Integrating knowledge graphs into machine learning models for survival prediction and biomarker discovery in patients with non-small-cell lung cancer.

Accurate survival prediction for Non-Small Cell Lung Cancer (NSCLC) patients remains a significant challenge for the scientific and clinical community despite decades of advanced analytics. Addressing this challenge not only helps inform the critical aspects of clinical study design and biomarker discovery but also ensures that the 'right patient' receives the 'right treatment'. However, survival prediction is a highly complex task, given the large number of 'omics; and clinical features, as well as the high degree of freedom that drive patient survival. Prior knowledge could play a critical role in uncovering the complexity of a disease and understanding the driving factors affecting a patient's survival. We introduce a methodology for incorporating prior knowledge into machine learning-based models for prediction of patient survival through Knowledge Graphs, demonstrating the advantage of such an approach for NSCLC patients. Using data from patients treated with immuno-oncologic therapies in the POPLAR (NCT01903993) and OAK (NCT02008227) clinical trials, we found that the use of knowledge graphs yielded significantly improved hazard ratios, including in the POPLAR cohort, for models based on biomarker tumor mutation burden compared with those based on knowledge graphs. Use of a model-defined mutational 10-gene signature led to significant overall survival differentiation for both trials. We provide parameterized code for incorporating knowledge graphs into survival analyses for use by the wider scientific community.

DeepSynergy: predicting anti-cancer drug synergy with Deep Learning.

Motivation: While drug combination therapies are a well-established concept in cancer treatment, identifying novel synergistic combinations is challenging due to the size of combinatorial space. However, computational approaches have emerged as a time- and cost-efficient way to prioritize combinations to test, based on recently available large-scale combination screening data. Recently, Deep Learning has had an impact in many research areas by achieving new state-of-the-art model performance. However, Deep Learning has not yet been applied to drug synergy prediction, which is the approach we present here, termed DeepSynergy. DeepSynergy uses chemical and genomic information as input information, a normalization strategy to account for input data heterogeneity, and conical layers to model drug synergies. Results: DeepSynergy was compared to other machine learning methods such as Gradient Boosting Machines, Random Forests, Support Vector Machines and Elastic Nets on the largest publicly available synergy dataset with respect to mean squared error. DeepSynergy significantly outperformed the other methods with an improvement of 7.2% over the second best method at the prediction of novel drug combinations within the space of explored drugs and cell lines. At this task, the mean Pearson correlation coefficient between the measured and the predicted values of DeepSynergy was 0.73. Applying DeepSynergy for classification of these novel drug combinations resulted in a high predictive performance of an AUC of 0.90. Furthermore, we found that all compared methods exhibit low predictive performance when extrapolating to unexplored drugs or cell lines, which we suggest is due to limitations in the size and diversity of the dataset. We envision that DeepSynergy could be a valuable tool for selecting novel synergistic drug combinations. Availability and implementation: DeepSynergy is available via www.bioinf.jku.at/software/DeepSynergy. Contact: klambauer@bioinf.jku.at. Supplementary information: Supplementary data are available at Bioinformatics online.

Orthologue chemical space and its influence on target prediction.

Motivation: In silico approaches often fail to utilize bioactivity data available for orthologous targets due to insufficient evidence highlighting the benefit for such an approach. Deeper investigation into orthologue chemical space and its influence toward expanding compound and target coverage is necessary to improve the confidence in this practice. Results: Here we present analysis of the orthologue chemical space in ChEMBL and PubChem and its impact on target prediction. We highlight the number of conflicting bioactivities between human and orthologues is low and annotations are overall compatible. Chemical space analysis shows orthologues are chemically dissimilar to human with high intra-group similarity, suggesting they could effectively extend the chemical space modelled. Based on these observations, we show the benefit of orthologue inclusion in terms of novel target coverage. We also benchmarked predictive models using a time-series split and also using bioactivities from Chemistry Connect and HTS data available at AstraZeneca, showing that orthologue bioactivity inclusion statistically improved performance. Availability and implementation: Orthologue-based bioactivity prediction and the compound training set are available at www.github.com/lhm30/PIDGINv2. Contact: ab454@cam.ac.uk. Supplementary information: Supplementary data are available at Bioinformatics online.

