Biomarkers Of Drug Sensitivity Research Articles

Abstract PO-031: Systematic discovery of chemotherapy response biomarkers in Peripheral T Cell Lymphomas

Abstract Background. Identifying which patients will benefit from individual therapies remains a general challenge in oncology. Predictive biomarkers of drug sensitivity, when known, can increase the rate of success of trials, and allow stratification of patients for targeted combination therapies, as recent shown by the GUIDANCE-01 trial in Large B-Cell Lymphoma. Peripheral T-Cell Lymphomas (PTCL) could particularly benefit from this approach, being heterogeneous diseases against which many therapies are active in unpredictable subsets of patients. A central challenge of biomarker discovery is finding true determinants of drug response, which may be multiple genes, among thousands of molecular features that may accidentally correlate. Here, we aim to mitigate this challenge by combining functional genetic screens and gene expression profiling in diverse PTCL cultures, to enable the systematic discovery of drug sensitivity biomarkers. Methods. To discover genes whose expression directly modifies drug sensitivity, we conducted genome-wide CRISPR screens with PTCL cells under treatment with five therapies with clinical activity in PTCL: Romidepsin, Pralatrexate, Gemcitabine, Oxaliplatin, and Bortezomib. To discover genes whose basal expression significantly correlates with specific drug sensitivities, we measured RNAseq and drug response functions for a diverse panel of 27 PTCL cultures. Genes in the intersection of both experiments are causally related to and correlate with drug responses in PTCL, and have the statistical benefit of detection by independent methods. Results. Functional genetic screens on therapy provided mechanistic insights for each drug of interest, and identified genes whose perturbation affects drug sensitivity. Whereas hundreds of genes nominally correlate with drug sensitivity in cell line panels, for each drug a shortlist of only 5 to 20 genes are both CRISPR hits and correlate with response across PTCL cultures. For each drug tested, multi-gene sensitivity scores constructed from hits stratify PTCL cultures into statistically distinct sensitive and non-sensitive subgroups (Mann Whitney P-Values <0.01). These genes’ relationships to drug mechanisms were often supported by prior studies, including functions in DNA repair, cell cycle regulation, and solute carriers required for cellular entry of specific therapies, such as SLC19A1 for Pralatrexate and SLC43A2 for Oxaliplatin. Conclusions. Combining functional genetic screens and correlative drug sensitivity measurements narrowed the search for predictive biomarkers of drug sensitivity, and may be a general means of refining biomarker hypotheses for validation in clinical datasets. Although chemotherapy sensitivity is commonly polygenic, multi-gene scores based on few mechanistically-related genes were able to significantly distinguish drug sensitive from resistant PTCLs. These approaches provide novel hypotheses for drug-gene relationships that may serve as the basis for molecular subtyping of individual lymphomas for precision regimens. Citation Format: Adam C Palmer, Jacob C Pantazis. Systematic discovery of chemotherapy response biomarkers in Peripheral T Cell Lymphomas [abstract]. In: Proceedings of the Fourth AACR International Meeting on Advances in Malignant Lymphoma: Maximizing the Basic-Translational Interface for Clinical Application; 2024 Jun 19-22; Philadelphia, PA. Philadelphia (PA): AACR; Blood Cancer Discov 2024;5(3_Suppl):Abstract nr PO-031.

VDX-111 targets proliferative pathways in canine cancer cell lines.

VDX-111 (also identified as AMPI-109) is a vitamin D derivative which has shown anticancer activity. To further assess the function of this compound against multiple cancer types, we examined the efficacy of VDX-111 against a panel of 30 well characterized canine cancer cell lines. Across a variety of cancer types, VDX-111 induced widely variable growth inhibition, cell death, and migration inhibition, at concentrations ranging from 10 nM to 1 μM. Growth inhibition sensitivity did not correlate strongly with tumor cell histotype; however, it was significantly correlated with the expression of genes in multiple cell signaling pathways, including the MAPK and PI3K-AKT pathways. We confirmed inhibition of these signaling pathways as likely participants in the effects of VDX-111. These results suggest that a subset of canine tumors may be sensitive to treatment with VDX-111, and suggests possible predictive markers of drug sensitivity and pharmacodynamic biomarkers of drug exposure that could be employed in future clinical trials.

