The pholcid spiders of Tunisia (Araneae: Pholcidae): new species, new records, and deep COI divergence in Holocnemus reini

Posted by
  The pholcid spiders of Tunisia (Araneae: Pholcidae): new species, new records, and deep COI divergence in Holocnemus reini Abstract Tunisia features a rapid transition between Mediterranean and Saharan biogeographical zones, resulting in a high degree of environmental heterogeneity. Despite this ecological diversity, Tunisian spiders have received limited attention compared to those of neighboring Maghreb countries. Here we combine the results of recent collections in Tunisia focusing on Pholcidae with a comprehensive review of previously published information, resulting in a total of six genera and eleven species. We present first records of the genera Micropholcus Deeleman-Reinhold & Prinsen, 1987 and Spermophorides Wunderlich, 1992 for Tunisia, represented by four new species: M. kahinae Huber sp. nov., M. echebbii Huber sp. nov., S. nabilae Huber & Kmira sp. nov., S. bchirae Huber sp. nov.; in addition, we redescribe S. huberti (Senglet, 1973) from Tunisian specimens,...

A Machine Learning-Enabled Venom Peptide Platform for Rapid Drug Discovery

Posted by

 


A Machine Learning-Enabled Venom Peptide Platform for Rapid Drug Discovery

Abstract

Background/Objectives: Nature has evolved millions of venom-derived peptides with diverse biological functions, a substantial fraction of which target complex membrane proteins such as G-protein-coupled receptors and ion channels. Many of these peptides are stabilized by multiple disulfide bonds, endowing them with exceptional structural stability and favorable pharmacological properties. 

Methods: Leveraging this natural diversity, we developed a robust venom peptide therapeutics discovery system built on phage display technology and constructed a library using approximately 482 venom-derived scaffolds. The library design was guided by a machine learning (ML) model capable of predicting mutation-tolerant residues that preserve peptide foldability, maximizing structural integrity and sequence diversity. 

Results: The resulting VCX library was evaluated through screening against four diverse targets (CD47, DLL3, IL33, and P2X7R), yielding strong binders for all four, a success rate of 100%. Furthermore, by integrating high-throughput recombinant expression of thioredoxin–venom fusion proteins along with ML-assisted affinity maturation, we rapidly identified potential leads for DLL3 binders. 

Conclusions: This venom-based discovery platform offers significant advantages in both functionality and developability compared with conventional peptide discovery approaches. By combining natural structural diversity, ML-guided design, and recombinant expression, it enables efficient identification of “antibody-like” binders with molecular weights much smaller than those of antibodies. Consequently, it provides a powerful strategy for developing next-generation peptide therapeutics targeting challenging protein–protein interactions and complex membrane proteins.

Cai, F., Zhou, L., Delgado, B., Chang, W., Tom, J., Hernandez, E., Joshi, P., Song, A., Masureel, M., Maun, H. R., Chang, A., & Zhang, Y. (2026). A Machine Learning-Enabled Venom Peptide Platform for Rapid Drug Discovery. Pharmaceuticals, 19(2), 288. https://doi.org/10.3390/ph19020288