metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:1571676
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      [YEAR_RANGE] 2020-2024 [TEXT] Draft genome sequence of the fungal
      biocontrol agent, Bacillus velezensis Kos.
    sentences:
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] Hallux valgus is a common progressive
        forefoot deformity. Although open techniques have shown good outcomes,
        no technique has been shown to be superior to other techniques. The
        current third generation of minimally invasive Chevron-Akin (MICA)
        technique features a percutaneous procedure with a stable internal
        fixation. The technique used in this study resulted in stable internal
        fixation; however, 1 screw was used in intramedullary fashion in the
        majority of cases. The purpose of this study is to review the early
        outcomes of MICA. Electronic Health Records (EHR) were queried for
        patients who underwent MICA to treat hallux valgus (HV) deformity, by a
        single surgeon. The primary clinical outcomes assessed were visual
        analog pain score (VAS), rate of revision surgery, and recurrence.
        Radiographic outcomes were assessed including pre and postoperative
        hallux valgus angle (HVA), intermetatarsal angle (IMA), and bony foot
        width. The secondary outcomes included postoperative complications. A
        total of 91 feet underwent MICA to correct symptomatic HV deformity. The
        mean age of this cohort was 53.63 ± 15.42 years, mean body mass index
        (BMI) of 26.81 ± 6.21 kg/m2, mean follow-up of 6.33 ± 6.39 months and 87
        feet belonged to female patients. Patients showed significant
        improvement in VAS and radiographic outcomes at final follow-up, with a
        mean improvement of 10.70° ± 6.42°, 2.39° ± 3.55°, and 5.30 mm ± 4.23 mm
        for the HVA, IMA, and bony foot width, respectively. Two patients (2.2%)
        required revision surgery for nonunion and removal of symptomatic
        hardware. One patient had a second metatarsal fracture treated
        nonoperatively. No feet had recurrence, hardware loosening, infection,
        or scar hypersensitivity. The current study reported on early outcomes
        for MICA. This technique appears to be effective and safe with no
        failure of fixation in our patients. We showed in our short-term
        follow-up, MICA led to significant improvement in pain and radiographic
        scores.Levels of Evidence: III, retrospective study.
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] BACKGROUND: Few studies have evaluated the
        effects of structured early mobilization included adults patients who
        were randomized into two groups: intervention (n = 40) and control (n =
        45). The intervention group underwent conventional physiotherapy and
        structured EM protocols, and the control group underwent conventional
        physiotherapy. The level of mobilization from 0 (no mobilization) to 5
        (walking), muscle strength (Medical Research Council scale), LADL (Katz
        Index), and incidence of complications were evaluated. RESULTS: The
        level of mobilization from day 1 to day 7 increased in the intervention
        group compared with the control group (p <.05). Muscle strength did not
        change during the protocol in the intervention and control groups {day
        1, at ICU discharge, and after ICU discharge}. The LADL did not differ
        between the intervention and control groups after ICU discharge or 30
        days after hospital discharge. The structured EM protocol was safe, and
        no severe complications were observed during the protocol. CONCLUSION: A
        structured EM protocol increased the level of mobilization without
        improving muscle strength and the LADL compared with conventional
        physiotherapy.
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] Here, we report the draft genome sequence
        of Bacillus velezensis strain Kos, isolated from casing soil used during
        Agaricus bisporus cultivation in Dublin, Ireland. B. velezensis Kos
        exhibits a suppressive ability toward Cladobotryum mycophilum,
        Trichoderma aggressivum, and Lecanicillium fungicola, which are common
        threats to A. bisporus production, cultivation, and quality.
  - source_sentence: >-
      [YEAR_RANGE] 2020-2024 [TEXT] Application of the grading system for
      "nociplastic pain" in chronic primary and chronic secondary pain
      conditions: a field study.
    sentences:
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] Adenomyoepithelioma (AME) of the breast is
        a rare tumor that can be benign or malignant and has varied
        morphological features. We report a case of a 62-year-old female with a
        history of right breast cancer who presented with abnormal screening
        mammography. The detection, presentation, and varied imaging
