Systematic quantitative characterization of cellular responses induced by multiple signals

Selectively cross-linked hydrogel-based cocktail drug delivery micro-chip for colon cancer combinatorial drug screening using AI-CSR platform for precision medicine

Cancer, ranked as the second leading cause of global mortality with a prevalence of 1 in 6 deaths, necessitates innovative approaches for effective treatment. Combinatorial drug therapy for cancer treatment targets several key pathways simultaneously and potentially enhances anti-cancer efficacy without intolerable side effects. However, it demands precise and accurate control of drug-dose combinations and their release. In this study, we demonstrated a selectively cross-linked hydrogel-based platform that can quantify and release drugs simultaneously for in-parallel cocktail drug screening. PDMS was used as the flow channel substrate and the poly (ethylene glycol) diacrylate (PEGDA) hydrogel array was formed by UV exposure using the photomask. Employing our platform, cocktails of anticancer drugs are precisely loaded and simultaneously released in-parallel into HCT-116 colon cancer cells, facilitating combinatorial drug screening. The integration of an artificial intelligence-based complex system response (AI-CSR) platform successfully identifies optimal drug-dose combinations from a pool of ten approved drugs. Notably, our cocktail drug chip demonstrates exceptional efficiency, screening 155 drug-dose combinations within a brief two and a half hours, a marked improvement over traditional methods. Furthermore, the device exhibits low drug consumption, requiring a mere 1 μL per patch of chip. Thus, our developed PDMS drug-loaded hydrogel platform presents a novel and expedited approach to quantifying drug concentrations, promising to be a faster, efficient and more precise approach for conducting cocktail drug screening experiments.

Personalized dose selection for the first Waldenström macroglobulinemia patient on the PRECISE CURATE.AI trial

The digital revolution in healthcare, amplified by the COVID-19 pandemic and artificial intelligence (AI) advances, has led to a surge in the development of digital technologies. However, integrating digital health solutions, especially AI-based ones, in rare diseases like Waldenström macroglobulinemia (WM) remains challenging due to limited data, among other factors. CURATE.AI, a clinical decision support system, offers an alternative to big data approaches by calibrating individual treatment profiles based on that individual's data alone. We present a case study from the PRECISE CURATE.AI trial with a WM patient, where, over two years, CURATE.AI provided dynamic Ibrutinib dose recommendations to clinicians (users) aimed at achieving optimal IgM levels. An 80-year-old male with newly diagnosed WM requiring treatment due to anemia was recruited to the trial for CURATE.AI-based dosing of the Bruton tyrosine kinase inhibitor Ibrutinib. The primary and secondary outcome measures were focused on scientific and logistical feasibility. Preliminary results underscore the platform's potential in enhancing user and patient engagement, in addition to clinical efficacy. Based on a two-year-long patient enrollment into the CURATE.AI-augmented treatment, this study showcases how AI-enabled tools can support the management of rare diseases, emphasizing the integration of AI to enhance personalized therapy.

Radiation therapy with phenotypic medicine: towards N-of-1 personalization

In current clinical practice, radiotherapy (RT) is prescribed as a pre-determined total dose divided over daily doses (fractions) given over several weeks. The treatment response is typically assessed months after the end of RT. However, the conventional one-dose-fits-all strategy may not achieve the desired outcome, owing to patient and tumor heterogeneity. Therefore, a treatment strategy that allows for RT dose personalization based on each individual response is preferred. Multiple strategies have been adopted to address this challenge. As an alternative to current known strategies, artificial intelligence (AI)-derived mechanism-independent small data phenotypic medicine (PM) platforms may be utilized for N-of-1 RT personalization. Unlike existing big data approaches, PM does not engage in model refining, training, and validation, and guides treatment by utilizing prospectively collected patient's own small datasets. With PM, clinicians may guide patients' RT dose recommendations using their responses in real-time and potentially avoid over-treatment in good responders and under-treatment in poor responders. In this paper, we discuss the potential of engaging PM to guide clinicians on upfront dose selections and ongoing adaptations during RT, as well as considerations and limitations for implementation. For practicing oncologists, clinical trialists, and researchers, PM can either be implemented as a standalone strategy or in complement with other existing RT personalizations. In addition, PM can either be used for monotherapeutic RT personalization, or in combination with other therapeutics (e.g. chemotherapy, targeted therapy). The potential of N-of-1 RT personalization with drugs will also be presented.

A new potential therapeutic approach for ALS: A case report with NGS analysis

RATIONALE

Amyotrophic lateral sclerosis (ALS) poses a significant clinical challenge due to its rapid progression and limited treatment options, often leading to deadly outcomes. Looking for effective therapeutic interventions is critical to improve patient outcomes in ALS.

PATIENT CONCERNS

The patient, a 75-year-old East Asian male, manifested an insidious onset of right-hand weakness advancing with dysarthria. Comprehensive Next-generation sequencing analysis identified variants in specific genes consistent with ALS diagnosis.

DIAGNOSES

ALS diagnosis is based on El Escorial diagnostic criteria.

INTERVENTIONS

This study introduces a novel therapeutic approach using artificial intelligence phenotypic response surface (AI-PRS) technology to customize personalized drug-dose combinations for ALS. The patient underwent a series of phases of AI-PRS-assisted trials, initially incorporating a 4-drug combination of Ibudilast, Riluzole, Tamoxifen, and Ropinirole. Biomarkers and regular clinical assessments, including nerve conduction velocity, F-wave, H-reflex, electromyography, and motor unit action potential, were monitored to comprehensively evaluate treatment efficacy.

OUTCOMES

Neurophysiological assessments supported the ALS diagnosis and revealed the co-presence of diabetic polyneuropathy. Hypotension during the trial necessitated an adaptation to a 2-drug combinational trial (ibudilast and riluzole). Disease progression assessment shifted exclusively to clinical tests of muscle strength, aligning with the patient's well-being.

LESSONS

The study raises the significance of personalized therapeutic strategies in ALS by AI-PRS. It also emphasizes the adaptability of interventions based on patient-specific responses. The encountered hypotension incident highlights the importance of attentive monitoring and personalized adjustments in treatment plans. The described therapy using AI-PRS, offering personalized drug-dose combinations technology is a potential approach in treating ALS. The promising outcomes warrant further evaluation in clinical trials for searching a personalized, more effective combinational treatment for ALS patients.

