ouabain; the method reduced the number of compounds for experimental screening by more than 200-fold.

Methods

  • Positives were mined from published senolytic reports and a commercial patent; negatives came from LOPAC-1280 and Prestwick FDA-approved-1280. Compounds were represented by 200 RDKit physicochemical descriptors, reduced to 165 features, and classified with SVM, random forest, XGBoost, and other models using 5-fold cross-validation.
  • The selected XGBoost model, trained on a 70:30 stratified split, was used to computationally screen 4,340 compounds; the top 21 with prediction scores P > 44% were selected for experimental validation.
  • Validation used IMR90 ER:RAS cells with 4-OHT (100 nM) for oncogene-induced senescence and A549 cells with etoposide (100 μM) for therapy-induced senescence, with nuclei counts, dose-response IC50 fitting, crystal violet survival, caspase-3/7 activity, intracellular K+ measurement, and RT-qPCR for NOXA, p16, p21, and cytokines.

Limitations

  • The paper states that feature selection and model/hyperparameter selection used the full dataset, so the 30% held-out performance metrics are over-optimistic; applying those steps only to the 70% training split would have reduced positives to 41 and made model selection less reliable.
  • The paper states that negatives were assumed to lack senolytic action because negative screening results are rarely published, risking mislabeled compounds; the data are severely imbalanced, heterogeneous, and the models generally showed poor common classification metrics with many false positives and false negatives.
  • The paper states that oleandrin and related cardiac glycosides have toxicity concerns, a narrow therapeutic range, and cardiotoxicity, so systemic use should be considered cautiously; further animal-model validation is needed. Evident from the text: validation was in vitro in two cell lines, with no in vivo efficacy or safety data reported.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1038/s41467-023-39120-1

