scholarly journals Anticancer drug synergy prediction in understudied tissues using transfer learning

2020 ◽  
Author(s):  
Yejin Kim ◽  
Shuyu Zheng ◽  
Jing Tang ◽  
Wenjin Jim Zheng ◽  
Zhao Li ◽  
...  
Keyword(s):  
Prediction Model ◽  
Transfer Learning ◽  
Learning Strategy ◽  
Mean Squared Error ◽  
Treatment Options ◽  
Drug Synergy ◽  
Learning From Data ◽  
Improved Accuracy ◽  
Synergy Prediction

Abstract Objective Drug combination screening has advantages in identifying cancer treatment options with higher efficacy without degradation in terms of safety. A key challenge is that the accumulated number of observations in in-vitro drug responses varies greatly among different cancer types, where some tissues are more understudied than the others. Thus, we aim to develop a drug synergy prediction model for understudied tissues as a way of overcoming data scarcity problems. Materials and Methods We collected a comprehensive set of genetic, molecular, phenotypic features for cancer cell lines. We developed a drug synergy prediction model based on multitask deep neural networks to integrate multimodal input and multiple output. We also utilized transfer learning from data-rich tissues to data-poor tissues. Results We showed improved accuracy in predicting synergy in both data-rich tissues and understudied tissues. In data-rich tissue, the prediction model accuracy was 0.9577 AUROC for binarized classification task and 174.3 mean squared error for regression task. We observed that an adequate transfer learning strategy significantly increases accuracy in the understudied tissues. Conclusions Our synergy prediction model can be used to rank synergistic drug combinations in understudied tissues and thus help to prioritize future in-vitro experiments. Code is available at https://github.com/yejinjkim/synergy-transfer.

scholarly journals Anti-cancer Drug Synergy Prediction in Understudied Tissues using Transfer Learning

2020 ◽  
Author(s):  
Yejin Kim ◽  
Shuyu Zheng ◽  
Jing Tang ◽  
W. Jim Zheng ◽  
Zhao Li ◽  
...  
Keyword(s):  
Prediction Model ◽  
Transfer Learning ◽  
Treatment Options ◽  
Cancer Drug ◽  
Drug Synergy ◽  
Learning From Data ◽  
Cancer Types ◽  
Improved Accuracy ◽  
Synergy Prediction

AbstractMotivationExploring an exponentially increasing yet more promising space, high-throughput combinatorial drug screening has advantages in identifying cancer treatment options with higher efficacy without degradation in terms of safety. A key challenge is that accumulated number of observations in in-vitro drug responses varies greatly among different cancer types, where some tissues (such as bone and prostate) are understudied than the others. Thus, we aim to develop a drug synergy prediction model for understudied data-poor tissues as overcoming data scarcity problem.ResultsWe collected a comprehensive set of genetic, molecular, phenotypic features for cancer cell lines from six different databases. We developed a drug synergy prediction model based on deep neural networks to integrate multi-modal input and utilize transfer learning from data-rich tissues to data-poor tissues. We showed improved accuracy in predicting drug synergy in understudied tissues without enough drug combination screening data nor after-treatment transcriptome. Our synergy prediction model can be used to rank synergistic drug combinations in understudied tissues and thus help prioritizing future in-vitro experiments.Availability and ImplementationOur algorithm will be publicly available via https://github.com/yejinjkim/drug-synergy-prediction

scholarly journals Deep Transfer Learning for Improved Detection of Keratoconus using Corneal Topographic Maps

2021 ◽  
Author(s):  
Ali H. Al-Timemy ◽  
Nebras H. Ghaeb ◽  
Zahraa M. Mosa ◽  
Javier Escudero
Keyword(s):  
Transfer Learning ◽  
Learning Strategy ◽  
Clinical Decision ◽  
Topographic Maps ◽  
Computer Assisted ◽  
Clinical Knowledge ◽  
Average Accuracy ◽  
Assisted Diagnosis ◽  
Improved Accuracy ◽  
Fine Tune

