TBTommaso Becchi

Tommaso Becchi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Tommaso Becchi has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    KDM: embedding DNA/RNA motifs and sequences in a shared k-mer space for unified discovery, analysis and binding prediction

    by Luca Fumagalli, Tommaso Becchi, Matteo Cereda, Uberto Pozzoli

    Motif discovery and binding-site prediction in DNA and RNA sequences are central tasks in regulatory genomics, yet the methodological landscape is split between interpretable but rigid position weight matrices (PWMs) and high-performing but opaque machine-learning models. We present KDM, a unifying framework in which both motifs and sequences are represented as probability distributions over a shared k-mer dictionary, embedded via the Hellinger transformation. This common geometry enables motif-sequence scoring, motif-motif comparison, de novo discovery, and binding prediction with a single primitive, the Bhattacharyya coefficient. We instantiate four tools on this representation: KDMMap for positional enrichment analysis, KDMMatch for information-content-aware motif matching, KDMFind for unsupervised motif discovery via projective non-negative matrix factorization, and KDM-LRLM for binding prediction with Lasso-regularized logistic regression. Across 1,324 transcription-factor ChIP-seq and 161 RBP eCLIP experiments, KDMMap matches CentriMo’s motif rankings in 84% of TF and 79% of RBP experiments, and KDMMatch agrees with Tomtom on motif annotation in 74.5% of TFs. On binding prediction across four datasets covering 2,475 experiments, KDM-LRLM matches or exceeds eight deep-learning and three k-mer-based competitors. Notably, AI methods overtake k-mer methods only in the top quartile of training-set size, indicating that data scale, not architecture, drives the recent dominance of deep models. KDM provides a single interpretable representation across the full motif-analysis workflow.

  • Open Access

    RNAMaRs: an interpretable framework for inferring multivalent RNA Motifs and cognate Regulators of Splicing

    by Mariachiara Grieco, Tommaso Becchi, Gabriele Boscagli, Francesca Priante, Livia Caizzi, Uberto Pozzoli, Matteo Cereda

    Alternative splicing expands proteomic diversity and is shaped by interactions between RNA-binding proteins (RBPs) and multivalent RNA motifs. Linking sequence elements to regulatory proteins remains difficult from sequence information alone. Here we present RNAMaRs, a interpretable statistical framework that combines motif discovery with in vivo binding and splicing responses to infer motif-RBP relationships. RNAMaRs learns RBP binding principles, weights signal quality, and optimizes motif discovery in an RBP-specific manner. Across ENCODE datasets RNAMaRs consistently prioritizes the perturbed regulator, especially for large splicing effects. Independent validation in prostate cancer cells recapitulates HNRNPK binding signatures, supporting transferability across an unseen cellular context.

  • Open Access

    Kandinsky: Enabling neighbourhood analysis of spatial omics data for functional insights on cell ecosystems

    by Pietro Andrei, Mariachiara Grieco, Amelia Acha-Sagredo, Tommaso Becchi, Pawan Dhami, Kathy Fung, Manuel Rodriguez-Justo, Matteo Cereda, Francesca D Ciccarelli

    Aims: Spatially resolved omics technologies enable investigation of cellular interactions within their local microenvironments (neighbourhoods) directly in situ. Although several computational methods have been developed for neighbourhood analysis, significant limitations remain in how neighbourhoods are defined and interrogated. Here, we present Kandinsky, a toolkit that provides a flexible and versatile framework for defining and analysing cell neighbourhoods. Methods: We developed Kandinsky to improve flexibility in neighbourhood analysis and maximise compatibility with a wide range of spatial omics data. We therefore implemented multiple approaches for identifying cell- or spot-based neighbourhoods that serve as input for four analytical modules: differential gene or protein expression analysis, neighbourhood clustering, co-localisation/dispersion, and spatial hot and cold areas. In addition to its core functionality, Kandinsky enables the execution of external tools within the same analytical framework. Results: We applied Kandinsky to real and simulated spatial datasets to benchmark its performance against existing methods and demonstrate its ability to uncover biologically meaningful spatial interactions. Kandinsky achieved competitive performance in terms of accuracy, memory usage, and runtime. In real datasets, it suggested transcriptional changes associated with acinar-to-beta cell reprogramming in the healthy pancreas; recapitulated stromal, immune, and tumour-associated clusters in pancreatic cancer; revealed the spatial co-localisation of myoepithelial cells with specific breast cancer subpopulations; and confirmed the association between regions of high CD74 expression and immune cell infiltration. Conclusion: Kandinsky is a flexible and versatile toolkit for neighbourhood analysis that facilitates the exploration and interpretation of complex spatial omics data.