Analysis of Differential Efficacy and Affinity of GABAA (α1/α2) Selective Modulators.

Selective modulators of the γ-amino butyric acid (GABAA) family of receptors have the potential to treat a range of disease states related to cognition, pain, and anxiety. While the development of various α subunit-selective modulators is currently underway for the treatment of anxiety disorders, a mechanistic understanding of the correlation between their bioactivity and efficacy, based on ligand-target interactions, is currently still lacking. In order to alleviate this situation, in the current study we have analyzed, using ligand- and structure-based methods, a data set of 5440 GABAA modulators. The Spearman correlation (ρ) between binding activity and efficacy of compounds was calculated to be 0.008 and 0.31 against the α1 and α2 subunits of GABA receptor, respectively; in other words, the compounds had little diversity in structure and bioactivity, but they differed significantly in efficacy. Two compounds were selected as a case study for detailed interaction analysis due to the small difference in their structures and affinities (ΔpKi(comp1_α1 - comp2_α1) = 0.45 log units, ΔpKi(comp1_α2 - comp2_α2) = 0 log units) as compared to larger relative efficacies (ΔRE(comp1_α1 - comp2_α1) = 1.03, ΔRE(comp1_α2 - comp2_α2) = 0.21). Docking analysis suggested that His-101 is involved in a characteristic interaction of the α1 receptor with both compounds 1 and 2. Residues such as Phe-77, Thr-142, Asn-60, and Arg-144 of the γ chain of the α1γ2 complex also showed interactions with heterocyclic rings of both compounds 1 and 2, but these interactions were disturbed in the case of α2γ2 complex docking results. Binding pocket stability analysis based on molecular dynamics identified three substitutions in the loop C region of the α2 subunit, namely, G200E, I201T, and V202I, causing a reduction in the flexibility of α2 compared to α1. These amino acids in α2, as compared to α1, were also observed to decrease the vibrational and dihedral entropy and to increase the hydrogen bond content in α2 in the apo state. However, freezing of both α1 and α2 was observed in the ligand-bound state, with an increased number of internal hydrogen bonds and increased entropy. Therefore, we hypothesize that the amino acid differences in the loop C region of α2 are responsible for conformational changes in the protein structure compared to α1, as well as for the binding modes of compounds and hence their functional signaling.

canSAR: updated cancer research and drug discovery knowledgebase.

canSAR (http://cansar.icr.ac.uk) is a public integrative cancer-focused knowledgebase for the support of cancer translational research and drug discovery. Through the integration of biological, pharmacological, chemical, structural biology and protein network data, it provides a single information portal to answer complex multidisciplinary questions including--among many others--what is known about a protein, in which cancers is it expressed or mutated, and what chemical tools and cell line models can be used to experimentally probe its activity? What is known about a drug, its cellular sensitivity profile and what proteins is it known to bind that may explain unusual bioactivity? Here we describe major enhancements to canSAR including new data, improved search and browsing capabilities and new target, cancer cell line, protein family and 3D structure summaries and tools.

Development of a novel azaspirane that targets the Janus kinase-signal transducer and activator of transcription (STAT) pathway in hepatocellular carcinoma in vitro and in vivo.

Signal transducer and activator of transcription 3 (STAT3) is a transcription factor that regulates genes involved in cell growth, proliferation, and survival, and given its association with many types of cancers, it has recently emerged as a promising target for therapy. In this work, we present the synthesis of N-substituted azaspirane derivatives and their biological evaluation against hepatocellular carcinoma (HCC) cells (IC50 = 7.3 µm), thereby identifying 2-(1-(4-(2-cyanophenyl)1-benzyl-1H-indol-3-yl)-5-(4-methoxy-phenyl)-1-oxa-3-azaspiro(5,5) undecane (CIMO) as a potent inhibitor of the JAK-STAT pathway with selectivity over normal LO2 cells (IC50 > 100 µm). The lead compound, CIMO, suppresses proliferation of HCC cells and achieves this effect by reducing both constitutive and inducible phosphorylation of JAK1, JAK2, and STAT3. Interestingly, CIMO displayed inhibition of Tyr-705 phosphorylation, which is required for nuclear translocation of STAT3, but it has no effect on Ser-727 phosphorylation. CIMO accumulates cancer cells in the sub-G1 phase and decreases STAT3 in the nucleus and thereby causes down-regulation of genes regulated via STAT3. Suppression of STAT3 phosphorylation by CIMO and knockdown of STAT3 mRNA using siRNA transfection displayed a similar effect on the viability of HCC cells. Furthermore, CIMO significantly decreased the tumor development in an orthotopic HCC mouse model through the modulation of phospho-STAT3, Ki-67, and cleaved caspase-3 in tumor tissues. Thus, CIMO represents a chemically novel and biologically in vitro and in vivo validated compound, which targets the JAK-STAT pathway as a potential cancer treatment.

