Khachatryan, A. | Search bioRxiv

bioRxiv2025

AmyloDeep: pLM-based ensemble model for predicting amyloid propensity from the amino acid sequence

Amyloids are predominantly {beta}-sheet-rich, stable protein structures that can maintain their presence in the human body for multiple years. Amyloid protein aggregates contribute to the development of multiple neurodegenerative diseases, such as Alzheimers, Parkinsons, and Huntingtons, and are involved in different vital functions, such as memory formation and immune system function. Here, we used advanced machine learning and deep learning techniques to predict amyloid propensity from the amino acid sequence. First, we aggregated labeled amino acid sequence data from multiple sources, obtaining a roughly balanced dataset of 2366 sequences for binary classification. We leveraged that data to both fine-tune the ESM2 model and to train new models based on protein embeddings from ESM2 and UniRep. The predictions from these models were then unified into a single soft voting ensemble model, yielding highly robust and accurate results. We further made a tool where users can provide the amino acid sequence and get the amyloid formation probabilities of different segments of the input sequence. Users can access the light version of AmyloDeep through the web server at https://amylodeep.com/, and the full model is available as a Python package at https://pypi.org/project/amylodeep/. Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=47 SRC="FIGDIR/small/676495v1_ufig1.gif" ALT="Figure 1"> View larger version (13K): org.highwire.dtl.DTLVardef@64615aorg.highwire.dtl.DTLVardef@339a7corg.highwire.dtl.DTLVardef@1e36e14org.highwire.dtl.DTLVardef@4fe717_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2022

Coevolution of reproducers and replicators at the origin of life and the conditions for the origin of genomes

There are two fundamentally distinct but inextricably linked types of biological evolutionary units, reproducers and replicators. Reproducers are cells and organelles that reproduce via various forms of division and maintain the physical continuity of compartments and their content. Replicators are genetic elements (GE), including genomes of cellular organisms and various autonomous elements, that both cooperate with reproducers and rely on the latter for replication. All known cells and organisms comprise a union between replicators and reproducers. We explore a model in which cells emerged via symbiosis between primordial metabolic reproducers (protocells) which evolved, on short time scales, via a primitive form of selection and random drift, and mutualist replicators. Mathematical modeling identifies the conditions, under which GE-carrying protocells can outcompete GE-less ones, taking into account that, from the earliest stages of evolution, replicators split into mutualists and parasites. Analysis of the model shows that, for the GE-containing protocells to win the competition and to be fixed in evolution, it is essential that the birth-death process of the GE is coordinated with the rate of protocell division. At the early stages of evolution, random, high-variance cell division is advantageous compared to symmetrical division because the former provides for the emergence of protocells containing only mutualists, preventing takeover by parasites. These findings illuminate the likely order of key events on the evolutionary route from protocells to cells that involved the origin of genomes, symmetrical cell division and anti-parasite defense systems. SignificanceThe origin of life, which is equivalent to the origin of cells, is arguably the greatest enigma in biology. The remarkable complexity characteristic of even the simplest extant cells could only evolve from simpler, pre-biological entities. Reconstructing that pre-cellular stage of evolution is a hard challenge. We present an evolutionary scenario in which cells evolved via symbiosis between protocells that harbored protometabolic reaction networks, could divide and were subject to selection, but lacked genomes, and primordial genetic elements. Mathematical modeling reveals conditions for the survival of such symbionts and the origin of modern-type genomes, in particular, coordination of the rates of protocell division and replication of genetic elements as well as random division of protocells.

evolutionary biology↗