The diagnostic/prognostic roles and biological function of the IFIT family members in acute myeloid leukemia

BackgroundThe Interferon-induced protein with tetratricopeptide repeat (IFIT) family, IFIT1/2/3/5, play an important role in different tumors progression. However, the prognosis significance and biological role of IFIT family members in acute myeloid leukemia (AML) remains unclear.MethodsWe obtained the gene expression data and clinical information of 173 AML patients from The Cancer Genome Atlas (TCGA) database. Several databases were used in our study, including GEPIA, MethSurv, STRING, GSCA and GeneMANIA database.ResultsThe mRNA expression of IFIT1/2/3/5 was elevated in AML patients and had a high ability to distinguish AML from controls based on the receiver operating characteristic (ROC) curve (AUC > 0.9). Kaplan–Meier survival analysis showed that higher levels of IFIT2/3/5 expression predict poor prognosis in AML patients. Besides, the DNA methylation analysis suggested that 7 CpG sites of IFIT2, 4 CpG sites of IFIT3 and 10 CpG sites of IFIT5 were significantly associated with the prognosis of AML patients. In addition, IFIT2/3/5 expression was significantly positively associated with the immune cell infiltration and immune checkpoint expression, such as CTLA4, PDCD1, LAG3, and TIGIT. Finally, drug sensitivity analysis revealed that AML patients with high expression of IFIT2/3/5 were resistant to multiple drugs, but sensitive to dasatinib.ConclusionIFIT family genes might serve as biomarkers for diagnosis, prognosis and drug sensitivity in AML patients. The activation or blocking of IFIT-related signaling pathways may provide novel insights into immunotherapy for patients with AML.

Patient-Derived Ex Vivo Cultures and Endpoint Assays with Surrogate Biomarkers in Functional Testing for Prediction of Therapeutic Response.

Prediction of therapeutic outcomes is important for cancer patients in order to reduce side effects and improve the efficacy of anti-cancer drugs. Currently, the most widely accepted method for predicting the efficacy of anti-cancer drugs is gene panel testing based on next-generation sequencing. However, gene panel testing has several limitations. For example, only 10% of cancer patients are estimated to have druggable mutations, even if whole-exome sequencing is applied. Additionally, even if optimal drugs are selected, a significant proportion of patients derive no benefit from the indicated drug treatment. Furthermore, most of the anti-cancer drugs selected by gene panel testing are molecularly targeted drugs, and the efficacies of cytotoxic drugs remain difficult to predict. Apart from gene panel testing, attempts to predict chemotherapeutic efficacy using ex vivo cultures from cancer patients have been increasing. Several groups have retrospectively demonstrated correlations between ex vivo drug sensitivity and clinical outcome. For ex vivo culture, surgically resected tumor tissue is the most abundant source. However, patients with recurrent or metastatic tumors do not usually undergo surgery, and chemotherapy may be the only option for those with inoperable tumors. Therefore, predictive methods using small amounts of cancer tissue from diagnostic materials such as endoscopic, fine-needle aspirates, needle cores and liquid biopsies are needed. To achieve this, various types of ex vivo culture and endpoint assays using effective surrogate biomarkers of drug sensitivity have recently been developed. Here, we review the variety of ex vivo cultures and endpoint assays currently available.

The pharmacoepigenomic landscape of cancer cell lines reveals the epigenetic component of drug sensitivity

Aberrant DNA methylation accompanies genetic alterations during oncogenesis and tumour homeostasis and contributes to the transcriptional deregulation of key signalling pathways in cancer. Despite increasing efforts in DNA methylation profiling of cancer patients, there is still a lack of epigenetic biomarkers to predict treatment efficacy. To address this, we analyse 721 cancer cell lines across 22 cancer types treated with 453 anti-cancer compounds. We systematically detect the predictive component of DNA methylation in the context of transcriptional and mutational patterns, i.e., in total 19 DNA methylation biomarkers across 17 drugs and five cancer types. DNA methylation constitutes drug sensitivity biomarkers by mediating the expression of proximal genes, thereby enhancing biological signals across multi-omics data modalities. Our method reproduces anticipated associations, and in addition, we find that the NEK9 promoter hypermethylation may confer sensitivity to the NEDD8-activating enzyme (NAE) inhibitor pevonedistat in melanoma through downregulation of NEK9. In summary, we envision that epigenomics will refine existing patient stratification, thus empowering the next generation of precision oncology.

