Author: admin

-Positive data from Phase Ib study of ASC30 oral tablet demonstrated up to 6.5% placebo-adjusted mean body weight reduction; safe and well tolerated with only mild-to-moderate gastrointestinal (GI) adverse events (AEs) across all multiple ascending dose (MAD) cohorts.

-Phase Ib study data of ASC30 subcutaneous (SQ) injection showed that observed half-life reached 46 days for the treatment formulation (Injection A) and 75 days for the maintenance formulation (Injection B).

-Combination of ASC47 and ASC31, a novel peptide agonist targeting both GLP-1R and GIPR, significantly outperformed both tirzepatide and ASC31 monotherapy in promoting weight loss, body fat loss, and muscle preservation in diet-induced obesity (DIO) mouse studies.

-Presentations further highlight the promising efficacy and safety profiles of Ascletis’ diverse obesity pipeline and validate its proprietary Artificial Intelligence-Assisted Structure-Based Drug Discovery (AISBDD) and Ultra-Long-Acting Platform (ULAP) technologies.

HONG KONG, Nov. 4, 2025 /PRNewswire/ — Ascletis Pharma Inc. (HKEX: 1672, “Ascletis”) announces multiple poster presentations of the full analysis of the Phase Ib study of ASC30 once-daily oral tablet, Phase Ib study of ASC30 once-monthly injection, and preclinical study of the combination of ASC31 and ASC47 at ObesityWeek^® 2025 in Atlanta, Georgia.

Abstract Title: A full analysis of 28-Day MAD Study of Oral GLP-1R Biased Small Molecule Agonist ASC30 for obesity

Results:

Efficacy: Body weight changes from baseline were 6.3% reduction (multiple ascending dose (MAD) 2, n=8, 40 mg), 4.3% reduction (MAD 1, n=7, 20 mg), and 0.2% increase (placebo, n=6). No plateau was observed at Day 29. Body weight change from baseline was 4.8% reduction for MAD 3 (n=7, 60 mg), with the maximum body weight change being 9.3% reduction in this cohort. Excluding two outliers, the mean body weight change from baseline was 5.9% reduction for MAD 3.

GI Tolerability: In the MAD study, MAD 1 (20 mg cohort) showed no vomiting, while MAD 2 (40 mg cohort) had events. Titrating from 2 mg to 5 mg did not cause vomiting in MAD 1, but titrating from 2 mg to 10 mg did result in vomiting in MAD 2. Compared with MAD 2, MAD 3 showed no increasing trend in severity or incidence of gastrointestinal (GI) adverse events (AEs), despite two discontinuations due to principal investigator’s decisions, and one discontinuation due to subject withdrawal.

Safety: No serious adverse events (SAEs) or Grade ≥ 3 AEs, including GI events, were observed. Labs, vitals, ECGs (QTc), and physical exams were normal. No hepatic safety signals were detected across all MAD cohorts.

Conclusion: ASC30 once-daily oral tablet demonstrated up to 6.5% placebo-adjusted mean body weight reduction from baseline after 28-day treatment. The highest dose level (MAD 3, 60 mg) exhibited up to 9.3% body weight reduction, showed no increasing trend in severity or incidence in GI AEs. ASC30 was safe and well tolerated with only mild-to-moderate GI AEs across all MAD cohorts. The safety profile of ASC30 tablets was consistent with or better than that of the GLP-1R agonist class.

Abstract Title: ASC30, a Once-Monthly SQ Injected Small Molecule GLP-1RA in Participants with Obesity: A Ph Ib Study

Results: The observed half-life (time for ASC30 concentrations to reduce to fifty percent (50%) of ASC30’s C_max) reached 46 days and 75 days, for ASC30 subcutaneous (SQ) treatment formulation (Injection A) and ASC30 SQ maintenance formulation (Injection B), respectively. C_max-to-C_day29 ratio of 1.5:1, supports ASC30 SQ treatment formulation monthly dosing, while C_max-to-C_day85 ratio of 2.5:1, supports ASC30 SQ maintenance formulation quarterly dosing.

No SAEs or Grade ≥ 3 AEs were observed. GI-related AEs were mild to moderate. Labs, vitals, ECGs (QTc), and physical exams were normal. No hepatic safety signals were detected across all cohorts.