Microwave-assisted synthesis, characterization and cytotoxic studies of novel estrogen receptor α ligands towards human breast cancer cells.

A new, simple, and microwave-assisted, solution-phase T3P®-DMSO mediated method for the preparation of a novel class of estrogen receptor alpha (ERα) ligands based on the 2-phenylquinoline scaffold was developed. Furthermore, the novel ERα ligands were tested for their bioactivity against ERα-positive and ERα-negative cell lines. The ligand (entry 4), with amine and nitro group substitution at C4 position, displayed significant cytotoxicity against MCF-7 and HepG2 cells with an IC50 value of 6 and 11µM, respectively. On the other hand, ERα-negative cells displayed resistance to quinolines induced cytotoxicity with an IC50 value >100Mm and they does not induce cytotoxicity in normal breast epithelial cells. Molecular docking analyses suggest a consistent binding mode for these ERα ligands in the ligand binding domain of the human ERα and predict the ligands to occupy the hydrophobic cavity in a similar fashion as estradiol or GW2368.

canSAR: an integrated cancer public translational research and drug discovery resource.

canSAR is a fully integrated cancer research and drug discovery resource developed to utilize the growing publicly available biological annotation, chemical screening, RNA interference screening, expression, amplification and 3D structural data. Scientists can, in a single place, rapidly identify biological annotation of a target, its structural characterization, expression levels and protein interaction data, as well as suitable cell lines for experiments, potential tool compounds and similarity to known drug targets. canSAR has, from the outset, been completely use-case driven which has dramatically influenced the design of the back-end and the functionality provided through the interfaces. The Web interface at http://cansar.icr.ac.uk provides flexible, multipoint entry into canSAR. This allows easy access to the multidisciplinary data within, including target and compound synopses, bioactivity views and expert tools for chemogenomic, expression and protein interaction network data.

Network-driven cancer cell avatars for combination discovery and biomarker identification for DNA damage response inhibitors.

Combination therapy is well established as a key intervention strategy for cancer treatment, with the potential to overcome monotherapy resistance and deliver a more durable efficacy. However, given the scale of unexplored potential target space and the resulting combinatorial explosion, identifying efficacious drug combinations is a critical unmet need that is still evolving. In this paper, we demonstrate a network biology-driven, simulation-based solution, the Simulated Cell™. Integration of omics data with a curated signaling network enables the accurate and interpretable prediction of 66,348 combination-cell line pairs obtained from a large-scale combinatorial drug sensitivity screen of 684 combinations across 97 cancer cell lines (BAC = 0.62, AUC = 0.7). We highlight drug combination pairs that interact with DNA Damage Response pathways and are predicted to be synergistic, and deep network insight to identify biomarkers driving combination synergy. We demonstrate that the cancer cell 'avatars' capture the biological complexity of their in vitro counterparts, enabling the identification of pathway-level mechanisms of combination benefit to guide clinical translatability.

Large-scale Pan-cancer Cell Line Screening Identifies Actionable and Effective Drug Combinations.