Plasma cytokine profiles and survival outcomes in the 1801 phase 1/2 clinical trial of 9-ING-41 (elraglusib) in patients with advanced cancer.

e14555 Background: 9-ING-41 (elraglusib) is a novel inhibitor of GSK-3β that has shown early signs of clinical benefit in a phase 1/2 clinical trial (ACT1801; NCT03678883). Early data support a multi-modal mechanism of action for elraglusib that targets both the tumor and immune system. Thus, the discovery and validation of biomarkers of drug sensitivity to elraglusib is a high priority. Here, we take inspiration from the literature on checkpoint inhibitor therapy and explore the potential of cytokines to predict elraglusib clinical response. Methods: Peripheral plasma samples from 59 patients enrolled in the 1801 phase 1/2 trial of elraglusib were assayed for 40 circulating cytokine levels. Patients advanced solid tumors refractory to standard treatments and received either elraglusib (1.0-15.0 mg/kg) as a single agent or in combination with other chemotherapies. Samples were taken from time points prior to elraglusib administration (pre-dose), after cycle 1, or after cycle 2. Each cytokine time point combination was used to stratify patients into high and low categories using an optimal cut-point determined using maximally selected rank statistics. Kaplan Meier and Cox Proportional Hazards analysis was used to determine the efficacy of each cytokine as a biomarker. The change in cytokine values between pre-dose and cycle 1 or pre-dose and cycle 2 was evaluated in a similar manner. Results: A total of 142 samples spanning eight different tumor histologies were collected and analyzed. A total of 240 cytokine-timepoint combinations were evaluated, and 53 significantly stratified patients by overall survival (p-value < 0.05). Of those, 35 showed that higher levels of the given cytokine correlated with a survival benefit and 18 a survival decrease. Notable among the cytokines demonstrating survival benefits were Granzyme B at Cycle 1 Day 4 (HR: 9.54, p-value:0.015) and TGF β at Cycle 1 Day 4 (HR: 8.48, p-value:0.0063). Strong hazard ratios were also observed for cytokines that correlated with survival decreases including TRAIL-R2 at Cycle 1 Day 2 (HR: 9.56e-02, p-value:0.0001), and IL-10 at Cycle 1 Day 4 (HR: 8.77e-02, p-value:0.007). Delta between timepoints was also able to stratifying patients by overall survival. Conclusions: Plasma cytokine profiling is a promising approach for discovery and validation of biomarkers prognostic for elraglusib clinical benefit. Numerous cytokines measured pre-dose stratified patients into significant survival groups suggesting a potential strategy for patient enrichment in clinical trials of elraglusib. These initial findings are being expanded by 1) increasing the cohort to accommodate histology specific investigations; 2) examining which cytokines are elraglusib response-specific versus drug-agnostic; and 3) combining cytokines in multivariate and machine learning models for optimal predictive capacity. Clinical trial information: NCT03678883 .

VCAN Hypomethylation and Expression as Predictive Biomarkers of Drug Sensitivity in Upper Urinary Tract Urothelial Carcinoma.

Versican (VCAN), also known as extracellular matrix proteoglycan 2, has been suggested as a potential biomarker in cancers. Previous research has found that VCAN is highly expressed in bladder cancer. However, its role in predicting outcomes for patients with upper urinary tract urothelial cancer (UTUC) is not well understood. In this study, we collected tissues from 10 patients with UTUC, including 6 with and 4 without lymphovascular invasion (LVI), a pathological feature that plays a significant role in determining metastasis. Results from RNA sequencing revealed that the most differentially expressed genes were involved in extracellular matrix organization. Using the TCGA database for clinical correlation, VCAN was identified as a target for study. A chromosome methylation assay showed that VCAN was hypomethylated in tumors with LVI. In our patient samples, VCAN expression was also found to be high in UTUC tumors with LVI. In vitro analysis showed that knocking down VCAN inhibited cell migration but not proliferation. A heatmap analysis also confirmed a significant correlation between VCAN and migration genes. Additionally, silencing VCAN increased the effectiveness of cisplatin, gemcitabine and epirubicin, thus providing potential opportunities for clinical application.

Deep thermal profiling for detection of functional proteoform groups.