Cites

85 of 85 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1 Compounds employed to train machine learning models of senolytic action. a We assembled training data from multiple sources. We mined 58 known senolytics (positives) from academic papers and a commercial patent, and integrated them with diverse compounds from the LOPAC-1280 and Prestwick FDA-approved-1280 chemical libraries (negatives). Chemical structures were featurised with 200 physicochemical descriptors computed with RDKit57 and binary labelled according to their senolytic action. These labelled data were employed to train binary classifiers predictive of senolytic activity. b Sources of the 58 senolytics employed for training, including the number of compounds per source and the cell lines where senolysis was identified. c Cluster structure of the senolytics employed for training using the RDKit descriptors as features. Plot shows the k-means clustering score and silhouette coefficient58 averaged across compounds for an increasing number of clusters (k). Error bars denote one standard deviation over 100 repeats with different initial seeds. The lack of a clear “elbow” in the k-means score and low silhouette coefficients suggest poor clustering among the senolytics employed for training. d Tanimoto distance graph of senolytics employed for training; nodes are compounds and edges represent compounds that are sufficiently close in the physicochemical feature space. Node colour indicates the data source as in panel b. To emphasise the overall dissimilarity between compounds, we set the edge thickness as the Tanimoto similarity (1-distance). Inset shows the distribution of Tanimoto distances across the 269 graph edges (median distance of 0.77). e Clustering of the Tanimoto distance graph using the Louvain algorithm for community detection60. Plot shows the average number of clusters with respect to the resolution parameter (γ) across 100 runs (error bars denote one standard deviation); increasing values of γ produce a larger number of clusters. We observe pronounced plateaus at 5 and 6 clusters, suggesting some degree of clustering in the data. We computed the adjusted Rand index61 (ARI) averaged across all compounds to quantify the similarity between cluster labels and compound source labels (15 labels; panel e). Low ARI values indicate that Louvain clusters are substantially different from the literature source labels.
Fig. 1 Compounds employed to train machine learning models of senolytic action. a We assembled training data from multiple sources. We mined 58 known senolytics (positives) from academic papers and a commercial patent, and integrated them with diverse compounds from the LOPAC-1280 and Prestwick FDA-approved-1280 chemical libraries (negatives). Chemical structures were featurised with 200 physicochemical descriptors computed with RDKit57 and binary labelled according to their senolytic action. These labelled data were employed to train binary classifiers predictive of senolytic activity. b Sources of the 58 senolytics employed for training, including the number of compounds per source and the cell lines where senolysis was identified. c Cluster structure of the senolytics employed for training using the RDKit descriptors as features. Plot shows the k-means clustering score and silhouette coefficient58 averaged across compounds for an increasing number of clusters (k). Error bars denote one standard deviation over 100 repeats with different initial seeds. The lack of a clear “elbow” in the k-means score and low silhouette coefficients suggest poor clustering among the senolytics employed for training. d Tanimoto distance graph of senolytics employed for training; nodes are compounds and edges represent compounds that are sufficiently close in the physicochemical feature space. Node colour indicates the data source as in panel b. To emphasise the overall dissimilarity between compounds, we set the edge thickness as the Tanimoto similarity (1-distance). Inset shows the distribution of Tanimoto distances across the 269 graph edges (median distance of 0.77). e Clustering of the Tanimoto distance graph using the Louvain algorithm for community detection60. Plot shows the average number of clusters with respect to the resolution parameter (γ) across 100 runs (error bars denote one standard deviation); increasing values of γ produce a larger number of clusters. We observe pronounced plateaus at 5 and 6 clusters, suggesting some degree of clustering in the data. We computed the adjusted Rand index61 (ARI) averaged across all compounds to quantify the similarity between cluster labels and compound source labels (15 labels; panel e). Low ARI values indicate that Louvain clusters are substantially different from the literature source labels.CC BY · PubMed Central
Fig. 2 Training of machine learning models and computational screening. a Pipeline for model training, compound screening, and hit validation. Several classification scores were used as performance metrics to determine the most suitable model for the computational screen. b Results from three machine learning models trained on 2523 compounds (Fig. 1a) and a reduced set of 165 features (Supplementary Fig. 1a); bar plots show average performance metrics computed in 5-fold cross-validation, with error bars denoting one standard deviation across folds. Mean ± s.d. are shown from n = 5 data folds. c The confusion matrices were computed from models trained on 70% of compounds, and tested on 17 positives and 740 negatives that were held-out from training. All models displayed poor performance metrics (Supplementary Table 1), and we chose the XGBoost algorithm for screening because of its lower number of false positives. d Results from computational screen of the L2100 TargetMol Anticancer and L3800 Selleck FDA-approved & Passed Phase chemical libraries, totalling 4340 compounds. The XGBoost model is highly selective and scored most compounds with a low probability of having senolytic action; a small fraction of N = 21 compounds were scored with P > 44%, which we selected for experimental validation. e Compounds selected for screening, ranked according to their z-score normalised prediction scores from the XGBoost model; the selected compounds are far outliers in the distribution of panel c. f Two-dimensional t-SNE visualisation of all compounds employed in this work; t-SNE plots were generated with perplexity 50, learning rate 200, and maximal number of iterations 120065. Compounds with prediction scores above 44% from the XGBoost model are marked with orange circles.