A functional personalised oncology approach against metastatic colorectal cancer in matched patient derived organoids

Globally, colorectal cancer (CRC) is the third most frequently occurring cancer. Progression on to an advanced metastatic malignancy (metCRC) is often indicative of poor prognosis, as the 5-year survival rates of patients decline rapidly. Despite the availability of many systemic therapies for the management of metCRC, the long-term efficacies of these regimens are often hindered by the emergence of treatment resistance due to intratumoral and intertumoral heterogeneity. Furthermore, not all systemic therapies have associated biomarkers that can accurately predict patient responses. Hence, a functional personalised oncology (FPO) approach can enable the identification of patient-specific combinatorial vulnerabilities and synergistic combinations as effective treatment strategies. To this end, we established a panel of CRC patient-derived organoids (PDOs) as clinically relevant biological systems, of which three pairs of matched metCRC PDOs were derived from the primary sites (ptCRC) and metastatic lesions (mCRC). Histological and genomic characterisation of these PDOs demonstrated the preservation of histopathological and genetic features found in the parental tumours. Subsequent application of the phenotypic-analytical drug combination interrogation platform, Quadratic Phenotypic Optimisation Platform, in these pairs of PDOs identified patient-specific drug sensitivity profiles to epigenetic-based combination therapies. Most notably, matched PDOs from one patient exhibited differential sensitivity patterns to the rationally designed drug combinations despite being genetically similar. These findings collectively highlight the limitations of current genomic-driven precision medicine in guiding treatment strategies for metCRC patients. Instead, it suggests that epigenomic profiling and application of FPO could complement the identification of novel combinatorial vulnerabilities to target synchronous ptCRC and mCRC.

A deep learning-based pipeline for analyzing the influences of interfacial mechanochemical microenvironments on spheroid invasion using differential interference contrast microscopic images

Metastasis is the leading cause of cancer-related deaths. During this process, cancer cells are likely to navigate discrete tissue-tissue interfaces, enabling them to infiltrate and spread throughout the body. Three-dimensional (3D) spheroid modeling is receiving more attention due to its strengths in studying the invasive behavior of metastatic cancer cells. While microscopy is a conventional approach for investigating 3D invasion, post-invasion image analysis, which is a time-consuming process, remains a significant challenge for researchers. In this study, we presented an image processing pipeline that utilized a deep learning (DL) solution, with an encoder-decoder architecture, to assess and characterize the invasion dynamics of tumor spheroids. The developed models, equipped with feature extraction and measurement capabilities, could be successfully utilized for the automated segmentation of the invasive protrusions as well as the core region of spheroids situated within interfacial microenvironments with distinct mechanochemical factors. Our findings suggest that a combination of the spheroid culture and DL-based image analysis enable identification of time-lapse migratory patterns for tumor spheroids above matrix-substrate interfaces, thus paving the foundation for delineating the mechanism of local invasion during cancer metastasis.

CURATE.AI COR-Tx platform as a digital therapy and digital diagnostic for cognitive function in patients with brain tumour postradiotherapy treatment: protocol for a prospective mixed-methods feasibility clinical trial

INTRODUCTION

Conventional interventional modalities for preserving or improving cognitive function in patients with brain tumour undergoing radiotherapy usually involve pharmacological and/or cognitive rehabilitation therapy administered at fixed doses or intensities, often resulting in suboptimal or no response, due to the dynamically evolving patient state over the course of disease. The personalisation of interventions may result in more effective results for this population. We have developed the CURATE.AI COR-Tx platform, which combines a previously validated, artificial intelligence-derived personalised dosing technology with digital cognitive training.

METHODS AND ANALYSIS

This is a prospective, single-centre, single-arm, mixed-methods feasibility clinical trial with the primary objective of testing the feasibility of the CURATE.AI COR-Tx platform intervention as both a digital intervention and digital diagnostic for cognitive function. Fifteen patient participants diagnosed with a brain tumour requiring radiotherapy will be recruited. Participants will undergo a remote, home-based 10-week personalised digital intervention using the CURATE.AI COR-Tx platform three times a week. Cognitive function will be assessed via a combined non-digital cognitive evaluation and a digital diagnostic session at five time points: preradiotherapy, preintervention and postintervention and 16-weeks and 32-weeks postintervention. Feasibility outcomes relating to acceptability, demand, implementation, practicality and limited efficacy testing as well as usability and user experience will be assessed at the end of the intervention through semistructured patient interviews and a study team focus group discussion at study completion. All outcomes will be analysed quantitatively and qualitatively.

ETHICS AND DISSEMINATION

This study has been approved by the National Healthcare Group (NHG) DSRB (DSRB2020/00249). We will report our findings at scientific conferences and/or in peer-reviewed journals.

TRIAL REGISTRATION NUMBER

NCT04848935.

Comparing the Performance of Multiple Small-Data Personalized Tacrolimus Dosing Models for Pediatric Liver Transplant: A Retrospective Study

Tacrolimus is a potent immunosuppressant used after pediatric liver transplant. However, tacrolimus's narrow therapeutic window, reliance on physicians' experience for the dose titration, and intra- and inter-patient variability result in liver transplant patients falling out of the target tacrolimus trough levels frequently. Existing personalized dosing models based on the area-under-the-concentration over time curves require a higher frequency of blood draws than the current standard of care and may not be practically feasible. We present a small-data artificial intelligence-derived platform, CURATE.AI, that uses data from individual patients obtained once daily to model the dose and response relationship and identify suitable doses dynamically. Retrospective optimization using 6 models of CURATE.AI and data from 16 patients demonstrated good predictive performance and identified a suitable model for further investigations.Clinical Relevance- This study established and compared the predictive performance of 6 personalized tacrolimus dosing models for pediatric liver transplant patients and identified a suitable model with consistently good predictive performance based on data from pediatric liver transplant patients.

Personalized Tacrolimus Dosing After Liver Transplantation: A Randomized Clinical Trial

Background

Inter- and intra-individual variability in tacrolimus dose requirements mandates empirical clinician-titrated dosing that frequently results in deviation from a narrow target range. Improved methods to individually dose tacrolimus are needed. Our objective was to determine whether a quantitative, dynamically-customized, phenotypic-outcome-guided dosing method termed Phenotypic Personalized Medicine (PPM) would improve target drug trough maintenance.