Abstract Clinical keratoconus (KCN) detection is a challenging and time-consuming task. In the diagnosis process, ophthalmologists must revise demographic and clinical ophthalmic examinations. The latter include slit-lamb, corneal topographic maps, and Pentacam indices (PI). We propose an Ensemble of Deep Transfer Learning (EDTL) based on corneal topographic maps. We consider four pretrained networks, SqueezeNet (SqN), AlexNet (AN), ShuffleNet (SfN), and MobileNet-v2 (MN), and fine-tune them on a dataset of KCN and normal cases, each including four topographic maps. We also consider a PI classifier. Then, our EDTL method combines the output probabilities of each of the five classifiers to obtain a decision based on the fusion of probabilities. Individually, the classifier based on PI achieved 93.1% accuracy, whereas the deep classifiers reached classification accuracies over 90% only in isolated cases. Overall, the average accuracy of the deep networks over the four corneal maps ranged from 86% (SfN) to 89.9% (AN). The classifier ensemble increased the accuracy of the deep classifiers based on corneal maps to values ranging (92.2% to 93.1%) for SqN and (93.1% to 94.8%) for AN. Including in the ensemble-specific combinations of corneal maps’ classifiers and PI increased the accuracy to 98.3%. Moreover, visualization of first learner filters in the networks and Grad-CAMs confirmed that the networks had learned relevant clinical features. This study shows the potential of creating ensembles of deep classifiers fine-tuned with a transfer learning strategy as it resulted in an improved accuracy while showing learnable filters and Grad-CAMs that agree with clinical knowledge. This is a step further towards the potential clinical deployment of an improved computer-assisted diagnosis system for KCN detection to help ophthalmologists to confirm the clinical decision and to perform fast and accurate KCN treatment.

Treatment Options in COVID-19: The Role of Bioavailable Antiviral Ribonucleoside Analog on NHC in vitro

2020 ◽  
Author(s):  
Lara Bittmann
Keyword(s):  
World Health Organization ◽  
Clinical Picture ◽  
Treatment Options ◽  
World Health ◽  
Wuhan City ◽  
The World ◽  
Novel Coronavirus ◽  
Health Organization

On December 31, 2019, WHO was informed of cases of pneumonia of unknown cause in Wuhan City, China. A novel coronavirus was identified as the cause by Chinese authorities on January 7, 2020 and was provisionally named "2019-nCoV". This new Coronavirus causes a clinical picture which has received now the name COVID-19. The virus has spread subsequently worldwide and was explained on the 11th of March, 2020 by the World Health Organization to the pandemic.

Are Carbonic Anhydrases Suitable Targets to Fight Protozoan Parasitic Diseases?

2019 ◽  
Vol 25 (39) ◽  
pp. 5266-5278 ◽  
Author(s):  
Katia D'Ambrosio ◽  
Claudiu T. Supuran ◽  
Giuseppina De Simone
Keyword(s):  
Drug Resistance ◽  
Animal Models ◽  
Carbonic Anhydrase ◽  
Drug Target ◽  
Treatment Options ◽  
Parasitic Diseases ◽  
Carbonic Anhydrases ◽  
Extensive Drug Resistance ◽  
Protozoan Infections

Protozoans belonging to Plasmodium, Leishmania and Trypanosoma genera provoke widespread parasitic diseases with few treatment options and many of the clinically used drugs experiencing an extensive drug resistance phenomenon. In the last several years, the metalloenzyme Carbonic Anhydrase (CA, EC 4.2.1.1) was cloned and characterized in the genome of these protozoa, with the aim to search for a new drug target for fighting malaria, leishmaniasis and Chagas disease. P. falciparum encodes for a CA (PfCA) belonging to a novel genetic family, the η-CA class, L. donovani chagasi for a β-CA (LdcCA), whereas T. cruzi genome contains an α-CA (TcCA). These three enzymes were characterized in detail and a number of in vitro potent and selective inhibitors belonging to the sulfonamide, thiol, dithiocarbamate and hydroxamate classes were discovered. Some of these inhibitors were also effective in cell cultures and animal models of protozoan infections, making them of considerable interest for the development of new antiprotozoan drugs with a novel mechanism of action.

Stew in its Own Juice: Protein Homeostasis Machinery Inhibition Reduces Cell Viability in Multiple Myeloma Cell Lines

2019 ◽  
Vol 19 (2) ◽  
pp. 112-119 ◽  
Author(s):  
Mariana B. de Oliveira ◽  
Luiz F.G. Sanson ◽  
Angela I.P. Eugenio ◽  
Rebecca S.S. Barbosa-Dantas ◽  
Gisele W.B. Colleoni
Keyword(s):  
Multiple Myeloma ◽  
Cell Death ◽  
Cell Viability ◽  
Cell Lines ◽  
Treatment Options ◽  
Compensatory Mechanism ◽  
Protein Homeostasis ◽  
Protein Response ◽  
Rpmi 8226

Introduction:Multiple myeloma (MM) cells accumulate in the bone marrow and produce enormous quantities of immunoglobulins, causing endoplasmatic reticulum stress and activation of protein handling machinery, such as heat shock protein response, autophagy and unfolded protein response (UPR).Methods:We evaluated cell lines viability after treatment with bortezomib (B) in combination with HSP70 (VER-15508) and autophagy (SBI-0206965) or UPR (STF- 083010) inhibitors.Results:For RPMI-8226, after 72 hours of treatment with B+VER+STF or B+VER+SBI, we observed 15% of viable cells, but treatment with B alone was better (90% of cell death). For U266, treatment with B+VER+STF or with B+VER+SBI for 72 hours resulted in 20% of cell viability and both treatments were better than treatment with B alone (40% of cell death). After both triplet combinations, RPMI-8226 and U266 presented the overexpression of XBP-1 UPR protein, suggesting that it is acting as a compensatory mechanism, in an attempt of the cell to handle the otherwise lethal large amount of immunoglobulin overload.Conclusion:Our in vitro results provide additional evidence that combinations of protein homeostasis inhibitors might be explored as treatment options for MM.

