Diagnosis knowledge constrained network based on first-order logic for syndrome differentiation.

Traditional Chinese medicine (TCM) has been recognized worldwide as a valuable asset of human medicine. The procedure of TCM is to treatment based on syndrome differentiation. However, the effect of TCM syndrome differentiation relies heavily on the experience of doctors. The gratifying progress of machine learning research in recent years has brought new ideas for TCM syndrome differentiation. In this paper, we propose a deep network model for TCM syndrome differentiation, which improves network performance by injecting TCM syndrome differentiation knowledge in the form of first-order logic into the deep network. Experimental results show that the accuracy of our proposed model reaches 89%, which is significantly better than the deep learning model MLP and other traditional machine learning models. In addition, we present the collected and formatted TCM syndrome differentiation (TSD) dataset, which contains more than 40,000 TCM clinical records. Moreover, 45 symptoms (""), 322 patterns(""), and more than 500 symptoms are labeled in TSD respectively. To the best of our knowledge, this is the first TCM syndrome differentiation dataset labeling diseases, syndromes and pattern. Such detailed labeling is helpful to explore the relationship between various elements of syndrome differentiation.

First Report of Pestalotiopsis trachicarpicola Causing Leaf Blight on Panax notoginseng in China.

Panax notoginseng (Burkill) F. H. Chen ex C. Y. Wu & K.M. Feng is a Chinese herbal medicinal plant for treating diseases of the central nervous system and cardiovascular system, widely used as a medicine and health-care product. In May 2022, leaf blight disease was found on leaves of 1-year-old P. notoginseng in the plantings （27.904°N, 112.918°E） of Xiangtan City (Hunan) with an area of 104 m2. Over 400 plants were investigated, up to 25% of the plants were symptomatic. From the margin of the leaf, the initial symptoms of water-soaked chlorosis and following dry yellow with slight shrinkage appeared. Later, leaf shrinkage became serious and chlorosis enlarged gradually, leading to leaf death and abscission. To identify the causal agent, 20 leaf lesions (4 mm2) collected from 20 individual 1-year-old plants were sterilized with 75% ethanol for 10 s, 5% NaOCl for 10 s, rinsed in sterilized water three times, placed on potato dextrose agar (PDA) with lactic acid (0.125%) for inhibition the growth of bacteria, and incubated at 28°C for 7 days (Fang, 1998). Five isolates were obtained from 20 leaf lesions of different plants with the isolation rate of 25% and purified by single sporing, which have similar colony and conidia morphology characteristics. One isolate PB2-a was selected randomly for further identification. Colonies of PB2-a on PDA were white with cottony mycelium, developing concentric circles (top view) or light yellow (back view). Conidia (23.1 ± 2.1 × 5.7 ± 0.8 µm, n=30)were fusiform, straight or slightly curved and contained conic basal cell, three light brown median cells and hyaline conic apical cell with appendages. The rDNA internal transcribed spacer (ITS), the translation elongation factor 1-alpha (tef1), and the ß-tubulin (TUB2) genes were amplified from genomic DNA of PB2-a using primers ITS4/ITS5 (White et al. 1990), EF1-526F/EF1-1567R (Maharachchikumbura et al. 2012), and Bt2a/Bt2b (Glass and Donaldson, 1995; O'Donnell and Cigelnik, 1997), respectively. BLAST search of sequenced ITS (OP615100), tef1 (OP681464) and TUB2 (OP681465) exhibited > 99% identity with the type strain of Pestalotiopsis trachicarpicola OP068 (JQ845947, JQ845946 and JQ845945). Phylogenetic tree of the concatenated sequences was constructed based on the maximum-likelihood method using MEGA-X. Isolate PB2-a was identified as P. trachicarpicola based on morphological and molecular data (Maharachchikumbura et al. 2011; Qi et al. 2022). PB2-a was tested for pathogenicity three times to confirm Koch's postulates. Twenty healthy leaves on 20 1-year-old plants were punctured with sterile needles and inoculated with 50 µl of conidial suspension (1×106 conidia/ml). The controls were inoculated with sterile water. All plants were placed in a greenhouse at 25°C under 80% relative humidity. After 7 days, all inoculated leaves developed leaf blight symptoms identical to those described above, whereas the control plants kept healthy. P. trachicarpicola were reisolated from infected leaves, and identical to those of the originals based on the colony characteristics and the sequenced data of ITS, tef1 and TUB2. P. trachicarpicola was reported as a pathogen of leaf blight on Photinia fraseri (Xu et al. 2022). To our knowledge, this is the first report of P. trachicarpicola causing leaf blight on P. notoginseng in Hunan, China. Leaf blight is one of the destructive diseases in P. notoginseng production, identification of the pathogen will be useful to develop effective disease management and protect P. notoginseng, a medical plant with economic value.