        characteristics of AMEs are discussed. The nonspecific imaging and
        histologic appearance of AME are highlighted, emphasizing the need for
        representative biopsy samples and histopathological review for
        diagnosis. Our case underlines the importance of wide surgical excision
        with negative margins in the presence of diagnostic uncertainty, which
        corresponds with the current recommended treatment for AME to prevent
        recurrence.
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] The paper introduces the Special Issue on
        Language Contact and Speaker Accommodation, which originates from the
        conference Phonetics and Phonology in Europe the linguistic systems.
        Accommodation is seen as the same gradual and non-homogeneous process at
        play in different contact settings. In the introductory sections, a
        discussion is offered on various situations in which linguistic systems
        are in contact and on the main factors that may be at play; the
        following sections offer an overview of the papers included in the
        Special Issue, which focus on accommodation in L2 and heritage speakers
        as well as on the time dimension of dialect or language societal
        contact. Finally, accommodation is discussed as the same process that is
        at work in any interaction, that may modify temporarily or long-term the
        system of L2 learners and bilinguals (for example, immigrants), that
        usually affects in the long-term the heritage speakers' system, and that
        only in the long term can lead to language changes involving entire
        communities.
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] ABSTRACT: The concept "nociplastic pain"
        has been developed for patients with features of nociceptive system
        sensitization that are not explained as nociceptive or neuropathic.
        Here, we tested how well the recently published grading system
        differentiates between chronic primary and secondary pain conditions. We
        recruited patients with fibromyalgia (FMS, n = 41), complex regional
        pain syndrome (CRPS, n = 11), osteoarthritis (OA, n = 21), or peripheral
        nerve injury (PNI, n = 8). We used clinical history, pain drawings,
        quantitative sensory testing (QST), and questionnaires to classify their
        pains as possibly or probably "nociplastic." All patients with chronic
        primary pain exhibited widespread/regional pain not explainable by
        either nociceptive or neuropathic mechanisms. Widespread pain occurred
        in 12 patients with OA but was identified as nociceptive in 11 of 12.
        Regional pain occurred in 4 patients with PNI but was identified as
        neuropathic in 3 of 4. At this step, the grading system had 100%
        sensitivity and 93% specificity. Clinical evidence for pain
        hypersensitivity by QST, and history of hypersensitivity and mental
        comorbidities did not differentiate between chronic primary pain (QST:
        36/52 = 69%, history: 43/52 = 83%) and secondary pain conditions (QST:
        20/29 = 69%, history: 24/29 83%). Based on these data, specificity
        remained excellent (93%), but sensitivity dropped substantially (60%)
        due to lacking evidence for pain hypersensitivity in many patients with
        FMS. This low sensitivity suggests that the published grading system is
        not suitable for screening purposes. We suggest structural and content
        modifications to improve sensitivity, including placement of patient
        history before clinical examination and addition of a high tender point
        count as evidence for widespread pain hypersensitivity.
  - source_sentence: '[YEAR_RANGE] 2020-2024 [TEXT] An Unusual Presentation of Wilson''s Disease.'
    sentences:
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] BACKGROUND: Despite the increasing
        popularity of various materials for ischemia-reperfusion (I/R) injury
        mitigation, research on botulinum toxin type A (BoNTA) remains limited.
        This study assesses BoNTA's efficacy in protecting flaps from I/R injury
        by inhibiting the nicotinamide adenine dinucleotide phosphate (NADPH)
        oxidase system and reducing reactive oxygen species (ROS) production.
        METHODS: Seventy-six Sprague-Dawley rats were studied. We examined the
        effects of BoNTA on superoxide production in four rats using a
        lucigenin-enhanced chemiluminescence assay (LECL). Another group of 60
        rats had their superficial inferior epigastric artery (SIEA) flaps
        treated with either BoNTA or saline and clamped for 0, 1, and 4 hours
        before reperfusion. Flap survival and histological outcomes were
        assessed five days post-operation. ROS production in SIEA flaps and
        femoral vessels was analyzed in 12 additional rats, post-I/R injury.
        RESULTS: The LECL results showed that the BoNTA group had significantly
