Automated graptolite identification at high taxonomic resolution using residual networks.

Graptolites, fossils significant for evolutionary studies and shale gas exploration, are traditionally identified visually by taxonomists due to their intricate morphologies and preservation challenges. Artificial intelligence (AI) holds great promise for transforming such meticulous tasks. In this paper, we demonstrate that graptolites can be identified with taxonomist accuracy using a deep learning model. We construct the most sophisticated and largest professional single organisms image dataset to date, which is composed of >34,000 images of 113 graptolite species annotated at pixel-level resolution to train the model, develop, and evaluate deep learning networks to classify graptolites. The model's performance surpassed taxonomists in accuracy, time, and generalization, achieving 86% and 81% accuracy in identifying graptolite genus and species, respectively. This AI-based method, capable of recognizing minute morphological details better than taxonomists, can be integrated into web and mobile apps, extending graptolite identification beyond research institutes and enhancing shale gas exploration efficiency.

4-[4-(4-Amino-1,2,5-oxadiazol-3-yl)-1,2,5-oxadiazol-3-yl]-1,2,5-oxadiazol-3-amine.

The complete molecule of the compound, C(6)H(4)N(8)O(3), is generated by a crystallographic twofold rotation axis that runs through the central ring. The flanking ring is twisted by 20.2 (1)° with respect to the central ring. One of the amino H atoms forms an intra-molecular N-H⋯N hydrogen bond; adjacent mol-ecules are linked by N-H⋯N hydrogen bonds forming a chain running along [10-2].

[Screening of AGGF1 interacting with inhibitor of differentiation-1].

OBJECTIVE: To screen the proteins interacting with inhibitor of differentiation 1(Id1) using yeast two-hybrid analysis in adult human lung cDNA libraries. METHODS: The coding sequence of Id1 was amplified by PCR and cloned into the bait plasmid. The recombinant bait vector pHybLex/Zeo-Id1 was verified by restriction endonuclease digestion before transformation into the yeast strain EGY48/pSH18-34, which was tested subsequently for reporter genes Leu2 and LacZ activation. The pHybLex/Zeo-Id1 plasmid and the cDNA library plasmid were sequentially transformed into the yeast strains and screened to obtain Leu2(+) and Leu2(+)LacZ(+) clones, with the false positive clones excluded using positive and negative controls, and the plasmid of the true positive clone was sequenced and blasted for homological analysis. RESULTS: Successful construction of pHybLex/Zeo-Id1 was confirmed by enzyme digestion. After transformation of pHybLex/Zeo-Id1 into EGY48/pSH18-34, no specific reporter genes Leu2 and LacZ activation was found. The pHybLex/Zeo-Id1 plasmid and the cDNA library plasmid were sequentially transformed into yeast strain, and 198 Leu(+) clones and 19 Leu(+)LacZ(+) double positive clones were obtained. After elimination of the false positive clones, one true positive clone was obtained, whose plasmid analysis by sequencing and blasting indicated high homology (99.5%, 556/559) to AGGF1 (an angiogenic factor with G-patch and FHA domains 1). AGGF1 expression was confirmed in the true positive yeast cells by Western blotting. CONCLUSION: AGGF1 is confirmed to interact with Id1 by yeast two-hybrid analysis for screening adult human lung cDNA libraries.