Fig. 2 Training of machine learning models and computational screening. a Pipeline for model training, compound screening, and hit validation. Several classification scores were used as performance metrics to determine the most suitable model for the computational screen. b Results from three machine learning models trained on 2523 compounds (Fig. 1a) and a reduced set of 165 features (Supplementary Fig. 1a); bar plots show average performance metrics computed in 5-fold cross-validation, with error bars denoting one standard deviation across folds. Mean ± s.d. are shown from n = 5 data folds. c The confusion matrices were computed from models trained on 70% of compounds, and tested on 17 positives and 740 negatives that were held-out from training. All models displayed poor performance metrics (Supplementary Table 1), and we chose the XGBoost algorithm for screening because of its lower number of false positives. d Results from computational screen of the L2100 TargetMol Anticancer and L3800 Selleck FDA-approved & Passed Phase chemical libraries, totalling 4340 compounds. The XGBoost model is highly selective and scored most compounds with a low probability of having senolytic action; a small fraction of N = 21 compounds were scored with P > 44%, which we selected for experimental validation. e Compounds selected for screening, ranked according to their z-score normalised prediction scores from the XGBoost model; the selected compounds are far outliers in the distribution of panel c. f Two-dimensional t-SNE visualisation of all compounds employed in this work; t-SNE plots were generated with perplexity 50, learning rate 200, and maximal number of iterations 120065. Compounds with prediction scores above 44% from the XGBoost model are marked with orange circles.CC BY · PubMed Central
Fig. 3 Experimental characterisation of compounds selected for screening in oncogene-induced senescent (OIS) cells. a Experimental setup of OIS model with IMR90 ER:RAS cells. Senescence was induced by addition of 4-OHT at 100 nM during the duration of the experiment (8 days). Control and senescent cells were plated in a 384-well plate on day five of 4-OHT induction. Top predicted compounds were added after multiwell seeding, and 72 h afterwards, the cells were fixed, and the nuclei stained and counted. b Bar plot of OIS positive experimental control, ouabain, at 46.4 nM. Data is normalised to DMSO. Data represented as individual points, and bars and error bars represent the mean ± SEM of three independent experiments. Statistical analysis was performed using a two-sided two-sample t-test for difference in mean value: ***p < 0.001; p = 2.6 × 10−4. c Results from experimental validation of controls and the top 21 compounds from Fig. 2d predicted to have senolytic action with P > 44%. Three compounds out of the 21 displayed senolytic activity: ginkgetin, oleandrin and periplocin; heatmap shows mean across n = 3 replicates. This drug screen was done once with three experimental replicates. d Dose-response curves of the three newly found senolytic compounds. The senolytic index (SI) is defined as the ratio between the IC50 of control cells and the IC50 of senescent cells. Data is normalised to DMSO. Mean ± s.d. are shown from n = 3 experiments. Oleandrin and periplocin are related steroid saponins, similar to ouabain. Ginkgetin is a structurally distinct biflavone; the structures of the three compounds can be found in Supplementary Fig. 11. e Tanimoto distance between the three validated senolytics and those employed for model training; distances were calculated using the RDKit descriptors that were employed in the training of machine learning models in Fig. 2b and Supplementary Table 2. Source data are provided as a Source Data file.
Fig. 3 Experimental characterisation of compounds selected for screening in oncogene-induced senescent (OIS) cells. a Experimental setup of OIS model with IMR90 ER:RAS cells. Senescence was induced by addition of 4-OHT at 100 nM during the duration of the experiment (8 days). Control and senescent cells were plated in a 384-well plate on day five of 4-OHT induction. Top predicted compounds were added after multiwell seeding, and 72 h afterwards, the cells were fixed, and the nuclei stained and counted. b Bar plot of OIS positive experimental control, ouabain, at 46.4 nM. Data is normalised to DMSO. Data represented as individual points, and bars and error bars represent the mean ± SEM of three independent experiments. Statistical analysis was performed using a two-sided two-sample t-test for difference in mean value: ***p < 0.001; p = 2.6 × 10−4. c Results from experimental validation of controls and the top 21 compounds from Fig. 2d predicted to have senolytic action with P > 44%. Three compounds out of the 21 displayed senolytic activity: ginkgetin, oleandrin and periplocin; heatmap shows mean across n = 3 replicates. This drug screen was done once with three experimental replicates. d Dose-response curves of the three newly found senolytic compounds. The senolytic index (SI) is defined as the ratio between the IC50 of control cells and the IC50 of senescent cells. Data is normalised to DMSO. Mean ± s.d. are shown from n = 3 experiments. Oleandrin and periplocin are related steroid saponins, similar to ouabain. Ginkgetin is a structurally distinct biflavone; the structures of the three compounds can be found in Supplementary Fig. 11. e Tanimoto distance between the three validated senolytics and those employed for model training; distances were calculated using the RDKit descriptors that were employed in the training of machine learning models in Fig. 2b and Supplementary Table 2. Source data are provided as a Source Data file.CC BY · PubMed Central