        lower superoxide production compared to controls, with notable
        reductions at 4 hours. While no significant differences were noted at
        the 0 and 1-hour marks, the 4-hour mark showed significant protective
        effects in BoNTA-treated groups. The survival rate was 90% for
        BoNTA-treated rats versus 60% for controls ( P = 0.028). Significant
        reductions in ROS were also observed in the 4-hour I/R group.
        CONCLUSIONS: BoNTA effectively protects against I/R injury by inhibiting
        the NADPH oxidase system and reducing ROS levels. These results support
        further investigation into the specific mechanisms of NADPH oxidase
        inhibition by BoNTA and its potential clinical applications, given its
        safety profile. CLINICAL RELEVANCE STATEMENT: The findings from the
        present study are expected to provide a basis for clinical studies
        regarding this use of BoNTA.
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] Hard tissue engineering scaffolds
        especially 3D printed scaffolds were considered an excellent strategy
        for craniomaxillofacial hard tissue regeneration, involving crania and
        facial bones and teeth. Porcine treated dentin matrix (pTDM) as
        xenogeneic extracellular matrix has the potential to promote the stem
        cell differentiation and mineralization as it contains plenty of
        bioactive factors similar with human-derived dentin tissue. However, its
        application might be impeded by the foreign body response induced by the
        damage-associated molecular patterns of pTDM, which would cause strong
        inflammation and hinder the regeneration. Ceria nanoparticles (CNPs)
        show a great promise at protecting tissue from oxidative stress and
        influence the macrophages polarization. Using 3D-bioprinting technology,
        we fabricated a xenogeneic hard tissue scaffold based on pTDM xenogeneic
        TDM-polycaprolactone (xTDM/PCL) and we modified the scaffolds by CNPs
        (xTDM/PCL/CNPs). Through series ofin vitroverification, we found
        xTDM/PCL/CNPs scaffolds held promise at up-regulating the expression of
        osteogenesis and odontogenesis related genes including collagen type 1,
        Runt-related transcription factor 2 (RUNX2), bone morphogenetic
        protein-2, osteoprotegerin, alkaline phosphatase (ALP) and DMP1 and
        inducing macrophages to polarize to M2 phenotype. Regeneration of bone
        tissues was further evaluated in rats by conducting the models of
        mandibular and skull bone defects. Thein vivoevaluation showed that
        xTDM/PCL/CNPs scaffolds could promote the bone tissue regeneration by
        up-regulating the expression of osteogenic genes involving ALP, RUNX2
        and bone sialoprotein 2 and macrophage polarization into M2.
        Regeneration of teeth evaluated on beagles demonstrated that
        xTDM/PCL/CNPs scaffolds expedited the calcification inside the scaffolds
        and helped form periodontal ligament-like tissues surrounding the
        scaffolds.
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] Wilson's disease affects the metabolism of
        copper and is a rare hereditary disorder that is inherited autosomally
        recessively. The liver and brain are the main organs affected by this
        disorder, which causes progressive hepatolenticular degeneration. A
        15-year-old male patient arrived at the outpatient department (OPD) with
        mild abdominal pain on the right side, and both eyes showed
        Kayser-Fleischer (KF) rings. An abdominal ultrasound showed that the
        spleen was enlarged. Copper levels in urine were found to be higher.
        After a liver biopsy, cirrhosis, and mild chronic active hepatitis were
        found. The majority of hematological indicators were normal; however, a
        peripheral blood smear revealed mild thrombocytopenia. Wilson's disease
        is uncommon, so diagnosing it requires a high degree of suspicion. In
        circumstances of inexplicable liver cirrhosis or isolated neurological
        symptoms, it could go unnoticed. The only primary complaint in the case
        being presented was abdominal pain. However, the age upon presentation,
        the existence of KF rings in both eyes, and other tests helped us get
        the diagnosis.
  - source_sentence: >-
      [YEAR_RANGE] 2020-2024 [TEXT] Role of artificial intelligence in behavior
      management of pediatric dental patients-a mini review.
    sentences:
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] PURPOSE: To examine the long-term success
        rate of pediatric endoscopic DCR surgery via telephone questionnaires,
        as determined by patients and their parents. METHODS: This is a
        retrospective cohort study of all patients who underwent DCR surgery at
        the Schneider Children's Medical Center of Israel between 2010 and 2020.
