Non-Profit Research Initiative

Where MoleculesMeet Machines

A non-profit research initiative decoding biochemical processes through AI. All work is open-source and freely available — science should benefit everyone, not shareholders.

# Latest experiment — binding affinity prediction
$ model.predict(protein_seq, target="BRCA1")
ΔG: -9.42 kcal/mol | confidence: 0.94
drug_candidate: True # novel kinase inhibitor
0
Research Streams
0
ML Architectures
0
Papers Active
$0
Profit Motive
🏥

100% Non-Profit · Open Source · Open Access

All our research, code, datasets, and publications are freely available under open licenses. We believe that AI-driven medical research must remain a public good — not locked behind paywalls or corporate interests. No investors. No shareholders. No profit motive. Just science for the benefit of humanity.

Research Focus

Biochemistry × Deep Learning

Six interconnected research streams. Each one a node in a larger network of discovery.

01

Protein Structure & Drug Design

Deep learning predicts protein conformations. We analyze binding pockets to identify drug targets for cancer, autoimmune disease, and neurodegeneration.

AlphaFoldMol. DynamicsDocking
02

Metabolic Pathway Analysis

Graph neural networks model metabolic networks. We find dysregulation patterns and intervention points invisible to traditional approaches.

GNNSystems BioMetabolomics
03

Drug-Target Interaction

Attention-based architectures predict molecular binding affinities. Screening millions of compounds — collapsing discovery from years to weeks.

TransformersVirtual ScreenADMET
04

Genomic Biomarkers

Large language models on genomic sequences. Identifying clinically relevant variants for rare diseases and oncology — precision medicine at sequence level.

Genomic LLMVariant CallPrecision
05

Clinical Trial Optimization

Reinforcement learning for adaptive trial design. Dynamic allocation, dosing, endpoints — improving power while cutting time-to-approval.

RLAdaptiveBayesian
06

Multi-Modal Diagnostics

Biochemical markers + medical imaging in unified AI pipelines. Histopathology, radiology, molecular data fused for superior diagnostic accuracy.

Multi-ModalHistopathFusion
Methodology

Research Pipeline

Hypothesis → Computation → Wet Lab → Clinic. Structured. Reproducible.

PHASE 01

Biochemical Hypothesis

Identify molecular targets via literature mining, knowledge graphs, and domain experts.

PHASE 02

Data Curation

PDB, UniProt, TCGA, GEO, ChEMBL + clinical partnerships. Quality-controlled and harmonized.

PHASE 03

Architecture Design

Purpose-built ML architectures for the biochemical domain. Not off-the-shelf.

PHASE 04

In-Silico Validation

Cross-validation, ablation, SOTA comparison. We don't publish unless we beat the baseline.

PHASE 05

Wet-Lab Confirmation

Biochemical assays, cell experiments, animal model validation of computational predictions.

PHASE 06

Clinical Translation

Diagnostic tools, treatment protocols, trial designs. The final mile from bench to bedside.

Output

Publications & Preprints

From working papers to peer review.

Active

Attention-Based Graph Networks for Kinase Inhibitor Binding Affinity

Novel GNN with 3D geometry + pocket features. 15% over DeepDTA on Davis & KIBA.

Active

Metabolic Perturbation Signatures in T2D: Multi-Omics Graph Transformers

Metabolomics + transcriptomics + proteomics via graph transformers. Early dysregulation markers.

Q4 2026

Genomic Foundation Models for Rare Disease Variant Prioritization

Fine-tuned genomic LLMs — pathogenic variant classification beyond ACMG.

2027

RL Framework for Adaptive Oncology Trials

RL-based dose-finding validated against 3+3 designs in extensive simulation.

Push the Boundaries With Us

This is a non-profit, open-source initiative. We seek collaborators from biochemistry, medicine, and computational biology who share our belief that medical AI research should remain free and accessible.

Get in Touch → View Source ↗