Dynamic recommendation systems aim to achieve real-time updates and dynamic migration of user interests, primarily utilizing user-item interaction sequences with timestamps to capture the dynamic changes in user interests and item attributes. Recent research has mainly centered on two aspects. First, it involves modeling the dynamic interaction relationships between users and items using dynamic graphs. Second, it focuses on mining their long-term and short-term interaction patterns. This is achieved through the joint learning of static and dynamic embeddings for both users and items. Although most existing methods have achieved some success in modeling the historical interaction sequences between users and items, there is still room for improvement, particularly in terms of modeling the long-term dependency structures of dynamic interaction histories and extracting the most relevant delayed interaction patterns. To address this issue, we proposed a Dynamic Context-Aware Recommendation System for dynamic recommendation. Specifically, our model is built on a dynamic graph and utilizes the static embeddings of recent user-item interactions as dynamic context. Additionally, we constructed a Gated Multi-Layer Perceptron encoder to capture the long-term dependency structure in the dynamic interaction history and extract high-level features. Then, we introduced an Attention Pooling network to learn similarity scores between high-level features in the user-item dynamic interaction history. By calculating bidirectional attention weights, we extracted the most relevant delayed interaction patterns from the historical sequence to predict the dynamic embeddings of users and items. Additionally, we proposed a loss function called the Pairwise Cosine Similarity loss for dynamic recommendation to jointly optimize the static and dynamic embeddings of two types of nodes. Finally, extensive experiments on two real-world datasets, LastFM, and the Global Terrorism Database showed that our model achieves consistent improvements over state-of-the-art baselines.
Citation: Zhiwen Hou, Fanliang Bu, Yuchen Zhou, Lingbin Bu, Qiming Ma, Yifan Wang, Hanming Zhai, Zhuxuan Han. DyCARS: A dynamic context-aware recommendation system[J]. Mathematical Biosciences and Engineering, 2024, 21(3): 3563-3593. doi: 10.3934/mbe.2024157
| [1] | Sohrab Najafipour, Abdolreza karami, Manoochehr Rasouli, Mehdi Kalani, Seyed-Jalal-Aldin Ashraf-Mansoori, Ali Moravej . Association of interleukin-2 gene variants (positions +114 and −384) and susceptibility to brucellosis in Iranian population. AIMS Molecular Science, 2017, 4(1): 103-109. doi: 10.3934/molsci.2017.1.103 |
| [2] | Viviana Imbua Levi Enoka, Gideon Mutie Kikuvi, Perpetual Wangui Ndung'u . Effect of garlic and onion extract chitosan nanoparticles on selected intestinal bacterial flora in indigenous rainbow rooster chicken in Kenya. AIMS Molecular Science, 2021, 8(2): 98-116. doi: 10.3934/molsci.2021008 |
| [3] | Carlos Gutierrez-Merino, Dorinda Marques-da-Silva, Sofia Fortalezas, Alejandro K. Samhan-Arias . The critical role of lipid rafts nanodomains in the cross-talk between calcium and reactive oxygen and nitrogen species in cerebellar granule neurons apoptosis by extracellular potassium deprivation. AIMS Molecular Science, 2016, 3(1): 12-29. doi: 10.3934/molsci.2016.1.12 |
| [4] | Francisco Les, Zsuzsa Iffiú-Soltész, Josep Mercarder, Christian Carpéné . Tyramine activates lipid accumulation in rat adipocytes: influences of in vitro and in vivo administration. AIMS Molecular Science, 2017, 4(3): 339-351. doi: 10.3934/molsci.2017.3.339 |
| [5] | Charles A. Downs, Abdel A. Alli, Nicholle M. Johnson, My N. Helms . Cigarette smoke extract is a Nox agonist and regulates ENaC in alveolar type 2 cells. AIMS Molecular Science, 2016, 3(3): 439-453. doi: 10.3934/molsci.2016.3.439 |
| [6] | Elisa Isopi, Giuseppe Legname . Pin1 and neurodegeneration: a new player for prion disorders?. AIMS Molecular Science, 2015, 2(3): 311-323. doi: 10.3934/molsci.2015.3.311 |
| [7] | Jian Zou, Fulton T. Crews . Glutamate/NMDA excitotoxicity and HMGB1/TLR4 neuroimmune toxicity converge as components of neurodegeneration. AIMS Molecular Science, 2015, 2(2): 77-100. doi: 10.3934/molsci.2015.2.77 |
| [8] | Genu George, Sumita K. Chellappan, Mandagini Geetha, Padinjaradath S. Appukuttan . Possible molecular basis for macromolecular antigen attachment to host cells: their immune complex with plasma antibodies have unoccupied binding sites enabling binding to smaller ligands. AIMS Molecular Science, 2017, 4(1): 91-102. doi: 10.3934/molsci.2017.1.91 |
| [9] | David Trac, My N. Helms . Nadph oxidase and epithelial sodium channels regulate neonatal mouse lung development. AIMS Molecular Science, 2017, 4(1): 28-40. doi: 10.3934/molsci.2017.1.28 |
| [10] | Noor Riyadh Thiab, Nicola King, Mary McMillan, Amer Almashhadany, Graham L Jones . Age-related protein and mRNA expression of glutathione peroxidases (GPx) and Hsp-70 in different regions of rat kidney with and without stressor. AIMS Molecular Science, 2016, 3(2): 125-137. doi: 10.3934/molsci.2016.2.125 |
Dynamic recommendation systems aim to achieve real-time updates and dynamic migration of user interests, primarily utilizing user-item interaction sequences with timestamps to capture the dynamic changes in user interests and item attributes. Recent research has mainly centered on two aspects. First, it involves modeling the dynamic interaction relationships between users and items using dynamic graphs. Second, it focuses on mining their long-term and short-term interaction patterns. This is achieved through the joint learning of static and dynamic embeddings for both users and items. Although most existing methods have achieved some success in modeling the historical interaction sequences between users and items, there is still room for improvement, particularly in terms of modeling the long-term dependency structures of dynamic interaction histories and extracting the most relevant delayed interaction patterns. To address this issue, we proposed a Dynamic Context-Aware Recommendation System for dynamic recommendation. Specifically, our model is built on a dynamic graph and utilizes the static embeddings of recent user-item interactions as dynamic context. Additionally, we constructed a Gated Multi-Layer Perceptron encoder to capture the long-term dependency structure in the dynamic interaction history and extract high-level features. Then, we introduced an Attention Pooling network to learn similarity scores between high-level features in the user-item dynamic interaction history. By calculating bidirectional attention weights, we extracted the most relevant delayed interaction patterns from the historical sequence to predict the dynamic embeddings of users and items. Additionally, we proposed a loss function called the Pairwise Cosine Similarity loss for dynamic recommendation to jointly optimize the static and dynamic embeddings of two types of nodes. Finally, extensive experiments on two real-world datasets, LastFM, and the Global Terrorism Database showed that our model achieves consistent improvements over state-of-the-art baselines.