        We performed long-term follow-ups to assess the quality of life,
        surgical complications, and satisfaction with surgical outcomes.
        RESULTS: Our study includes seventy-nine patients with a total of 108
        eyes. The mean age at the time of DCR was 7.05 years (Std = 4, min =
        0.3, max = 17.7) Mean follow-up time was 5.7 years (Std =2.5, min = 1.4,
        max = 11.1). Tubes were inserted for a mean of 129 days (Std = 101).
        Fifty-seven patients (72%) declared they had no complications after
        surgery, three patients (4%) reported pain after surgery, and 14
        patients (17.7%) reported tube extrusion, which occurred 7-21 days after
        surgery. Forty-four patients (56%) reported no recurrence of symptoms,
        29 (37%) complained of mild epiphora, and 18 (23%) reported some ocular
        discharge. Sixty-eight patients (86%) stated that they did not undergo
        additional surgery, while the remaining 11 (14%) reported undergoing a
        revision operation for symptom control. Satisfaction rate (1-7) mean
        score reported was 6.15 (Std = 1.6). Sixty-two (78%) reported improved
        quality of life, while 17 (22%) reported no improvement. Our
        questionnaire results have been compared with the TEARS scores with
        similar findings. CONCLUSION: Regardless of its etiology, endoscopic DCR
        surgery in the pediatric population is safe and efficient, with a high
        long-term patient satisfaction rate, as reported via a telephone
        questionnaire.
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] The influence of behavioral science on
        various organizations has been experiencing remarkable growth worldwide.
        With the integration of recent technological advancements, behavioral
        science's impact has expanded into diverse fields such as finance and
        policy. The term "artificial intelligence" (AI) has become increasingly
        prevalent, but it is essential to provide clarity before proceeding. AI
        pertains to the theory and creation of systems capable of executing
        tasks that typically necessitate human intelligence. Integrating
        artificial intelligence (AI) in pediatric dentistry has emerged as a
        promising avenue to enhance patient care, improve diagnostic accuracy,
        streamline treatment planning, and augment patient engagement. AI-driven
        tools such as image analysis, natural language processing, and machine
        learning algorithms assist in early caries detection, orthodontic
        treatment planning, behavior management, and personalized oral hygiene
        education for pediatric patients. This paper presents an overview of
        AI's applications in pediatric dentistry, particularly behavior
        management, highlighting its potential to revolutionize traditional
        pediatric dental practices.
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] Autoimmune hemolytic anemia. The 6-month
        cumulative incidence of hospitalization with infection was 17.6% (95%CI:
        15.2-20.0). The most frequently characterized infections were pulmonary
        (40.2%). Opportunistic infections were observed in 28 (16.6%) patients,
        including 11 cases of pneumocystosis. All cases of pneumocystosis
        occurred in patients concomitantly exposed to corticosteroids, none of
        them had prophylaxis and all but 2 were aged 70 years. Overall, the
        main factors associated with hospitalization with infection were an age
        70 years and the exposure to corticosteroids. The 30-day overall
        mortality after hospitalization with infection was 12.5% (95%CI:
        8.0-18.0). In conclusion, the incidence of hospitalizations with
        infection, including opportunistic infections, is high in adult patients
        with primary AIHA treated with rituximab, as well as the subsequent
        mortality. Pneumocystosis prophylaxis should be encouraged in elderly
        patients exposed to corticosteroids.
  - source_sentence: >-
      [YEAR_RANGE] 2020-2024 [TEXT] Evaluation of human antibodies from
      vaccinated volunteers for protection against Yersinia pestis infection.
    sentences:
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] INTRODUCTION: Chronic obstructive
        pulmonary disease (COPD) has traditionally been diagnosed based on the
        criterion of an FEV1/FVC <0.70. However, this definition has limitations
        as it may only detect patients with later-stage disease, when pathologic
        changes have become irreversible. Consequently, it potentially omits
        individuals with early-stage disease, in whom the pathologic changes
        could be delayed or reversed. AREAS COVERED: This narrative review
        summarizes recent evidence regarding early-stage COPD, which may not
        fulfill the spirometric criteria but nonetheless exhibits features of
        COPD or is at risk of future COPD progression. EXPERT OPINION: A