Methods

In a single-center, randomized, pragmatic clinical trial ( NCT03527238 ), 62 adults were screened, enrolled, and randomized prior to liver transplantation 1:1 to standard-of-care (SOC) clinician-determined or PPM-guided dosing of tacrolimus. The primary outcome measure was percent days with large (>2 ng/mL) deviation from target range from transplant to discharge. Secondary outcomes included percent days outside-of-target-range and mean area-under-the-curve (AUC) outside-of-target-range per day. Safety measures included rejection, graft failure, death, infection, nephrotoxicity, or neurotoxicity.

Results

56 (29 SOC, 27 PPM) patients completed the study. The primary outcome measure was found to be significantly different between the two groups. Patients in the SOC group had a mean of 38.4% of post-transplant days with large deviations from target range; the PPM group had 24.3% of post-transplant days with large deviations; (difference -14.1%, 95% CI: -26.7 to -1.5 %, P=0.029). No significant differences were found in the secondary outcomes. In post-hoc analysis, the SOC group had a 50% longer median length-of-stay than the PPM group [15 days (Q1-Q3: 11-20) versus 10 days (Q1-Q3: 8.5-12); difference 5 days, 95% CI: 2-8 days, P=0.0026].

Conclusions

PPM guided tacrolimus dosing leads to better drug level maintenance than SOC. The PPM approach leads to actionable dosing recommendations on a day-to-day basis.

Lay Summary

In a study on 62 adults who underwent liver transplantation, researchers investigated whether a new dosing method called Phenotypic Personalized Medicine (PPM) would improve daily dosing of the immunosuppression drug tacrolimus. They found that PPM guided tacrolimus dosing leads to better drug level maintenance than the standard-of-care clinician-determined dosing. This means that the PPM approach leads to actionable dosing recommendations on a day-to-day basis and can help improve patient outcomes.

IDentif.AI-Omicron: Harnessing an AI-Derived and Disease-Agnostic Platform to Pinpoint Combinatorial Therapies for Clinically Actionable Anti-SARS-CoV-2 Intervention

Nanomedicine-based and unmodified drug interventions to address COVID-19 have evolved over the course of the pandemic as more information is gleaned and virus variants continue to emerge. For example, some early therapies (e.g., antibodies) have experienced markedly decreased efficacy. Due to a growing concern of future drug resistant variants, current drug development strategies are seeking to find effective drug combinations. In this study, we used IDentif.AI, an artificial intelligence-derived platform, to investigate the drug-drug and drug-dose interaction space of six promising experimental or currently deployed therapies at various concentrations: EIDD-1931, YH-53, nirmatrelvir, AT-511, favipiravir, and auranofin. The drugs were tested in vitro against a live B.1.1.529 (Omicron) virus first in monotherapy and then in 50 strategic combinations designed to interrogate the interaction space of 729 possible combinations. Key findings and interactions were then further explored and validated in an additional experimental round using an expanded concentration range. Overall, we found that few of the tested drugs showed moderate efficacy as monotherapies in the actionable concentration range, but combinatorial drug testing revealed significant dose-dependent drug-drug interactions, specifically between EIDD-1931 and YH-53, as well as nirmatrelvir and YH-53. Checkerboard validation analysis confirmed these synergistic interactions and also identified an interaction between EIDD-1931 and favipiravir in an expanded range. Based on the platform nature of IDentif.AI, these findings may support further explorations of the dose-dependent drug interactions between different drug classes in further pre-clinical and clinical trials as possible combinatorial therapies consisting of unmodified and nanomedicine-enabled drugs, to combat current and future COVID-19 strains and other emerging pathogens.

The IDentif.AI-x pandemic readiness platform: Rapid prioritization of optimized COVID-19 combination therapy regimens

IDentif.AI-x, a clinically actionable artificial intelligence platform, was used to rapidly pinpoint and prioritize optimal combination therapies against COVID-19 by pairing a prospective, experimental validation of multi-drug efficacy on a SARS-CoV-2 live virus and Vero E6 assay with a quadratic optimization workflow. A starting pool of 12 candidate drugs developed in collaboration with a community of infectious disease clinicians was first narrowed down to a six-drug pool and then interrogated in 50 combination regimens at three dosing levels per drug, representing 729 possible combinations. IDentif.AI-x revealed EIDD-1931 to be a strong candidate upon which multiple drug combinations can be derived, and pinpointed a number of clinically actionable drug interactions, which were further reconfirmed in SARS-CoV-2 variants B.1.351 (Beta) and B.1.617.2 (Delta). IDentif.AI-x prioritized promising drug combinations for clinical translation and can be immediately adjusted and re-executed with a new pool of promising therapies in an actionable path towards rapidly optimizing combination therapy following pandemic emergence.

Genome-wide identification, classification and expression analysis of the JmjC domain-containing histone demethylase gene family in Jatropha curcas L

JmjC domain-containing proteins, an important family of histone lysine demethylase, play significant roles in maintaining the homeostasis of histone methylation. In this study, we comprehensively analyzed the JmjC domain-containing gene family in Jatropha curcas and found 20 JmjC domain-containing genes (JcJMJ genes). Phylogenetic analysis revealed that these JcJMJ genes can be classified into five major subgroups, and genes in each subgroup had similar motif and domain composition. Cis-regulatory element analysis showed that the number and types of cis-regulatory elements owned by the promoter of JcJMJ genes in different subgroup were significantly different. Moreover, miRNA target prediction result revealed a complicated miRNA-mediated post-transcriptional regulatory network, in which JcJMJ genes were regulated by different numbers and types of miRNAs. Further analysis of the tissue and stress expression profiles showed that many JcJMJ genes had tissue and stress expression specificity. All these results provided valuable information for understanding the evolution of JcJMJ genes and the complex transcriptional and post transcriptional regulation involved, and laid the foundation for further functional analysis of JcJMJ genes.