Fig. 4 Senolytic performance of oleandrin and periplocin. a Cell survival assay measuring the senolytic effect in OIS. The panels show a representative crystal violet staining of tissue culture dishes of confluent senescent IMR90 ER:RAS and control IMR90 ER:STOP cells cultured with 100 nM 4OHT, and treated with 10 nM oleandrin, ouabain and periplocin, and DMSO as vehicle control for 72 h. b Cell survival by quantification of the crystal violet staining of the experiment shown in a, as described in “Methods” section. Data represented as individual data points, and bars and error bars representing the mean ± SEM of 12 independent experiments. Statistical analysis was performed using a one-way ANOVA (Tukey’s test) for multiple comparisons. c Cell survival assay measuring the senolytic effect in replicative senescence. Graphs representing the cell survival by quantification of the crystal violet staining of confluent cultures of IMR90 cells at passage 27 (replicative senescence) and IMR90 cells at passage 13 (control) treated with 10 nM oleandrin, ouabain and periplocin, and DMSO as vehicle control for 72 h (related to Supplementary Fig. 9b). Data represented as individual data points, and bars and error bars representing the mean ± SEM of 12 independent experiments. Statistical analysis was performed using a one-way ANOVA (Tukey’s test) for multiple comparisons. d Caspase 3/7 activity assay in control IMR90 ER:STOP and senescent IMR90 ER:RAS cells cultured in media containing 100 nM 4OHT, and treated during 35 h with 10 nM oleandrin, ouabain and periplocin, and DMSO as vehicle control. The panels show representative fluorescent images of caspase 3/7 positive cells (lower panels) and brightfield images (upper panels) of the same field for cell scoring. Percentage of green fluorescent cells per condition is indicated in the panel figures. Representative data of one of two independent experiments. Scale bars represent 100 μm. ns not significant, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001. Source data are provided as a Source Data file.
Fig. 4 Senolytic performance of oleandrin and periplocin. a Cell survival assay measuring the senolytic effect in OIS. The panels show a representative crystal violet staining of tissue culture dishes of confluent senescent IMR90 ER:RAS and control IMR90 ER:STOP cells cultured with 100 nM 4OHT, and treated with 10 nM oleandrin, ouabain and periplocin, and DMSO as vehicle control for 72 h. b Cell survival by quantification of the crystal violet staining of the experiment shown in a, as described in “Methods” section. Data represented as individual data points, and bars and error bars representing the mean ± SEM of 12 independent experiments. Statistical analysis was performed using a one-way ANOVA (Tukey’s test) for multiple comparisons. c Cell survival assay measuring the senolytic effect in replicative senescence. Graphs representing the cell survival by quantification of the crystal violet staining of confluent cultures of IMR90 cells at passage 27 (replicative senescence) and IMR90 cells at passage 13 (control) treated with 10 nM oleandrin, ouabain and periplocin, and DMSO as vehicle control for 72 h (related to Supplementary Fig. 9b). Data represented as individual data points, and bars and error bars representing the mean ± SEM of 12 independent experiments. Statistical analysis was performed using a one-way ANOVA (Tukey’s test) for multiple comparisons. d Caspase 3/7 activity assay in control IMR90 ER:STOP and senescent IMR90 ER:RAS cells cultured in media containing 100 nM 4OHT, and treated during 35 h with 10 nM oleandrin, ouabain and periplocin, and DMSO as vehicle control. The panels show representative fluorescent images of caspase 3/7 positive cells (lower panels) and brightfield images (upper panels) of the same field for cell scoring. Percentage of green fluorescent cells per condition is indicated in the panel figures. Representative data of one of two independent experiments. Scale bars represent 100 μm. ns not significant, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001. Source data are provided as a Source Data file.CC BY · PubMed Central
Fig. 5 Activity of oleandrin and periplocin on their senolytic targets. a, b Intracellular K+ levels measured using Asante staining in a 100 nM 4OHT containing cultures of senescent IMR90 ER:RAS cells treated with 10 nM oleandrin, ouabain and periplocin, or DMSO as vehicle control, compared with IMR90 ER:STOP controls (n = 7), and b in IMR90 cells at passage 27 (replicative senescence) treated with 10 nM oleandrin, ouabain and periplocin, or DMSO as control vehicle compared to IMR90 cells at passage 13 (control) (n = 6). Data represented as individual data points and the mean ± SEM. Statistical analysis was performed using a one-way ANOVA (Tukey’s test) for multiple comparisons. Representative images of Asante cell staining are shown in Supplementary Fig. 9h, i. c, d mRNA expression of NOXA determined by RT-qPCR in c 100 nM 4OHT containing cultures of senescent IMR90 ER:RAS cells treated with 10 nM oleandrin, ouabain and periplocin, and DMSO as control, compared to control IMR90 ER:STOP cells (n = 4), and d IMR90 cells at passage 27 (replicative senescence) treated with 10 nM oleandrin, ouabain and periplocin, and DMSO control compared to IMR90 proliferating cells at passage 13 (control) (n = 3). Data represented as individual data points and the mean ± SEM. Statistical analysis was performed using a one-way ANOVA (Dunnett’s test) for multiple comparisons. ns not significant, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001. Source data are provided as a Source Data file.
Fig. 5 Activity of oleandrin and periplocin on their senolytic targets. a, b Intracellular K+ levels measured using Asante staining in a 100 nM 4OHT containing cultures of senescent IMR90 ER:RAS cells treated with 10 nM oleandrin, ouabain and periplocin, or DMSO as vehicle control, compared with IMR90 ER:STOP controls (n = 7), and b in IMR90 cells at passage 27 (replicative senescence) treated with 10 nM oleandrin, ouabain and periplocin, or DMSO as control vehicle compared to IMR90 cells at passage 13 (control) (n = 6). Data represented as individual data points and the mean ± SEM. Statistical analysis was performed using a one-way ANOVA (Tukey’s test) for multiple comparisons. Representative images of Asante cell staining are shown in Supplementary Fig. 9h, i. c, d mRNA expression of NOXA determined by RT-qPCR in c 100 nM 4OHT containing cultures of senescent IMR90 ER:RAS cells treated with 10 nM oleandrin, ouabain and periplocin, and DMSO as control, compared to control IMR90 ER:STOP cells (n = 4), and d IMR90 cells at passage 27 (replicative senescence) treated with 10 nM oleandrin, ouabain and periplocin, and DMSO control compared to IMR90 proliferating cells at passage 13 (control) (n = 3). Data represented as individual data points and the mean ± SEM. Statistical analysis was performed using a one-way ANOVA (Dunnett’s test) for multiple comparisons. ns not significant, *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001. Source data are provided as a Source Data file.CC BY · PubMed Central