        comprehensive approach, including symptoms assessment, various
        physiologic tests, and radiologic features, is required to diagnose
        COPD. This approach is necessary to identify currently underdiagnosed
        patients and to halt disease progression in at- risk patients.
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] BACKGROUND: Interventional therapies for
        severe pulmonary arterial hypertension (PAH) can provide right
        ventricular (RV) decompression and preserve cardiac output.
        Transcatheter stent placement in a residual ductus arteriosus (PDA) is
        one potentially effective option in critically ill infants and young
        children with PAH. We sought to assess recovery of RV function by
        echocardiographic strain in infants and young children following PDA
        stenting for acute PAH. METHODS: Retrospective review of patients < 2
        years old who underwent PDA stenting for acute PAH. Clinical data were
        abstracted from the electronic medical record. RV strain (both total and
        free wall components) was assessed from echocardiographic images at
        baseline and 3, 6, and 12 months post-intervention, as well as at last
        echocardiogram. RESULTS: Nine patients underwent attempted ductal
        stenting for PAH. The median age at intervention was 38 days and median
        weight 3.7 kg. One-third (3of 9) of patients had PAH associated with a
        congenital diaphragmatic hernia. PDA stents were successfully deployed
        in eight patients. Mean RV total strain was - 14.9 ± 5.6% at baseline
        and improved to - 23.8 ± 2.2% at 6 months post-procedure (p < 0.001).
        Mean free wall RV strain was - 19.5 ± 5.4% at baseline and improved to -
        27.7 ± 4.1% at 6 months (p = 0.002). Five patients survived to
        discharge, and four patients survived 1 year post-discharge. CONCLUSION:
        PDA stenting for severe, acute PAH can improve RV function as assessed
        by strain echocardiography. The quantitative improvement is more
        prominent in the first 6 months post-procedure and stabilizes
        thereafter.
      - >-
        [YEAR_RANGE] 2020-2024 [TEXT] Yersinia pestis has a broad host range and
        has caused lethal bubonic and pneumonic plague in humans. With the
        emergence of multiple resistant strains and the potential for biothreat
        use, there is an urgent need for new therapeutic strategies that can
        protect populations from natural or deliberate infection. Targeting F1
        has been proven to be the main strategy for developing vaccines and
        therapeutic antibodies, but data on anti-F1 antibodies, especially in
        humans, are scarce. To date, three human anti-F1 monoclonal antibodies
        (m252, αF1Ig2, and αF1Ig8) from naive populations have been reported.
        Here, we constructed an antibody library from vaccinees immunized with
        the plague subunit vaccine IIa by phage display. The genetic basis,
        epitopes, and biological functions of the obtained mAbs were assessed
        and evaluated in plague-challenged mice. Three human mAbs, namely, F3,
        F19, and F23, were identified. Their biolayer responses were 0.4, 0.6,
        and 0.6 nm, respectively. The dissociation constants (KD) of the F1
        antigen were 1 pM, 0.165 nM, and 1 pM, respectively. Although derived
        from distinct Ab lineages, that is, VH3-30-D3-10-JH4 (F3&F23) and
        VH3-43-D6-19-JH4 (F19), these mAbs share similar binding sites in F1
        with some overlap with αF1Ig8 but are distinct from αF1Ig2. Each of them
        provided a significant protective effect for Balb/c mice against a 100
        median lethal dose (MLD) challenge of a virulent Y. pestis strain when
        administered at a dose of 100 μg. No synergistic or antagonistic effects
        were observed among them. These mAbs are novel and excellent candidates
        for further drug development and use in clinical practice.IMPORTANCEIn
        this study, we identified three human monoclonal antibodies with a high
        affinity to F1 protein of Yersinia pestis. We discovered that they have
        relatively lower somatic hypermutations compared with antibodies, m252,
        αF1Ig2, and αF1Ig8, derived from the naive library reported previously.
        We also observed that these mAbs share similar binding sites in F1 with
        some overlapping with αF1Ig8 but distinct from that of αF1Ig2.
        Furthermore, each of them could provide complete protection for mice
        against a lethal dose of Yersinia pestis challenge. Our data provided
        new insights into the anti-F1 Ab repertories and their associated
        epitopes during vaccination in humans. The findings support the
        additional novel protective human anti-F1Abs for potential therapeutics
        against plaque.
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer

