Drug-target interaction (DTI) is fundamental to novel drug research and development (R &D), playing a critical role in elucidating drug mechanisms of action and improving the cost-effectiveness of drug discovery. Although China has seen rapid accumulation of drug-target resources in recent years, the industry still faces challenges such as a shortage of original targets and excessively high target concentration. The rapid advancement of artificial intelligence (AI) has provided an efficient technological pathway for DTI prediction, establishing it as a core tool for accelerating drug discovery. This paper systematically reviews the fundamental data support framework for DTI prediction tasks, elaborating in detail on three core data types— drug characterization, target characterization, and drug-target associations-as well as the classification and application boundaries of mainstream benchmark datasets tailored to different tasks within the field. On this basis, it comprehensively surveys the technological evolution of AI-driven DTI prediction, summarizing the core paradigms and technical advances of traditional machine learning and deep learning methods in a single-modality setting, alongside cutting-edge multimodal approaches that integrate two modalities (cross-subject/within-subject fusion) and three or more modalities for multidimensional information integration. Finally, this paper analyzes the current major challenges in data quality, model generalizability and interpretability, and real-world deployment, while also discussing future trends in standardized dataset construction, generative AI, and large-scale biomedical foundation models, aiming to provide a reference for both research and industrial applications in the AI-driven DTI prediction field.

Objective To obtain the protective performance parameters of barium sulfate mortar against positron nuclide γ-rays, provide reference data for precise shielding calculations, and guide the design, evaluation, and construction of radiation shielding. Methods The FLUKA program was used to build a model for simulating the dose equivalent rate variation around points of interest under the irradiation of the most commonly used positron nuclide ¹⁸F with changes in the thicknesses of lead and barium sulfate mortar. The transmission curves of lead and barium sulfate mortar were fitted, and the half-value layer (HVL) and lead equivalence of barium sulfate mortar were calculated based on the fitted curves. Results The ambient dose equivalent rate coefficient of positron nuclide ¹⁸F was 1.339 4×10⁻¹ μSv·m²/MBq·h and the HVL for lead was 4.037 mm, with deviations of 0.043% and 1.53% compared to the values provided in the AAPM Report No. 108, respectively. The HVLs for γ-rays produced by ¹⁸F, using barium sulfate mortar with apparent densities of 4.20, 4.00, and 3.90 g/cm³ mixed with 35.2-grade cement in a 4∶1 mass ratio, were 2.914, 2.969, and 3.079 cm, respectively. The lead equivalences were 0.1385, 0.1360, and 0.1311 mmPb/mm, respectively. Conclusion The three types of barium sulfate mortar can provide good protection against γ-rays in positron imaging locations. As the apparent density of barium sulfate increases, its protective effect improves slightly but remains significantly better than common construction materials like concrete and solid bricks.

Objective To simulate and analyze the dose distribution from external exposure and its influencing factors of induced radioactivity in proton therapy site. Methods Referencing a domestically under-construction proton therapy facility, a geometric model of the proton therapy site was constructed, and the FLUKA program was used to simulate the distribution of the induced radioactive dose of the proton therapy site under the conditions of different energies, beam angles, irradiation time, cooling time and medium of the treatment site. Results For a 230 MeV proton beam with a current of 3.0 nA, directed along the negative Z-axis and irradiating a phantom for two minutes, at the shutdown moment, the ambient dose equivalent rates in air and vacuum 5, 30, and 50 cm away from the phantom surface were (1 039.02±5.82)-(127.86±1.20) and (1 037.96±4.38)~(127.35±0.93) μSv/h, respectively. The mean difference was 0.51~1.06 μSv/h, and the air-immersed external irradiation accounted for <1% of the total irradiation, which rapidly decreased to 1/15 of the shutdown moment value after cooling for 10 minutes. Under the condition of 130~250 MeV, the ambient dose equivalent rates at the shutdown moments 5, 30 and 50 cm away from the surface of the phantom were (427.49±3.12)-(1 058.41±4.66), (100.36±0.92)-(259.70±1.69) and (50.15±0.68)-(131.93±1.11) μSv/h, respectively. Irradiation for one-five minutes, and at the moment of shutdown at 5, 30, and 50 cm from the surface of the phantom were (688.19±3.33)-(1 594.04±8.08), (167.60±1.35)-(388.24±2.96) and (84.73±0.69)-(195.94±1.56) μSv/h. The peripheral dose-equivalent rate of the sensed radioactivity decreases with the irradiation time, the energy of the beam, and the distance from the model. The peak dose equivalent rate around the induced radioactivity exists in the beam direction, which is significantly larger than that in the non-beam direction. Conclusion Proton therapy sites are characterized by relatively large levels of induced peripheral radioactive dose equivalent rates, mainly originating from patients. In actual practice, a suitable working position can be chosen according to the direction of the beam current, especially the direction of the final irradiation field beam current, in the non-beam current direction and as far away from the patient as possible. Within 10 minutes after the end of treatment, staff should try to avoid close contact with the patients.