Personalised, Rational, Efficacy-Driven Cancer Drug Dosing via an Artificial Intelligence SystEm (PRECISE): A Protocol for the PRECISE CURATE.AI Pilot Clinical Trial

Introduction: Oncologists have traditionally administered the maximum tolerated doses of drugs in chemotherapy. However, these toxicity-guided doses may lead to suboptimal efficacy. CURATE.AI is an indication-agnostic, mechanism-independent and efficacy-driven personalised dosing platform that may offer a more optimal solution. While CURATE.AI has already been applied in a variety of clinical settings, there are no prior randomised controlled trials (RCTs) on CURATE.AI-guided chemotherapy dosing for solid tumours. Therefore, we aim to assess the technical and logistical feasibility of a future RCT for CURATE.AI-guided solid tumour chemotherapy dosing. We will also collect exploratory data on efficacy and toxicity, which will inform RCT power calculations.

Methods and analysis: This is an open-label, single-arm, two-centre, prospective pilot clinical trial, recruiting adults with metastatic solid tumours and raised baseline tumour marker levels who are planned for palliative-intent, capecitabine-based chemotherapy. As CURATE.AI is a small data platform, it will guide drug dosing for each participant based only on their own tumour marker levels and drug doses as input data. The primary outcome is the proportion of participants in whom CURATE.AI is successfully applied to provide efficacy-driven personalised dosing, as judged based on predefined considerations. Secondary outcomes include the timeliness of dose recommendations, participant and physician adherence to CURATE.AI-recommended doses, and the proportion of clinically significant dose changes. We aim to initially enrol 10 participants from two hospitals in Singapore, perform an interim analysis, and consider either cohort expansion or an RCT. Recruitment began in August 2020. This pilot clinical trial will provide key data for a future RCT of CURATE.AI-guided personalised dosing for precision oncology.

Ethics and dissemination: The National Healthcare Group (NHG) Domain Specific Review Board has granted ethical approval for this study (DSRB 2020/00334). We will distribute our findings at scientific conferences and publish them in peer-reviewed journals.

Trial registration number: NCT04522284

Development of New Tuberculosis Drugs: Translation to Regimen Composition for Drug-Sensitive and Multidrug-Resistant Tuberculosis

Tuberculosis (TB) kills more people than any other infectious disease. Challenges for developing better treatments include the complex pathology due to within-host immune dynamics, interpatient variability in disease severity and drug pharmacokinetics-pharmacodynamics (PK-PD), and the growing emergence of resistance. Model-informed drug development using quantitative and translational pharmacology has become increasingly recognized as a method capable of drug prioritization and regimen optimization to efficiently progress compounds through TB drug development phases. In this review, we examine translational models and tools, including plasma PK scaling, site-of-disease lesion PK, host-immune and bacteria interplay, combination PK-PD models of multidrug regimens, resistance formation, and integration of data across nonclinical and clinical phases.We propose a workflow that integrates these tools with computational platforms to identify drug combinations that have the potential to accelerate sterilization, reduce relapse rates, and limit the emergence of resistance.

IDentif.AI: Rapidly optimizing combination therapy design against severe Acute Respiratory Syndrome Coronavirus 2 (SARS-Cov-2) with digital drug development

The emergence of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) led to multiple drug repurposing clinical trials that have yielded largely uncertain outcomes. To overcome this challenge, we used IDentif.AI, a platform that pairs experimental validation with artificial intelligence (AI) and digital drug development to rapidly pinpoint unpredictable drug interactions and optimize infectious disease combination therapy design with clinically relevant dosages. IDentif.AI was paired with a 12-drug candidate therapy set representing over 530,000 drug combinations against the SARS-CoV-2 live virus collected from a patient sample. IDentif.AI pinpointed the optimal combination as remdesivir, ritonavir, and lopinavir, which was experimentally validated to mediate a 6.5-fold enhanced efficacy over remdesivir alone. Additionally, it showed hydroxychloroquine and azithromycin to be relatively ineffective. The study was completed within 2 weeks, with a three-order of magnitude reduction in the number of tests needed. IDentif.AI independently mirrored clinical trial outcomes to date without any data from these trials. The robustness of this digital drug development approach paired with in vitro experimentation and AI-driven optimization suggests that IDentif.AI may be clinically actionable toward current and future outbreaks.

Project IDentif.AI: Harnessing Artificial Intelligence to Rapidly Optimize Combination Therapy Development for Infectious Disease Intervention

In 2019/2020, the emergence of coronavirus disease 2019 (COVID-19) resulted in rapid increases in infection rates as well as patient mortality. Treatment options addressing COVID-19 included drug repurposing, investigational therapies such as remdesivir, and vaccine development. Combination therapy based on drug repurposing is among the most widely pursued of these efforts. Multi-drug regimens are traditionally designed by selecting drugs based on their mechanism of action. This is followed by dose-finding to achieve drug synergy. This approach is widely-used for drug development and repurposing. Realizing synergistic combinations, however, is a substantially different outcome compared to globally optimizing combination therapy, which realizes the best possible treatment outcome by a set of candidate therapies and doses toward a disease indication. To address this challenge, the results of Project IDentif.AI (Identifying Infectious Disease Combination Therapy with Artificial Intelligence) are reported. An AI-based platform is used to interrogate a massive 12 drug/dose parameter space, rapidly identifying actionable combination therapies that optimally inhibit A549 lung cell infection by vesicular stomatitis virus within three days of project start. Importantly, a sevenfold difference in efficacy is observed between the top-ranked combination being optimally and sub-optimally dosed, demonstrating the critical importance of ideal drug and dose identification. This platform is disease indication and disease mechanism-agnostic, and potentially applicable to the systematic N-of-1 and population-wide design of highly efficacious and tolerable clinical regimens. This work also discusses key factors ranging from healthcare economics to global health policy that may serve to drive the broader deployment of this platform to address COVID-19 and future pandemics.