This is a sentence-transformers model trained on the parquet dataset. It maps sentences & paragraphs to a 512-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Maximum Sequence Length: 512 tokens
Output Dimensionality: 512 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- parquet

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 512, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("pankajrajdeo/Bioformer-8L-UMLS-Pubmed-ST-TCE-Epoch-1")
# Run inference
sentences = [
    '[YEAR_RANGE] 2020-2024 [TEXT] Evaluation of human antibodies from vaccinated volunteers for protection against Yersinia pestis infection.',
    '[YEAR_RANGE] 2020-2024 [TEXT] Yersinia pestis has a broad host range and has caused lethal bubonic and pneumonic plague in humans. With the emergence of multiple resistant strains and the potential for biothreat use, there is an urgent need for new therapeutic strategies that can protect populations from natural or deliberate infection. Targeting F1 has been proven to be the main strategy for developing vaccines and therapeutic antibodies, but data on anti-F1 antibodies, especially in humans, are scarce. To date, three human anti-F1 monoclonal antibodies (m252, αF1Ig2, and αF1Ig8) from naive populations have been reported. Here, we constructed an antibody library from vaccinees immunized with the plague subunit vaccine IIa by phage display. The genetic basis, epitopes, and biological functions of the obtained mAbs were assessed and evaluated in plague-challenged mice. Three human mAbs, namely, F3, F19, and F23, were identified. Their biolayer responses were 0.4, 0.6, and 0.6 nm, respectively. The dissociation constants (KD) of the F1 antigen were 1 pM, 0.165 nM, and 1 pM, respectively. Although derived from distinct Ab lineages, that is, VH3-30-D3-10-JH4 (F3&F23) and VH3-43-D6-19-JH4 (F19), these mAbs share similar binding sites in F1 with some overlap with αF1Ig8 but are distinct from αF1Ig2. Each of them provided a significant protective effect for Balb/c mice against a 100 median lethal dose (MLD) challenge of a virulent Y. pestis strain when administered at a dose of 100 μg. No synergistic or antagonistic effects were observed among them. These mAbs are novel and excellent candidates for further drug development and use in clinical practice.IMPORTANCEIn this study, we identified three human monoclonal antibodies with a high affinity to F1 protein of Yersinia pestis. We discovered that they have relatively lower somatic hypermutations compared with antibodies, m252, αF1Ig2, and αF1Ig8, derived from the naive library reported previously. We also observed that these mAbs share similar binding sites in F1 with some overlapping with αF1Ig8 but distinct from that of αF1Ig2. Furthermore, each of them could provide complete protection for mice against a lethal dose of Yersinia pestis challenge. Our data provided new insights into the anti-F1 Ab repertories and their associated epitopes during vaccination in humans. The findings support the additional novel protective human anti-F1Abs for potential therapeutics against plaque.',
    '[YEAR_RANGE] 2020-2024 [TEXT] BACKGROUND: Interventional therapies for severe pulmonary arterial hypertension (PAH) can provide right ventricular (RV) decompression and preserve cardiac output. Transcatheter stent placement in a residual ductus arteriosus (PDA) is one potentially effective option in critically ill infants and young children with PAH. We sought to assess recovery of RV function by echocardiographic strain in infants and young children following PDA stenting for acute PAH. METHODS: Retrospective review of patients < 2 years old who underwent PDA stenting for acute PAH. Clinical data were abstracted from the electronic medical record. RV strain (both total and free wall components) was assessed from echocardiographic images at baseline and 3, 6, and 12 months post-intervention, as well as at last echocardiogram. RESULTS: Nine patients underwent attempted ductal stenting for PAH. The median age at intervention was 38 days and median weight 3.7 kg. One-third (3of 9) of patients had PAH associated with a congenital diaphragmatic hernia. PDA stents were successfully deployed in eight patients. Mean RV total strain was - 14.9 ± 5.6% at baseline and improved to - 23.8 ± 2.2% at 6 months post-procedure (p < 0.001). Mean free wall RV strain was - 19.5 ± 5.4% at baseline and improved to - 27.7 ± 4.1% at 6 months (p = 0.002). Five patients survived to discharge, and four patients survived 1 year post-discharge. CONCLUSION: PDA stenting for severe, acute PAH can improve RV function as assessed by strain echocardiography. The quantitative improvement is more prominent in the first 6 months post-procedure and stabilizes thereafter.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 512]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