Conclusion: ASC30 ultra-long-acting, slow-release SQ depot formulations demonstrated 46-day observed half-life (treatment formulation) and 75-day observed half-life (maintenance formulation), supporting both once-monthly treatment and once-quarterly maintenance therapies.

ASC30 SQ formulations were well tolerated, with only mild-to-moderate treatment-emergent adverse events (TEAEs), comparable or superior to those observed with GLP-1R agonists. Developed with Ascletis’ Ultra-Long-Acting Platform (ULAP) technology, ASC30 treatment and maintenance formulations represent a potential breakthrough in chronic weight management by improving treatment convenience, adherence, and quality of life.

Abstract Title: GLP-1R/GIPR Peptide Agonist ASC31 + ASC47 Shows 119.6% More Weight Loss than Tirzepatide in DIO Mice

Results: The combination of ASC47 plus ASC31 resulted in a 44.8% reduction in weight compared to a 19.1% reduction for ASC31 monotherapy. This was a 134% greater reduction than ASC31 alone. The combination of ASC47 plus tirzepatide resulted in a 38.1% reduction in weight compared to a 20.4% reduction for tirzepatide alone. This was an 87% greater reduction in weight compared to tirzepatide alone. The mean greater reduction in weight of ASC31 in combination with ASC47 compared to ASC31 alone (134%) is statistically significantly higher than that of tirzepatide plus ASC47 compared to tirzepatide alone (87%).

Conclusion: The combination of ASC47 and ASC31 significantly outperformed both tirzepatide and ASC31 monotherapy in promoting weight loss, body fat loss, and muscle preservation. The combination of ASC47 with either ASC31 or tirzepatide restored the body composition of obese mice to the level of healthy non-obese mice. ASC31 is a dual GLP-1R and GIPR peptide agonist. ASC47 is a small molecule thyroid hormone receptor beta (THRβ)-selective agonist and was designed with unique and differentiated properties to enable targeted delivery to adipose tissue.

Detailed data presented at ObesityWeek^® 2025 can be found at Ascletis’ website (link).

“These presentations highlight the exciting efficacy and safety profiles of our diverse obesity pipeline of both small molecules and peptides and validate our proprietary AISBDD and ULAP technologies,” said Jinzi Jason Wu, Ph.D., Founder, Chairman and CEO of Ascletis. “As we advance clinical development of ASC30, ASC31, and ASC47, we remain focused on close discussion with strategic partners to ensure that Ascletis is best positioned to address the needs of patients with obesity globally.”

About ASC30

ASC30 is an investigational GLP-1R biased small molecule agonist and has unique and differentiated properties that enable the same small molecule for both oral tablet and subcutaneous injection administrations. ASC30 is a new chemical entity (NCE), with U.S. and global compound patent protection until 2044 without patent extensions.

About ASC31

ASC31 is an in-house discovered and developed novel peptide agonist targeting both GLP-1R and GIPR, which demonstrated a favorable pharmacokinetic profile in non-human primates as well as promising in vitro activities and in vivo efficacy in the diet-induced obese (DIO) mice. ASC31 is part of Ascletis’ discovery efforts to apply its Ultra-Long-Acting Platform (ULAP) to in-house discovered novel subcutaneously (SQ) injectable peptides and oral peptides.

About ASC47

ASC47 is an adipose-targeted, once-monthly SQ injected THRβ-selective small molecule agonist, discovered and developed in-house at Ascletis. ASC47 possesses unique and differentiated properties to enable adipose targeting, resulting in dose-dependent high drug concentrations in the adipose tissue.

About Ascletis Pharma Inc.

Ascletis Pharma Inc. is a fully integrated biotechnology company focused on the development and commercialization of potential best-in-class and first-in-class therapeutics to treat metabolic diseases. Utilizing its proprietary Artificial Intelligence-Assisted Structure-Based Drug Discovery (AISBDD) and Ultra-Long-Acting Platform (ULAP) technologies, Ascletis has developed multiple drug candidates in-house, including its lead program, ASC30, a small molecule GLP-1R agonist designed to be administered once daily orally and once monthly to once quarterly subcutaneously as a treatment therapy and a maintenance therapy for chronic weight management. Ascletis is listed on the Hong Kong Stock Exchange (1672.HK). For more information, please visit www.ascletis.com.