Drug-Drug Interactions of Irinotecan, 5-Fluorouracil, Folinic Acid and Oxaliplatin and Its Activity in Colorectal Carcinoma Treatment

The combination of folinic acid, 5-fluorouracil, oxaliplatin and/or irinotecan (FOLFOXIRI) is the standard of care for metastatic colorectal cancer (CRC). This strategy inhibits tumor growth but provokes drug resistance and serious side effects. We aimed to improve FOLFOXIRI by optimization of the dosing and the sequence of drug administration. We employed an orthogonal array composite design and linear regression analysis to obtain cell line-specific drug combinations for four CRC cell lines (DLD1, SW620, HCT116, LS174T). Our results confirmed the synergy between folinic acid and 5-fluorouracil and additivity, or even antagonism, between the other drugs of the combination. The drug combination administered at clinical doses resulted in significantly higher antagonistic interactions compared to the low-dose optimized drug combination (ODC). We found that the concomitant administration of the optimized drug combination (ODC) was comparatively active to sequential administration. However, the administration of oxaliplatin or the active metabolite of irinotecan seemed to sensitize the cells to the combination of folinic acid and 5-fluorouracil. ODCs were similarly active in non-cancerous cells as compared to the clinically used doses, indicating a lack of reduction of side effects. Interestingly, ODCs were inactive in CRC cells chronically pretreated with FOLFOXIRI, suggesting the occurrence of resistance. We were unable to improve FOLFOXIRI in terms of efficacy or specificity. Improvement of CRC treatment should come from the optimization of targeted drugs and immunotherapy strategies.

Enabling Technologies for Personalized and Precision Medicine

Individualizing patient treatment is a core objective of the medical field. Reaching this objective has been elusive owing to the complex set of factors contributing to both disease and health; many factors, from genes to proteins, remain unknown in their role in human physiology. Accurately diagnosing, monitoring, and treating disorders requires advances in biomarker discovery, the subsequent development of accurate signatures that correspond with dynamic disease states, as well as therapeutic interventions that can be continuously optimized and modulated for dose and drug selection. This work highlights key breakthroughs in the development of enabling technologies that further the goal of personalized and precision medicine, and remaining challenges that, when addressed, may forge unprecedented capabilities in realizing truly individualized patient care.

CURATE.AI: Optimizing Personalized Medicine with Artificial Intelligence

The clinical team attending to a patient upon a diagnosis is faced with two main questions: what treatment, and at what dose? Clinical trials' results provide the basis for guidance and support for official protocols that clinicians use to base their decisions upon. However, individuals rarely demonstrate the reported response from relevant clinical trials, often the average from a group representing a population or subpopulation. The decision complexity increases with combination treatments where drugs administered together can interact with each other, which is often the case. Additionally, the individual's response to the treatment varies over time with the changes in his or her condition, whether via the indication or physiology. In practice, the drug and the dose selection depend greatly on the medical protocol of the healthcare provider and the medical team's experience. As such, the results are inherently varied and often suboptimal. Big data approaches have emerged as an excellent decision-making support tool, but their application is limited by multiple challenges, the main one being the availability of sufficiently big datasets with good quality, representative information. An alternative approach-phenotypic personalized medicine (PPM)-finds an appropriate drug combination (quadratic phenotypic optimization platform [QPOP]) and an appropriate dosing strategy over time (CURATE.AI) based on small data collected exclusively from the treated individual. PPM-based approaches have demonstrated superior results over the current standard of care. The side effects are limited while the desired output is maximized, which directly translates into improving the length and quality of individuals' lives.

Artificial intelligence enabled parabolic response surface platform identifies ultra-rapid near-universal TB drug treatment regimens comprising approved drugs

Background

Shorter, more effective treatments for tuberculosis (TB) are urgently needed. While many TB drugs are available, identification of the best regimens is challenging because of the large number of possible drug-dose combinations. We have found consistently that responses of cells or whole animals to drug-dose stimulations fit a parabolic response surface (PRS), allowing us to identify and optimize the best drug combinations by testing only a small fraction of the total search space. Previously, we used PRS methodology to identify three regimens (PRS Regimens I–III) that in murine models are much more effective than the standard regimen used to treat TB. However, PRS Regimens I and II are unsuitable for treating drug-resistant TB and PRS Regimen III includes an experimental drug. Here, we use PRS methodology to identify from an expanded pool of drugs new highly effective near-universal drug regimens comprising only approved drugs.

Methods and findings

We evaluated combinations of 15 different drugs in a human macrophage TB model and identified the most promising 4-drug combinations. We then tested 14 of these combinations in Mycobacterium tuberculosis-infected BALB/c mice and chose for PRS dose optimization and further study the two most potent regimens, designated PRS Regimens IV and V, consisting of clofazimine (CFZ), bedaquiline (BDQ), pyrazinamide (PZA), and either amoxicillin/clavulanate (AC) or delamanid (DLM), respectively. We then evaluated the efficacy in mice of optimized PRS Regimens IV and V, as well as a 3-drug regimen, PRS Regimen VI (CFZ, BDQ, and PZA), and compared their efficacy to PRS Regimen III (CFZ, BDQ, PZA, and SQ109), previously shown to reduce the time to achieve relapse-free cure in mice by 80% compared with the Standard Regimen (isoniazid, rifampicin, PZA, and ethambutol). Efficacy measurements included early bactericidal activity, time to lung sterilization, and time to relapse-free cure. PRS Regimens III–VI all rapidly sterilized the lungs and achieved relapse-free cure in 3 weeks (PRS Regimens III, V, and VI) or 5 weeks (PRS Regimen IV). In contrast, mice treated with the Standard Regimen still had high numbers of bacteria in their lungs after 6-weeks treatment and none achieved relapse-free cure in this time-period.

Conclusions

We have identified three new regimens that rapidly sterilize the lungs of mice and dramatically shorten the time required to achieve relapse-free cure. All mouse drug doses in these regimens extrapolate to doses that are readily achievable in humans. Because PRS Regimens IV and V contain only one first line drug (PZA) and exclude fluoroquinolones and aminoglycosides, they should be effective against most TB cases that are multidrug resistant (MDR-TB) and many that are extensively drug-resistant (XDR-TB). Hence, these regimens have potential to shorten dramatically the time required for treatment of both drug-sensitive and drug-resistant TB. If clinical trials confirm that these regimens dramatically shorten the time required to achieve relapse-free cure in humans, then this radically shortened treatment has the potential to improve treatment compliance, decrease the emergence of drug resistance, and decrease the healthcare burden of treating both drug-sensitive and drug-resistant TB.