parquet

Dataset: parquet
Size: 1,571,676 training samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 10 tokens
mean: 23.85 tokens
max: 63 tokens

min: 25 tokens
mean: 189.13 tokens
max: 512 tokens

	anchor	positive
type	string	string
details	min: 10 tokens mean: 23.85 tokens max: 63 tokens	min: 25 tokens mean: 189.13 tokens max: 512 tokens

Samples:

anchor	positive
`[YEAR_RANGE] 1925-1929 [TEXT] Endotracheal Anæsthesia.`	[YEAR_RANGE] 1925-1929 [TEXT] With certain exceptions, endotracheal anaesthesia is the best method for operations on the head and neck and for any other operation in which there may be a difficulty in controlling the patient's air-way. (2) Expiration should be provided for, in endotracheal anaesthesia, either by means of a second tube or by a tube of calibre sufficient to permit to-and-fro respiration. (3) Cocainization of the upper air-passages has decided advantages in endotracheal anaesthesia. (4) "Blind" intubation through the nose renders the method possible in cases where it is impossible to use a speculum. (5) The insufflation method is not specially indicated in abdominal surgery. (6) The routine use of endotracheal anaesthesia in teaching-hospitals for every class of case is detrimental to the production of sound anaesthetic knowledge in students who are likely to become general practitioners.
`[YEAR_RANGE] 1925-1929 [TEXT] A Further Contribution to the Subject of Aplastic Anæmia.`	[YEAR_RANGE] 1925-1929 [TEXT] In the description of the condition of benign aplastic anaemia in pigs, attention is directed, among other things, to changes in the bone-marrow which seem of fundamental importance in understanding normal erythrogenesis.It is possible that an indirect van den Bergh reaction can be converted into an immediate direct by controlling the H-ion concentration suitably, either with buffer solutions or with less dissociable acids, such as acetic, used in preparing the van den Bergh reagent. The question of the interpretation of direct and indirect reactions, therefore, would seem to be reopened.Following Minot and Murphy's work, a pig with aplastic anaemia was fed with liver. The lesions in the liver, considered with the marked improvement in the blood which followed on liver feeding in this case, lead one to regard the condition as one of blood and marrow inefficiency due primarily to hepatic insufficiency.A comparison of pernicious anaemia with the benign aplas...
`[YEAR_RANGE] 1925-1929 [TEXT] DISCUSSION ON THE TREATMENT OF URETHRAL STRICTURE AND FISTULÆ BY EXCISION.`	[YEAR_RANGE] 1925-1929 [TEXT] For hard tunnel strictures and in cases of perineal fistula we should be bolder to adopt the principle of excision rather than that of mere external urethrotomy.A preliminary suprapubic cystotomy is advised, and also the avoidance, as far as possible, of the indwelling catheter. All fistulae should be excised completely, not merely opened, scraped and drained.The operator should not be in too great a hurry to pass sounds of too large a calibre after the operation, as in many cases there is little tendency to re-formation of the stricture.

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Evaluation Dataset

parquet

Dataset: parquet
Size: 1,571,676 evaluation samples
Columns: anchor and positive
Approximate statistics based on the first 1000 samples:
anchor positive
type string string
details
min: 11 tokens
mean: 31.45 tokens
max: 65 tokens

min: 10 tokens
mean: 280.57 tokens
max: 512 tokens

	anchor	positive
type	string	string
details	min: 11 tokens mean: 31.45 tokens max: 65 tokens	min: 10 tokens mean: 280.57 tokens max: 512 tokens