The complexity of the functional proteome extends considerably beyond the coding genome, resulting in millions of proteoforms. Investigation of proteoforms and their functional roles is important to understand cellular physiology and its deregulation in diseases but challenging to perform systematically. Here we applied thermal proteome profiling with deep peptide coverage to detect functional proteoform groups in acute lymphoblastic leukemia cell lines with different cytogenetic aberrations. We detected 15,846 proteoforms, capturing differently spliced, cleaved and post-translationally modified proteins expressed from 9,290 genes. We identified differential co-aggregation of proteoform pairs and established links to disease biology. Moreover, we systematically made use of measured biophysical proteoform states to find specific biomarkers of drug sensitivity. Our approach, thus, provides a powerful and unique tool for systematic detection and functional annotation of proteoform groups.

Visualizing DNA Damage Repair Proteins in Patient-Derived Ovarian Cancer Organoids via Immunofluorescence Assays.

Immunofluorescence is one of the most widely used techniques to visualize target antigens with high sensitivity and specificity, allowing for the accurate identification and localization of proteins, glycans, and small molecules. While this technique is well-established in two-dimensional (2D) cell culture, less is known about its use in three-dimensional (3D) cell models. Ovarian cancer organoids are 3D tumor models that recapitulate tumor cell clonal heterogeneity, the tumor microenvironment, and cell-cell and cell-matrix interactions. Thus, they are superior to cell lines for the evaluation of drug sensitivity and functional biomarkers. Therefore, the ability to utilize immunofluorescence on primary ovarian cancer organoids is extremely beneficial in understanding the biology of this cancer. The current study describes the technique of immunofluorescence to detect DNA damage repair proteins in high-grade serous patient-derived ovarian cancer organoids (PDOs). After exposing the PDOs to ionizing radiation, immunofluorescence is performed on intact organoids to evaluate nuclear proteins as foci. Images are collected using z-stack imaging on confocal microscopy and analyzed using automated foci counting software. The described methods allow for the analysis of temporal and special recruitment of DNA damage repair proteins and colocalization of these proteins with cell-cycle markers.

Enabling Single-Cell Drug Response Annotations from Bulk RNA-Seq Using SCAD.

The single-cell RNAsequencing (scRNA-seq) quantifies the gene expression of individual cells, while the bulk RNA sequencing (bulk RNA-seq) characterizes the mixed transcriptome of cells. The inference of drug sensitivities for individual cells can provide new insights to understand the mechanism of anti-cancer response heterogeneity and drug resistance at the cellular resolution. However, pharmacogenomic information related to their corresponding scRNA-Seq is often limited. Therefore, a transfer learning model is proposed to infer the drug sensitivities at single-cell level. This framework learns bulk transcriptome profiles and pharmacogenomics information from population cell lines in a large public dataset and transfers the knowledge to infer drug efficacy of individual cells. The results suggest that it is suitable to learn knowledge from pre-clinical cell lines to infer pre-existing cell subpopulations with different drug sensitivities prior to drug exposure. In addition, the model offers a new perspective on drug combinations. It is observed that drug-resistant subpopulation can be sensitive to other drugs (e.g., a subset of JHU006 is Vorinostat-resistant while Gefitinib-sensitive); such finding corroborates the previously reported drug combination (Gefitinib + Vorinostat) strategy in several cancer types. The identified drug sensitivity biomarkers reveal insights into the tumor heterogeneity and treatment at cellular resolution.

Abstract 239: Assessment of immunotherapeutic efficacy of entinostat by using the 3d-explore ex vivo platform utilizing tumoroids of fresh patient tumor samples with intact tumor microenvironment