Rheumatoid arthritis (RA) is a chronic inflammatory debilitating autoimmune disease [1]. Cell mediated and humoral immune reactions are involved in pathogenesis of rheumatoid arthritis [2]. The disease is characterized by severe joint inflammations of whole body along with damage to cartilage and bones [3]. Leukocyte infiltration and pannus formation are also responsible for the pathogenesis of RA. Although, the exact cause has not been elucidated still now. Several pro-inflammatory and anti-inflammatory cytokines secreted by immune cells are responsible for the cause of RA. In particular, it was reported that tumor necrosis factor (TNF), interleukin-1β (IL-1β), interleukin-15 (IL-15), transforming growth factor-β (TGF-β), interleukin-6 (IL-6) are important pro-inflammatory cytokines responsible for initiation and progression of RA [4,5]. In view of these findings, modulation of pro-inflammatory cytokines is a desired goal for the management of arthritis.
Most prescribed treatment for RA is a non-steroidal anti-inflammatory drugs (NSAID's). These drugs effectively reduce symptoms of RA, but at same time cause various side effects like gastrointestinal sickness and renal morbidity [6]. Disease modifying anti-rheumatic drugs (DMARD's) and biologics are also prescribed. Biologics are expensive and DMARD's are also associated with severe side effects. Reducing side effects and deleterious effect of antiarthritic drug should be taken into account while designing new therapeutics for RA. One of the possible strategies to suppress systemic inflammation is employment of natural compounds such as botanicals, bioactive food components or functional foods. Along with these, efficacies of various plants extracts and other natural compounds have been exploited for their antiarthritic activity.
Probiotics are ingestible microbial products which when administered in a particular number exert a beneficial effect on host body. These dietary feed supplements are used as probiotics because of their well-known immunomodulatory properties[7,8,9]. Probiotics modulate immune response at gut level. Probiotics are also in use for their antimicrobial, anti-inflammatory and immunomodulatory properties in urinary tract infections [10]. In our previous study we have discovered that L. casei and L. acidophilus has shown potent anti-inflammatory properties in the carrageenan model of acute inflammation [11]. In the present study, anti-inflammatory and anti-arthritic activities were investigated by using collagen induced arthritis (CIA) model. Anti-inflammatory activity of L. casei and L. acidophilus was checked by measuring the mRNA expression of TNF, IL-6 and IL-1β to validate our previous findings of anti-inflammatory activity. Standard anti-arthritic drug indomethacin was used for comparison.
Thirty healthy male Wistar rats, two months old (200 g) were included in this study. Animals were randomly divided into five groups (n = 6). These were purchased from Indian Institute of Toxicology Research (ⅡTR), Lucknow, India and maintained in animal house at Department of Microbiology, Barkatullah University, Bhopal, Madhya Pradesh. Animals were acclimatized for fifteen days before the experiment started. Animals were housed in stainless steel cages and were fed with standard diet purchased from Amrut Feed Ltd, India, given water ad libitum (Principles of Laboratory Animal Care NIH publication no, 85-23, revised 1985) and maintained under laboratory conditions (Temperature 22 ± 2 ℃, Relative humidity 60–70%, and 12-12 hrs light-dark cycle). All procedures and techniques used in this study were in accordance to the ethical committee guidelines.
L. acidophilus (ATCC 314) and L. casei (ATCC 334) were purchased from Hi Media, Navi Mumbai, India. Lyophilized cultures were streaked over De Mann Rogosa Agar (MRS) at 37 ℃ in anaerobic condition.
All chemical used in this study were of molecular and analytical grade.
Collagen induced arthritis model was induced by the method given by Remmers [12] with some necessary modifications. Rats were injected intra peritoneally with collagen (Bovine tracheal cartilage type Ⅱ) and incomplete freund's adjuvant on day 1except group Ⅰ animals. Booster doses of the same were injected on the 8th day. Preventive oral treatments were given to all the groups. Oral administration 500 μL of distilled water, 2 × 108 CFU/mL of L. casei, L. acidophilus suspended in 500 μL of distilled water were started on day 1 and continued till the 28th day for group Ⅱ, Ⅳ and Ⅴ group animals respectively. Indomethacin suspended in 500 μL of distilled water was administered at 10 mg/g body weight from day 1 to 28 to group Ⅲ animals [13]. Paw thickness were measured for all the experimental animals at day 0 and at the end of each week with dial gauge caliper.
