scholarly journals Integrated deep learned transcriptomic and structure-based predictor of clinical trials outcomes

2016 ◽  
Author(s):  
Artem V. Artemov ◽  
Evgeny Putin ◽  
Quentin Vanhaelen ◽  
Alexander Aliper ◽  
Ivan V. Ozerov ◽  
...  

AbstractDespite many recent advances in systems biology and a marked increase in the availability of high-throughput biological data, the productivity of research and development in the pharmaceutical industry is on the decline. This is primarily due to clinical trial failure rates reaching up to 95% in oncology and other disease areas. We have developed a comprehensive analytical and computational pipeline utilizing deep learning techniques and novel systems biology analytical tools to predict the outcomes of phase I/II clinical trials. The pipeline predicts the side effects of a drug using deep neural networks and estimates drug-induced pathway activation. It then uses the predicted side effect probabilities and pathway activation scores as an input to train a classifier which predicts clinical trial outcomes. This classifier was trained on 577 transcriptomic datasets and has achieved a cross-validated accuracy of 0.83. When compared to a direct gene-based classifier, our multi-stage approach dramatically improves the accuracy of the predictions. The classifier was applied to a set of compounds currently present in the pipelines of several major pharmaceutical companies to highlight potential risks in their portfolios and estimate the fraction of clinical trials that were likely to fail in phase I and II.

Vaccines ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 565
Author(s):  
Anastasia Piniaeva ◽  
Georgy Ignatyev ◽  
Liubov Kozlovskaya ◽  
Yury Ivin ◽  
Anastasia Kovpak ◽  
...  

Global polio eradication requires both safe and effective vaccines, and safe production processes. Sabin oral poliomyelitis vaccine (OPV) strains can evolve to virulent viruses and result in poliomyelitis outbreaks, and conventional inactivated poliomyelitis vaccine (Salk-IPV) production includes accumulation of large stocks of neurovirulent wild polioviruses. Therefore, IPV based on attenuated OPV strains seems a viable option. To increase the global supply of affordable inactivated vaccine in the still not-polio free world we developed an IPV made from the Sabin strains–PoliovacSin. Clinical trials included participants 18–60 years of age. A phase I single-center, randomized, double-blind placebo-controlled clinical trial included 60 participants, who received one dose of PoliovacSin or Placebo. A phase II multicenter, randomized, double-blind, comparative clinical trial included 200 participants, who received one dose of PoliovacSin or Imovax Polio. All vaccinations were well tolerated, and PoliovacSin had a comparable safety profile to the Placebo or the reference Imovax Polio preparations. A significant increase in neutralizing antibody levels to polioviruses types 1–3 (Sabin and wild) was observed in PoliovacSin and Imovax Polio vaccinated groups. Therefore, clinical trials confirmed good tolerability, low reactogenicity, and high safety profile of the PoliovacSin and its pronounced immunogenic properties. The preparation was approved for clinical trials involving infants.


Author(s):  
Ji-Hye Seo ◽  
Ock-Joo Kim ◽  
Sang-Ho Yoo ◽  
Eun Kyung Choi ◽  
Ji-Eun Park

The phase I trial is the first step in administering a drug to humans, but it has no therapeutic purpose. Under the absence of therapeutic purpose, healthy volunteers demonstrated different motivations, unlike the actual patients participating in trials. There were many reported motivations, such as financial motivation, contributing to the health science, accessing ancillary health care benefits, scientific interest or interest in the goals of the study, meeting people, and general curiosity. The aim of this study was to identify the motivation and characteristics of healthy volunteers participating in phase I trials in the Republic of Korea. We gave surveys to 121 healthy volunteers to study their demographic characteristics and the reasons of participation. We identified whether the decision to participate in the research was influenced by demographic factors and whether the perception and attitudes toward the research were influenced by the characteristics of the healthy volunteers. After completion of the first survey, 12 healthy volunteers who had participated in a phase I clinical trial were selected to answer the second interview. According to our survey, most healthy volunteers were unmarried men and economically dependent. Most of them participated in the study because of financial reward. The most important factor to measure financial reward was the research period. Also, 43% of the volunteers were university students, 42% answered “university graduation” and 55% were residing in family-owned houses. Many healthy volunteers were found to be living in family homes and to have a student status or lack of economic independence. Results of the survey showed that 64% of respondents indicated having more than one clinical trial participation. In-depth interviews showed that healthy volunteers had diverse motivation to participate in research and that healthy volunteer perceive the clinical trial positively. The main motivation for healthy volunteers’ participation in research was “financial reward.” Healthy volunteers also considered research schedules, processes, and safety, and had a positive perception of clinical trials, but they thought that the public has a negative perception.


