Biology subjects

Goncearenco, A.

Publications and source records attributed to Goncearenco, A..

4 recordsLinked to original sources

bioRxiv2024

PINDER: The protein interaction dataset and evaluation resource

Protein-protein interactions (PPIs) are fundamental to understanding biological processes and play a key role in therapeutic advancements. As deep-learning docking methods for PPIs gain traction, benchmarking protocols and datasets tailored for effective training and evaluation of their generalization capabilities and performance across real-world scenarios become imperative. Aiming to overcome limitations of existing approaches, we introduce PINDER, a comprehensive annotated dataset that uses structural clustering to derive non-redundant interface-based data splits and includes holo (bound), apo (unbound), and computationally predicted structures. PINDER consists of 2,319,564 dimeric PPI systems (and up to 25 million augmented PPIs) and 1,955 high-quality test PPIs with interface data leakage removed. Additionally, PINDER provides a test subset with 180 dimers for comparison to AlphaFold-Multimer without any interface leakage with respect to its training set. Unsurprisingly, the PINDER benchmark reveals that the performance of existing docking models is highly overestimated when evaluated on leaky test sets. Most importantly, by retraining DiffDock-PP on PINDER interface-clustered splits, we show that interface cluster-based sampling of the training split, along with the diverse and less leaky validation split, leads to strong generalization improvements.

bioinformatics↗

bioRxiv2022

From sequence to function through structure: deep learning for protein design

The process of designing biomolecules, in particular proteins, is witnessing a rapid change in available tooling and approaches, moving from design through physicochemical force fields, to producing plausible, complex sequences fast via end-to-end differentiable statistical models. To achieve conditional and controllable protein design, researchers at the interface of artificial intelligence and biology leverage advances in natural language processing (NLP) and computer vision techniques, coupled with advances in computing hardware to learn patterns from growing biological databases, curated annotations thereof, or both. Once learned, these patterns can be leveraged to provide novel insights into mechanistic biology and the design of biomolecules. However, navigating and understanding the practical applications for the many recent protein design tools is complex. To facilitate this, we 1) document recent advances in deep learning (DL) assisted protein design from the last three years, 2) present a practical pipeline that allows to go from de novo-generated sequences to their predicted properties and web-powered visualization within minutes, and 3) leverage it to suggest a generated protein sequence which might be used to engineer a biosynthetic gene cluster to produce a molecular glue-like compound. Lastly, we discuss challenges and highlight opportunities for the protein design field. AvailabilitypLM generated and UniRef50 sampled sequence sets and predictions are available at http://data.bioembeddings.com/public/design. Code-base and Notebooks for analysis are available at https://github.com/hefeda/PGP. An online version of Table 1 can be found at https://github.com/hefeda/design_tools. O_TBL View this table: org.highwire.dtl.DTLVardef@1823c4borg.highwire.dtl.DTLVardef@1449504org.highwire.dtl.DTLVardef@193458borg.highwire.dtl.DTLVardef@1bab4c4org.highwire.dtl.DTLVardef@b1d39f_HPS_FORMAT_FIGEXP M_TBL O_FLOATNOTable 1:C_FLOATNO O_TABLECAPTIONmachine-learning-based protein design methods. Methods ordered by their release date, accounting for the date of pre-prints when available. Class (1-4) captured in Fig. 1. Expanded method detail in main text. Unnamed methods are referenced by the first name of the first author. Online version at https://github.com/hefeda/design_tools. Legend: Architecture: The architecture of the deep learning model; E2E: an end-to-end differentiable solution; Input: the input to run (infer from) the model, e.g. a contact map; Output: the output, e.g. a protein sequence; Dataset: the number and type of samples used to train the method; Params: the exact or estimated number of parameters of the model; 1: the 3D recovery was performed in an external, second step; 2: conditioned generation; -: no input required for generation. C_TABLECAPTION C_TBL

bioinformatics↗

bioRxiv2018

Nucleotide and codon background mutability shape cancer mutational spectrum and advance driver mutation identification

Identifying driver mutations in cancer is notoriously difficult. To date, recurrence of a mutation in patients remains one of the most reliable markers of mutation driver status. However, some mutations are more likely to occur than others due to differences in background mutation rates arising from various forms of infidelity of DNA replication and repair machinery, endogenous, and exogenous mutagens.\n\nWe used cancer-type and mutagen-specific mutability to study the contribution of background processes of mutagenesis and DNA repair in shaping the observed mutational spectrum in cancer. We developed and tested probabilistic model that adjusts the number of mutation recurrences in patients by background mutability in order to find mutations which may be under selection in cancer.\n\nWe showed that observed recurrence frequency of cancer mutations scaled with the background mutability, especially for tumor suppressor genes. In oncogenes, however, highly recurring mutations were characterized by relatively low mutability, resulting in a U-shaped trend. Mutations not yet observed in any tumor had relatively low mutability values, indicating that background mutability might limit the mutation occurrence.\n\nWe compiled a dataset of missense mutations from 58 genes with experimentally validated functional and transforming impacts from different studies. We found that mutability of driver mutations was lower than the mutability of passengers and consequently adjusting mutation recurrence frequency by mutability significantly improved ranking of mutations and driver prediction. Even though no training on existing data was involved, our approach performed similar or better to the existing state-of-the-art methods.\n\nAvailabilityhttps://www.ncbi.nlm.nih.gov/research/mutagene/gene

cancer biology↗

bioRxiv2018

Integrated proteogenomic analysis of metastatic thoracic tumors identifies APOBEC mutagenesis and copy number alterations as drivers of proteogenomic tumor evolution and heterogeneity

Elucidation of the proteogenomic evolution of metastatic tumors may offer insight into the poor prognosis of patients harboring metastatic disease. We performed whole-exome and transcriptome sequencing, copy number alterations (CNA) and mass spectrometry-based quantitative proteomics of 37 lung adenocarcinoma (LUAD) and thymic carcinoma (TC) metastases obtained by rapid autopsy and found evidence of patient-specific, multi-dimensional heterogeneity. Extreme mutational heterogeneity was evident in a subset of patients whose tumors showed increased APOBEC-signature mutations and expression of APOBEC3 region transcripts compared to patients with lesser mutational heterogeneity. TP53 mutation status was associated with APOBEC hypermutators in our cohort and in three independent LUAD datasets. In a thymic carcinoma patient, extreme heterogeneity and increased APOBEC3AB expression was associated with a high-risk germline APOBEC3AB variant allele. Patients with CNA occurring late in tumor evolution had corresponding changes in gene expression and protein abundance indicating genomic instability as a mechanism of downstream transcriptomic and proteomic heterogeneity between metastases. Across all tumors, proteomic heterogeneity was greater than copy number and transcriptomic heterogeneity. Enrichment of interferon pathways was evident both in the transcriptome and proteome of the tumors enriched for APOBEC mutagenesis despite a heterogeneous immune microenvironment across metastases suggesting a role for the immune microenvironment in the expression of APOBEC transcripts and generation of mutational heterogeneity. The evolving, heterogeneous nature of LUAD and TC, through APOBEC-mutagenesis and CNA illustrate the challenges facing treatment outcomes.

cancer biology↗