Johns Hopkins University Developed Platform for Kidney Drug Discovery

Renal PRISM

Predictive Reproducible Insights from Scalable Multi-omics

An open benchmark suite, harmonized kidney cell atlas, and community portal for AI-driven drug target discovery — developed at Johns Hopkins University to address the most under-treated global health crisis.

Investigators:
Chirag Parikh, MD PhD
Clinical and Translational Lead
Ashish Nimgaonkar, MD MSc
Computational Medicine, Discovery & Development Lead
Genomics
Transcriptomics
Proteomics
Phenomics
0
Million with Kidney Disease
0
FDA-Approved AKI Therapies
0
Failed Drug Programs
0
Lost in Failed Trials

A Crisis Without a Cure

Acute kidney injury affects over 40 million people worldwide, causing over 6 million deaths annually, yet it remains the most under-addressed global health crisis. In hospitals, AKI drives morbidity and cost; in low- and middle-income countries, it is community-acquired, affecting younger populations. Despite two decades and $2B+ in failed trials, there are zero FDA-approved therapies to prevent AKI-to-CKD progression.

Even small AKI episodes drive CKD through repeated micro-injury, making AKI the principal engine fueling the global rise of kidney disease. Over 850 million people live with kidney disease; each progression to dialysis costs $90K+/year. The window between acute injury and chronic progression remains poorly understood and entirely untargeted by existing therapies.

40M+
Annual AKI cases
6M+
Deaths annually
$90K+
Annual dialysis cost
0
Approved therapies
AKI-to-CKD Progression
Healthy
Kidney
Baseline
Acute
Injury
AKI Event
24-48 hrs
Injury
Response
Transition
Weeks to months
Chronic
Disease
CKD
◆ Research Focus
Understanding the post-AKI transition period to identify potential intervention strategies

A Four-Layer Open Platform

Powered by multi-modal AI integrating single-cell and spatial tissue biology, human genetics, clinical data, and drug chemistry — providing standardized evaluation tasks, confidence-scored predictions, and a self-service portal.

01

Harmonized Multi-Omics Atlas

Curated integration of publicly available single-nucleus transcriptomes from KPMP, NEPTUNE, ERCB, and GTEx, with spatial tissue maps and plasma proteomics — standardized to shared ontologies (HGNC, MONDO, CL).

snRNA-seq · Proteomics · GWAS
02

Benchmark Suite & Scoring Engine

Eight-dimension Target Biology Profile (TBP) engine: genetic evidence, disease validation, druggability, safety, homeostatic dispensability, development feasibility, competitive differentiation, and biomarker potential.

MR · eQTL · Open Targets · ChEMBL
03

Community Portal & Leaderboard

Interactive web portal where researchers explore the atlas, submit model predictions, benchmark against ground truth labels, and compare approaches on standardized tasks.

Open Access · Leaderboard · API
04

AI Model Hub

Multi-modal AI with causal inference (Mendelian randomization, gene regulatory networks), Bayesian uncertainty quantification, and privacy-preserving federated learning — every prediction carries a confidence score.

Causal Inference · Bayesian UQ · Federated Learning

Data at a Glance

Explore representative visualizations from our pilot analyses — built on genomics, transcriptomics, proteomics, phenomics datasets and published literature.

Kidney Single-Nucleus Transcriptome Atlas

UMAP projection of major renal cell types from snRNA-seq data (representative visualization)

Data source: Kidney Precision Medicine Project (KPMP). Visualization represents major cell-type clusters from publicly available snRNA-seq datasets. Points are simulated for illustration; positions approximate published UMAP coordinates.

The Target Biology Profile (TBP) engine scores each candidate across 8 orthogonal dimensions. Below are illustrative profiles for select targets using publicly available evidence.

Target Candidate A

Enzyme

Target Candidate B

Transcription Factor

Target Candidate C

Enzyme

Target Candidate D

Secreted Protein

Over two decades and $2B+ invested, more than 20 drug programs targeting AKI have failed in clinical trials. Renal PRISM systematically analyzes why — and what the field can learn.