2020 ◽  
Vol 16 (9) ◽  
pp. e859-e867
Author(s):  
Rachel S. Hianik ◽  
Gavin P. Campbell ◽  
Eli Abernethy ◽  
Colleen Lewis ◽  
Christina S. Wu ◽  
...  

PURPOSE: Debate continues over whether explicit recommendations for a clinical trial should be included as an element of shared decision making within oncology. We aimed to determine if and how providers make explicit recommendations in the setting of phase I cancer clinical trials. METHODS: Twenty-three patient/provider conversations about phase I trials were analyzed to determine how recommendations are made and how the conversations align with a shared decision-making framework. In addition, 19 providers (9 of whose patient encounters were observed) were interviewed about the factors they consider when deciding whether to recommend a phase I trial. RESULTS: We found that providers are comprehensive in the factors they consider when recommending clinical trials. The two most frequently stated factors were performance status (89%) and patient preferences (84%). Providers made explicit recommendations in 19 conversations (83%), with 12 of those being for a phase I trial (12 [63%] of 19). They made these recommendations in a manner consistent with a shared decision-making model; 18 (95%) of the 19 conversations during which a recommendation was made included all steps, or all but 1 step, of shared decision making, as did 11 of the 12 conversations during which a phase I trial was recommended. In 7 (58%) of these later conversations, providers also emphasized the importance of the patient’s opinion. CONCLUSION: We suggest that providers not hesitate to make explicit recommendations for phase I clinical trials, because they are able to do so in a manner consistent with shared decision making. With further research, these results can be applied to other clinical trial settings.


Cells ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 2529
Author(s):  
Satoshi Kamoto ◽  
Masahiro Shinada ◽  
Daiki Kato ◽  
Sho Yoshimoto ◽  
Namiko Ikeda ◽  
...  

Podoplanin (PDPN), a small transmembrane mucin-like glycoprotein, is ectopically expressed on tumor cells. PDPN is known to be linked with several aspects of tumor malignancies in certain types of human and canine tumors. Therefore, it is considered to be a novel therapeutic target. Monoclonal antibodies targeting PDPN expressed in human tumor cells showed obvious anti-tumor effects in preclinical studies using mouse models. Previously, we generated a cancer-specific mouse–dog chimeric anti-PDPN antibody, P38Bf, which specifically recognizes PDPN expressed in canine tumor cells. In this study, we investigated the safety and anti-tumor effects of P38Bf in preclinical and clinical trials. P38Bf showed dose-dependent antibody-dependent cellular cytotoxicity against canine malignant melanoma cells. In a preclinical trial with one healthy dog, P38Bf administration did not induce adverse effects over approximately 2 months. In phase I/II clinical trials of three dogs with malignant melanoma, one dog vomited, and all dogs had increased serum levels of C-reactive protein, although all adverse effects were grade 1 or 2. Severe adverse effects leading to withdrawal of the clinical trial were not observed. Furthermore, one dog had stable disease with P38Bf injections. This is the first reported clinical trial of anti-PDPN antibody therapy using spontaneously occurring canine tumor models.


2013 ◽  
Vol 9 (6) ◽  
pp. 287-293 ◽  
Author(s):  
Richard F. Brown ◽  
Debbie L. Cadet ◽  
Robert H. Houlihan ◽  
Maria D. Thomson ◽  
Emily C. Pratt ◽  
...  

