Multiple sclerosis (MS) is a white matter (WM) disease characterized by the formation of WM lesions, which can be visualized by magnetic resonance imaging (MRI). The fluid-attenuated inversion recovery (FLAIR) MRI pulse sequence is used clinically and in research for the detection of WM lesions. However, in clinical settings, some MRI pulse sequences can be missing because of various constraints. We propose to use 3D fully convolutional neural networks to predict FLAIR pulse sequences from other MRI pulse sequences. In addition, we evaluate the contribution of each input pulse sequence with a pulse-sequence-specific saliency map. Our approach is tested on a real multiple sclerosis image dataset and evaluated by comparing our approach to other methods and by assessing the lesion contrast in the synthetic FLAIR pulse sequence. Both the qualitative and quantitative results show that our method is competitive for FLAIR synthesis.