Contact：

Peter Vozzo
ICR Healthcare
443-231-0505 (U.S.)
[email protected]

Ascletis Pharma Inc. PR and IR teams
+86-181-0650-9129 (China)
[email protected]
[email protected]

SOURCE Ascletis Pharma Inc.

In a world of interconnected financial markets, policymakers and regulators face the complex task of identifying and addressing risks before they escalate into crises. The 2008-09 global crisis and recent episodes of market dysfunction highlight the need for early warning tools to detect vulnerabilities in real time. However, predicting financial market stress remains challenging, as traditional econometric models often fail to capture the complex, nonlinear dynamics and interconnectedness of modern financial systems.

Recent advances in artificial intelligence (AI) provide new tools to address these challenges. AI methods excel at analysing high-dimensional datasets and uncovering hidden patterns. While they are widely applied in asset pricing (Kelly et al. 2024), they are increasingly used for financial stability monitoring (Fouliard et al. 2021, du Plessis and Fritsche 2025). However, the ‘black box’ nature of AI models has limited their ability to generate actionable policy insights.

This article highlights recent research (Aldasoro et al. 2025, Aquilina et al. 2025) that advances the deployment of AI tools to anticipate financial market stress. These studies demonstrate the potential of AI to forecast market stress and dysfunction, offering both methodological innovations and actionable insights for policymakers by addressing the black-box issue.

The challenge of anticipating financial market stress

Financial market stress can take many forms, including liquidity shortages, price dislocations, and breakdowns in arbitrage relationships. Events such as the 1998 LTCM crisis, the 2008-09 global crisis, and the 2020 ‘dash for cash’ highlight the systemic risks posed by market dysfunction. These disruptions often begin in specific market segments, such as foreign exchange or money markets, but can quickly spread throughout the financial system, threatening its stability. Increasingly, stress has also shifted from traditional banks to non-bank financial intermediaries, reflecting the evolving nature of financial intermediation.

Traditional early warning systems, which were primarily designed to predict full-blown crises, have had mixed success. These models often suffer from high false positive rates and struggle to account for the nonlinear interactions and feedback loops that amplify shocks during periods of stress.

Machine learning (ML) offers a promising alternative, particularly for generating early warning signals. Unlike traditional models, ML algorithms can process vast datasets, identify complex relationships, and adapt to changing market conditions. The studies discussed here demonstrate the potential of these tools to anticipate market stress and provide policymakers with timely warnings.

Using machine learning to model the tail behaviour of financial market conditions

Aldasoro et al. (2025) present a novel framework for predicting financial market stress using machine learning. The study begins by constructing market condition indicators (MCIs) for three key US markets critical to financial stability: Treasury, foreign exchange, and money markets. These indicators (illustrated in Figure 1) capture dislocations in liquidity, volatility, and arbitrage conditions.

Figure 1 Market condition indices for US Treasury, foreign exchange, and money markets        

Notes: This figure shows the five-day moving average of market condition indices for the US Treasury, money, and foreign exchange (FX) markets (upper, middle, and lower panels respectively). The sample period is from 01/01/2003 to 31/05/2024.

The paper employs random forest models, a popular tree-based machine learning algorithm, to forecast the full distribution of future market conditions. This approach uses multiple decision trees and averages their predictions, reducing the risk of overfitting. The results are noteworthy: random forest models outperform traditional time-series approaches, particularly in predicting tail risks over longer time horizons (up to 12 months). This is especially evident in forecasting foreign exchange market conditions (Figure 2).

Figure 2 Forecast accuracy of random forest and autoregressive models

Notes: This figure compares quantile losses between the random forest and autoregressive models based on out-of-sample predictions across forecast horizons. Negative values indicate better performance of the random forest model.

To address the black-box issue, the study uses Shapley value analysis to explain the main factors driving market stress predictions. The analysis reveals that macroeconomic expectations and uncertainty, particularly around monetary policy, are significant contributors to market vulnerability. Liquidity conditions and the state of the global financial cycle also play critical roles. This approach not only improves predictive accuracy but also provides actionable insights for policymakers, enabling them to respond proactively to the build-up of vulnerabilities.