Oncology drug combinations can improve therapeutic responses and increase treatment options for patients. The number of possible combinations is vast and responses can be context-specific. Systematic screens can identify clinically relevant, actionable combinations in defined patient subtypes. We present data for 109 anticancer drug combinations from AstraZeneca's oncology small molecule portfolio screened in 755 pan-cancer cell lines. Combinations were screened in a 7 × 7 concentration matrix, with more than 4 million measurements of sensitivity, producing an exceptionally data-rich resource. We implement a new approach using combination Emax (viability effect) and highest single agent (HSA) to assess combination benefit. We designed a clinical translatability workflow to identify combinations with clearly defined patient populations, rationale for tolerability based on tumor type and combination-specific "emergent" biomarkers, and exposures relevant to clinical doses. We describe three actionable combinations in defined cancer types, confirmed in vitro and in vivo, with a focus on hematologic cancers and apoptotic targets. SIGNIFICANCE: We present the largest cancer drug combination screen published to date with 7 × 7 concentration response matrices for 109 combinations in more than 750 cell lines, complemented by multi-omics predictors of response and identification of "emergent" combination biomarkers. We prioritize hits to optimize clinical translatability, and experimentally validate novel combination hypotheses. This article is featured in Selected Articles from This Issue, p. 695.

Analysis of acquired resistance mechanisms to osimertinib in patients with EGFR-mutated advanced non-small cell lung cancer from the AURA3 trial.

Osimertinib, an epidermal growth factor receptor tyrosine kinase inhibitor (EGFR-TKI), potently and selectively inhibits EGFR-TKI-sensitizing and EGFR T790M resistance mutations. This analysis evaluates acquired resistance mechanisms to second-line osimertinib (n = 78) in patients with EGFR T790M advanced non-small cell lung cancer (NSCLC) from AURA3 (NCT02151981), a randomized phase 3 study comparing osimertinib with chemotherapy. Plasma samples collected at baseline and disease progression/treatment discontinuation are analyzed using next-generation sequencing. Half (50%) of patients have undetectable plasma EGFR T790M at disease progression and/or treatment discontinuation. Fifteen patients (19%) have >1 resistance-related genomic alteration; MET amplification (14/78, 18%) and EGFR C797X mutation (14/78, 18%).

Early Clearance of Plasma Epidermal Growth Factor Receptor Mutations as a Predictor of Outcome on Osimertinib in Advanced Non-Small Cell Lung Cancer; Exploratory Analysis from AURA3 and FLAURA.

PURPOSE: Plasma circulating tumor DNA (ctDNA) analysis is used for genotyping advanced non-small cell lung cancer (NSCLC); monitoring dynamic ctDNA changes may be used to predict outcomes. PATIENTS AND METHODS: This was a retrospective, exploratory analysis of two phase III trials [AURA3 (NCT02151981), FLAURA (NCT02296125)]. All patients had EGFR mutation-positive (EGFRm; ex19del or L858R) advanced NSCLC; AURA3 also included T790M-positive NSCLC. Osimertinib (FLAURA, AURA3), or comparator EGFR-tyrosine kinase inhibitor (EGFR-TKI; gefitinib/erlotinib; FLAURA), or platinum-based doublet chemotherapy (AURA3) was given. Plasma EGFRm was analyzed at baseline and Weeks 3/6 by droplet digital PCR. Outcomes were assessed by detectable/non-detectable baseline plasma EGFRm and plasma EGFRm clearance (non-detection) at Weeks 3/6. RESULTS: In AURA3 (n = 291), non-detectable versus detectable baseline plasma EGFRm had longer median progression-free survival [mPFS; HR, 0.48; 95% confidence interval (CI), 0.33-0.68; P < 0.0001]. In patients with Week 3 clearance versus non-clearance (n = 184), respectively, mPFS (months; 95% CI) was 10.9 (8.3-12.6) versus 5.7 (4.1-9.7) with osimertinib and 6.2 (4.0-9.7) versus 4.2 (4.0-5.1) with platinum-pemetrexed. In FLAURA (n = 499), mPFS was longer with non-detectable versus detectable baseline plasma EGFRm (HR, 0.54; 95% CI, 0.41-0.70; P < 0.0001). For Week 3 clearance versus non-clearance (n = 334), respectively, mPFS was 19.8 (15.1 to not calculable) versus 11.3 (9.5-16.5) with osimertinib and 10.8 (9.7-11.1) versus 7.0 (5.6-8.3) with comparator EGFR-TKI. Similar outcomes were observed by Week 6 clearance/non-clearance. CONCLUSIONS: Plasma EGFRm analysis as early as 3 weeks on-treatment has the potential to predict outcomes in EGFRm advanced NSCLC.