Artificial intelligence in nanomedicine

The field of nanomedicine has made substantial strides in the areas of therapeutic and diagnostic development. For example, nanoparticle-modified drug compounds and imaging agents have resulted in markedly enhanced treatment outcomes and contrast efficiency. In recent years, investigational nanomedicine platforms have also been taken into the clinic, with regulatory approval for Abraxane® and other products being awarded. As the nanomedicine field has continued to evolve, multifunctional approaches have been explored to simultaneously integrate therapeutic and diagnostic agents onto a single particle, or deliver multiple nanomedicine-functionalized therapies in unison. Similar to the objectives of conventional combination therapy, these strategies may further improve treatment outcomes through targeted, multi-agent delivery that preserves drug synergy. Also, similar to conventional/unmodified combination therapy, nanomedicine-based drug delivery is often explored at fixed doses. A persistent challenge in all forms of drug administration is that drug synergy is time-dependent, dose-dependent and patient-specific at any given point of treatment. To overcome this challenge, the evolution towards nanomedicine-mediated co-delivery of multiple therapies has made the potential of interfacing artificial intelligence (AI) with nanomedicine to sustain optimization in combinatorial nanotherapy a reality. Specifically, optimizing drug and dose parameters in combinatorial nanomedicine administration is a specific area where AI can actionably realize the full potential of nanomedicine. To this end, this review will examine the role that AI can have in substantially improving nanomedicine-based treatment outcomes, particularly in the context of combination nanotherapy for both N-of-1 and population-optimized treatment.

Application of kriging models for a drug combination experiment on lung cancer

Combinatorial drugs have been widely applied in disease treatment, especially chemotherapy for cancer, due to its improved efficacy and reduced toxicity compared with individual drugs. The study of combinatorial drugs requires efficient experimental designs and proper follow-up statistical modeling techniques. Linear and nonlinear models are often used in the response surface modeling for such experiments. We propose the use of kriging models to better depict the response surfaces of combinatorial drugs. We illustrate our method via a drug combination experiment on lung cancer and further show how proper experimental designs can reduce the necessary run size. We demonstrate that only 27 runs are needed to predict all 512 runs in the original experiment and achieve better precision than existing analyses.

Prediction of drug cocktail effects when the number of measurements is limited

Cocktails of drugs can be more effective than single drugs, because they can potentially work at lower doses and avoid resistance. However, it is impossible to test all drug cocktails drawn from a large set of drugs because of the huge number of combinations. To overcome this combinatorial explosion problem, one can sample a relatively small number of combinations and use a model to predict the rest. Recently, Zimmer and Katzir et al. presented a model that accurately predicted the effects of cocktails at all doses based on measuring pairs of drugs. This model requires measuring each pair at several different doses and uses interpolation to reduce experimental noise. However, often, it is not possible to measure each pair at multiple doses (for example, in scarce patient-derived tumor material or in large screens). Here, we ask whether measurements at only a single dose can also predict high-order drug cocktails. To address this, we present a fully factorial experimental dataset on all drug cocktails built of 6 chemotherapy drugs on 2 cancer cell lines. We develop a formula that uses only pair measurements at a single dose to predict much of the variation up to 6-drug cocktails in the present data, outperforming commonly used Bliss independence and regression approaches. This model, called the pairs model, is an extension of the Bliss independence model to pairs: For M drugs, it equals the product of all pair effects to the power 1/(M−1). The pairs model also shows good agreement with previously published data on antibiotic triplets and quadruplets. The present model can only predict combinations at the same doses in which the pairs were measured and is not able to predict effects at other doses. This study indicates that pair-based approaches might be able to usefully predict and prioritize high-order combinations, even in large screens or when material for testing is limited.

Drug cocktails are a promising strategy for diseases such as cancer and infections, because cocktails can be more effective than individual drugs and can overcome problems of drug resistance. However, finding the best cocktail comprising a given set of drugs is challenging because the number of experiments needed is huge and grows exponentially with the number of drugs. This problem is exacerbated when the experiments are expensive and the material for testing is rare. Here, we present a way to address this challenge using a mathematical formula, called the pairs model, that requires relatively few experimental tests in order to estimate the effects of cocktails and to predict which cocktail is most effective. The formula does well on experimental data generated in this study using combinations of between 3 and 6 anticancer drugs, as well as on existing data that use combinations of antibiotics.

Drug regimens identified and optimized by output-driven platform markedly reduce tuberculosis treatment time

The current drug regimens for treating tuberculosis are lengthy and onerous, and hence complicated by poor adherence leading to drug resistance and disease relapse. Previously, using an output-driven optimization platform and an in vitro macrophage model of Mycobacterium tuberculosis infection, we identified several experimental drug regimens among billions of possible drug-dose combinations that outperform the current standard regimen. Here we use this platform to optimize the in vivo drug doses of two of these regimens in a mouse model of pulmonary tuberculosis. The experimental regimens kill M. tuberculosis much more rapidly than the standard regimen and reduce treatment time to relapse-free cure by 75%. Thus, these regimens have the potential to provide a markedly shorter course of treatment for tuberculosis in humans. As these regimens omit isoniazid, rifampicin, fluoroquinolones and injectable aminoglycosides, they would be suitable for treating many cases of multidrug and extensively drug-resistant tuberculosis.

Current antibiotic therapies for tuberculosis are lengthy and onerous. Here, the authors use an output-driven approach to optimize drug doses for two experimental drug regimens in a mouse model of tuberculosis, leading to improved regimens that reduce treatment time by 75%.

Predicting Drug Combination Index and Simulating the Network-Regulation Dynamics by Mathematical Modeling of Drug-Targeted EGFR-ERK Signaling Pathway

Synergistic drug combinations enable enhanced therapeutics. Their discovery typically involves the measurement and assessment of drug combination index (CI), which can be facilitated by the development and applications of in-silico CI predictive tools. In this work, we developed and tested the ability of a mathematical model of drug-targeted EGFR-ERK pathway in predicting CIs and in analyzing multiple synergistic drug combinations against observations. Our mathematical model was validated against the literature reported signaling, drug response dynamics, and EGFR-MEK drug combination effect. The predicted CIs and combination therapeutic effects of the EGFR-BRaf, BRaf-MEK, FTI-MEK, and FTI-BRaf inhibitor combinations showed consistent synergism. Our results suggest that existing pathway models may be potentially extended for developing drug-targeted pathway models to predict drug combination CI values, isobolograms, and drug-response surfaces as well as to analyze the dynamics of individual and combinations of drugs. With our model, the efficacy of potential drug combinations can be predicted. Our method complements the developed in-silico methods (e.g. the chemogenomic profile and the statistically-inferenced network models) by predicting drug combination effects from the perspectives of pathway dynamics using experimental or validated molecular kinetic constants, thereby facilitating the collective prediction of drug combination effects in diverse ranges of disease systems.

