Recep Adiyaman
Vision About Experience Education Skills Publications Tools Newsletter Updates Podcasts Blog Contact CV Subscribe
All Issues
Older Newer
Daily Signal February 25, 2026 · 7 min read

Issue #55: ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation

Protein Design Digest - 2026-02-25 - Discovery of potent ALK tyrosine kinase inhibitors for thyroid cancer via machine learning modeling, molecular docking, MD simulations, and DFT study.

Share X LinkedIn
Protein Design Daily

Building something in Protein Design?

I love collaborating on new challenges. Let's build together.

LinkedIn Email

Subscribe to Protein Design Digest

Daily curated signals from arXiv, PubMed, and BioRxiv.

Signal of the Day

ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation

Sequential recommendation increasingly employs latent multi-step reasoning to enhance test-time computation. Despite empirical gains, existing approaches largely drive intermediate reasoning states via target-dominant objectives without imposing explicit feasibility constraints. This results in latent drift, where reasoning trajectories deviate into implausible regions. We argue that effective recommendation reasoning should instead be viewed as navigation on a collaborative manifold rather than free-form latent refinement. To this end, we propose ManCAR (Manifold-Constrained Adaptive Reasoning), a principled framework that grounds reasoning within the topology of a global interaction graph. ManCAR constructs a local intent prior from the collaborative neighborhood of a user’s recent actions, represented as a distribution over the item simplex. During training, the model progressively aligns its latent predictive distribution with this prior, forcing the reasoning trajectory to remain within the valid manifold. At test time, reasoning proceeds adaptively until the predictive distribution stabilizes, avoiding over-refinement. We provide a variational interpretation of ManCAR to theoretically validate its drift-prevention and adaptive test-time stopping mechanisms. Experiments on seven benchmarks demonstrate that ManCAR consistently outperforms state-of-the-art baselines, achieving up to a 46.88% relative improvement w.r.t. NDCG@10. Our code is available at https://github.com/FuCongResearchSquad/ManCAR.

Why this matters:

Also Worth Reading

Investigation of the potential mechanism by which methylparaben induces psoriasis: an integrated study using network toxicology, molecular docking, molecular dynamics simulation, and eight machine learning algorithms.

Psoriasis is a chronic inflammatory skin disease with limited safe and effective treatments. Methylparaben, a widely used preservative in cosmetics, pharmaceuticals, and food, is an emerging environmental pollutant linked to immune-related skin disorders, but its role and mechanism in psoriasis remain unclear. This study explored its potential mechanism using network toxicology, molecular docking, molecular dynamics simulation, and eight machine learning algorithms. Methylparaben targets were retrieved from GeneCards and TCMSP, and psoriasis-related targets from CTD and GeneCards. Overlapping targets were screened with Venny 2.1.0. A PPI network was constructed via STRING, and core targets identified using Cytoscape 3.10.2. GO and KEGG enrichment analyses were performed on DAVID. Molecular docking evaluated the binding affinity of methylparaben with key targets. A total of 138 compound-related and 5,592 psoriasis-related targets were identified. Core targets such as INS, HIF1A, and PPARG are involved in regulating immune-inflammatory responses, keratinocyte proliferation and differentiation, and oxidative stress. GO analysis revealed enrichment in xenobiotic metabolism, lipopolysaccharide response, and metal ion binding. KEGG analysis highlighted pathways related to cancer, chemical carcinogenesis from reactive oxygen species, and drug metabolism via cytochrome P450 enzymes. Molecular docking showed stable binding of methylparaben to INS (-4.5 kcal/mol), HIF1A (-5.9 kcal/mol), and PPARG (-5.5 kcal/mol), primarily through hydrogen bonds and hydrophobic interactions. Methylparaben may exert its effects on psoriasis via multi-target and multi-pathway mechanisms, influencing inflammation, oxidative stress, and cellular regulation. These findings provide valuable insight into its toxicological mechanism and potential therapeutic application.

scDock: Streamlining drug discovery targeting cell-cell communication via scRNA-seq analysis and molecular docking

Summary Identifying drugs that target intercellular communication networks represents a promising therapeutic strategy, yet linking single-cell RNA sequencing (scRNA-seq) analysis to structure-based drug screening remains technically challenging and requires substantial bioinformatics expertise. We present scDock, an integrated and user-friendly pipeline that seamlessly connects scRNA-seq data processing, cell–cell communication inference, and molecular docking-based drug discovery. Through a single configuration file, users can execute the complete workflow, from raw scRNA-seq data to ranked drug candidates, without programming skills. scDock automates the identification of disease-relevant ligand–receptor interactions from scRNA-seq data and perfoms structure-based virtual screening against these communication targets using Protein Data Bank (PDB) or AlphaFold-predicted protein structures. The pipeline generates comprehensive outputs at each stage, enabling users to explore intercellular signaling alterations and discover therapeutic compounds targeting specific cell–cell communications. scDock addresses a critical gap by providing an accessible end-to-end solution for communication-targeted drug discovery from single-cell data. Availability and Implementation scDock is freely available at https://github.com/Andrewneteye4343/scDock . It is implemented in R, Python, shell scripts, and supports Linux systems, including Ubuntu and Debian.

Development of DHODH inhibitors incorporating virtual screening, pharmacophore modeling, fragment-based optimization methods, ADMET, molecular docking, molecular dynamics, PCA analysis, and free energy landscape

Research & AI Updates

From the Industry

Quick Reads

Evaluation of plasticizer toxicity effects and mechanisms in gastric cancer based on network toxicology and molecular docking.

The hypothesized toxicity and potential molecular mechanism of gastric cancer induced by exposure of two plasticizers (DBP and DEP) were studied by network toxicology. Read more →

Bio and Geno-toxic Activities of Cadmium- Arsenic Salts Combination And/or Fluoride in Female Rats Confirmed by Molecular Docking.

Heavy metals are increasingly recognized as major toxic agents and potential carcinogens. Read more →

Integrative network toxicology and molecular docking preliminarily explore the potential role of polystyrene microplastics in childhood obesity.

Childhood obesity is a severe global epidemic, and emerging evidence suggests environmental pollutants like polystyrene microplastics (PS-MPs) may disrupt metabolic homoeostasis though mechanistic insights remain limited. Read more →

Discovery of a novel VEGFR2 inhibitor using integrated structure-based docking study and functional validation: potential applications in targeted cancer therapy.

Cancer remains a predominant cause of mortality worldwide, with conventional therapies often limited by adverse side effects and the development of drug resistance. Read more →

Rendezvous and Docking of Mobile Ground Robots for Efficient Transportation Systems

In-Motion physical coupling of multiple mobile ground robots has the potential to enable new applications like in-motion transfer that improves efficiency in handling and transferring goods, which tackles current challenges in logistics. Read more →

Catechins in insomnia-Alzheimer’s disease comorbidity: A network pharmacology and molecular docking study.

The comorbidity of insomnia and Alzheimer’s disease (AD) is strongly driven by the interplay between circadian rhythm disruption and immune dysfunction. Read more →

Folding Thermodynamics and Kinetics of the N-Terminal Domain of the Circadian Clock-Regulated Histidine Kinase SasA.

Despite groundbreaking advancements in protein structure prediction, particularly with AlphaFold2/3 and RoseTTAFold, the protein folding problem remains elusive. Read more →

ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation

Sequential recommendation increasingly employs latent multi-step reasoning to enhance test-time computation. Read more →

Pipeline Tip

Always validate pLDDT scores before using AlphaFold models for docking.

Resources & Tools

The protein structure is the language of life; design is its poetry. — Recep Adiyaman

BS HF DK