Formal modelling of toll like receptor 4 and JAK/STAT signalling pathways: insight into the roles of SOCS-1, interferon-β and proinflammatory cytokines in sepsis

Abstract

Sepsis is one of the major causes of human morbidity and results in a considerable number of deaths each year. Lipopolysaccharide-induced sepsis has been associated with TLR4 signalling pathway which in collaboration with the JAK/STAT signalling regulate endotoxemia and inflammation. However, during sepsis our immune system cannot maintain a balance of cytokine levels and results in multiple organ damage and eventual death. Different opinions have been made in previous studies about the expression patterns and the role of proinflammatory cytokines in sepsis that attracted our attention towards qualitative properties of TLR4 and JAK/STAT signalling pathways using computer-aided studies. René Thomas' formalism was used to model septic and non-septic dynamics of TLR4 and JAK/STAT signalling. Comparisons among dynamics were made by intervening or removing the specific interactions among entities. Among our predictions, recurrent induction of proinflammatory cytokines with subsequent downregulation was found as the basic characteristic of septic model. This characteristic was found in agreement with previous experimental studies, which implicate that inflammation is followed by immunomodulation in septic patients. Moreover, intervention in downregulation of proinflammatory cytokines by SOCS-1 was found desirable to boost the immune responses. On the other hand, interventions either in TLR4 or transcriptional elements such as NFκB and STAT were found effective in the downregulation of immune responses. Whereas, IFN-β and SOCS-1 mediated downregulation at different levels of signalling were found to be associated with variations in the levels of proinflammatory cytokines. However, these predictions need to be further validated using wet laboratory experimental studies to further explore the roles of inhibitors such as SOCS-1 and IFN-β, which may alter the levels of proinflammatory cytokines at different stages of sepsis.

Figure 1. TLR4 and JAK/STAT signalling pathway.

Overview of TLR4 and JAK/STAT signalling pathway adopted from previous experimental studies and databases associated with signalling pathways , –. TLR4 activates two separate signalling pathways, including MyD88 and TRIF dependent pathways . TIRAP/Mal and TRAM are recruited by TLR4 as adaptor proteins to activate MyD88 and TRIF dependent pathways, respectively , . Following MYD88 activation, IRAK4 is phosphorylated by MyD88-MAL complex, which ultimately results in the phosphorylation of IRAK1 protein. Phosphorylated IRAK1 activates TRAF6 which after forming a complex with TAK1-TAB1/2 activates Iκκ complex . Iκκα and Iκκβ catalyse the phosphorylation of IκB, resulting in its dissociation from NFκB. Afterwards NFκB translocate into nucleus and transcribes PICyts which results in the subsequent induction of SOCS-1 , . Along with PICyts, SARM and A20 are also transcribed by NFκB which inhibit TRIF and TRAF6, respectively , . Interaction of SOCS-1 with MAL results in its polyubiquitylation and degradation of MAL . SOCS-1 also result in the degradation of NFκB after binding with its p65 subunit . Moreover, it is also responsible for inhibiting PICyts mediated JAK/STAT signalling . The alternate pathway for the MyD88 independent induction of NFκB is TRIF which associates with RIP-1 and induce TRAF6 . Cytoplasmic domain of TLR4 associates with TRAM and TRIF, and interacts with a complex of TBK1 and Iκκi to induce phosphorylation of IRF3 . After dimerization, phosphorylated IRF3 translocate into nucleus which results in the production of type I IFNs. IFN-β is responsible for the downregulation of PICyts through a shift of TH1 to TH2 responses and induce immune regulation. Recently SOCS-1 mediated downregulation of IFN-β has been observed .

Figure 2. The BRN of TLR4 and JAK/STAT signalling pathway.

The reduced BRN of TLR4 and JAK/STAT signalling pathway is derived from Figure 1. Nodes represent entities, whereas interactions between them are shown as edges. Sign on the edges represent the type of interaction between nodes i.e. positive for activation (solid arrows) and negative for inhibition (dotted arrows). Integers “1” and “2” on the edges represent the threshold levels of entities (see Material and Methods section).

Figure 3. State graph of TLR4 and JAK/STAT signalling during non-septic and septic conditions.