Abstract Background: Entinostat, a selective histone deacetylase 1/3 inhibitor has been shown to promote a robust anti-tumor response and increased neoantigen expression and antigen-specific T cell activation in preclinical tumor models. Entinostat plays a role in neutralizing myeloid derived suppressor cells (MDSC) to improve anti-tumor immune response. Entinostat is currently being tested in later-stage clinical trials in various types of cancer. Using a novel 3D ex-vivo platform with fresh patient tumor samples we assessed the therapeutic efficacy of Entinostat with intact stromal components and tumor immune microenvironment. Methods: All tumor samples were obtained with patient consent and relevant IRB approval. Unpropagated 3D tumoroids with intact TME measuring 150 µm in size were prepared from fresh tumor samples from renal cell carcinoma (RCC) patients using a proprietary technology developed at Nilogen Oncosystems. Tumoroids prepared from each patient’s tumor sample were pooled to represent the tumor heterogeneity and treated ex vivo with Entinostat for 48h to detect treatment-mediated changes in tumor immune cell composition including lymphoid and myeloid markers and their activation status. Results: Tumoroids treated with Entinostat increased NK, NKT, CD4 and CD8+T cells compared to untreated control. Ex vivo treatment with Entinostat led to an increase in CD69 and Granzyme B expression in tumor resident CD4+ T cells. Immune checkpoint receptors, 41BB and PD-1 expression was increased in CD8+T cells followed by Entinostat treatment. Decreased monocytic MDSC was seen in Entinostat treated tumoroids compared to untreated control and this was associated with decreased GM-CSF, IL-4, IL-6 cytokine levels and increased IFN-γ and IL-2, quantified by multiplex cytokine assay. Interestingly, the tumor cell killing study revealed a higher percentage of death in early stage MDSC (eMDSC) indicating a direct effect of Entinostat on MDSC survival. Conclusions: These results demonstrate that Entinostat treatment leads to a broad range of immune cell activation and MDSC inhibition in RCC. These data provide a mechanistic rationale utilizing our 3D tumoroid platform for discovery of potential biomarkers of drug sensitivity and to identify novel immunotherapeutic approaches. Clinical applications of 3D-EXplore may help to identify RCC patients who may likely benefit from Entinostat treatment. Citation Format: Krithika Nandakumar Kodumudi, Brittany Bunch, Jared Ehrhart, Matt Weitzman, Olivia MacIntosh, Kelly Sussman, Soner Altiok. Assessment of immunotherapeutic efficacy of entinostat by using the 3d-explore ex vivo platform utilizing tumoroids of fresh patient tumor samples with intact tumor microenvironment [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 239.

Abstract LB519: Bimodality of gene expression in cancer patients as interpretable biomarkers for drug sensitivity

Abstract Identifying biomarkers predictive of cancer cells’ response to drug treatment constitutes one of the main challenges in precision oncology. Recent large-scale cancer pharmacogenomic studies have opened new avenues of research to develop predictive biomarkers by profiling thousands of human cancer cell lines at the molecular level and screening them with hundreds of approved drugs and experimental chemical compounds. Many studies have leveraged these data to build predictive models of response using various statistical and machine learning methods. However, a common challenge in these methods is the lack of interpretability as to how they make the predictions, hindering the clinical translation of these models. To alleviate this issue, we used the recent logic modeling approach to develop a new machine learning pipeline that explores the space of bimodally expressed genes in multiple large in vitro pharmacogenomic studies and builds multivariate, nonlinear, yet interpretable logic-based models predictive of drug response. We showcased the performance of the approach in a compendium of the three largest in vitro pharmacogenomic data sets to build robust and interpretable models for 101 drugs that span 17 drug classes with high validation rate in independent datasets. These results along with in vivo validation support a better translation of gene expression biomarkers between model systems using bimodal genes. Citation Format: Benjamin Haibe-Kains, Wail Ba-alawi. Bimodality of gene expression in cancer patients as interpretable biomarkers for drug sensitivity [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr LB519.

A Bayesian model of dose-response for cancer drug studies

Exploratory cancer drug studies test multiple tumor cell lines against multiple candidate drugs. The goal in each paired (cell line, drug) experiment is to map out the dose-response curve of the cell line as the dose level of the drug increases. We propose Bayesian tensor filtering (BTF), a hierarchical Bayesian model for dose-response modeling in multisample, multitreatment cancer drug studies. BTF uses low-dimensional embeddings to share statistical strength between similar drugs and similar cell lines. Structured shrinkage priors in BTF encourage smoothness in the dose-response curves while remaining adaptive to sharp jumps when the data call for it. We focus on a pair of cancer drug studies exhibiting a particular pathology in their experimental design, leading us to a nonconjugate monotone mixture-of-gammas likelihood. To perform posterior inference, we develop a variant of the elliptical slice sampling algorithm for sampling from linearly-constrained multivariate normal priors with nonconjugate likelihoods. In benchmarks, BTF outperforms state-of-the-art methods for covariance regression and dynamic Poisson matrix factorization. On the two cancer drug studies, BTF outperforms the current standard approach in biology and reveals potential new biomarkers of drug sensitivity in cancer. Code is available at https://github.com/tansey/functionalmf.

Bimodal Gene Expression in Patients with Cancer Provides Interpretable Biomarkers for Drug Sensitivity.

A new machine learning pipeline exploits the bimodality of gene expression to provide a reliable set of candidate predictive biomarkers with a high potential for clinical translatability.