Comparison of classical tumour growth models for patient derived and cell-line derived xenografts using the nonlinear mixed-effects framework.

In this study we compare seven mathematical models of tumour growth using nonlinear mixed-effects which allows for a simultaneous fitting of multiple data and an estimation of both mean behaviour and variability. This is performed for two large datasets, a patient-derived xenograft (PDX) dataset consisting of 220 PDXs spanning six different tumour types and a cell-line derived xenograft (CDX) dataset consisting of 25 cell lines spanning eight tumour types. Comparison of the models is performed by means of visual predictive checks (VPCs) as well as the Akaike Information Criterion (AIC). Additionally, we fit the models to 500 bootstrap samples drawn from the datasets to expand the comparison of the models under dataset perturbations and understand the growth kinetics that are best fitted by each model. Through qualitative and quantitative metrics the best models are identified the effectiveness and practicality of simpler models is highlighted.

Knowledge graph-based recommendation framework identifies drivers of resistance in EGFR mutant non-small cell lung cancer.

Resistance to EGFR inhibitors (EGFRi) presents a major obstacle in treating non-small cell lung cancer (NSCLC). One of the most exciting new ways to find potential resistance markers involves running functional genetic screens, such as CRISPR, followed by manual triage of significantly enriched genes. This triage process to identify 'high value' hits resulting from the CRISPR screen involves manual curation that requires specialized knowledge and can take even experts several months to comprehensively complete. To find key drivers of resistance faster we build a recommendation system on top of a heterogeneous biomedical knowledge graph integrating pre-clinical, clinical, and literature evidence. The recommender system ranks genes based on trade-offs between diverse types of evidence linking them to potential mechanisms of EGFRi resistance. This unbiased approach identifies 57 resistance markers from >3,000 genes, reducing hit identification time from months to minutes. In addition to reproducing known resistance markers, our method identifies previously unexplored resistance mechanisms that we prospectively validate.

Identification of a Molecularly-Defined Subset of Breast and Ovarian Cancer Models that Respond to WEE1 or ATR Inhibition, Overcoming PARP Inhibitor Resistance.

PURPOSE: PARP inhibitors (PARPi) induce synthetic lethality in homologous recombination repair (HRR)-deficient tumors and are used to treat breast, ovarian, pancreatic, and prostate cancers. Multiple PARPi resistance mechanisms exist, most resulting in restoration of HRR and protection of stalled replication forks. ATR inhibition was highlighted as a unique approach to reverse both aspects of resistance. Recently, however, a PARPi/WEE1 inhibitor (WEE1i) combination demonstrated enhanced antitumor activity associated with the induction of replication stress, suggesting another approach to tackling PARPi resistance. EXPERIMENTAL DESIGN: We analyzed breast and ovarian patient-derived xenoimplant models resistant to PARPi to quantify WEE1i and ATR inhibitor (ATRi) responses as single agents and in combination with PARPi. Biomarker analysis was conducted at the genetic and protein level. Metabolite analysis by mass spectrometry and nucleoside rescue experiments ex vivo were also conducted in patient-derived models. RESULTS: Although WEE1i response was linked to markers of replication stress, including STK11/RB1 and phospho-RPA, ATRi response associated with ATM mutation. When combined with olaparib, WEE1i could be differentiated from the ATRi/olaparib combination, providing distinct therapeutic strategies to overcome PARPi resistance by targeting the replication stress response. Mechanistically, WEE1i sensitivity was associated with shortage of the dNTP pool and a concomitant increase in replication stress. CONCLUSIONS: Targeting the replication stress response is a valid therapeutic option to overcome PARPi resistance including tumors without an underlying HRR deficiency. These preclinical insights are now being tested in several clinical trials where the PARPi is administered with either the WEE1i or the ATRi.

Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen.

The effectiveness of most cancer targeted therapies is short-lived. Tumors often develop resistance that might be overcome with drug combinations. However, the number of possible combinations is vast, necessitating data-driven approaches to find optimal patient-specific treatments. Here we report AstraZeneca's large drug combination dataset, consisting of 11,576 experiments from 910 combinations across 85 molecularly characterized cancer cell lines, and results of a DREAM Challenge to evaluate computational strategies for predicting synergistic drug pairs and biomarkers. 160 teams participated to provide a comprehensive methodological development and benchmarking. Winning methods incorporate prior knowledge of drug-target interactions. Synergy is predicted with an accuracy matching biological replicates for >60% of combinations. However, 20% of drug combinations are poorly predicted by all methods. Genomic rationale for synergy predictions are identified, including ADAM17 inhibitor antagonism when combined with PIK3CB/D inhibition contrasting to synergy when combined with other PI3K-pathway inhibitors in PIK3CA mutant cells.