Low rates of physician recommendations of African American patients to clinical trials warrant further investigation. Interventions to reduce misunderstandings and aid decision making need to target both patients and family members.


2013 ◽  
Vol 31 (15_suppl) ◽  
pp. 6587-6587 ◽  
Author(s):  
Rui Qin ◽  
Amylou C. Dueck ◽  
Daniel Satele ◽  
Julian R. Molina ◽  
Charles Erlichman ◽  
...  

6587 Background: Recently the Patient-Reported Outcomes version of the CTCAE was developed to augment clinically graded adverse events with information reported directly by patients on clinical trials (Basch, 2009). The validation and potential application of PRO-CTCAE in phase I clinical trials are of great interest as toxicity is the primary endpoint. Methods: Selected PRO-CTCAE items (21 items measuring 12 symptomatic adverse events) corresponding to the major adverse events required to be graded clinically were collected in an ongoing phase I clinical trial of weekly cilengitide and paclitaxel in patients with advanced solid malignancies (NCT01276496). PRO-CTCAE was administered in a paper booklet by a clinical research associate prior to treatment on days 1, 8 and 15 of their regular visits. These PRO-CTCAE items were summarized descriptively in comparison to clinician-assessed CTCAE ver 4.0 (NCI, 2009) during the first cycle. As a pilot study to assess feasibility of PRO-CTCAE in phase I trials, PRO-CTCAE was not intended for determination of dose-limiting toxicity. Results: Twelve patients were accrued to two separate doses of cilengitide and paclitaxel. The median age was 56 (range 36—67) and half of patients were female. All patients had an ECOG performance score <= 1. Over 90% of patients had received prior surgery and chemotherapy. All but one patient completed weekly PRO-CTCAE during the first cycle, the only patient refused to complete weeks 2 and 3 did not give a reason. PRO-CTCAE captured most of the symptomatic adverse events reflected in clinician-assessed CTCAE. Some symptomatic adverse events were not reported clinically by CTCAE but were reported by patients by PRO-CTCAE. Overall, PRO-CTCAE items indicated slightly more severe degree of symptoms experienced by patients than those reported in CTCAE. Conclusions: This is the first study that PRO-CTCAE items were integrated within regular study visits in a phase I trial. The administration of PRO-CTCAE has been proved feasible and fruitful, providing consistent and enhanced symptomatic toxicity from the patient point of view. The addition of PRO-CTCAE did not significantly increase patient burden. Clinical trial information: NCT01276496.


2019 ◽  
Vol 37 (15_suppl) ◽  
pp. 5559-5559
Author(s):  
Bradley Corr ◽  
Marisa Moroney ◽  
Jeanelle Sheeder ◽  
Brandon Sawyer ◽  
S. Gail Eckhardt ◽  
...  

5559 Background: Ovarian cancer patients who enroll in Phase I clinical trials are typically platinum resistant, heavily pretreated patients with a poor prognosis. Historically, clinical benefit of Phase I trials in this patient population has been uncertain. We assessed prognostic factors and survival in women with recurrent, previously treated ovarian cancer who enrolled in Phase I clinical trials. Methods: We performed a retrospective analysis of all ovarian cancer patients who were treated on Phase I clinical trials from 2008 through 2018 at the University of Colorado Cancer Center. Patient characteristics, treatment-related toxicities and survival data were assessed. Descriptive statistics and Cox proportional hazards models were utilized to identify risk factors associated with survival time. Results: A total of 132 individual patients were treated on Phase I clinical trials. Patients had a median age of 59 years (range 33-88) with a median of 5.5 (range 1-13) previous chemotherapy lines. 53/132 (40%) of patients were treated on multiple Phase I trials with a median of 1 (range 0-5) prior Phase 1 clinical trial enrollments. All patients had an ECOG performance status of 0 or 1. Overall response rate (defined as complete or partial response) was 9% and disease control rate (defined as complete or partial response or stable disease as best response) was 33%. Median overall survival (OS) was 11.5 months (95% CI: 9.3-13.7). Two patients died on trial due to progression of disease while no patients died due to treatment-related toxicity. In multivariate analysis, independent risk factors predicting shorter survival were elevated CA-125 (HR 2.8; 95% CI: 1.6-5.2) and albumin < 3.5 g/dL (HR 2.5; 95% CI: 1.65-3.79). BMI > 25 predicted longer survival (HR 0.65; 95% CI: 0.44-0.96). Conclusions: Phase I clinical trials for heavily pretreated ovarian cancer patients are safe by a standard of no patients experiencing toxicity-related deaths in our study. They are clinically efficacious with patients experiencing OS of 11.5 months, which is comparable to existing approved therapies. Elevated CA-125 and low albumin levels predict shorter survival, while BMI > 25 predicts longer survival. Phase I clinical trial options should be considered for all heavily pretreated ovarian cancer patients if available to them.