Current Trends in Multidrug Optimization: An Alley of Future Successful Treatment of Complex Disorders

The identification of effective and long-lasting cancer therapies still remains elusive, partially due to patient and tumor heterogeneity, acquired drug resistance, and single-drug dose-limiting toxicities. The use of drug combinations may help to overcome some limitations of current cancer therapies by challenging the robustness and redundancy of biological processes. However, effective drug combination optimization requires the careful consideration of numerous parameters. The complexity of this optimization problem is clearly nontrivial and likely requires the assistance of advanced heuristic optimization techniques. In the current review, we discuss the application of optimization techniques for the identification of optimal drug combinations. More specifically, we focus on the application of phenotype-based screening approaches in the field of cancer therapy. These methods are divided into three categories: (1) modeling methods, (2) model-free approaches based on biological search algorithms, and (3) merged approaches, particularly phenotypically driven network biology methods and computation network models relying on phenotypic data. In addition to a brief description of each approach, we include a critical discussion of the advantages and disadvantages of each method, with a strong focus on the limitations and considerations needed to successfully apply such methods in biological research.

Current Trends in Multidrug Optimization

The identification of effective and long-lasting cancer therapies still remains elusive, partially due to patient and tumor heterogeneity, acquired drug resistance, and single-drug dose-limiting toxicities. The use of drug combinations may help to overcome some limitations of current cancer therapies by challenging the robustness and redundancy of biological processes. However, effective drug combination optimization requires the careful consideration of numerous parameters. The complexity of this optimization problem is clearly nontrivial and likely requires the assistance of advanced heuristic optimization techniques. In the current review, we discuss the application of optimization techniques for the identification of optimal drug combinations. More specifically, we focus on the application of phenotype-based screening approaches in the field of cancer therapy. These methods are divided into three categories: (1) modeling methods, (2) model-free approaches based on biological search algorithms, and (3) merged approaches, particularly phenotypically driven network biology methods and computation network models relying on phenotypic data. In addition to a brief description of each approach, we include a critical discussion of the advantages and disadvantages of each method, with a strong focus on the limitations and considerations needed to successfully apply such methods in biological research.

Individualizing liver transplant immunosuppression using a phenotypic personalized medicine platform

Postoperative liver transplant immunosuppression was personalized using a phenotypic, disease mechanism–independent and indication-agnostic approach.

Output-driven feedback system control platform optimizes combinatorial therapy of tuberculosis using a macrophage cell culture model

Tuberculosis (TB) remains a major global public health problem, and improved treatments are needed to shorten duration of therapy, decrease disease burden, improve compliance, and combat emergence of drug resistance. Ideally, the most effective regimen would be identified by a systematic and comprehensive combinatorial search of large numbers of TB drugs. However, optimization of regimens by standard methods is challenging, especially as the number of drugs increases, because of the extremely large number of drug-dose combinations requiring testing. Herein, we used an optimization platform, feedback system control (FSC) methodology, to identify improved drug-dose combinations for TB treatment using a fluorescence-based human macrophage cell culture model of TB, in which macrophages are infected with isopropyl β-D-1-thiogalactopyranoside (IPTG)-inducible green fluorescent protein (GFP)-expressing Mycobacterium tuberculosis (Mtb). On the basis of only a single screening test and three iterations, we identified highly efficacious three- and four-drug combinations. To verify the efficacy of these combinations, we further evaluated them using a methodologically independent assay for intramacrophage killing of Mtb; the optimized combinations showed greater efficacy than the current standard TB drug regimen. Surprisingly, all top three- and four-drug optimized regimens included the third-line drug clofazimine, and none included the first-line drugs isoniazid and rifampin, which had insignificant or antagonistic impacts on efficacy. Because top regimens also did not include a fluoroquinolone or aminoglycoside, they are potentially of use for treating many cases of multidrug- and extensively drug-resistant TB. Our study shows the power of an FSC platform to identify promising previously unidentified drug-dose combinations for treatment of TB.

Optimization of drug combinations using Feedback System Control

We describe a protocol for the discovery of synergistic drug combinations for the treatment of disease. Synergistic drug combinations lead to the use of drugs at lower doses, which reduces side effects and can potentially lead to reduced drug resistance, while being clinically more effective than the individual drugs. To cope with the extremely large search space for these combinations, we developed an efficient combinatorial drug screening method called the Feedback System Control (FSC) technique. Starting with a broad selection of drugs, the method follows an iterative approach of experimental testing in a relevant bioassay and analysis of the results by FSC. First, the protocol uses a cell viability assay to generate broad dose-response curves to assess the efficacy of individual compounds. These curves are then used to guide the dosage input of each drug to be tested in combination. Data from applied drug combinations are input into the differential evolution (DE) algorithm, which predicts new combinations to be tested in vitro. This process identifies optimal drug-dose combinations, while saving orders of magnitude in experimental effort. The complete optimization process is estimated to take ∼4 weeks. FSC does not require insight into the disease mechanism, and it has therefore been applied to find combination therapies for many different pathologies, including cancer and infectious diseases, and it has also been used in organ transplantation.

Diagnosis of prostate cancer via nanotechnological approach

Prostate cancer is one of the leading causes of cancer-related deaths among the Caucasian adult males in Europe and the USA. Currently available diagnostic strategies for patients with prostate cancer are invasive and unpleasant and have poor accuracy. Many patients have been overly or underly treated resulting in a controversy regarding the reliability of current conventional diagnostic approaches. This review discusses the state-of-the-art research in the development of novel noninvasive prostate cancer diagnostics using nanotechnology coupled with suggested diagnostic strategies for their clinical implication.