Verification

Claims the paper makes

53 Own result · 27 Own interpretation · 22 Own method · 14 No basis given · 8 Not checked yet · 6 Partly supported · 3 Supported · 3 Sources not found · 2 Supported so far · 2 Couldn’t confirm · 2 No full text of the sources · accuracy not yet measured

Verify all 11 references — free account
  • It may state two separate claims as one. 44
  • Probably not a substantial claim. 32
  • The quote only partly states this claim. 1
69 of 69

  • The authors state this as an assumption.

    The background compounds from LOPAC-1280 and Prestwick FDA-approved-1280 lack senolytic action.

    “The full list of positives was then merged with a large background of compounds assumed to lack senolytic action.”
    “This assumption was needed due to the lack of data on negative screening results in the literature.”

  • The paper relies on this without support.

    Machine learning models can bias their predictions towards the training data they have been exposed to.

    “Since machine learning models can bias their predictions towards the training data they have been exposed to, we chose the negatives from two diverse chemical libraries, LOPAC-1280 and Prestwick FDA-approved-1280, which contain a wide range of FDA-approved or clinical-stage compounds.”

  • The paper relies on this without support.

    Current approaches to drug discovery suffer from high attrition rates in late-stage preclinical and clinical development.

    “Current approaches to drug discovery suffer from notoriously high attrition rates in late-stage preclinical and clinical development.”

  • The paper relies on this without support.

    The LOPAC-1280 and Prestwick FDA-approved-1280 libraries are sufficiently diverse for training machine learning models.