(A) Each node represents a particular state observed during signalling associated with non-septic and septic conditions. Integers “0”, “1” and “2” within the nodes represent qualitative levels of proteins in the order of TLR4, IFN-β, NFκB, PICyts and SOCS-1. Inactive entities are represented by integer “0” whereas active and overactive entities are represented by integers “1” and “2”, respectively. Nodes and trajectories, which were specifically observed during signalling dynamics associated with sepsis, are shown in red, whereas common nodes and trajectories found in both conditions are shown in black. Trajectories start from state “10000”, representing the activation of TLR4, and ultimately lead towards “00000”, which is a stable state in non-septic condition. On the other hand, a trajectory labelled with “η” from state “00000” to starting state “10000” results in a cyclic path during signalling dynamics associated with sepsis. MyD88 and TRIF dependent signalling are shown as black lines and dashed arrows, respectively. Nodes, which represent crosstalk of both signalling pathways i.e. IFN-β and NFκB with qualitative level “1” are presented in oval shapes. Arrows labelled with Greek small letters are used to represent trajectories associated with different signalling events (see legend in the figure). The conditions necessary to produce a state graph shown in the figure are given in Table 1. (B–D) specific states and trajectories which can possibly represent the complete state graph given in (A).

Figure 4. State graph of CASE 1-N and 1-S.

(A) Each node represents a particular state observed during signalling associated with CASE 1-N and CASE 1-S. Integers “0”, “1” and “2” within the nodes represent qualitative levels of proteins in the order of TLR4, IFN-β, NFκB, PICyts and SOCS-1. Inactive entities are represented by integer “0” whereas active and overactive entities are represented by integers “1” and “2”, respectively. States and trajectories, which were specifically observed during signalling dynamics associated with CASE 1-S, are shown in red, whereas common states and trajectories found in both CASES are shown in black. Trajectories start from state “10000”, representing the activation of TLR4 and ultimately lead towards “00000” and “00121”, which are stable states in CASE 1-N. On the other hand, only one stable state “00121” was observed during signalling dynamics associated with CASE 1-S and a trajectory labelled with “η” from state “00000” to starting state “10000” results in cyclic path. Trajectories associated with loss of SOCS-1 mediated downregulation of PICyts in CASE 1-N and CASE 1-S are presented as bold arrows labelled with symbol “Δε”. Nodes are labelled with stars in which NFκB and PICyts were active simultaneously and have the probability to lead towards overactive immune response. MyD88 and TRIF dependent signalling are shown as black lines and dashed arrows, respectively. Nodes, which represent crosstalk of both signalling pathways i.e. IFN-β and NFκB with qualitative level “1” are presented in oval shapes. Arrows labelled with Greek small letters are used to represent trajectories associated with different signalling events (see legend in the figure). The conditions necessary to produce a state graph are shown in the figure are given in Table 3. (B–D) specific states and trajectories which can possibly represent the complete state graph given in (A).

Figure 5. State graph of CASE 2-N and 2-S.

(A) Each node represents a particular state observed during signalling associated with CASE 2-N and CASE 2-S. Integers “0”, “1” and “2” within the nodes represent qualitative levels of proteins in the order of TLR4, IFN-β, NFκB, PICyts and SOCS-1. Inactive entities are represented by integer “0” whereas active and overactive entities are represented by integers “1” and “2”, respectively. Nodes and trajectories, which were specifically observed during signalling dynamics associated with CASE 2-S, are shown in red, whereas common nodes and trajectories found in both CASES are shown in black. Trajectories start from state “10000”, representing the activation of TLR4 and ultimately lead towards “00000” and “00121”, which are stable states in CASE 2-N. On the other hand, only one stable state “00121” was observed during signalling dynamics associated with CASE 2-S and a trajectory labelled with “η” from state “00000” to starting state “10000” results in cyclic path. Trajectories associated with loss of SOCS-1 mediated downregulation of PICyts in CASE 2-N and CASE 2-S are presented as bold arrows labelled with symbol “Δε” whereas loss of SOCS-1 mediated downregulation of IFN-β are labelled with symbol “Δδ”. MyD88 and TRIF dependent signalling are shown as black lines and dashed arrows, respectively. Nodes, which represent crosstalk of both signalling pathways i.e. IFN-β and NFκB with qualitative level “1” are presented in oval shapes. Arrows labelled with Greek small letters are used to represent trajectories associated with different signalling events (see legend in the figure). The conditions necessary to produce a state graph shown in the figure are given in Table 3. (B–D) specific states and trajectories which can possibly represent the complete state graph given in (A).

Figure 6. State graph of CASE 3-N and 3-S.