Neighbours of cancer-related proteins have key influence on pathogenesis and could increase the drug target space for anticancer therapies.

Even targeted chemotherapies against solid cancers show a moderate success increasing the need to novel targeting strategies. To address this problem, we designed a systems-level approach investigating the neighbourhood of mutated or differentially expressed cancer-related proteins in four major solid cancers (colon, breast, liver and lung). Using signalling and protein-protein interaction network resources integrated with mutational and expression datasets, we analysed the properties of the direct and indirect interactors (first and second neighbours) of cancer-related proteins, not found previously related to the given cancer type. We found that first neighbours have at least as high degree, betweenness centrality and clustering coefficient as cancer-related proteins themselves, indicating a previously unknown central network position. We identified a complementary strategy for mutated and differentially expressed proteins, where the affect of differentially expressed proteins having smaller network centrality is compensated with high centrality first neighbours. These first neighbours can be considered as key, so far hidden, components in cancer rewiring, with similar importance as mutated proteins. These observations strikingly suggest targeting first neighbours as a novel strategy for disrupting cancer-specific networks. Remarkably, our survey revealed 223 marketed drugs already targeting first neighbour proteins but applied mostly outside oncology, providing a potential list for drug repurposing against solid cancers. For the very central first neighbours, whose direct targeting would cause several side effects, we suggest a cancer-mimicking strategy by targeting their interactors (second neighbours of cancer-related proteins, having a central protein affecting position, similarly to the cancer-related proteins). Hence, we propose to include first neighbours to network medicine based approaches for (but not limited to) anticancer therapies.

Modelling of compound combination effects and applications to efficacy and toxicity: state-of-the-art, challenges and perspectives.

The development of treatments involving combinations of drugs is a promising approach towards combating complex or multifactorial disorders. However, the large number of compound combinations that can be generated, even from small compound collections, means that exhaustive experimental testing is infeasible. The ability to predict the behaviour of compound combinations in biological systems, whittling down the number of combinations to be tested, is therefore crucial. Here, we review the current state-of-the-art in the field of compound combination modelling, with the aim to support the development of approaches that, as we hope, will finally lead to an integration of chemical with systems-level biological information for predicting the effect of chemical mixtures.

Novel Adamantanyl-Based Thiadiazolyl Pyrazoles Targeting EGFR in Triple-Negative Breast Cancer.

The epidermal growth factor receptor (EGFR) is a validated therapeutic target for triple-negative breast cancer (TNBC). In the present study, we synthesize novel adamantanyl-based thiadiazolyl pyrazoles by introducing the adamantane ring to thiazolopyrazoline. On the basis of loss of cell viability in TNBC cells, 4-(adamantan-1-yl)-2-(3-(2,4-dichlorophenyl)-5-phenyl-4,5-dihydro-1H-pyrazol-1-yl)thiazole (APP) was identified as a lead compound. Using a Parzen-Rosenblatt Window classifier, APP was predicted to target the EGFR protein, and the same was confirmed by surface plasmon resonance. Further analysis revealed that APP suppressed the phosphorylation of EGFR at Y992, Y1045, Y1068, Y1086, Y1148, and Y1173 in TNBC cells. APP also inhibited the phosphorylation of ERK at Y204 and of STAT3 at Y705, implying that APP downregulates the activity of EGFR downstream effectors. Small interfering RNA mediated depletion of EGFR expression prevented the effect of APP in BT549 and MDA-MB-231 cells, indicating that APP specifically targets the EGFR. Furthermore, APP modulated the expression of the proteins involved in cell proliferation and survival. In addition, APP altered the expression of epithelial-mesenchymal transition related proteins and suppressed the invasion of TNBC cells. Hence, we report a novel and specific inhibitor of the EGFR signaling cascade.