    “We reasoned that these libraries are sufficiently diverse for training machine learning models.”

  • The authors state this as an assumption.

    All compounds from the LOPAC-1280 and Prestwick FDA-approved-1280 libraries lack senolytic action.

    “Although all compounds from these two library sources were assumed to be negative”

  • The paper relies on this without support.

    Periplocin and oleandrin had not been previously identified as senolytics.

    “periplocin and oleandrin, two cardiac glycosides which have not been previously identified as senolytics”

  • The paper relies on this without support.

    Senolysis is a rare molecular property and the number of senolytics reported in the literature so far is limited.

    “the small number of senolytics in the training data is a consequence of senolysis being a rare molecular property and the limited number of senolytics reported in the literature so far.”

  • The authors state this as an assumption.

    The underlying assumptions for the statistical tests, including sample independence, variance equality, and normality, were assumed to be met although not explicitly examined.

    “Underlying assumptions for these tests, including sample independence, variance equality, and normality were assumed to be met although not explicitly examined.”
8 of 8

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

4 of 4

Citations

Cites

Show all 86 references

Research works printed but not linked: 2

  1. van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn Res. 9, 2579–2605 (2008).
  2. Louppe, G., Wehenkel, L., Sutera, A. & Geurts, P. Understanding variable importances in forests of randomized trees. Adv. Neural Inf. Process. Syst. 26 Available at: https://proceedings.neurips.cc/paper/2013/hash/e3796ae838835da0b6f6ea37bcf8bcb7-Abstract.html (2013).

Cited by

Sorted by citations

See all 139

Related

See all

Metadata

Authors
Smer-Barreto, V., Quintanilla, A., Elliott, R. J. R., Dawson, J. C., Sun, J., Campa, V. M., Lorente-Macías, Á., Unciti-Broceta, A., Carragher, N. O., Acosta, J. C., & Oyarzún, D. A.
Affiliations
  • Edinburgh Cancer Research (GB)
  • Universidad de Cantabria (ES)
  • University of Edinburgh (GB)
  • The Alan Turing Institute (GB)
Corresponding author
  • Smer-Barreto, Vanessa
  • Acosta, Juan Carlos
  • Oyarzún, Diego A.
ORCID
Venue
Nature Communications
Publisher
Springer Science and Business Media LLC
Published
2023-06-10
Volume
14
Issue
1
Pages
3445-3445
ISSN
2041-1723 (ISSN-L)
DOI
10.1038/s41467-023-39120-1
PMC
PMC10257182
OpenAlex
W4380152694
Semantic Scholar
d9a31a94f6f0a105f67c80f4b055dce4b6563858
Cited by
139
References
86
Citations by year
2026: 42 · 2025: 57 · 2024: 33 · 2023: 7
FWCI
12.31
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Communications (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DIGITAL.CSIC (Spanish National Research Council (CSIC)) (submittedVersion, cc-by)
  • UCrea (University of Cantabria) (submittedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DIGITAL.CSIC (Spanish National Research Council (CSIC)) (submittedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, cc-by)
Funders
  • Cancer Research UK (16243, C47559/A16243)
  • University of Edinburgh (MC_UU_00009/2)
  • Ministerio de Ciencia e Innovación (10.13039, 501100011033, PID2020, PID2020-117860GB-I00, MCIN /AEI /10.13039)
  • Medical Research Council (MC_UU_00009/2)
  • Consejo Superior de Investigaciones Científicas
  • Agencia Estatal de Investigación (501100011033, 10.13039/501100011033, 13039, 10.13039)
Topics
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Cell Biology › Telomeres, Telomerase, and Senescence
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
Keywords
senolytics, cellular senescence, machine learning, drug discovery, ginkgetin, oleandrin, periplocin, chemical library screening, senescence-associated secretory phenotype, lung fibroblasts, lung adenocarcinoma cells
MeSH terms
Machine Learning, Senotherapeutics, Aging, Artificial Intelligence, Humans, Cellular Senescence

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

A language model drew the claims from the paper on 2026-11-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-11-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review