Inferred Ancestral Origin of Cancer Cell Lines Associates with Differential Drug Response.

Disparities between risk, treatment outcomes and survival rates in cancer patients across the world may be attributed to socioeconomic factors. In addition, the role of ancestry is frequently discussed. In preclinical studies, high-throughput drug screens in cancer cell lines have empowered the identification of clinically relevant molecular biomarkers of drug sensitivity; however, the genetic ancestry from tissue donors has been largely neglected in this setting. In order to address this, here, we show that the inferred ancestry of cancer cell lines is conserved and may impact drug response in patients as a predictive covariate in high-throughput drug screens. We found that there are differential drug responses between European and East Asian ancestries, especially when treated with PI3K/mTOR inhibitors. Our finding emphasizes a new angle in precision medicine, as cancer intervention strategies should consider the germline landscape, thereby reducing the failure rate of clinical trials.

Abstract 395: Prediction of genomic based drug sensitivity signatures to enable optimal drug positioning

Abstract Cancer by nature, is a heterogeneous disease, which can lead to highly variable patient responses for targeted therapies - even within the same clinically defined cancer type or subtype. Identifying drug sensitivity biomarkers, patient specific traits that are highly correlated with positive response, has proven to be an effective strategy to identify positioning opportunities and selecting patients. Here, we describe our biomarker identification workflow which identifies drug specific genomic sensitivity signatures, a collection of genomic aberrations that are found to be predictive of patient response, which can be used for patient selection as well as understanding a compound's mechanism of action. Using available drug efficacy data (in vitro or in vivo results) with paired baseline genomics data, we build diverse models to predict sample sensitivity to a drug. For every model, we train and measure the performance and how each genomic aberration contributes to model performance, those that do not sufficiently increase predictability are removed. This process is repeated, with each new model training on a smaller subset of genomic aberrations, until we have the minimum number of genomic aberrations needed to reach peak predictive performance. The resulting set of genomic aberrations make up a genomic sensitivity signature. Instead of using one type of algorithm to build these models, we train three distinct model types: linear, decision tree and custom kernel based. The multiple model architecture allows us to model the unique underlying biological mechanism of a compound's efficacy, such as synthetic lethal relationships or resistant pathway deactivation, ultimately giving us a collection of robust biomarker signatures. In addition to mechanistic understanding, clinical feasibility was a top priority. Therefore, our workflow architecture has been tested and validated to incorporate mutation, copy number alteration and/or gene expression based biomarkers either in combination or alone. This flexibility lowers the data required to use our workflow, making it more widely available to investigational drugs. Our identification of genomic sensitivity signatures can then be used for clinical patient selection or positioning a compound for a clinically defined cancer type, based on the prevalence of the predicted signature. Overall, this workflow is a powerful approach identifying diverse, mechanism based drug sensitivity signatures that can enable identifying the right patient for a therapy of interest. Citation Format: Coryandar Gilvary, Olivier Elemento, Neel Madhukar. Prediction of genomic based drug sensitivity signatures to enable optimal drug positioning [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 395.

Abstract PO-070: Bimodality of gene expression in cancer patient tumors as interpretable biomarkers for drug sensitivity

Abstract Identifying biomarkers predictive of cancer cells’ response to drug treatment constitutes one of the main challenges in precision oncology. Recent large-scale cancer pharmacogenomic studies have boosted the research for finding predictive biomarkers by profiling thousands of human cancer cell lines at the molecular level and screening them with hundreds of approved drugs and experimental chemical compounds. Many studies have leveraged these data to build predictive models of response using various statistical and machine learning methods. However, a common challenge in these methods is the lack of interpretability as to how they make the predictions and which features were the most associated with response, hindering the clinical translation of these models. To alleviate this issue, we develop a new machine learning pipeline based on the recent LOBICO approach that explores the space of bimodally expressed genes in multiple large in vitro pharmacogenomic studies and builds multivariate, nonlinear, yet interpretable logic-based models predictive of drug response. Using our method, we used a compendium of three of the largest pharmacogenomic data sets to build robust and interpretable models for 101 drugs that span 17 drug classes with high validation rate in independent datasets. Citation Format: Wail Ba-alawi, Sisira Kadambat Nair, Bo Li, Anthony Mammoliti, Petr Smirnov, Arvind Singh Mer, Linda Penn, Benjamin Haibe-Kains. Bimodality of gene expression in cancer patient tumors as interpretable biomarkers for drug sensitivity [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-070.

