Aims: This study aims to identify nucleotide variations in human T-lymphotropic virus type 1 (HTLV-1) proviral genome that might be related with the different clinical conditions associated to the virus. Materials & methods: 91 complete HTLV-1 genomes available in GenBank with their respective clinical information were subjected to in silico analyzes (subtyping, molecular characterization and machine learning). Results: We identified 22 mutations that seems to be important in patients’ clinical condition. The presence of some mutations demonstrated alterations in the proteins physicochemical profile, such as the P34L, present in the p12 protein. Furthermore, a correlation between mutations in long terminal repeat and pX region seems to be important for clinical manifestation. Conclusions: Some mutations have the potential to alter the conformation of viral proteins that are important for infection outcomes. Therefore, further functional studies should be performed to assess the impact of these variations on the pathogenesis and on the development of clinical manifestations associated with HTLV-1.