On the 29th day, all animals were sacrificed in aseptic conditions. Blood samples were collected to isolate serum for cytokines assay. Right hind paws knee joints were also collected from each animal for RT PCR analysis of mRNA expressions for cytokines.
IL-6, TNF, IL-1β (pro-inflammatory cytokines) and IL-4, IL-10 (anti-inflammatory cytokines) (pg/mL) were estimated in serum samples with the help of ELISA Reader (Lisa Plus, Germany). IL-6 and TNF, IL-1β (Ray Bio®) and IL-4 and IL-10 (DNA bio) ELISA kits were used. Assays were performed according to the manufacturer's recommendations.
Paws were harvested and homogenized followed by addition of sodium lauryl sarconisate and centrifuged to remove the cell debris. RNA was precipitated by the addition of potassium acetate and acetic acid. Cold absolute ethanol was added for the precipitation of RNA. Total RNA was isolated by RNAzol method (Tel-Test, Friendswood, TX) according to the manufacturer's instructions.
The quantity and purity of RNA were determined by using a spectrophotometer (Shimadzu) at 260 and 280 nm. Samples with ratios > 1.7 were accepted for further analysis. These samples were treated with DNAase (Genei, Banglore, India) to remove the contaminating DNA. One microgram of total RNA from rat knee joint were reverse-transcribed into cDNA using 200 units of M-MLV reverse transcriptase (Invitrogen Co.) in 20 µL of reaction volume. cDNA was amplified in 20 µL of reaction mixture including 10 mM Tris-HCl (pH 8.3), 50 mM KCl, 1.5 mM MgCl2, 0.2 mM dNTP, 0.4 µM each of the 3' and 5' primer and 0.5 U Taq polymerase (Takara Co.) using a PTC-100 Programmable Thermal Controller (MJ Research, Waltham, MA, USA). All primers were designed using the published cDNA sequences and the primer selection software, with the help of web site, Primer 3 (http://www.genome.wi.mit.edu). Primer sequences and operating conditions are given in Table 1. PCR products thus obtained were separated on 1% agarose gel, stained with ethidium bromide, and photographed. Intensities of bands were measured by using ImageMaster VDSTM (Amersham Biosciences, Uppsala, Sweden) with image analysis software, ImageMaster Total Lab TM (Amersham Biosceinces). The amounts of target PCR products were normalized against GAPDH PCR product in the corresponding samples.
| Gene name | Oligonucleotide sequence (5'-3') | Denaturing, ℃ (time) |
Annealing, ℃ (time) |
Elongation, ℃ (time) |
Cycle No. | Product size | Gene bank No. |
| mGAPDH | F-ATGGGAAGCTGGTCATCAAC R-GGATGCAGGGATGATGTTCT |
94 (30 s) | 58 (30 s) | 72 (60 s) | 30 | 440 | NM_017008 |
| mTNF | F-GTCGTAAACCACCAAGC R-GACTCCAAAGTAGACCTGCCC |
94 (45 s) | 58 (45 s) | 72 (90 s) | 35 | 393 | AY 427675 |
| mIL-1β | F-GGCATAACAGGCTCATCTGG R-CATCATCCCACGAGTCACAG |
94 (45 s) | 58 (45 s) | 72 (90 s) | 35 | 414 | NM_031512 |
| mIL-6 | F-CCACTGCCTTCCCTACTTCA R-TGGTCCTTAGCCACTCCTTC |
94 (60 s) | 63 (60 s) | 72 (120 s) | 37 | 498 | NM_012589 |
| mIL-4 | F-ATG CACCGAGATGTTTGTACC R-TTCAGTGTTCTGAGCGTGGA |
95 (60 s) | 60 (60 s) | 72 (90 s) | 40 | 275 | NM_201270.1 |
| mIL-10 | F-GGAGTGAAGACCAAAGG R-TCTCCCAGGGAATTCAAATG |
94 (30 s) | 57 (1 s) | 72 (60 s) | 40 | 340 | NM_012854 |
| mGAPDH: human glyceraldehyde-3-phosphate dehydrogenase; mTNF: murine tumor necrosis factor α; IL-1β: interleukin-1β; IL-6: interleukin-6; IL-4: Interleukin-4; IL-10: Interleukin-10 | |||||||
DownLoad: CSVThe results are expressed as a mean ± SEM of six rats per group. The result obtained from different groups was analyzed by one way ANOVA followed by Bonferroni's Multiple Comparison Test. Data were considered statistically significant if P < 0.0001.
A significant increase in paw thickness was observed in group Ⅱ animals from 3.46 ± 0.04 to 3.78 ± 0.10 mm from 7th to 28th day while there was no change in the paw thickness (3.16 ± 0.08 mm) observed in group Ⅰ animals from 0 to 28th day. Lactobacillus treatment significantly decreased paw thickness in group Ⅳ and Ⅴ animals when compared with group Ⅱ animals. Paw thicknesses were 3.7 ± 0.16 and 3.48 ± 0.06 mm for group Ⅳ and Ⅴ respectively. A significant decreased in thickness to 3.4 ± 0.04 and 3.08 ± 0.08 mm for Ⅳ and Ⅴ groups at P < 0.0001 was observed on 28th day when compared with group Ⅱ animals. However group Ⅲ animals were also showing a significant decreased in paw thickness of 3.62 ± 0.09 mm on 7th day and 3.2 ± 0.08 mm on 28th day (at P < 0.0001) (Figure 1).