(A) Each node represents a particular state observed during signalling associated with CASE 3-N and CASE 3-S. Integers “0”, “1” and “2” within the nodes represent qualitative levels of proteins in the order of TLR4, IFN-β, NFκB, PICyts and SOCS-1. Inactive entities are represented by integer “0” whereas active and overactive entities are represented by integers “1” and “2”, respectively. Nodes and trajectories, which were specifically observed during signalling dynamics associated with CASE 3-S, are shown in red, whereas common nodes and trajectories found in both CASES are shown in black. Trajectories start from state “10000”, representing the activation of TLR4, ultimately, lead towards “00000”, which is the stable state in CASE 3-N. On the other hand, a trajectory labelled with “η” from state “00000” to starting state “10000” results in a cyclic path during signalling dynamics associated with CASE 3-S. Trajectories associated with loss of IFN-β mediated downregulation of PICyts in CASE 3-N and CASE 3-S are presented as bold arrows labelled with symbol “Δγ”. MyD88 and TRIF dependent signalling are shown as black lines and dashed arrows, respectively. Nodes, which represent crosstalk of both signalling pathways i.e. IFN-β and NFκB with qualitative level “1” are presented in oval shapes. Arrows labelled with Greek small letters are used to represent trajectories associated with different signalling events (see legend in the figure). The conditions necessary to produce a state graph shown in the figure are given in Table 3. (B–D) specific states and trajectories which can possibly represent the complete state graph given in (A).

Figure 7. State graph of CASE 4-N and 4-S.

Each node represents a particular state observed during signalling associated with CASE 4-N and CASE 4-S. Values “0” and “1” within the nodes represent qualitative levels of proteins in the order of TLR4, IFN-β, NFκB, PICyts and SOCS-1. Inactive entities are represented by integer “0” whereas active entities are represented by integer “1”. Trajectories, which were specifically observed during signalling dynamics associated with CASE 4-S, are shown in red, whereas common states and trajectories found in both CASES are shown in black. Trajectories start from state “10000”, representing the activation of TLR4, ultimately, lead towards “00000”, which is a stable state in CASE 4-N. On the other hand, a trajectory labelled with “η” from state “00000” to starting state “10000” results in a cyclic path during signalling dynamics associated with CASE 4-S. State “00121” which represents the immune response was absent in state graph and not shown in this figure. MyD88 and TRIF dependent signalling are shown as black lines and dashed arrows, respectively. Nodes, which represent crosstalk of both signalling pathways i.e. IFN-β and NFκB with qualitative level “1” are presented in oval shapes. Arrows labelled with Greek small letters are used to represent trajectories associated with different signalling events (see legend in the figure). The conditions necessary to produce a state graph shown in the figure are given in Table 3.

Figure 8. State graph of CASE 5-N and 5-S.

(A) Each node represents a particular state observed during signalling associated with CASE 5-N and CASE 5-S. Integers “0” and “1” within the nodes represent qualitative levels of proteins in the order of TLR4, IFN-β, NFκB, PICyts and SOCS-1. Inactive entities are represented by integer “0” whereas active entities are represented by integer “1”. Nodes and trajectories, which were specifically observed during signalling dynamics associated with CASE 5-S, are shown in red, whereas common nodes and trajectories found in both CASES are shown in black. Trajectories start from state “10000”, representing the activation of TLR4, ultimately, lead towards “00000”, which is a stable state in CASE 5-N. On the other hand, a trajectory labelled with “η” from state “00000” to starting state “10000” results in a cyclic path during signalling dynamics associated with CASE 5-S. MyD88 and TRIF dependent signalling are shown as black lines and dashed arrows, respectively. Nodes, which represent crosstalk of both signalling pathways i.e. IFN-β and NFκB with qualitative level “1” are presented in oval shapes. Arrows labelled with Greek small letters are used to represent trajectories associated with different signalling events (see legend in the figure). The conditions necessary to produce a state graph shown in the figure are given in Table 3. (B–D) specific states and trajectories which can possibly represent the complete state graph given in (A).

Figure 9. Implication of the study.

(A) Edges labelled with Greek small letters and states as nodes are used to represent trajectories associated with different signalling events observed in this study (see legend in Figure 3). Specific states and trajectories of normal and recurrent signalling shown in Figures 3–8 were used to draw the hypothesis shown in (B–C). Possible effects of TLR4 and JAK/STAT signalling on pathogen load, induction pattern of PICyts, IFN-β and SOCS-1 mediated downregulation of PICyts are shown for non-septic (B) and septic (C) cases. During non-septic case, the pattern of IFN-β and then SOCS-1 limits the qualitative levels of PICyts along with the successful reduction of pathogen load. On the other hand, during sepsis, it has been proposed that changed expression pattern of IFN-β and SOCS-1 inhibit the PICyts with resultant increase in the pathogen load.