Amyotrophic Lateral Sclerosis (ALS) is a devastating neurodegenerative disease characterized by the progressive degeneration of upper and lower motor neurons. The progression of the disease is variable, with median survival of three years post disease onset. Riluzole, approved in 1995, is the only drug globally licenced for the treatment of ALS. However, riluzole has limited efficacy, prolonging patients' life span by only 3 months. New therapies are therefore urgently needed. This work sought to (i) utilize computational systems biology tools to investigate patient-phenotype heterogeneity and identify novel therapeutic targets and disease pathways in ALS; (ii) develop a high-throughput phenotypic drug screening assay to discover new compounds able to rescue a characteristic ALS phenotype: TDP43 protein aggregation. The discovery of new ALS treatments has been partly hampered by the complexity and heterogeneity of the disease. The first result chapter addresses these issues using an in-silico approach. Specifically, Weighted Gene Co-expression Network Analysis (WGCNA) was used to analyse a published transcriptomic dataset of patient post-mortem brain samples to identify causal relationships between co-expression networks and disease phenotypes and ultimately identify new druggable targets. Using this framework, it was found that ALS patients with bulbar onset presented a strong activation of oligodendroglial gene co-expression networks, which was not observed in the limb onset cohort. Further orthogonal validation in post-mortem tissue from a different ALS cohort revealed that sporadic ALS patients with bulbar onset had a significantly higher number of differentiated oligodendrocytes in the motor cortex. Overall, these observations implicate a particular role for oligodendrocyte dysfunction in bulbar onset ALS. Cytoplasmic accumulation of misfolded and aggregated TDP43 (transactive response DNA-binding protein 43kDa) in the brain and spinal cord of ALS patients is the pathological hallmark of the disease and found in the vast majority of the ALS population, sporadic and familial. In this work, CRISPR/Cas9 technology was used to generate a HEK293 cellular model carrying a pathogenic mutation on the gene that encodes TDP43 which, under oxidative stress, developed cytoplasmic TDP43 aggregates. This work served as the basis for the development of a phenotypic drug screening assay to identify small molecules able that ameliorate TDP43 protein aggregation. The screening of a library of 6652 small molecules (including FDA-approved drugs, investigational compounds, and natural products) led to the identification of several promising compounds that were taken forward for further validation. Following the primary drug screening, hit compounds were tested across a suite of assays designed to verify their activity in stem cell-derived spinal motor neurons and to confirm lack of neuronal toxicity. Finally, the last chapter explores the mechanism of action of the active compounds through a combination of bioinformatic tools and in-vitro experiments. Collectively, this thesis presents the development of a robust platform for the discovery of new disease targets and small-molecule therapeutics for ALS.