Short (15−30 residue) chains of amino acids at the amino termini of expressed proteins known as signal peptides (SPs) specify secretion in living cells. We trained an attentionbased neural network, the Transformer model, on data from all available organisms in Swiss-Prot to generate SP sequences. Experimental testing demonstrates that the model-generated SPs are functional: when appended to enzymes expressed in an industrial Bacillus subtilis strain, the SPs lead to secreted activity that is competitive with industrially used SPs. Additionally, the model-generated SPs are diverse in sequence, sharing as little as 58% sequence identity to the closest known native signal peptide and 73% ± 9% on average.

Intellectual disability (ID) and autism spectrum disorder (ASD) are the most common neurodevelopmental disorders and are characterized by substantial impairment in intellectual and adaptive functioning, with their genetic and molecular basis remaining largely unknown. Here, we identify biallelic variants in the gene encoding one of the Elongator complex subunits, ELP2, in patients with ID and ASD. Modelling the variants in mice recapitulates the patient features, with brain imaging and tractography analysis revealing microcephaly, loss of white matter tract integrity and an aberrant functional connectome. We show that the Elp2 mutations negatively impact the activity of the complex and its function in translation via tRNA modification. Further, we elucidate that the mutations perturb protein homeostasis leading to impaired neurogenesis, myelin loss and neurodegeneration. Collectively, our data demonstrate an unexpected role for tRNA modification in the pathogenesis of monogenic ID and ASD and define Elp2 as a key regulator of brain development.

The development of cancer therapies may be improved by the discovery of tumor-specific molecular dependencies. The requisite tools include genetic and chemical perturbations, each with its strengths and limitations. Drug perturbations can be readily applied to primary cancer samples at a large scale, but mechanistic understanding of hits and further pharmaceutical development is often complicated by the fact that a small compound has a range of affinities to multiple proteins. To computationally infer the molecular dependencies of individual cancers from their ex-vivo drug sensitivity profiles, we developed a mathematical model that deconvolutes these data using measurements of protein-drug affinity profiles. Our method, DepInfeR, correctly identified known dependencies, including EGFR dependence in Her2+ breast cancer cell line, FLT3 dependence in AML tumors with FLT3-ITD mutations, and the differential dependencies on the B-cell receptor pathway in two major subtypes of chronic lymphocytic leukemia (CLL). Furthermore, our method uncovered new subgroup-specific dependencies, including a previously unreported dependence of high-risk CLL on Checkpoint kinase 1 (CHEK1). The method also produced a more accurate map of the molecular dependencies in a heterogeneous set of 117 CLL samples. The ability to deconvolute polypharmacological phenotypes into underlying causal molecular dependencies should increase the utility of high-throughput drug response assays for functional precision oncology.