OBJECTIVE: To explore the changes of the serum immune cytokines in medical radiation workers exposure to low dose ionizing radiation. METHODS: Totally 244 medical professionals working with radiation(61 diagnosis radiology,51 nuclear medicine,74 radio therapeutics and 58 interventional radiology) from 7 hospitals of Guangdong Province were selected as study subjects by using the typical sampling method; 51 administration workers who did not expose to radiation were selected as control group. The radiation dose of these individuals was monitored by thermoluminescent measurement instrument for one year. Venous blood was collected and the levels of interferon γ(IFN-γ),interleukin 10(IL-10),transforming growth factor-β1(TGF-β1) in serum were examined by enzyme-linked immuno sorbent assay. RESULTS: The maximum annual average dose of radiation per person of the medical radiation workers was 0. 41 mSv/a. It was smaller than the occupational exposure limit(20. 00 mSv/a). The annual average dose of radiation per person in the group of nuclear medicine was significantly higher than those of diagnosis radiology,radio therapeutics and interventional radiology(P <0. 01). Among the male staffs,the expression of IL-10 in the diagnosis radiology group,radio therapeutics group and interventional radiology group was lower than that in the control group(P < 0. 05); the expression of IL-10 in radio therapeutics group was lower than those in nuclear medicine group and interventional radiology group(P < 0. 05); the ratio of IFN-γ/IL-10 in radio therapeutics group was higher than those in diagnosis radiology group,nuclear medicine group,interventional radiology group and control group(P < 0. 05). These individuals were divided into 3 different dose group(0. 03-,0. 06-and > 0. 15 m Sv/a) based on their average radiation dose. The expression of IL-10 in male staffs of these3 dose groups was lower than that of the male control group(P < 0. 05). CONCLUSION: Long-term low dose ionizing radiation may restrain the expression level of IL-10 in the male staffs.

Objective To improve the understanding of pulmonary mucormycosis by analyzing the clinical manifestations,imaging features,diagnosis,treatment and prognosis of this disease.Methods The clinical data of eight patients diagnosed as pulmonary mucormycosis by histopathologic examination were retrospectively analyzed.Results Eight patients included six males and two females with age from 36 days to 66 years.Underlying conditions covered diabetes (n =4),renal transplantation (n =3),premature (n =1) and long-term corticosteroid treatment in two cases.Imaging manifestations revealed multiple irregular lumps or nodules in three cases,multiple cavities with thick wall in three cases,diffuse lung infiltrate in one case and lung opacities in one case.The diagnoses of seven patients were confirmed by percutaneous needle lung biopsy and the remaining one was diagnosed with fiberoptic bronchoscopy biopsy.Surgery combined with amphotericin B liposome(60 mg/d for three weeks)was applied to one patient who was cured with no recurrence after a 22 month follow-up.Three cases were given amphotericin B liposome (a newborn with 7mg/d for 62 days,the other two 60 mg/d for 31 days and 70 mg/d for 71 days respectively).All had achieved marked response with follow up from 8 to 29 months,but one patient relapsed and died of recurrent lung mucormycosis.The other three patients were treated with itraconazole 400-200 mg/d from 21 days to 1 year with duration of follow up from 1 month to 20 months.One patient was not evaluable due to missing.Two patients relapsed and one died.Conclusion Pulmonary mucormycosis is difficult to diagnose and treat with a high mortality.Percutaneous tranthoracic lung biopsy is a useful diagnostic method.Amphotericin B liposome or itraconazole may be active against mucus.Early control of causes is essential to improve the prognosis and reduce the recurrence in patients with pulmonary mucormycosis.