2016 ◽  
Vol 62 (3) ◽  
pp. 442-448 ◽  
Author(s):  
Susan M Mockus ◽  
Sara E Patterson ◽  
Cara Statz ◽  
Carol J Bult ◽  
Gregory J Tsongalis

Abstract BACKGROUND Availability of genomic information used in the management of cancer treatment has outpaced both regulatory and reimbursement efforts. Many types of clinical trials are underway to validate the utility of emerging genome-based biomarkers for diagnostic, prognostic, and predictive applications. Clinical trials are a key source of evidence required for US Food and Drug Administration approval of therapies and companion diagnostics and for establishing the acceptance criteria for reimbursement. CONTENT Determining the eligibility of patients for molecular-based clinical trials and the interpretation of data emerging from clinical trials is significantly hampered by 2 primary factors: the lack of specific reporting standards for biomarkers in clinical trials and the lack of adherence to official gene and variant naming standards. Clinical trial registries need specifics on the mutation required for enrollment as opposed to allowing a generic mutation entry such as, “EGFR mutation.” The use of clinical trials data in bioinformatics analysis and reporting is also gated by the lack of robust, state of the art programmatic access support. An initiative is needed to develop community standards for clinical trial descriptions and outcome reporting that are modeled after similar efforts in the genomics research community. SUMMARY Systematic implementation of reporting standards is needed to insure consistency and specificity of biomarker data, which will in turn enable better comparison and assessment of clinical trial outcomes across multiple studies. Reporting standards will facilitate improved identification of relevant clinical trials, aggregation and comparison of information across independent trials, and programmatic access to clinical trials databases.


Author(s):  
Danielle Cristina Garbuio ◽  
Cristina Mara Zamarioli ◽  
Maísa Oliveira de Melo ◽  
Patrícia Maria Berardo Gonçalves Maia Campos ◽  
Emília Campos de Carvalho ◽  
...  

ABSTRACT Objective: to evaluate the safety of a topical formulation containing chamomile microparticles coated with chitosan in the skin of healthy participants. Method: phase I blind, controlled, non-randomized, single-dose clinical trial with control for skin, base formulation, and formulation with microparticles. The variables analyzed were irritation and hydration by the Wilcoxon and Kruskall-Wallis tests. Results: the study started with 35 participants with a mean age of 26.3 years. Of these, 30 (85.71%) were female, 29 (82.90%) were white skinned and 32 (91.40%) had no previous pathologies. One participant was removed from the study reporting erythema at the site of application, and four other participants for not attending the last evaluation. In the 30 participants who completed the study, the tested formulation did not cause erythema, peeling, burning, pruritus or pain; there was an improvement in cutaneous hydration in the site of application of the formulation with microparticles. In the evaluation of the barrier function, there was an increase in transepidermal water loss in all sites. Conclusion: the formulation with chamomile microparticles is safe for topical use, not causing irritation and improving skin hydration over four weeks of use. Its effects on barrier function need further investigation. No. RBR-3h78kz in the Brazilian Registry of Clinical Trials (ReBEC).


Sign in / Sign up

Export Citation Format

Share Document