Identification of Therapeutic Targets for Amyotrophic Lateral Sclerosis Using PandaOmics – An AI-Enabled Biological Target Discovery Platform

Abstract

Amyotrophic lateral sclerosis (ALS) is a severe neurodegenerative disease with ill-defined pathogenesis, calling for urgent developments of new therapeutic regimens. Herein, we applied PandaOmics, an AI-driven target discovery platform, to analyze the expression profiles of central nervous system (CNS) samples (237 cases; 91 controls) from public datasets, and direct iPSC-derived motor neurons (diMNs) (135 cases; 31 controls) from Answer ALS. Seventeen high-confidence and eleven novel therapeutic targets were identified and will be released onto ALS.AI (http://als.ai/). Among the proposed targets screened in the c9ALS Drosophila model, we verified 8 unreported genes (KCNB2, KCNS3, ADRA2B, NR3C1, P2RY14, PPP3CB, PTPRC, and RARA) whose suppression strongly rescues eye neurodegeneration. Dysregulated pathways identified from CNS and diMN data characterize different stages of disease development. Altogether, our study provides new insights into ALS pathophysiology and demonstrates how AI speeds up the target discovery process, and opens up new opportunities for therapeutic interventions.

High-confidence cancer patient stratification through multiomics investigation of DNA repair disorders

“…The efficiency of the PandaOmics platform has recently been shown for prediction of novel age-associated targets for drug discovery purposes [ 43 ]. Importantly, its capabilities for target discovery cover both analysis across multiple types of diseases as well as in depth characterization of key molecular players driving the progression of a specific disease [ 44 ]. This includes, for instance, the identification of cyclin-dependent kinase 20 (CDK20) as a novel target in hepatocellular carcinoma and generation of potent CDK20 inhibitors using the generative chemistry platform Chemistry42 coupled with subsequent in vitro explorations [ 30 , 45 ].…”

AlphaFold accelerates artificial intelligence powered drug discovery: efficient discovery of a novel CDK20 small molecule inhibitor

“…PandaOmics is an automated drug discovery AI engine to accelerate and optimize key steps of the early stages of drug discovery 30 . This biocomputational platform combines bioinformatics methods for data analysis, visualization and interpretation with advanced multimodal deep learning approaches for target identification [31][32][33][34][35] . PandaOmics therapeutic target and biomarker identification system is based on the combination of multiple scores derived from text and OMICs data associating genes with a disease of interest.…”

“…AI tools are extremely helpful for efficient target hypothesis generation. The overall scoring approach results in the ranked list of target hypotheses for a given disease which can be subsequently filtered according to their novelty, accessibility by small molecules and antibodies, safety, tissue specificity, crystal structure availability and major biological structures 33,34 .…”

Future directions in regulatory affairs

“…AI and ML are playing an increasingly important role in drug discovery (17). Their application will reduce the failure rate in early-stage drug discovery and development and speed up this step in the pathway (18)(19)(20). It should also reduce the risks and cost of drug development.…”