Combining machine learning with large language models

Aquilina et al. (2025) take a different approach by integrating numerical data with textual information using large language models (LLMs). The study focuses on deviations from triangular arbitrage parity (TAP) in the euro-yen currency pair, a key indicator of dysfunction in the foreign exchange market. By combining recurrent neural networks (RNNs) with LLMs, the authors develop a two-stage framework to forecast market stress and identify its underlying drivers.

The recurrent neural network detects periods of heightened triangular arbitrage parity deviations up to 60 working days in advance, effectively predicting market dysfunctions that may occur within a one-month window. Out-of-sample testing on 3.5 years of data demonstrates the model’s practical value. For example, the model identified elevated risks before the March 2023 banking turmoil, despite being trained only on data up to the end of 2020 (Figure 3). However, it did not predict the market anomaly caused by the onset of COVID-19, as the event’s origins were external to the financial system.

Figure 3 Predictive accuracy of market dysfunction episodes

Notes: True data: 20-day average of the daily euro-yen triangular arbitrage parity difference with the US dollar as the vehicle currency, calculated on a minute-by-minute basis. The vertical red dashed line represents the end of the training period, end-2020; everything to the right of this line is considered pseudo out-of-sample.

To address the black-box challenge, Aquilina et al. (2025) develop a new architecture for recurrent neural network models that dynamically assigns weights to input variables. This allows the model to identify which indicators are most important for predicting future market conditions at any given time. These weights can then be fed into an LLM to search financial news and commentary for contextual information, helping to uncover potential triggers of market stress.

For instance, during the March 2023 banking turmoil, the model flagged elevated risks in euro liquidity and cross-currency arbitrage. Guided by these signals, the LLM identified news articles discussing tightening dollar funding conditions and rising geopolitical tensions. This targeted approach transforms opaque statistical forecasts into narrative explanations that policymakers can understand and act upon.

Policy implications and conclusions

While much more research into these issues is needed, these approaches show the promise of leveraging AI tools for financial stability monitoring and analysis.

• First, our work has shown that machine learning models are useful in forecasting future conditions of various markets.
• Second, the integration of numerical and textual data through machine learning and large language models provides a richer understanding of market dynamics. Policymakers can use these tools to monitor emerging risks in real time, combining quantitative forecasts with qualitative insights from financial news and commentary.
• Finally, the interpretability of machine learning models is critical for their adoption in policy settings. Techniques like Shapley value analysis and variable-specific weighting not only improve the transparency of forecasts but also provide actionable information about the drivers of market stress.

Overall, these approaches represent a significant step forward in leveraging AI to detect vulnerabilities in financial markets. By combining different methods, the studies offer novel tools for forecasting market stress and understanding its underlying drivers. However, these methods are not without limitations, such as the risk of overfitting and the need for substantial computational resources. Policymakers and regulators should invest in the necessary data and infrastructure to fully harness the potential of these tools.

References

Aldasoro, I, P Hördahl and S Zhu (2022), “Under pressure: market conditions and stress”, BIS Quarterly Review (19): 31–45.

Aldasoro, I, P Hördahl, A Schrimpf and X S Zhu (2025), “Predicting Financial Market Stress with Machine Learning”, BIS Working Papers No. 1250.

Aquilina, M, D Araujo, G Gelos, T Park and F Pérez-Cruz (2025), “Harnessing Artificial Intelligence for Monitoring Financial Markets”, BIS Working Papers No. 1291.

Du Plessis, E and U Fritsche (2025), “New forecasting methods for an old problem: Predicting 147 years of systemic financial crises”, Journal of Forecasting 44 (1): 3-40.

Fouliard, J, M Howell, H Rey and V Stavrakeva (2021), “Answering the queen: Machine learning and financial crises”, NBER Working Paper 28302.

Huang, W, A Ranaldo, A Schrimpf and F Somogyi (2025), “Constrained liquidity provision in currency markets”, Journal of Financial Economics 167: 104028.

Kelly, B, S Malamud and K Zhou (2024), “The Virtue of Complexity in Return Prediction”, Journal of Finance 79: 459-503.

Pasquariello, P (2014), “Financial Market Dislocations”, Review of Financial Studies 27(6): 1868–1914.