Introduction

The achievement of histological remission (HR) is a key treatment goal in ulcerative colitis (UC), as it is suggestive of better disease management and predicts response to therapy.
The absence of neutrophils in epithelium and lamina is crucial to define HR. However, the role of neutrophil number and localisation remains unclear. We aimed to develop a novel artificial intelligence (AI)-driven system to automate neutrophil detection, localisation, and quantification, supporting assessment of HR and enable the prediction of response to therapy.

Aims & Methods

We developed an AI-driven system by integrating two deep learning models to (1) segment whole slide images (WSIs) into epithelium, crypts and lamina propria and to (2) detect and quantify neutrophils. Outputs from these models were combined to compute neutrophil densities in the lamina propria, epithelium, and overall tissue. The optimal neutrophil density cut-offs to assess disease activity (Geboes score >2B.0) in UC patients were identified in the AMAC phase 2 Mirikizumab trial, and subsequently validated in the multicentre prospective PICaSSO cohort study. Cut-offs to determine treatment response at weeks 12 and 52 (histological improvement [HI; Geboes score ≤3.1] and histological remission [HR; Geboes score ≤2B.0]), were also evaluated.

Results

Table 1 shows the system diagnostic performance in assessing disease activity and predicting response to therapy at W12 and W52 in the Mirikizumab cohort.
303 WSIs from active UC patients from the multicentre, randomised, double-blind, parallel-arm, placebo-controlled phase 2 clinical trial of Mirikizumab were analysed. The model yielded a DICE SØrensen of 0.57 for segmentation, precision of 82.3% and recall of 77.0% for neutrophil detection. The system identified an overall optimal neutrophil density cut-off (cells/mm²) predictive of disease activity of >21.7.0 (>10.1 and >30.4 for epithelium and lamina propria, respectively), with an accuracy of 86% (85% and 85%, respectively). Further validation in the multicenter PICaSSO cohort yielded to similar results.
Moreover, the overall optimal cut-off to predict histological remission at W52 was <20.8 (<10.4 and <27.9 for epithelium and lamina propria, respectively), with an accuracy of 82.0% (81% and 80%, respectively).

Conclusion

Our novel AI-based system demonstrates strong potential as an automated tool to detect, localise, and quantify neutrophils to assess histological activity and predict response to therapy in a clinical trial UC cohort and real-world settings. This framework could be applied in clinical trials and routine clinical practice, offering objective guidance for personalised management in UC patients.

References

[1] Santacroce G, Meseguer P, Zammarchi I, et al. P406 A novel active learning-based digital pathology protocol annotation for histologic assessment in Ulcerative Colitis using PICaSSO Histologic Remission Index (PHRI). Journal of Crohn's and Colitis, Volume 18, Issue Supplement_1, January 2024, Pages i843–i844
[2] Graham S, Vu QD, Jahanifar M, et al. CoNIC Challenge: Pushing the frontiers of nuclear detection, segmentation, classification and counting. Med Image Anal. 2024;92:103047.

Disclosure

MI received research grants and consultant fees from Olympus, Pentax, Eli Lilly, and Janssen. All other authors declare no competing interests.

Introduction

Current treatment options for IBD are limited by low clinical remission rates and loss of response. Most therapies target single pathogenic pathways and while combinations of biologics targeting different pathogenic cytokines can increase clinical remission rates, dosing schedules are inconvenient. JAK inhibitors, target multiple cytokine pathways, but are limited by safety concerns.
Salt-inducible kinases (SIKs) are a subfamily of serine/threonine kinases in the AMP-activated protein kinase (AMPK) family and act as key regulators of immune cell signaling. SIK inhibitors have been shown to target multiple cytokine pathways.
Three SIK isoforms exist: SIK1, SIK2 and SIK3. SIK inhibitors targeting multiple isoforms have been investigated in clinical trials. Although there have been signals of activity in patients with ulcerative colitis and psoriasis, limited efficacy and safety concerns related to SIK1 and 2 inhibition have hampered their development.

Aims & Methods

We performed structure based drug design to identify highly potent and selective SIK3 inhibitors that could offerbest in class efficacy and safety for the treatment of various auto-immune diseases. Our effort led to to the discovery of 100s of compounds spanning SIK3 binding sites. Compounds were tested in protein and cell-based assays to evaluate potency and selectivity against SIK3 and in a phenotypic human whole blood TNFα assay. Lead optimization involving rigorous testing in safety and pharmacology panels, resulted in the selection of lead candidates that were tested in a variety of translational models to identify the most efficacious compounds. Human PK predictions were performed using non-clinical in vivo PK assessments and allometric scaling leading to the selection of the drug candidate, which entered GLP toxicology studies.