Figure 1. Figure showing the paw thickness (cm) of collagen induced arthritic rats on 7th, 14th, 21st and 28th day. Group Ⅱ animals were showing highest paw thickness (cm) on 28th day when compared with other groups at P < 0.0001. Results are expressed as Mean ± SEM of six rats per group.Serum level of IL-6, IL-1β and TNF level were significantly increased in group Ⅱ animals while significantly lower levels of these pro-inflammatory mediators were observed in other counterparts. 63.34 ± 0.18, 178.6 ± 0.27 and 650.1 ± 0.44 pg/mL were found in case group Ⅱ animals for IL-6, IL-1β and TNF respectively (Figure 2). Abrupt decreased in IL-4 and IL-10 level at 63.33 ± 0.57 and 15.7 ± 0.20 pg/mL respectively in case of group Ⅱ animals. Lactobacillus treatment increased serum level of IL-4 and IL-10 in group Ⅳ and Ⅴ animals. Results of group Ⅲ were also found to be statistically significant at P < 0.0001 with group Ⅱ animals (Figure 2).
Figure 2. Figure showing the concentration of IL-4 and IL-10 (pg/mL) of collagen induced arthritic rats. Group Ⅱ animals show significantly lower levels of IL-4 and IL-10 (pg/mL) when compared with the other counterparts at P < 0.0001. Results are expressed as Mean ± SEM of six rats per group. (b) Figure showing the concentration of IL-6, IL-β and TNF (pg/mL) of collagen induced arthritic rats. Group Ⅱ show significant increase in IL-6, IL-β and TNF (pg/mL) when compared with the other counterparts at P < 0.0001. Results are expressed as Mean ± SEM of six rats per group.Effect of L. casei and L. acidophilus was investigated by RT-PCR analysis for various cytokines at the transcription level. On the 29th day, mRNA expression levels of pro and anti-inflammatory cytokine level was estimated by total RNA sample prepared from the right hind knee joints. mRNA expressions of IL-6, IL-1β and TNF were stimulated in group Ⅱ animals when compared with other groups and very less expression of IL-4 and IL-10 were observed. Whereas Lactobacillus treatment up-regulated the IL-4 and IL-10 expressions in group Ⅳ and Ⅴ animals. The group Ⅰ animals were showing normal expression for all the cytokines. In case of group Ⅲ animals, IL-1β and TNF were simulated and less expression of IL-6 was observed. Also, IL-4 was stimulated in comparison to IL-10 in group Ⅲ animals (Figures 3 and 4).
Figure 3. Expressions of IL-6, IL-β, TNF, IL-4 and IL-10 mRNA from hind paw of collagen induced arthritic rats on 29th day. Lane Ⅰ-Control (Group Ⅰ); Lane Ⅱ-Arthritic control (Group Ⅱ); Lane Ⅲ-Drug administered; Lane Ⅳ-L. casei administered; Lane Ⅴ-L. acidophilus administered. Each PCR product was normalized to GAPDH. The observed bands were verified on the gels, with the predicted sizes of GAPDH (440 bp), TNF (393 bp), IL-1β (414 bp), IL-6 (498 bp), IL-4 (275 bp) and IL-10 (340 bp).
Figure 4. Figure showing gel intensities. Values are Mean ± SEM of six rats per group. Statistical analysis was performed by one-way ANOVA. * P < 0.001 vs. arthritic control group.Based on anti-inflammatory properties of L. casei and L. acidophilus in serum [11], it was considered that they both might have shown anti-inflammatory properties at transcription level also. The aim of the present study was to evaluate effect of L. casei and L. acidophilus on expressions of IL-6, IL-1β, TNF, IL-4 and IL-10 mRNA in CIA model of arthritis. When compared with the other experimental models of arthritis, CIA model is a promising model for validation and efficacy of anti-arthritic drugs [14]. Results obtained in this study were similar with our previous findings. L. casei and L. acidophilus significantly decreased the paw thickness in experimental animals when compared with their other counter parts. These treatments significantly decreased the pro-inflammatory and increased the anti-inflammatory cytokines [11]. Collagen induced arthritis is an immune mediated inflammatory reaction. Initial symptoms include paw edema and soft tissue thickening. Lactobacillus is acting as an immunosuppressive agent. Decrease in paw thickness is one of the major factors which evaluate the efficacy of anti-arthritic drugs or therapy. Both L. casei and L. acidophilus decreased paw thickness when compared to other counterparts.
Rheumatoid arthritis is a chronic and devastating autoimmune disorder that leads to persistent, progressive symmetrical inflammation in joints and subsequent erosive destruction of cartilage and bone [15,16]. Anti-arthritic drugs used for treating chronic inflammatory conditions are usually prescribed for long term to properly control the disordered immune system. Thus, there is a strong need to develop safe and effective drugs for the long-term use. Many researchers have studied non-chemical compounds for nonsteroidal anti-inflammatory properties with the aim of developing new treatments for clinical use [17].