scholarly journals Mechanism of CK2.3, a Novel Mimetic Peptide of Bone Morphogenetic Protein Receptor Type IA, Mediated Osteogenesis

2019 ◽  
Vol 20 (10) ◽  
pp. 2500 ◽  
Author(s):  
Vrathasha Vrathasha ◽  
Hilary Weidner ◽  
Anja Nohe
Keyword(s):  
Signaling Pathways ◽  
Treatment Options ◽  
Time Frame ◽  
Bmp Signaling ◽  
C2c12 Cells ◽  
Molecular Sequence ◽  
Sequence Of Events ◽  
Protein Receptor

Background: Osteoporosis is a degenerative skeletal disease with a limited number of treatment options. CK2.3, a novel peptide, may be a potential therapeutic. It induces osteogenesis and bone formation in vitro and in vivo by acting downstream of BMPRIA through releasing CK2 from the receptor. However, the detailed signaling pathways, the time frame of signaling, and genes activated remain largely unknown. Methods: Using a newly developed fluorescent CK2.3 analog, specific inhibitors for the BMP signaling pathways, Western blot, and RT-qPCR, we determined the mechanism of CK2.3 in C2C12 cells. We then confirmed the results in primary BMSCs. Results: Using these methods, we showed that CK2.3 stimulation activated OSX, ALP, and OCN. CK2.3 stimulation induced time dependent release of CK2β from BMPRIA and concurrently CK2.3 colocalized with CK2α. Furthermore, CK2.3 induced BMP signaling depends on ERK1/2 and Smad1/5/8 signaling pathways. Conclusion: CK2.3 is a novel peptide that drives osteogenesis, and we detailed the molecular sequence of events that are triggered from the stimulation of CK2.3 until the induction of mineralization. This knowledge can be applied in the development of future therapeutics for osteoporosis.

scholarly journals Molecular and Cellular Mechanisms of Metformin in Cervical Cancer

Cancers ◽  
2021 ◽  
Vol 13 (11) ◽  
pp. 2545
Author(s):  
Ya-Hui Chen ◽  
Po-Hui Wang ◽  
Pei-Ni Chen ◽  
Shun-Fa Yang ◽  
Yi-Hsuan Hsiao
Keyword(s):  
Cervical Cancer ◽  
Potential Role ◽  
Treatment Options ◽  
Cellular Mechanisms ◽  
Anticancer Effects ◽  
Clinical Benefits ◽  
Underlying Mechanisms

Cervical cancer is one of the major gynecologic malignancies worldwide. Treatment options include chemotherapy, surgical resection, radiotherapy, or a combination of these treatments; however, relapse and recurrence may occur, and the outcome may not be favorable. Metformin is an established, safe, well-tolerated drug used in the treatment of type 2 diabetes; it can be safely combined with other antidiabetic agents. Diabetes, possibly associated with an increased site-specific cancer risk, may relate to the progression or initiation of specific types of cancer. The potential effects of metformin in terms of cancer prevention and therapy have been widely studied, and a number of studies have indicated its potential role in cancer treatment. The most frequently proposed mechanism underlying the diabetes–cancer association is insulin resistance, which leads to secondary hyperinsulinemia; furthermore, insulin may exert mitogenic effects through the insulin-like growth factor 1 (IGF-1) receptor, and hyperglycemia may worsen carcinogenesis through the induction of oxidative stress. Evidence has suggested clinical benefits of metformin in the treatment of gynecologic cancers. Combining current anticancer drugs with metformin may increase their efficacy and diminish adverse drug reactions. Accumulating evidence is indicating that metformin exerts anticancer effects alone or in combination with other agents in cervical cancer in vitro and in vivo. Metformin might thus serve as an adjunct therapeutic agent for cervical cancer. Here, we reviewed the potential anticancer effects of metformin against cervical cancer and discussed possible underlying mechanisms.

scholarly journals In Vitro Effects of Doxycycline on Replication of Feline Coronavirus

Pathogens ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 312
Author(s):  
Magdalena Dunowska ◽  
Sayani Ghosh
Keyword(s):  
Inhibitory Concentration ◽  
Infectious Virus ◽  
Treatment Options ◽  
Inhibitory Effect ◽  
Virus Titration ◽  
Reverse Transcription Quantitative Pcr ◽  
In Vitro Effects ◽  
Dose Dependent ◽  
Feline Coronavirus

