Despite dramatic advances in molecular and imaging technologies, there are currently no effective pharmacological treatments for the core symptoms of autism spectrum disorder (ASD). Major obstructions to this include a lack of aetiologically-driven or pathophysiologically-accurate animal models; an absence of tests that indicate efficacy; and reliance of clinical trials on DSM/ICD10 categories which provide a collection of biologically heterogeneous patients. Further, even if novel treatments are developed there is no EU platform to clinically test them. Our hypothesis is that a focus on cross-species endophenotypes, finding biologically-homogenous groups of patients, and developing a clinical research network will overcome the limitations in target identification, early triage and clinical trials. Hence, leading European institutions and three SMEs will partner with the EFPIA to: a) develop in vitro models, and animal models that carry confirmed genetic risks, and in these animals to focus on cross-species endophenotypes (e.g., cognitive function, electrophysiology) to facilitate new drug discovery; b) validate the use of sMRI and fMRI-based endophenotypes in genetically-selected healthy volunteers, infants at risk for ASD, and children and adults (including twins) with and without ASD, as early and surrogate markers for efficacy; and to combine this with PET approaches to provide guidance regarding optimal clinical trial design; and c) identify biomarkers that can be used to stratify patients within an umbrella DSM-diagnosis, thus allowing for targeted clinical trials, individualized treatment and back-translation of subgroup-specific biomarkers into preclinical drug discovery. To increase the chance of a breakthrough we will implement new analytical approaches (e.g. support vector machine learning algorithms) and will actively collaborate with patient groups and other international efforts (e.g. the Autism Genetic Resource Exchange (AGRE)).