Cytokines play major role in the progression of rheumatoid arthritis. An imbalance between pro-inflammatory and anti-inflammatory cytokine activities, favors the induction of autoimmunity, chronic inflammation and thereby joint damage [18]. Mainly IL-1β, TNF, IL-8, IL-12, IL-15, IL-17 and IL-18 are responsible for the inflammatory reaction. Along with these mediators, leukotriene B4 are also implicated in the process and playing a key role in neutrophil recruitment during immune inflammation [19]. TNF responsible for inflammation, differentiation and proliferation of T and B cells and bone resorption [20], whereas IL-1β causes the destruction of cartilage and bones [21]. Blocking TNF suppresses inflammation and ameliorates cartilage destruction while IL-6 is responsible for the joint destruction. Lactobacillus significantly decreased pro-inflammatory cytokine levels in serum. Lactobacillus might suppress the signaling pathway that leads to TNF, IL-1β and IL-6 synthesis. TNF, IL-1β and IL-6 had been considered to have critical roles in RA and CIA in that they promote the production of most other pro-inflammatory mediators [22]. Oral administration of Lactobacillus significantly increased anti-inflammatory cytokines (IL-10 and IL-4) level from serum. IL-10 is a macrophage deactivator and also found to be associated with blocking the synthesis of TNF, IL-1, IL-6, IL-8, and GM-CSF in human monocytes [23] and cox-2 inhibitors [24,25]. IL-4 is pleiotropic T-cell derived cytokine that acts by inhibiting the synthesis of pro-inflammatory cytokines such as IL-1, TNF, IL-6, IL-8 and IL-12 by macrophages and monocytes [26]. Moreover, it also stimulates several cytokine inhibitors such as interleukin-1 receptor antagonist (IL-1Ra), soluble IL-1-receptor type Ⅱ and TNF receptors. In addition, it also suppresses metalloproteinase synthesis and stimulates tissue inhibitor of metalloproteinase-1 production in human mononuclear phagocytes [27,28]. Lactobacillus might offer a complementary therapy, which inhibited pro-inflammatory cytokines whereas up-regulated anti-inflammatory cytokines.
In addition, anti-inflammatory effect of L. casei and L. acidophilus was also validated from the mRNA expression of cytokines from knee joints. mRNA level of IL-6, TNF and IL-1β were highly stimulated in knee joints of arthritic rats, whereas Lactobacillus treatment decreased the level as that of normal rats. Studies have established that IL-6 has an important role in leukocyte recruitment, apoptosis and T cell activation [29]. Additionally, TNF stimulates neutrophils to transcribe and release cytokines and chemokines biosynthesis [30]. Inhibition of TNF, IL-1β and IL-6 release can reduce the severity of inflammation. On the other way, Lactobacillus treatment enhanced the expression of IL-4 and IL-10. L. casei showed similar results in randomized double-blind clinical trial [31]. Consumption of L. casei fermented milk prevented the Salmonella reactive arthritis [32]. Results presented in this study are first to demonstrate that L. casei and L. acidophilus had shown inhibitory effects on the expression of IL-6, IL-1β and TNF and thus possess a potent immunosuppressive and anti-inflammatory activity.
We have demonstrated that Lactobacillus possess immunomodulatory property as suggested by RT PCR analysis of various pro-inflammatory and anti-inflammatory cytokines in animal model of experimental arthritis. Lactobacillus has therapeutic anti-arthritic activity as tested in CIA model. Notably, oral administration of Lactobacillus caused suppression of pro-inflammatory cytokines IL-6, IL-1β and TNF along with up-regulation of anti-inflammatory cytokines IL-4 and IL-10 in serum as well as at the transcription level. Also, there was lowering of paw thickness. On the basis of our results in present study, we suggest that Lactobacillus is a promising therapeutic agent or dietary supplement for rheumatoid arthritis.
The author would like to thank Department of Microbiology, Barkatullah University, Bhopal for laboratory facility provided to conduct the study.
There are nonfinancial competing interests (political, personal, religious, ideological, academic, intellectual, commercial, or any other) to declare in relation to this manuscript.
| [1] |
Z. Lin, An empirical investigation of user and system recommendations in e-commerce, Decis. Support Syst., 68 (2014), 111–124. https://doi.org/10.1016/j.dss.2014.10.003 doi: 10.1016/j.dss.2014.10.003
|
| [2] |
T. Iba, K. Nemoto, B. Peters, P. A. Gloor, Analyzing the creative editing behavior of wikipedia editors: Through dynamic social network analysis, Proc.-Soc. Behav. Sci., 2 (2010), 6441–6456. https://doi.org/10.1016/j.sbspro.2010.04.054 doi: 10.1016/j.sbspro.2010.04.054
|