A streamlined search technology for identification of synergistic drug combinations

A major key to improvement of cancer therapy is the combination of drugs. Mixing drugs that already exist on the market may offer an attractive alternative. Here we report on a new model-based streamlined feedback system control (s-FSC) method, based on a design of experiment approach, for rapidly finding optimal drug mixtures with minimal experimental effort. We tested combinations in an in vitro assay for the viability of a renal cell adenocarcinoma (RCC) cell line, 786-O. An iterative cycle of in vitro testing and s-FSC analysis was repeated a few times until an optimal low dose combination was reached. Starting with ten drugs that target parallel pathways known to play a role in the development and progression of RCC, we identified the best overall drug combination, being a mixture of four drugs (axitinib, erlotinib, dasatinib and AZD4547) at low doses, inhibiting 90% of cell viability. The removal of AZD4547 from the optimized drug combination resulted in 80% of cell viability inhibition, while still maintaining the synergistic interaction. These optimized drug combinations were significantly more potent than monotherapies of all individual drugs (p < 0.001, CI < 0.3).

Nanodiamonds: The intersection of nanotechnology, drug development, and personalized medicine

The implementation of nanomedicine in cellular, preclinical, and clinical studies has led to exciting advances ranging from fundamental to translational, particularly in the field of cancer. Many of the current barriers in cancer treatment are being successfully addressed using nanotechnology-modified compounds. These barriers include drug resistance leading to suboptimal intratumoral retention, poor circulation times resulting in decreased efficacy, and off-target toxicity, among others. The first clinical nanomedicine advances to overcome these issues were based on monotherapy, where small-molecule and nucleic acid delivery demonstrated substantial improvements over unmodified drug administration. Recent preclinical studies have shown that combination nanotherapies, composed of either multiple classes of nanomaterials or a single nanoplatform functionalized with several therapeutic agents, can image and treat tumors with improved efficacy over single-compound delivery. Among the many promising nanomaterials that are being developed, nanodiamonds have received increasing attention because of the unique chemical-mechanical properties on their faceted surfaces. More recently, nanodiamond-based drug delivery has been included in the rational and systematic design of optimal therapeutic combinations using an implicitly de-risked drug development platform technology, termed Phenotypic Personalized Medicine-Drug Development (PPM-DD). The application of PPM-DD to rapidly identify globally optimized drug combinations successfully addressed a pervasive challenge confronting all aspects of drug development, both nano and non-nano. This review will examine various nanomaterials and the use of PPM-DD to optimize the efficacy and safety of current and future cancer treatment. How this platform can accelerate combinatorial nanomedicine and the broader pharmaceutical industry toward unprecedented clinical impact will also be discussed.

Preclinical optimization of a broad-spectrum anti-bladder cancer tri-drug regimen via the Feedback System Control (FSC) platform

Therapeutic outcomes of combination chemotherapy have not significantly advanced during the past decades. This has been attributed to the formidable challenges of optimizing drug combinations. Testing a matrix of all possible combinations of doses and agents in a single cell line is unfeasible due to the virtually infinite number of possibilities. We utilized the Feedback System Control (FSC) platform, a phenotype oriented approach to test 100 options among 15,625 possible combinations in four rounds of assaying to identify an optimal tri-drug combination in eight distinct chemoresistant bladder cancer cell lines. This combination killed between 82.86% and 99.52% of BCa cells, but only 47.47% of the immortalized benign bladder epithelial cells. Preclinical in vivo verification revealed its markedly enhanced anti-tumor efficacy as compared to its bi- or mono-drug components in cell line-derived tumor xenografts. The collective response of these pathways to component drugs was both cell type- and drug type specific. However, the entire spectrum of pathways triggered by the tri-drug regimen was similar in all four cancer cell lines, explaining its broad spectrum killing of BCa lines, which did not occur with its component drugs. Our findings here suggest that the FSC platform holdspromise for optimization of anti-cancer combination chemotherapy.

Rapid optimization of drug combinations for the optimal angiostatic treatment of cancer

Drug combinations can improve angiostatic cancer treatment efficacy and enable the reduction of side effects and drug resistance. Combining drugs is non-trivial due to the high number of possibilities. We applied a feedback system control (FSC) technique with a population-based stochastic search algorithm to navigate through the large parametric space of nine angiostatic drugs at four concentrations to identify optimal low-dose drug combinations. This implied an iterative approach of in vitro testing of endothelial cell viability and algorithm-based analysis. The optimal synergistic drug combination, containing erlotinib, BEZ-235 and RAPTA-C, was reached in a small number of iterations. Final drug combinations showed enhanced endothelial cell specificity and synergistically inhibited proliferation (p < 0.001), but not migration of endothelial cells, and forced enhanced numbers of endothelial cells to undergo apoptosis (p < 0.01). Successful translation of this drug combination was achieved in two preclinical in vivo tumor models. Tumor growth was inhibited synergistically and significantly (p < 0.05 and p < 0.01, respectively) using reduced drug doses as compared to optimal single-drug concentrations. At the applied conditions, single-drug monotherapies had no or negligible activity in these models. We suggest that FSC can be used for rapid identification of effective, reduced dose, multi-drug combinations for the treatment of cancer and other diseases.

Mechanism-independent optimization of combinatorial nanodiamond and unmodified drug delivery using a phenotypically driven platform technology

Combination chemotherapy can mediate drug synergy to improve treatment efficacy against a broad spectrum of cancers. However, conventional multidrug regimens are often additively determined, which have long been believed to enable good cancer-killing efficiency but are insufficient to address the nonlinearity in dosing. Despite improved clinical outcomes by combination treatment, multi-objective combination optimization, which takes into account tumor heterogeneity and balance of efficacy and toxicity, remains challenging given the sheer magnitude of the combinatorial dosing space. To enhance the properties of the therapeutic agents, the field of nanomedicine has realized novel drug delivery platforms that can enhance therapeutic efficacy and safety. However, optimal combination design that incorporates nanomedicine agents still faces the same hurdles as unmodified drug administration. The work reported here applied a powerful phenotypically driven platform, termed feedback system control (FSC), that systematically and rapidly converges upon a combination consisting of three nanodiamond-modified drugs and one unmodified drug that is simultaneously optimized for efficacy against multiple breast cancer cell lines and safety against multiple control cell lines. Specifically, the therapeutic window achieved from an optimally efficacious and safe nanomedicine combination was markedly higher compared to that of an optimized unmodified drug combination and nanodiamond monotherapy or unmodified drug administration. The phenotypically driven foundation of FSC implementation does not require any cellular signaling pathway data and innately accounts for population heterogeneity and nonlinear biological processes. Therefore, FSC is a broadly applicable platform for both nanotechnology-modified and unmodified therapeutic optimizations that represent a promising path toward phenotypic personalized medicine.