2000
Anaritide (Auriculin)
Target: ANP receptor
Phase III failure — no improvement in dialysis-free survival
2003
Insulin-like Growth Factor 1
Target: IGF1R
Phase III failure — no benefit in established AKI
2008
Eritoran
Target: TLR4
Phase III failure in sepsis — kidney endpoints negative
2012
Teprasiran (QPI-1002)
Target: p53 (siRNA)
Phase III — missed primary endpoint in cardiac surgery AKI
2015
ANG-3777 (BB3)
Target: HGF mimetic
Phase II — inconclusive results in kidney transplant DGF
2019
Reltecimod (AB103)
Target: CD28 co-stimulation
Phase III — no improvement in necrotizing soft tissue infections with organ failure endpoints
2022
Multiple GLP-1 RA programs
Target: GLP-1R (renal endpoints)
Ongoing — renal-specific AKI prevention endpoints still unproven
2024
Renal PRISM
Approach: AI-driven target prioritization
Open platform to systematically learn from failures and identify better targets

Active AKI Clinical Trials

Phase 2 & 3 interventional trials currently recruiting or active — a landscape Renal PRISM aims to inform

Source: ClinicalTrials.gov · Updated May 2026
58
Active Trials
12
Phase 3
9,400+
Patients Enrolled
0
Approved Therapies
TIN816 in Sepsis-Associated AKI
Phase 2b
Novartis
n=320 2024–2027
Ravulizumab (ARTEMIS) — Complement C5 Inhibition in AKI
Phase 3
Alexion / AstraZeneca
n=736 2023–2027
AZD4144 (SERENIA) — Novel Mechanism in AKI
Phase 2
AstraZeneca
n=124 2024–2026
LSALT Peptide in Sepsis-Associated AKI
Phase 2
Arch Biopartners
n=240 2023–2026
Deferoxamine for Contrast-Associated AKI Prevention
Phase 2
Brigham and Women's Hospital
n=320 2022–2026
Fenoldopam for AKI Prevention in Cardiac Surgery
Phase 3
Multi-center Academic
n=1,000 2023–2027
Remote Ischemic Preconditioning — Cardiac Surgery AKI
Phase 3
Duke University
n=7,500 2021–2026
Nangibotide — TREM-1 Inhibition in Septic Shock
Phase 2
Inotrem
n=450 2022–2026
Stem Cell Therapy for AKI Recovery
Phase 2
Multiple Sponsors
n=60–120 2023–2027
Multiple NCTs
Dexmedetomidine for Perioperative AKI Prevention
Phase 3
Multi-center Academic
n=2,400 2022–2026
Thiamine for Sepsis-Associated AKI
Phase 2
Beth Israel Deaconess
n=200 2023–2026
SGLT2 Inhibitors for AKI-to-CKD Prevention
Phase 3
Multiple Pharma
n=varies 2023–2028
Multiple NCTs
Showing a curated selection of 12 representative trials from 58 active Phase 2/3 AKI studies on ClinicalTrials.gov. Despite decades of effort and billions invested, no therapy has received FDA approval for AKI treatment or AKI-to-CKD prevention — underscoring the need for AI-driven target discovery approaches like Renal PRISM.

New Endotypes & Emerging Targets

Pilot analyses integrating publicly available single-cell transcriptomics, proteomics, and genetic causal inference are generating new insights into AKI-to-CKD biology — and revealing patterns in why prior therapeutic approaches have not succeeded.

🧬

Novel AKI-to-CKD Endotypes

Computational analysis of kidney injury transcriptomes suggests the existence of distinct molecular subtypes within the AKI-to-CKD transition, potentially requiring different therapeutic approaches.

🏹

Multi-Omics Target Candidates

Pilot scoring across 8 dimensions — genetic evidence, druggability, safety, disease validation, and more — has prioritized a portfolio of candidates spanning novel mechanisms, known pathways, and biomarker opportunities not previously linked to AKI progression.

🔬

Proteomics-Validated Biomarkers

Multi-cohort plasma proteomics analysis has identified circulating proteins that distinguish AKI patients who will progress to CKD from those who recover — enabling earlier intervention and precision trial enrichment strategies.

14+
Target Candidates Profiled
8
Scoring Dimensions
3+
Novel Endotypes Identified
4
Multi-Omics Data Layers

Open Science, By Design

Targeting ~2,500 researchers, 30+ institutions, and 10+ industry labs — with all datasets, models, and benchmarks freely available to the global research community.

📚

Open Data

Harmonized atlas and benchmark datasets released under permissive licenses. FAIR-compliant metadata with full provenance tracking.

🤖

Open Models

All AI models, training code, and evaluation scripts published on GitHub and Hugging Face. Reproducible end-to-end pipelines.

🌐

Open Community

Interactive portal for dataset exploration, model benchmarking, and collaborative target validation. No gatekeeping — science should be open.