| [3] |
T. R. Liyanagunawardena, A. A. Adams, S. A. Williams, MOOCs: A systematic study of the published literature 2008–2012, Int. Rev. Res. Open Distrib. Learn., 14 (2013), 202–227. https://doi.org/10.19173/irrodl.v14i3.1455 doi: 10.19173/irrodl.v14i3.1455
|
| [4] | Q. Liu, S. Wu, L. Wang, T. Tan, Predicting the next location: A recurrent model with spatial and temporal contexts, in Thirtieth AAAI Conference on Artificial Intelligence, 30 (2016). https://doi.org/10.1609/aaai.v30i1.9971 |
| [5] | S. Wu, Q. Liu, P. Bai, L. Wang, T. Tan, SAPE: A system for situation-aware public security evaluation, in Thirtieth AAAI Conference on Artificial Intelligence, 30 (2016). https://doi.org/10.1609/aaai.v30i1.9828 |
| [6] |
Z. Hou, X. Lv, Y. Zhou, L. Bu, Q. Ma, Y. Wang, A dynamic graph Hawkes process based on linear complexity self-attention for dynamic recommender systems, PeerJ. Comput. Sci., 9 (2023), 1368. https://doi.org/10.7717/peerj-cs.1368 doi: 10.7717/peerj-cs.1368
|
| [7] | Y. Zheng, X. Yi, M. Li, R. Li, Z. Shan, E. Chang, et al., Forecasting fine-grained air quality based on big data, in 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (2015), 2267–2276. https://doi.org/10.1145/2783258.2788573 |
| [8] | X. Wang, X. He, M. Wang, F. Feng, T. Chua, Neural graph collaborative filtering, in 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, (2019), 165–174. https://doi.org/10.1145/3331184.3331267 |
| [9] | X. He, K. Deng, X. Wang, Yan Li, Y. Zhang, M. Wang, LightGCN: Simplifying and powering graph convolution network for recommendation, in 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, (2020), 639–648. https://doi.org/10.1145/3397271.3401063 |
| [10] |
Y. Koren, R. Bell, C. Volinsky, Matrix factorization techniques for recommender systems, Computer, 42 (2009), 30–37. https://doi.org/10.1109/MC.2009.263 doi: 10.1109/MC.2009.263
|
| [11] | D. Lee, H. S. Seung, Algorithms for non-negative matrix factorization, in 13th International Conference on Neural Information Processing Systems, (2000), 535–541. |
| [12] | R. Salakhutdinov, A. Mnih, Probabilistic matrix factorization, in 20th International Conference on Neural Information Processing Systems, (2007), 1257–1264. |
| [13] |
S. Raza, C. Ding, Progress in context-aware recommender systems-An overview, Comput. Sci. Rev., 31 (2019), 84–97. https://doi.org/10.1016/j.cosrev.2019.01.001 doi: 10.1016/j.cosrev.2019.01.001
|
| [14] | G. Adomavicius, K. Bauman, A. Tuzhilin, M. Unger, Context-aware recommender systems: From foundations to recent developments, in Recommender Systems Handbook, (2022), 211–250. https://doi.org/10.1007/978-1-0716-2197-4_6 |
| [15] | C. Wu, A. Ahmed, A. Beutel, A. J. Smola, H. Jing, Recurrent recommender networks, in Tenth ACM International Conference on Web Search and Data Mining, (2017), 495–503. https://doi.org/10.1145/3018661.3018689 |
| [16] | S. Kumar, X. Zhang, J. Leskovec, Predicting dynamic embedding trajectory in temporal interaction networks, in 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, (2019), 1269–1278. https://doi.org/10.1145/3292500.3330895 |
| [17] | X. Li, M. Zhang, S. Wu, Z. Liu, L. Wang, P. S. Yu, Dynamic graph collaborative filtering, in 2020 IEEE International Conference on Data Mining, (2020), 322–331. https://doi.org/10.1109/ICDM50108.2020.00041 |
| [18] | Z. Kefato, S. Girdzijauskas, N. Sheikh, A. Montresor, Dynamic embeddings for interaction prediction, in Web Conference 2021, (2021), 1609–1618. https://doi.org/10.1145/3442381.3450020 |
| [19] |
S. Wu, F. Sun, W. Zhang, X. Xie, B. Cui, Graph neural networks in recommender systems: A survey, ACM Comput. Surv., 55 (2022), 1–37. https://doi.org/10.1145/3535101 doi: 10.1145/3535101
|
| [20] | P. Covington, J. Adams, E. Sargin, Deep neural networks for YouTube recommendations, in 10th ACM Conference on Recommender Systems, (2016), 191–198. https://doi.org/10.1145/2959100.2959190 |
| [21] | H. Dai, Y. Wang, R. Trivedi, L. Song, Recurrent coevolutionary latent feature processes for continuous-time recommendation, in 1st Workshop on Deep Learning for Recommender Systems, (2016), 29–34. https://doi.org/10.1145/2988450.2988451 |
| [22] | Y. K. Tan, X. Xu, Y. Liu, Improved recurrent neural networks for session-based recommendations, in 1st Workshop on Deep Learning for Recommender Systems, (2016), 17–22. https://doi.org/10.1145/2988450.2988452 |
| [23] | Z. Wang, W. Wei, G. Cong, X. Li, X. Mao, M. Qiu, Global context enhanced graph neural networks for session-based recommendation, in 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, (2020), 169–178. https://doi.org/10.1145/3397271.3401142 |
| [24] | S. Wu, Y. Tang, Y. Zhu, L. Wang, X. Xie, T. Tan, Session-based recommendation with graph neural networks, in AAAI Technical Track: AI and the Web, 33 (2019), 346–353. https://doi.org/10.1609/aaai.v33i01.3301346 |