Surrogate endpoints for early-stage breast cancer: a review of the state of the art, controversies, and future prospects.

Drug approval for early-stage breast cancer (EBC) has been historically granted in the context of registration trials based on adequate outcomes such as disease-free survival and overall survival. Improvements in long-term outcomes have made it more difficult to demonstrate the clinical benefit of a new cancer drug in large, randomized, comparative clinical trials. Therefore, the use of surrogate endpoints rather than traditional measures allows for cancer drug trials to proceed with smaller sample sizes and shorter follow-up periods, which reduces drug development time. Among surrogate endpoints for breast cancer, the increase in pathological complete response (pCR) rates was considered appropriate for accelerated drug approval. The association between pCR and long-term outcomes was strongest in patients with aggressive tumor subtypes, such as triple-negative and human epidermal growth factor receptor 2 (HER2)-positive/hormone receptor-negative breast cancers. Whereas in hormone receptor-positive/HER2-negative EBC, the most accepted surrogate markers for endocrine therapy–based trials include changes in Ki67 and the preoperative endocrine prognostic index. Beyond the classic endpoints, further prognostic tools are required to provide EBC patients with individualized and effective therapies, and the neoadjuvant setting provides an excellent platform for drug development and biomarker discovery. Nowadays, the availability of multigene signatures is offering a standardized quantitative and reproducible tool to potentiate the efficacy of standard treatment for high-risk patients and develop de-escalated treatments for patients at lower risk of relapse. In this article, we first evaluate the surrogacies used for long-term outcomes and the underlying evidence supporting the use of each surrogate endpoint for the accelerated or regular drug approval process in EBC. Next, we provide an overview of the most recent studies and innovative strategies in a (neo)adjuvant setting as a platform to accelerate new drug approval. Finally, we highlight some clinical trials aimed at tailoring systemic treatment of EBC using prognosis-related factors or early biomarkers of drug sensitivity or resistance.

A recursive framework for predicting the time-course of drug sensitivity

The biological processes involved in a drug’s mechanisms of action are oftentimes dynamic, complex and difficult to discern. Time-course gene expression data is a rich source of information that can be used to unravel these complex processes, identify biomarkers of drug sensitivity and predict the response to a drug. However, the majority of previous work has not fully utilized this temporal dimension. In these studies, the gene expression data is either considered at one time-point (before the administration of the drug) or two time-points (before and after the administration of the drug). This is clearly inadequate in modeling dynamic gene–drug interactions, especially for applications such as long-term drug therapy. In this work, we present a novel REcursive Prediction (REP) framework for drug response prediction by taking advantage of time-course gene expression data. Our goal is to predict drug response values at every stage of a long-term treatment, given the expression levels of genes collected in the previous time-points. To this end, REP employs a built-in recursive structure that exploits the intrinsic time-course nature of the data and integrates past values of drug responses for subsequent predictions. It also incorporates tensor completion that can not only alleviate the impact of noise and missing data, but also predict unseen gene expression levels (GEXs). These advantages enable REP to estimate drug response at any stage of a given treatment from some GEXs measured in the beginning of the treatment. Extensive experiments on two datasets corresponding to multiple sclerosis patients treated with interferon are included to showcase the effectiveness of REP.

Current Advances and Limitations of Deep Learning in Anticancer Drug Sensitivity Prediction.

Anticancer drug screening can accelerate drug discovery to save the lives of cancer patients, but cancer heterogeneity makes this screening challenging. The prediction of anticancer drug sensitivity is useful for anticancer drug development and the identification of biomarkers of drug sensitivity. Deep learning, as a branch of machine learning, is an important aspect of in silico research. Its outstanding computational performance means that it has been used for many biomedical purposes, such as medical image interpretation, biological sequence analysis, and drug discovery. Several studies have predicted anticancer drug sensitivity based on deep learning algorithms. The field of deep learning has made progress regarding model performance and multi-omics data integration. However, deep learning is limited by the number of studies performed and data sources available, so it is not perfect as a pre-clinical approach for use in the anticancer drug screening process. Improving the performance of deep learning models is a pressing issue for researchers. In this review, we introduce the research of anticancer drug sensitivity prediction and the use of deep learning in this research area. To provide a reference for future research, we also review some common data sources and machine learning methods. Lastly, we discuss the advantages and disadvantages of deep learning, as well as the limitations and future perspectives regarding this approach.