Results

O3R-5671 is a highly potent and specific SIK3 inhibitor with sub-nanomolar potency for SIK3 and low activity against SIK1 and 2 and over all human kinases. It demonstrated potent activity in a panel of human primary phenotypic cell assays inhibiting TNFα, IL-12, and IL-23 release in LPS-stimulated myeloid cells, and inhibiting TNFa release in LPS-stimulated human whole blood. O3R-5671 also inhibited activation of TCR-stimulated human primary T cells and induced IL-10 secretion from myeloid cells.
In vivo, O3R-5671 demonstrated dose-dependent activity in a mouse LPS challenge model, dose-dependent efficacy in two distinct mouse models of IBD, and dose-dependent efficacy in mouse models of IL-23-induced psoriasis and psoriatic arthritis. Cross-species PK and allometric scaling were used to predict O3R-5671’s human PK profile- which is expected to be conducive to potent SIK3 inhibition and clinical efficacy in patients with IBD.
O3R-5671 demonstrated a highly attractive profile in ADME and in vitro safety panels. Six-week GLP toxicity studies in rats and dogs established no observed adverse effect levels (NOAELs) which support dosing in humans with doses that are predicted to be pharmacologically active with a large safety margin.

Conclusion

O3R-5671 is a highly specific and potent SIK3 inhibitor that is predicted to have a flat PK profile in humans. These properties should allow O3R-5671 to apply strong drug pressure on SIK3 while sparing SIK1 and 2. This is expected to result in the inhibition of multiple pathogenic cytokines including TNFa and IL-23, both of which have been validated as IBD targets. A clinical trial is ongoing to establish the safety and PK profile of O3R-5671 and understand its effect on pharmacodynamic biomarkers.

Disclosure

All authors were employed by Galapagos who discovered O3R-5671 or Novalix, a CRO that was employed by Galapagos. Some authors are employed by Onco3R therapeutics, who are currently developing O3R-5671

Introduction

Non-celiac gluten/wheat sensitivity (NCGWS) is characterized by gastrointestinal and extra-intestinal symptoms triggered by gluten/wheat ingestion. Symptoms of NCGWS overlap with those of irritable bowel syndrome (IBS) or functional dyspepsia (FD). Due to diagnostic challenges and symptom overlap, data on the prevalence and predictors of NCGWS among patients with IBS or FD, especially those with refractory symptoms, are limited.

Aims & Methods

This was a prospective, multicentric, double-blind, placebo-controlled, crossover trial conducted from October 2021 to March 2023 in India.This was prospectivly registered with the clinical trials Registry, INDIA (CTRI/2021/10/037323). Adults aged 18–65 years with Rome IV-defined irritable bowel syndrome (IBS) or functional dyspepsia (FD) refractory to standard treatment were enrolled after excluding celiac disease, wheat allergy, and alarm features. Participants underwent a two-step diagnostic protocol. In Step I, patients adhered to a 6-week strict gluten-free diet (GFD) under dietitian supervision. Weekly assessments of gastrointestinal and extra-intestinal symptoms, health-related quality of life (HRQoL), and psychological scores were performed using validated instruments. Gluten responders—defined by ≥30% reduction in one to three primary symptoms—were advanced to Step II: a randomized, double-blind, placebo-controlled gluten challenge with crossover. Subjects received indistinguishable gluten or placebo cookies (8 g/day) for one week, followed by a one-week washout and crossover. A ≥30% symptom difference between gluten and placebo phases confirmed non-celiac gluten/wheat sensitivity (NCGWS). Primary outcome was NCGWS prevalence; secondary outcomes included symptom and HRQoL changes post-GFD and predictors of NCGWS. Statistical analyses included intention-to-treat principles and multivariable regression to identify baseline predictors.

Results

Of the 252 patients screened, 177 were enrolled for 6-week GFD (step I), and 154 patients completed this phase (mean age 41.9±14.2 years, 53.2% males). Eighty two (52.3%) patients responded to GFD, of whom 77 entered step 2 (DBPCGC). Thirty one (20.1%) patients had significant symptom worsening on blinded gluten ingestion, suggesting the presence of NCGWS. Independent predictors of NCGWS were female gender, FD-IBS overlap, headache, fatigue, and anxiety. Significant improvements in gastrointestinal symptoms, health-related quality of life, and psychological scores were observed after GFD in responders. No significant impact of diet sequence was noted.

Conclusion