Feline infectious peritonitis (FIP) is a sporadic fatal disease of cats caused by a virulent variant of feline coronavirus (FCoV), referred to as FIP virus (FIPV). Treatment options are limited, and most of the affected cats die or are euthanized. Anecdotally, doxycycline has been used to treat FIP-affected cats, but there are currently no data to support or discourage such treatment. The aim of this study was to establish whether doxycycline inhibits replication of FIPV in vitro. The virus was cultured in Crandell-Rees feline kidney cells with various concentrations of doxycycline (0 to 50 µg/mL). The level of FIPV in cultures was determined by virus titration and FCoV-specific reverse-transcription quantitative PCR. Cell viability was also monitored. There was no difference in the level of infectious virus or viral RNA between doxycycline-treated and untreated cultures at 3, 12- and 18-hours post-infection. However, at 24 h, the growth of FIPV was inhibited by approximately two logs in cultures with >10 µg/mL doxycycline. This inhibition was dose-dependent, with inhibitory concentration 50% (IC50) 4.1 µg/mL and IC90 5.4 µg/mL. Our data suggest that doxycycline has some inhibitory effect on FIPV replication in vitro, which supports future clinical trials of its use for the treatment of FIP-affected cats.

scholarly journals Lomeguatrib Increases the Radiosensitivity of MGMT Unmethylated Human Glioblastoma Multiforme Cell Lines

2021 ◽  
Vol 22 (13) ◽  
pp. 6781
Author(s):  
Anna Kirstein ◽  
Daniela Schilling ◽  
Stephanie E. Combs ◽  
Thomas E. Schmid
Keyword(s):  
Glioblastoma Multiforme ◽  
Cell Lines ◽  
Dna Methyltransferase ◽  
Treatment Options ◽  
Treatment Resistance ◽  
Cell Cycle Distribution ◽  
Human Glioblastoma ◽  
Human Glioblastoma Multiforme ◽  
Mgmt Protein

Background: Treatment resistance of glioblastoma multiforme to chemo- and radiotherapy remains a challenge yet to overcome. In particular, the O6-methylguanine-DNA-methyltransferase (MGMT) promoter unmethylated patients have only little benefit from chemotherapy treatment using temozolomide since MGMT counteracts its therapeutic efficacy. Therefore, new treatment options in radiotherapy need to be developed to inhibit MGMT and increase radiotherapy response. Methods: Lomeguatrib, a highly specific MGMT inhibitor, was used to inactivate MGMT protein in vitro. Radiosensitivity of established human glioblastoma multiforme cell lines in combination with lomeguatrib was investigated using the clonogenic survival assay. Inhibition of MGMT was analyzed using Western Blot. Cell cycle distribution and apoptosis were investigated to determine the effects of lomeguatrib alone as well as in combination with ionizing radiation. Results: Lomeguatrib significantly decreased MGMT protein and reduced radiation-induced G2/M arrest. A radiosensitizing effect of lomeguatrib was observed when administered at 1 µM and increased radioresistance at 20 µM. Conclusion: Low concentrations of lomeguatrib elicit radiosensitization, while high concentrations mediate a radioprotective effect.

scholarly journals Oxidative Stress as a Possible Target in the Treatment of Toxoplasmosis: Perspectives and Ambiguities

2021 ◽  
Vol 22 (11) ◽  
pp. 5705
Author(s):  
Karolina Szewczyk-Golec ◽  
Marta Pawłowska ◽  
Roland Wesołowski ◽  
Marcin Wróblewski ◽  
Celestyna Mila-Kierzenkowska
Keyword(s):  
Oxidative Stress ◽  
Animal Studies ◽  
Treatment Options ◽  
Natural Antioxidants ◽  
Redox Status ◽  
Host Cells ◽  
Common Disease ◽  
Parasite Viability

Toxoplasma gondii is an apicomplexan parasite causing toxoplasmosis, a common disease, which is most typically asymptomatic. However, toxoplasmosis can be severe and even fatal in immunocompromised patients and fetuses. Available treatment options are limited, so there is a strong impetus to develop novel therapeutics. This review focuses on the role of oxidative stress in the pathophysiology and treatment of T. gondii infection. Chemical compounds that modify redox status can reduce the parasite viability and thus be potential anti-Toxoplasma drugs. On the other hand, oxidative stress caused by the activation of the inflammatory response may have some deleterious consequences in host cells. In this respect, the potential use of natural antioxidants is worth considering, including melatonin and some vitamins, as possible novel anti-Toxoplasma therapeutics. Results of in vitro and animal studies are promising. However, supplementation with some antioxidants was found to promote the increase in parasitemia, and the disease was then characterized by a milder course. Undoubtedly, research in this area may have a significant impact on the future prospects of toxoplasmosis therapy.

Sign in / Sign up

Export Citation Format

Share Document