| [25] | C. Xu, P. Zhao, Y. Liu, V. S. Sheng, J. Xu, F. Zhuang, Graph contextualized self-attention network for session-based recommendation, in Twenty-Eighth International Joint Conference on Artificial Intelligence, (2019), 3940–3946. https://doi.org/10.24963/ijcai.2019/547 |
| [26] | B. Hidasi, A. Karatzoglou, L. Baltrunas, D. Tikk, Session-based recommendations with recurrent neural networks, preprint, arXiv: 1511.06939. |
| [27] | J. Li, P. Ren, Z. Chen, Z. Ren, T. Lian, J. Ma, Neural attentive session-based recommendation, in 2017 ACM on Conference on Information and Knowledge Management, (2017), 1419–1428. https://doi.org/10.1145/3132847.3132926 |
| [28] | Q. Liu, S. Wu, D. Wang, Z. Li, L. Wang, Context-aware sequential recommendation, in 2016 IEEE 16th International Conference on Data Mining (ICDM), (2016), 1053–1058. https://doi.org/10.1109/ICDM.2016.0135 |
| [29] | J. You, Y. Wang, A. Pal, P. Eksombatchai, C. Rosenburg, Hierarchical temporal convolutional networks for dynamic recommender systems, in The World Wide Web Conference, (2019), 2236–2246. https://doi.org/10.1145/3308558.3313747 |
| [30] | Y. Wang, N. Du, R. Trivedi, L. Song, Coevolutionary latent feature processes for continuous-time user-item interactions, in 30th Conference on Neural Information Processing Systems, (2016), 1–9. |
| [31] | Q. Wu, Y. Gao, X. Gao, P. Weng, G. Chen, Dual sequential prediction models linking sequential recommendation and information dissemination, in 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, (2019), 447–457. https://doi.org/10.1145/3292500.3330959 |
| [32] | R. Trivedi, M. Farajtabar, P. Biswal, H. Zha, DyRep: Learning representations over dynamic graphs, in International Conference on Learning Representations 2019 Conference, (2019). |
| [33] | A. Beutel, P. Covington, S. Jain, C. Xu, J. Li, V. Gatto, et al., Latent cross: Making use of context in recurrent recommender systems, in Eleventh ACM International Conference on Web Search and Data Mining, (2018), 46–54. https://doi.org/10.1145/3159652.3159727 |
| [34] | Y. Zhu, H. Li, Y. Liao, B. Wang, Z. Guan, H. Liu, et al., What to do next: Modeling user behaviors by time-LSTM, in 26th International Joint Conference on Artificial Intelligence, (2017), 3602–3608. |
| [35] | Y. Zhang, X. Yang, J. Ivy, M. Chi, ATTAIN: Attention-based time-aware LSTM networks for disease progression modeling, in Twenty-Eighth International Joint Conference on Artificial Intelligence, (2019), 4369–4375. https://doi.org/10.24963/ijcai.2019/607 |
| [36] | W. Kang, J. McAuley, Self-attentive sequential recommendation, in 2018 IEEE International Conference on Data Mining, (2018), 197–206. https://doi.org/10.1109/ICDM.2018.00035 |
| [37] | D. Hendrycks, K. Gimpel, Gaussian error linear units (GeLUs), preprint, arXiv: 1606.08415. |
| [38] | M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L. Chen, MobileNetV2: Inverted residuals and linear bottlenecks, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2018), 4510–4520. https://doi.org/10.1109/CVPR.2018.00474 |
| [39] | Y. N. Dauphin, A. Fan, M. Auli, D. Grangier, Language modeling with gated convolutional networks, in 34th International Conference on Machine Learning, 70 (2017), 933–941. |
| [40] | R. K. Srivastava, K. Greff, J. Schmidhuber, Highway networks, preprint, arXiv: 1505.00387. |
| [41] |
S. Hochreiter, J. Schmidhuber, Long Short-Term Memory, Neural Comput., 9 (1997), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735 doi: 10.1162/neco.1997.9.8.1735
|
| [42] | J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2018), 7132–7141. https://doi.org/10.1109/CVPR.2018.00745 |
| [43] | C. Santos, M. Tan, B. Xiang, B. Zhou, Attentive pooling networks, preprint, arXiv: 1602.03609. |
| [44] | R. Hadsell, S. Chopra, Y. LeCun, Dimensionality reduction by learning an invariant mapping, in 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), (2006), 1735–1742. https://doi.org/10.1109/CVPR.2006.100 |
| [45] | S. Yang, W. Yu, Y. Zheng, H. Yao, T. Mei, Adaptive semantic-visual tree for hierarchical embeddings, in 27th ACM International Conference on Multimedia, (2019), 2097–2105. https://doi.org/10.1145/3343031.3350995 |
| [46] | X. He, K. Deng, X. Wang, Y. Li, Y. Zhang, M. Wang, Lightgcn: Simplifying and powering graph convolution network for recommendation, in 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, (2020), 639–648. https://doi.org/10.1145/3397271.3401063 |
| [47] | C. Hsieh, L. Yang, Y. Cui, T. Lin, S. Belongie, D. Estrin, Collaborative metric learning, in 26th International Conference on World Wide Web, (2017), 193–201. https://doi.org/10.1145/3038912.3052639 |