Samples:

anchor	positive
`[YEAR_RANGE] 2020-2024 [TEXT] Impact of Forced Swimming Stress on Serum Adiponectin and Endothelin-1 Levels in Wistar Rats: Comparative Analysis of Dietary Effects.`	[YEAR_RANGE] 2020-2024 [TEXT] Aim This study aimed to assess the impact of forced repeated swimming stress on serum adiponectin and endothelin-1 levels in Wistar rats, comparing the effects between those fed a standard diet and those on a high-fat diet. Methods Twenty adult male Wistar rats were divided into two dietary groups: a standard food diet group (NFD, n=10) and a high-fat diet group (HFD, n=10). Both groups underwent daily forced swimming stress for six days, with durations increasing from 5 to 30 minutes. The protocol finished in an acute bout of swimming exercise on the seventh day with a duration of 40 minutes. Adherence to ethical guidelines was strictly maintained, and serum adiponectin and endothelin-1 levels were measured pre- and post-exercise using the ELISA method. Results Before swimming, the mean adiponectin levels were 4.30±1.50 ng/mL in the NFD group and 3.53±0.70 ng/mL in the HFD group. Post-exercise, these levels significantly decreased to 2.4±0.84 ng/mL (p=0.0...
`[YEAR_RANGE] 2020-2024 [TEXT] A Case of Anti-Leucine-Rich Glioma-Inactivated Protein 1 (Anti-LGI1) Limbic Encephalitis With New-Onset Panic Attacks.`	[YEAR_RANGE] 2020-2024 [TEXT] Anti-leucine-rich glioma-inactivated protein 1. This report discusses a unique onset of anti-LGI1 limbic encephalitis where an elderly female presented with symptoms of new-onset panic attacks and rhythmic facial movements for one week. She was then admitted to neurology for further serum, cerebrospinal fluid(CSF), and lab testing. She was eventually found to be positive for antibodies against LGI1 voltage-gated potassium channels, which confirmed the diagnosis of limbic encephalitis. The quick recognition of symptoms and escalation of management allowed the patient to experience drastic improvements after the initiation of steroids, immunotherapy, and lacosamide. Since anti-LGI1 limbic encephalitis is underdiagnosed, it can lead to irreversible long-term cognitive sequelae (that is, memory deficits). Thus, awareness of the typically associated findings of FBDS, cognitive disturbances, psychiatric changes, and hyponatremia can aid in early diagnosis and pr...
`[YEAR_RANGE] 2020-2024 [TEXT] A Case of Horner's Syndrome Aiding the Diagnosis of Internal Carotid Artery Dissection (ICAD): A Life-Saving Twist of Fate.`	[YEAR_RANGE] 2020-2024 [TEXT] A 59-year-old male patient came to the outpatient department with complaints of left-sided hemicranial headache with drooping of the left upper eyelid (UL) for three days associated with difficulty in swallowing and deviation of the tongue. The patient had a history of vigorous coughing for the past 15 days for which he did not take any medications. He was thoroughly evaluated in the outpatient department and diagnosed with Horner's syndrome. Acute Horner's syndrome with pain is nearly a hallmark of carotid dissection, and MRI of the brain and orbit was thus advised. On MRI, a hyperdense area was noted around the left internal carotid artery for which he was advised magnetic resonance angiography, which revealed internal carotid artery dissection (ICAD) of the left side. The patient was diagnosed with left-sided Horner's syndrome following left ICAD with involvement of the left hypoglossal nerve. He was started on antiplatelets and anticoagulants and close...

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 128
learning_rate: 2e-05
num_train_epochs: 2
max_steps: 23328
log_level: info
fp16: True
dataloader_num_workers: 16
load_best_model_at_end: True
resume_from_checkpoint: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 128
per_device_eval_batch_size: 8
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 2
max_steps: 23328
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 0
log_level: info
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 16
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: True
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: True
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
dispatch_batches: None
split_batches: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	Validation Loss
0.0001	1	0.184	-
0.0857	1000	0.0177	-
0.1715	2000	0.0301	-
0.2572	3000	0.02	-
0.3429	4000	0.0164	-
0.4286	5000	0.0182	-
0.5144	6000	0.0189	-
0.6001	7000	0.0172	-
0.6858	8000	0.0179	-
0.7715	9000	0.0163	-
0.8573	10000	0.0187	-
0.9430	11000	0.0163	-
0.9999	11664	-	0.0004

Framework Versions

Python: 3.11.11
Sentence Transformers: 3.4.1
Transformers: 4.48.2
PyTorch: 2.6.0+cu124
Accelerate: 1.3.0
Datasets: 3.2.0
Tokenizers: 0.21.0

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}