Research Credibility

22+ Bio Papers at the
World's Top Venues

Our computational methods are validated at conferences ranked by Google Scholar alongside Nature and Science for impact — the same venues where Google DeepMind publishes AlphaFold. Every milestone linked to official conference evidence.

AAAI-26 ORAL PRESENTATION
Agentic Causal Graph Learning for Drug Target Discovery
Oral presentation at the AIDD Workshop — fewer than 2% of AAAI submissions receive this honor. Active causal hypothesis testing for drug target identification across the NAD+ biosynthesis pathway.
5 bio papers 17.6% conference acceptance rate AIDD Workshop →
AAAI-26 ORAL PRESENTATION
Neuro-Symbolic AI for Alzheimer's: Biomarker Prediction & Verifiable Intervention Planning
Oral at the LMReasoning Workshop. Physics-informed biomarker prediction with formal verification guarantees — directly applicable to Alzheimer's drug target validation.
2 oral presentations AAAI accepts fewer than 1 in 5 submissions LMReasoning Workshop →
AAAI-26 3 POSTERS
De Novo Drug Design, Bayesian Molecular Discovery, and Nanobiomaterials Assistants
Three additional bio-relevant papers across AIDD, AI4Research, and LMReasoning workshops: generative AI for drug design, active learning for molecular screening, and multi-agent reasoning for nanobiomaterials.
AAAI-26 #4 Google Scholar h5:220 OpenReview →
ICLR 2026 ~5 BIO PAPERS
Biomedical AI & Alzheimer's Causal Models
Five papers across 3 workshop tracks at the #2 ranked AI conference globally (Google Scholar h5-index: 304). Alzheimer's drug discovery, biomedical reasoning, and verified molecular generation. Publishing alongside Google DeepMind and OpenAI.
#2 Google Scholar h5-index: 304 ICLR Official →
AI4X-AC 2 ORAL PRESENTATIONS
Brain Resilience, Cell Painting & Cancer Treatment Optimization
Six papers at the Applied AI for Science conference including 2 oral presentations. Topics spanning brain resilience modeling, high-content cell painting analysis, and AI-optimized cancer treatment scheduling — all leveraging our ACHT and VAP architectures.
6 papers, 2 oral Applied AI for Science
NeurIPS 2025 AI4D3 WORKSHOP
Active Causal Hypothesis Testing for Drug Target Discovery
Selected for the AI4D3 Drug Discovery Workshop at NeurIPS — the #1 ranked AI conference globally (Google Scholar h5-index: 337). Workshop organized by Harvard Medical School, Genentech/Roche, and AbbVie's Prescient Design team.
#1 Google Scholar h5:337 Alongside Insilico Medicine, Genentech AI4D3 Schedule →
Stanford ACCEPTED
Architectural Immune System: Correcting Synthetic Fallacies in AI-Driven Science
Paper accepted at Stanford's Agents4Science Workshop. Advisory board includes Guido Imbens (Nobel Laureate, Stanford), Barbara Cheifet (Chief Editor, Nature Biotechnology), and Eric Topol (Scripps Research). Our framework for detecting and correcting AI hallucinations in scientific discovery.
Nobel laureate on advisory board Nature Biotechnology editor involved Stanford Workshop → Our Paper →
ELLIS ML4MOLECULES
Physics-Informed Surrogates for Verified Molecular Simulation
Poster at the European Machine Learning excellence network's ML4Molecules workshop. Physics-informed surrogate models that accelerate molecular dynamics by 100-1,000x while maintaining DFT-level accuracy — directly applicable to protein-ligand binding simulations.
European ML excellence ML4Molecules →
MLGenX 3 PAPERS
Alzheimer's Drug Discovery & Causal Molecular Reasoning
Three papers at the ICLR-affiliated MLGenX workshop focused on Alzheimer's drug discovery. Generative models for neuroprotective compound design with causal ADMET prediction and verified synthesis planning.
ICLR-affiliated Alzheimer's focus
Validated at the same venues where Google DeepMind publishes AlphaFold
NeurIPS (#1 GS h5:337) | ICLR (#2 GS h5:304) | AAAI (#4 GS h5:220) | Stanford | ELLIS
Publishing alongside: Google DeepMind OpenAI Harvard Medical School Genentech/Roche Stanford MIT

See Our Computational Platform

From molecular docking to toxicity prediction — every tool built on peer-reviewed, conference-validated methods.