| [48] | B. Fu, W. Zhang, G. Hu, X. Dai, S. Huang, J. Chen, Dual side deep context-aware modulation for social recommendation, in Web Conference 2021, (2021), 2524–2534. https://doi.org/10.1145/3442381.3449940 |
| [49] | T. Mikolov, I. Sutskever, K. Chen, G. Corrado, J. Dean, Distributed representations of words and phrases and their compositionality, in 26th International Conference on Neural Information Processing Systems, 2 (2013), 3111–3119. |
| [50] | R. Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, in 2014 IEEE Conference on Computer Vision and Pattern Recognition, (2014), 580–587. https://doi.org/10.1109/CVPR.2014.81 |
| [51] | N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: A simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., 15 (2014), 1929–1958. |
| [52] | B. Hidasi, D. Tikk, Fast ALS-based tensor factorization for context-aware recommendation from implicit feedback, in 2012th European Conference on Machine Learning and Knowledge Discovery in Databases, (2012), 67–82. |
| [53] | X. Glorot, Y. Bengio, Understanding the difficulty of training deep feedforward neural networks, in 13th International Conference on Artificial Intelligence and Statistics (AISTATS) 2010, (2010), 249–256. |
| [54] | J. Chung, C. Gulcehre, K. Cho, Y. Bengio, Empirical evaluation of gated recurrent neural networks on sequence modeling, preprint, arXiv: 1412.3555. |
| [55] | A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, et al., Attention is all you need, in 31st International Conference on Neural Information Processing Systems, (2017), 6000–6010. |
| [56] |
T. Silveira, M. Zhang, X. Lin, Y. Liu, S. Ma, How good your recommender system is? A survey on evaluations in recommendation, Int. J. Mach. Learn. Cybern., 10 (2019), 813–831. https://doi.org/10.1007/s13042-017-0762-9 doi: 10.1007/s13042-017-0762-9
|
| 1. | Zhexin Fan, Bo Yang, R. Paul Ross, Catherine Stanton, Jianxin Zhao, Hao Zhang, Wei Chen, The prophylactic effects of different Lactobacilli on collagen-induced arthritis in rats, 2020, 11, 2042-6496, 3681, 10.1039/C9FO02556A | |
| 2. | Chunhong Liu, Li Lin, Weidong Cui, Lei Wang, Min Ai, Zhongwei Zhao, Xiaohan Ma, Shengyu Li, Lactiplantibacillus plantarum HG20 attenuates II type collagen-induced rheumatoid arthritis in rats via anti-inflammatory and inhibition of apoptosis, 2022, 132, 1365-2672, 2323, 10.1111/jam.15333 |
Figures(7) / Tables(10)
Zhiwen Hou, Fanliang Bu, Yuchen Zhou, Lingbin Bu, Qiming Ma, Yifan Wang, Hanming Zhai, Zhuxuan Han. DyCARS: A dynamic context-aware recommendation system[J]. Mathematical Biosciences and Engineering, 2024, 21(3): 3563-3593. doi: 10.3934/mbe.2024157
| Gene name | Oligonucleotide sequence (5'-3') | Denaturing, ℃ (time) |
Annealing, ℃ (time) |
Elongation, ℃ (time) |
Cycle No. | Product size | Gene bank No. |
| mGAPDH | F-ATGGGAAGCTGGTCATCAAC R-GGATGCAGGGATGATGTTCT |
94 (30 s) | 58 (30 s) | 72 (60 s) | 30 | 440 | NM_017008 |
| mTNF | F-GTCGTAAACCACCAAGC R-GACTCCAAAGTAGACCTGCCC |
94 (45 s) | 58 (45 s) | 72 (90 s) | 35 | 393 | AY 427675 |
| mIL-1β | F-GGCATAACAGGCTCATCTGG R-CATCATCCCACGAGTCACAG |
94 (45 s) | 58 (45 s) | 72 (90 s) | 35 | 414 | NM_031512 |
| mIL-6 | F-CCACTGCCTTCCCTACTTCA R-TGGTCCTTAGCCACTCCTTC |
94 (60 s) | 63 (60 s) | 72 (120 s) | 37 | 498 | NM_012589 |
| mIL-4 | F-ATG CACCGAGATGTTTGTACC R-TTCAGTGTTCTGAGCGTGGA |
95 (60 s) | 60 (60 s) | 72 (90 s) | 40 | 275 | NM_201270.1 |
| mIL-10 | F-GGAGTGAAGACCAAAGG R-TCTCCCAGGGAATTCAAATG |
94 (30 s) | 57 (1 s) | 72 (60 s) | 40 | 340 | NM_012854 |
| mGAPDH: human glyceraldehyde-3-phosphate dehydrogenase; mTNF: murine tumor necrosis factor α; IL-1β: interleukin-1β; IL-6: interleukin-6; IL-4: Interleukin-4; IL-10: Interleukin-10 | |||||||
DownLoad: CSV| Gene name | Oligonucleotide sequence (5'-3') | Denaturing, ℃ (time) |
Annealing, ℃ (time) |
Elongation, ℃ (time) |
Cycle No. | Product size | Gene bank No. |
| mGAPDH | F-ATGGGAAGCTGGTCATCAAC R-GGATGCAGGGATGATGTTCT |
94 (30 s) | 58 (30 s) | 72 (60 s) | 30 | 440 | NM_017008 |
| mTNF | F-GTCGTAAACCACCAAGC R-GACTCCAAAGTAGACCTGCCC |
94 (45 s) | 58 (45 s) | 72 (90 s) | 35 | 393 | AY 427675 |
| mIL-1β | F-GGCATAACAGGCTCATCTGG R-CATCATCCCACGAGTCACAG |
94 (45 s) | 58 (45 s) | 72 (90 s) | 35 | 414 | NM_031512 |
| mIL-6 | F-CCACTGCCTTCCCTACTTCA R-TGGTCCTTAGCCACTCCTTC |
94 (60 s) | 63 (60 s) | 72 (120 s) | 37 | 498 | NM_012589 |
| mIL-4 | F-ATG CACCGAGATGTTTGTACC R-TTCAGTGTTCTGAGCGTGGA |
95 (60 s) | 60 (60 s) | 72 (90 s) | 40 | 275 | NM_201270.1 |
| mIL-10 | F-GGAGTGAAGACCAAAGG R-TCTCCCAGGGAATTCAAATG |
94 (30 s) | 57 (1 s) | 72 (60 s) | 40 | 340 | NM_012854 |
| mGAPDH: human glyceraldehyde-3-phosphate dehydrogenase; mTNF: murine tumor necrosis factor α; IL-1β: interleukin-1β; IL-6: interleukin-6; IL-4: Interleukin-4; IL-10: Interleukin-10 | |||||||
